cargo: update dependencies

Last of the functions that need to be ported over to strided-ndarray.

.clang-format

@@ -1,3 +1,32 @@
-BasedOnStyle: Google
+BasedOnStyle: LLVM
+
+Language: Cpp
+Standard: Cpp11
+
+AccessModifierOffset: -1
+AlignEscapedNewlines: Left
+AlwaysBreakAfterReturnType: None
+AlwaysBreakTemplateDeclarations: Yes
+AllowAllParametersOfDeclarationOnNextLine: false
+AllowShortFunctionsOnASingleLine: Inline
+BinPackParameters: false
+BreakBeforeBinaryOperators: NonAssignment
+BreakBeforeTernaryOperators: true
+BreakConstructorInitializers: AfterColon
+BreakInheritanceList: AfterColon
+ColumnLimit: 120
+ConstructorInitializerAllOnOneLineOrOnePerLine: true
+ContinuationIndentWidth: 4
+DerivePointerAlignment: false
+IndentCaseLabels: true
+IndentPPDirectives: None
 IndentWidth: 4
-ReflowComments: false
+MaxEmptyLinesToKeep: 1
+PointerAlignment: Left
+ReflowComments: true
+SortIncludes: false
+SortUsingDeclarations: true
+SpaceAfterTemplateKeyword: false
+SpacesBeforeTrailingComments: 2
+TabWidth: 4
+UseTab: Never

.gitignore

@@ -1,3 +1,4 @@
 __pycache__
 /target
+/nac3standalone/demo/linalg/target
 nix/windows/msys2

.pre-commit-config.yaml

@@ -1,24 +1,24 @@
 # See https://pre-commit.com for more information
 # See https://pre-commit.com/hooks.html for more hooks
 
-default_stages: [commit]
+default_stages: [pre-commit]
 
 repos:
   - repo: local
     hooks:
       - id: nac3-cargo-fmt
         name: nac3 cargo format
-        entry: cargo
+        entry: nix
         language: system
         types: [file, rust]
         pass_filenames: false
         description: Runs cargo fmt on the codebase.
-        args: [fmt]
+        args: [develop, -c, cargo, fmt, --all]
       - id: nac3-cargo-clippy
         name: nac3 cargo clippy
-        entry: cargo
+        entry: nix
         language: system
         types: [file, rust]
         pass_filenames: false
         description: Runs cargo clippy on the codebase.
-        args: [clippy, --tests]
+        args: [develop, -c, cargo, clippy, --tests]

Cargo.toml

@@ -4,6 +4,7 @@ members = [
   "nac3ast",
   "nac3parser",
   "nac3core",
+  "nac3core/nac3core_derive",
   "nac3standalone",
   "nac3artiq",
   "runkernel",

flake.lock

@@ -2,11 +2,11 @@
   "nodes": {
     "nixpkgs": {
       "locked": {
-        "lastModified": 1721924956,
+        "lastModified": 1733940404,
-        "narHash": "sha256-Sb1jlyRO+N8jBXEX9Pg9Z1Qb8Bw9QyOgLDNMEpmjZ2M=",
+        "narHash": "sha256-Pj39hSoUA86ZePPF/UXiYHHM7hMIkios8TYG29kQT4g=",
         "owner": "NixOS",
         "repo": "nixpkgs",
-        "rev": "5ad6a14c6bf098e98800b091668718c336effc95",
+        "rev": "5d67ea6b4b63378b9c13be21e2ec9d1afc921713",
         "type": "github"
       },
       "original": {

flake.nix

@@ -6,6 +6,7 @@
   outputs = { self, nixpkgs }:
     let
       pkgs = import nixpkgs { system = "x86_64-linux"; };
+      pkgs32 = import nixpkgs { system = "i686-linux"; };
     in rec {
       packages.x86_64-linux = rec {
         llvm-nac3 = pkgs.callPackage ./nix/llvm {};
@@ -13,9 +14,24 @@
           ''
           mkdir -p $out/bin
           ln -s ${pkgs.llvmPackages_14.clang-unwrapped}/bin/clang $out/bin/clang-irrt
-          ln -s ${pkgs.llvmPackages_14.clang}/bin/clang $out/bin/clang-irrt-test
           ln -s ${pkgs.llvmPackages_14.llvm.out}/bin/llvm-as $out/bin/llvm-as-irrt
           '';
+        demo-linalg-stub = pkgs.rustPlatform.buildRustPackage {
+          name = "demo-linalg-stub";
+          src = ./nac3standalone/demo/linalg;
+          cargoLock = {
+            lockFile = ./nac3standalone/demo/linalg/Cargo.lock;
+          };
+          doCheck = false;
+        };
+        demo-linalg-stub32 = pkgs32.rustPlatform.buildRustPackage {
+          name = "demo-linalg-stub32";
+          src = ./nac3standalone/demo/linalg;
+          cargoLock = {
+            lockFile = ./nac3standalone/demo/linalg/Cargo.lock;
+          };
+          doCheck = false;
+        };
         nac3artiq = pkgs.python3Packages.toPythonModule (
           pkgs.rustPlatform.buildRustPackage rec {
             name = "nac3artiq";
@@ -24,7 +40,6 @@
             cargoLock = {
               lockFile = ./Cargo.lock;
             };
-            cargoTestFlags = [ "--features" "test" ];
             passthru.cargoLock = cargoLock;
             nativeBuildInputs = [ pkgs.python3 (pkgs.wrapClangMulti pkgs.llvmPackages_14.clang) llvm-tools-irrt pkgs.llvmPackages_14.llvm.out llvm-nac3 ];
             buildInputs = [ pkgs.python3 llvm-nac3 ];
@@ -34,7 +49,9 @@
               echo "Checking nac3standalone demos..."
               pushd nac3standalone/demo
               patchShebangs .
-              ./check_demos.sh
+              export DEMO_LINALG_STUB=${demo-linalg-stub}/lib/liblinalg.a
+              export DEMO_LINALG_STUB32=${demo-linalg-stub32}/lib/liblinalg.a
+              ./check_demos.sh -i686
               popd
               echo "Running Cargo tests..."
               cargoCheckHook
@@ -90,18 +107,18 @@
             (pkgs.fetchFromGitHub {
               owner = "m-labs";
               repo = "sipyco";
-              rev = "939f84f9b5eef7efbf7423c735d1834783b6140e";
+              rev = "094a6cd63ffa980ef63698920170e50dc9ba77fd";
-              sha256 = "sha256-15Nun4EY35j+6SPZkjzZtyH/ncxLS60KuGJjFh5kSTc=";
+              sha256 = "sha256-PPnAyDedUQ7Og/Cby9x5OT9wMkNGTP8GS53V6N/dk4w=";
             })
             (pkgs.fetchFromGitHub {
               owner = "m-labs";
               repo = "artiq";
-              rev = "923ca3377d42c815f979983134ec549dc39d3ca0";
+              rev = "28c9de3e251daa89a8c9fd79d5ab64a3ec03bac6";
-              sha256 = "sha256-oJoEeNEeNFSUyh6jXG8Tzp6qHVikeHS0CzfE+mODPgw=";
+              sha256 = "sha256-vAvpbHc5B+1wtG8zqN7j9dQE1ON+i22v+uqA+tw6Gak=";
             })
           ];
           buildInputs = [
-            (python3-mimalloc.withPackages(ps: [ ps.numpy ps.scipy ps.jsonschema ps.lmdb nac3artiq-instrumented ]))
+            (python3-mimalloc.withPackages(ps: [ ps.numpy ps.scipy ps.jsonschema ps.lmdb ps.platformdirs nac3artiq-instrumented ]))
             pkgs.llvmPackages_14.llvm.out
           ];
           phases = [ "buildPhase" "installPhase" ];
@@ -164,6 +181,11 @@
           pre-commit
           rustfmt
         ];
+        shellHook =
+          ''
+          export DEMO_LINALG_STUB=${packages.x86_64-linux.demo-linalg-stub}/lib/liblinalg.a
+          export DEMO_LINALG_STUB32=${packages.x86_64-linux.demo-linalg-stub32}/lib/liblinalg.a
+          '';
       };
       devShells.x86_64-linux.msys2 = pkgs.mkShell {
         name = "nac3-dev-shell-msys2";

nac3artiq/Cargo.toml

@@ -12,15 +12,10 @@ crate-type = ["cdylib"]
 itertools = "0.13"
 pyo3 = { version = "0.21", features = ["extension-module", "gil-refs"] }
 parking_lot = "0.12"
-tempfile = "3.10"
+tempfile = "3.13"
-nac3parser = { path = "../nac3parser" }
 nac3core = { path = "../nac3core" }
 nac3ld = { path = "../nac3ld" }
 
-[dependencies.inkwell]
-version = "0.4"
-default-features = false
-features = ["llvm14-0", "target-x86", "target-arm", "target-riscv", "no-libffi-linking"]
-
 [features]
 init-llvm-profile = []
+no-escape-analysis = ["nac3core/no-escape-analysis"]

nac3artiq/demo/embedding_map.py

@@ -7,33 +7,6 @@ class EmbeddingMap:
         self.function_map = {}
         self.attributes_writeback = []
 
-        # preallocate exception names
-        self.preallocate_runtime_exception_names(["RuntimeError",
-                                          "RTIOUnderflow",
-                                          "RTIOOverflow",
-                                          "RTIODestinationUnreachable",
-                                          "DMAError",
-                                          "I2CError",
-                                          "CacheError",
-                                          "SPIError",
-                                          "0:ZeroDivisionError",
-                                          "0:IndexError",
-                                          "0:ValueError",
-                                          "0:RuntimeError",
-                                          "0:AssertionError",
-                                          "0:KeyError",
-                                          "0:NotImplementedError",
-                                          "0:OverflowError",
-                                          "0:IOError",
-                                          "0:UnwrapNoneError"])
-
-    def preallocate_runtime_exception_names(self, names):
-        for i, name in enumerate(names):
-            if ":" not in name:
-                name = "0:artiq.coredevice.exceptions." + name
-            exn_id = self.store_str(name)
-            assert exn_id == i
-
     def store_function(self, key, fun):
         self.function_map[key] = fun
         return key

nac3artiq/demo/min_artiq.py

@@ -112,10 +112,15 @@ def extern(function):
     register_function(function)
     return function
 
-def rpc(function):
+
-    """Decorates a function declaration defined by the core device runtime."""
+def rpc(arg=None, flags={}):
-    register_function(function)
+    """Decorates a function or method to be executed on the host interpreter."""
-    return function
+    if arg is None:
+        def inner_decorator(function):
+            return rpc(function, flags)
+        return inner_decorator
+    register_function(arg)
+    return arg
 
 def kernel(function_or_method):
     """Decorates a function or method to be executed on the core device."""
@@ -201,7 +206,7 @@ class Core:
         embedding = EmbeddingMap()
 
         if allow_registration:
-            compiler.analyze(registered_functions, registered_classes)
+            compiler.analyze(registered_functions, registered_classes, set())
             allow_registration = False
 
         if hasattr(method, "__self__"):

nac3artiq/demo/str_abi.py

@@ -0,0 +1,26 @@
+from min_artiq import *
+from numpy import ndarray, zeros as np_zeros
+
+
+@nac3
+class StrFail:
+    core: KernelInvariant[Core]
+
+    def __init__(self):
+        self.core = Core()
+
+    @kernel
+    def hello(self, arg: str):
+        pass
+
+    @kernel
+    def consume_ndarray(self, arg: ndarray[str, 1]):
+        pass
+
+    def run(self):
+        self.hello("world")
+        self.consume_ndarray(np_zeros([10], dtype=str))
+
+
+if __name__ == "__main__":
+    StrFail().run()

nac3artiq/src/lib.rs

@@ -1,10 +1,4 @@
-#![deny(
+#![deny(future_incompatible, let_underscore, nonstandard_style, clippy::all)]
-    future_incompatible,
-    let_underscore,
-    nonstandard_style,
-    rust_2024_compatibility,
-    clippy::all
-)]
 #![warn(clippy::pedantic)]
 #![allow(
     unsafe_op_in_unsafe_fn,
@@ -16,64 +10,65 @@
     clippy::wildcard_imports
 )]
 
-use std::collections::{HashMap, HashSet};
+use std::{
-use std::fs;
+    collections::{HashMap, HashSet},
-use std::io::Write;
+    fs,
-use std::process::Command;
+    io::Write,
-use std::rc::Rc;
+    process::Command,
-use std::sync::Arc;
+    rc::Rc,
+    sync::Arc,
+};
 
-use inkwell::{
+use itertools::Itertools;
+use parking_lot::{Mutex, RwLock};
+use pyo3::{
+    create_exception, exceptions,
+    prelude::*,
+    types::{PyBytes, PyDict, PyNone, PySet},
+};
+use tempfile::{self, TempDir};
+
+use nac3core::{
+    codegen::{
+        concrete_type::ConcreteTypeStore, gen_func_impl, irrt::load_irrt, CodeGenLLVMOptions,
+        CodeGenTargetMachineOptions, CodeGenTask, CodeGenerator, WithCall, WorkerRegistry,
+    },
+    inkwell::{
         context::Context,
         memory_buffer::MemoryBuffer,
-    module::{Linkage, Module},
+        module::{FlagBehavior, Linkage, Module},
         passes::PassBuilderOptions,
         support::is_multithreaded,
         targets::*,
         OptimizationLevel,
-};
+    },
-use itertools::Itertools;
+    nac3parser::{
-use nac3core::codegen::{gen_func_impl, CodeGenLLVMOptions, CodeGenTargetMachineOptions};
+        ast::{Constant, ExprKind, Located, Stmt, StmtKind, StrRef},
-use nac3core::toplevel::builtins::get_exn_constructor;
-use nac3core::typecheck::typedef::{TypeEnum, Unifier, VarMap};
-use nac3parser::{
-    ast::{ExprKind, Stmt, StmtKind, StrRef},
         parser::parse_program,
-};
+    },
-use pyo3::create_exception;
-use pyo3::prelude::*;
-use pyo3::{exceptions, types::PyBytes, types::PyDict, types::PySet};
-
-use parking_lot::{Mutex, RwLock};
-
-use nac3core::{
-    codegen::irrt::load_irrt,
-    codegen::{concrete_type::ConcreteTypeStore, CodeGenTask, WithCall, WorkerRegistry},
     symbol_resolver::SymbolResolver,
     toplevel::{
-        composer::{ComposerConfig, TopLevelComposer},
+        builtins::get_exn_constructor,
+        composer::{BuiltinFuncCreator, BuiltinFuncSpec, ComposerConfig, TopLevelComposer},
         DefinitionId, GenCall, TopLevelDef,
     },
-    typecheck::typedef::{FunSignature, FuncArg},
+    typecheck::{
-    typecheck::{type_inferencer::PrimitiveStore, typedef::Type},
+        type_inferencer::PrimitiveStore,
+        typedef::{into_var_map, FunSignature, FuncArg, Type, TypeEnum, Unifier, VarMap},
+    },
 };
-
 use nac3ld::Linker;
 
-use tempfile::{self, TempDir};
+use codegen::{
-
+    attributes_writeback, gen_core_log, gen_rtio_log, rpc_codegen_callback, ArtiqCodeGenerator,
-use crate::codegen::attributes_writeback;
-use crate::{
-    codegen::{rpc_codegen_callback, ArtiqCodeGenerator},
-    symbol_resolver::{DeferredEvaluationStore, InnerResolver, PythonHelper, Resolver},
 };
+use symbol_resolver::{DeferredEvaluationStore, InnerResolver, PythonHelper, Resolver};
+use timeline::TimeFns;
 
 mod codegen;
 mod symbol_resolver;
 mod timeline;
 
-use timeline::TimeFns;
-
 #[derive(PartialEq, Clone, Copy)]
 enum Isa {
     Host,
@@ -127,7 +122,7 @@ struct Nac3 {
     isa: Isa,
     time_fns: &'static (dyn TimeFns + Sync),
     primitive: PrimitiveStore,
-    builtins: Vec<(StrRef, FunSignature, Arc<GenCall>)>,
+    builtins: Vec<BuiltinFuncSpec>,
     pyid_to_def: Arc<RwLock<HashMap<u64, DefinitionId>>>,
     primitive_ids: PrimitivePythonId,
     working_directory: TempDir,
@@ -147,14 +142,32 @@ impl Nac3 {
         module: &PyObject,
         registered_class_ids: &HashSet<u64>,
     ) -> PyResult<()> {
-        let (module_name, source_file) = Python::with_gil(|py| -> PyResult<(String, String)> {
+        let (module_name, source_file, source) =
+            Python::with_gil(|py| -> PyResult<(String, String, String)> {
                 let module: &PyAny = module.extract(py)?;
-            Ok((module.getattr("__name__")?.extract()?, module.getattr("__file__")?.extract()?))
+                let source_file = module.getattr("__file__");
+                let (source_file, source) = if let Ok(source_file) = source_file {
+                    let source_file = source_file.extract()?;
+                    (
+                        source_file,
+                        fs::read_to_string(source_file).map_err(|e| {
+                            exceptions::PyIOError::new_err(format!(
+                                "failed to read input file: {e}"
+                            ))
+                        })?,
+                    )
+                } else {
+                    // kernels submitted by content have no file
+                    // but still can provide source by StringLoader
+                    let get_src_fn = module
+                        .getattr("__loader__")?
+                        .extract::<PyObject>()?
+                        .getattr(py, "get_source")?;
+                    ("<expcontent>", get_src_fn.call1(py, (PyNone::get(py),))?.extract(py)?)
+                };
+                Ok((module.getattr("__name__")?.extract()?, source_file.to_string(), source))
             })?;
 
-        let source = fs::read_to_string(&source_file).map_err(|e| {
-            exceptions::PyIOError::new_err(format!("failed to read input file: {e}"))
-        })?;
         let parser_result = parse_program(&source, source_file.into())
             .map_err(|e| exceptions::PySyntaxError::new_err(format!("parse error: {e}")))?;
 
@@ -194,10 +207,8 @@ impl Nac3 {
                     body.retain(|stmt| {
                         if let StmtKind::FunctionDef { ref decorator_list, .. } = stmt.node {
                             decorator_list.iter().any(|decorator| {
-                                if let ExprKind::Name { id, .. } = decorator.node {
+                                if let Some(id) = decorator_id_string(decorator) {
-                                    id.to_string() == "kernel"
+                                    id == "kernel" || id == "portable" || id == "rpc"
-                                        || id.to_string() == "portable"
-                                        || id.to_string() == "rpc"
                                 } else {
                                     false
                                 }
@@ -210,9 +221,8 @@ impl Nac3 {
                 }
                 StmtKind::FunctionDef { ref decorator_list, .. } => {
                     decorator_list.iter().any(|decorator| {
-                        if let ExprKind::Name { id, .. } = decorator.node {
+                        if let Some(id) = decorator_id_string(decorator) {
-                            let id = id.to_string();
+                            id == "extern" || id == "kernel" || id == "portable" || id == "rpc"
-                            id == "extern" || id == "portable" || id == "kernel" || id == "rpc"
                         } else {
                             false
                         }
@@ -265,7 +275,7 @@ impl Nac3 {
                     arg_names.len(),
                 ));
             }
-            for (i, FuncArg { ty, default_value, name }) in args.iter().enumerate() {
+            for (i, FuncArg { ty, default_value, name, .. }) in args.iter().enumerate() {
                 let in_name = match arg_names.get(i) {
                     Some(n) => n,
                     None if default_value.is_none() => {
@@ -301,6 +311,64 @@ impl Nac3 {
         None
     }
 
+    /// Returns a [`Vec`] of builtins that needs to be initialized during method compilation time.
+    fn get_lateinit_builtins() -> Vec<Box<BuiltinFuncCreator>> {
+        vec![
+            Box::new(|primitives, unifier| {
+                let arg_ty = unifier.get_fresh_var(Some("T".into()), None);
+
+                (
+                    "core_log".into(),
+                    FunSignature {
+                        args: vec![FuncArg {
+                            name: "arg".into(),
+                            ty: arg_ty.ty,
+                            default_value: None,
+                            is_vararg: false,
+                        }],
+                        ret: primitives.none,
+                        vars: into_var_map([arg_ty]),
+                    },
+                    Arc::new(GenCall::new(Box::new(move |ctx, obj, fun, args, generator| {
+                        gen_core_log(ctx, &obj, fun, &args, generator)?;
+
+                        Ok(None)
+                    }))),
+                )
+            }),
+            Box::new(|primitives, unifier| {
+                let arg_ty = unifier.get_fresh_var(Some("T".into()), None);
+
+                (
+                    "rtio_log".into(),
+                    FunSignature {
+                        args: vec![
+                            FuncArg {
+                                name: "channel".into(),
+                                ty: primitives.str,
+                                default_value: None,
+                                is_vararg: false,
+                            },
+                            FuncArg {
+                                name: "arg".into(),
+                                ty: arg_ty.ty,
+                                default_value: None,
+                                is_vararg: false,
+                            },
+                        ],
+                        ret: primitives.none,
+                        vars: into_var_map([arg_ty]),
+                    },
+                    Arc::new(GenCall::new(Box::new(move |ctx, obj, fun, args, generator| {
+                        gen_rtio_log(ctx, &obj, fun, &args, generator)?;
+
+                        Ok(None)
+                    }))),
+                )
+            }),
+        ]
+    }
+
     fn compile_method<T>(
         &self,
         obj: &PyAny,
@@ -313,6 +381,7 @@ impl Nac3 {
         let size_t = self.isa.get_size_type();
         let (mut composer, mut builtins_def, mut builtins_ty) = TopLevelComposer::new(
             self.builtins.clone(),
+            Self::get_lateinit_builtins(),
             ComposerConfig { kernel_ann: Some("Kernel"), kernel_invariant_ann: "KernelInvariant" },
             size_t,
         );
@@ -389,7 +458,6 @@ impl Nac3 {
                         pyid_to_type: pyid_to_type.clone(),
                         primitive_ids: self.primitive_ids.clone(),
                         global_value_ids: global_value_ids.clone(),
-                        class_names: Mutex::default(),
                         name_to_pyid: name_to_pyid.clone(),
                         module: module.clone(),
                         id_to_pyval: RwLock::default(),
@@ -420,9 +488,25 @@ impl Nac3 {
 
             match &stmt.node {
                 StmtKind::FunctionDef { decorator_list, .. } => {
-                    if decorator_list.iter().any(|decorator| matches!(decorator.node, ExprKind::Name { id, .. } if id == "rpc".into())) {
+                    if decorator_list
-                        store_fun.call1(py, (def_id.0.into_py(py), module.getattr(py, name.to_string().as_str()).unwrap())).unwrap();
+                        .iter()
-                        rpc_ids.push((None, def_id));
+                        .any(|decorator| decorator_id_string(decorator) == Some("rpc".to_string()))
+                    {
+                        store_fun
+                            .call1(
+                                py,
+                                (
+                                    def_id.0.into_py(py),
+                                    module.getattr(py, name.to_string().as_str()).unwrap(),
+                                ),
+                            )
+                            .unwrap();
+                        let is_async = decorator_list.iter().any(|decorator| {
+                            decorator_get_flags(decorator)
+                                .iter()
+                                .any(|constant| *constant == Constant::Str("async".into()))
+                        });
+                        rpc_ids.push((None, def_id, is_async));
                     }
                 }
                 StmtKind::ClassDef { name, body, .. } => {
@@ -430,19 +514,26 @@ impl Nac3 {
                     let class_obj = module.getattr(py, class_name.as_str()).unwrap();
                     for stmt in body {
                         if let StmtKind::FunctionDef { name, decorator_list, .. } = &stmt.node {
-                            if decorator_list.iter().any(|decorator| matches!(decorator.node, ExprKind::Name { id, .. } if id == "rpc".into())) {
+                            if decorator_list.iter().any(|decorator| {
+                                decorator_id_string(decorator) == Some("rpc".to_string())
+                            }) {
+                                let is_async = decorator_list.iter().any(|decorator| {
+                                    decorator_get_flags(decorator)
+                                        .iter()
+                                        .any(|constant| *constant == Constant::Str("async".into()))
+                                });
                                 if name == &"__init__".into() {
                                     return Err(CompileError::new_err(format!(
                                         "compilation failed\n----------\nThe constructor of class {} should not be decorated with rpc decorator (at {})",
                                         class_name, stmt.location
                                     )));
                                 }
-                                rpc_ids.push((Some((class_obj.clone(), *name)), def_id));
+                                rpc_ids.push((Some((class_obj.clone(), *name)), def_id, is_async));
                             }
                         }
                     }
                 }
-                _ => ()
+                _ => (),
             }
 
             let id = *name_to_pyid.get(&name).unwrap();
@@ -481,13 +572,12 @@ impl Nac3 {
             pyid_to_type: pyid_to_type.clone(),
             primitive_ids: self.primitive_ids.clone(),
             global_value_ids: global_value_ids.clone(),
-            class_names: Mutex::default(),
             id_to_pyval: RwLock::default(),
             id_to_primitive: RwLock::default(),
             field_to_val: RwLock::default(),
             name_to_pyid,
             module: module.to_object(py),
-            helper,
+            helper: helper.clone(),
             string_store: self.string_store.clone(),
             exception_ids: self.exception_ids.clone(),
             deferred_eval_store: self.deferred_eval_store.clone(),
@@ -498,6 +588,10 @@ impl Nac3 {
             .register_top_level(synthesized.pop().unwrap(), Some(resolver.clone()), "", false)
             .unwrap();
 
+        // Process IRRT
+        let context = Context::create();
+        let irrt = load_irrt(&context, resolver.as_ref());
+
         let fun_signature =
             FunSignature { args: vec![], ret: self.primitive.none, vars: VarMap::new() };
         let mut store = ConcreteTypeStore::new();
@@ -535,13 +629,12 @@ impl Nac3 {
         let top_level = Arc::new(composer.make_top_level_context());
 
         {
-            let rpc_codegen = rpc_codegen_callback();
             let defs = top_level.definitions.read();
-            for (class_data, id) in &rpc_ids {
+            for (class_data, id, is_async) in &rpc_ids {
                 let mut def = defs[id.0].write();
                 match &mut *def {
                     TopLevelDef::Function { codegen_callback, .. } => {
-                        *codegen_callback = Some(rpc_codegen.clone());
+                        *codegen_callback = Some(rpc_codegen_callback(*is_async));
                     }
                     TopLevelDef::Class { methods, .. } => {
                         let (class_def, method_name) = class_data.as_ref().unwrap();
@@ -552,7 +645,7 @@ impl Nac3 {
                             if let TopLevelDef::Function { codegen_callback, .. } =
                                 &mut *defs[id.0].write()
                             {
-                                *codegen_callback = Some(rpc_codegen.clone());
+                                *codegen_callback = Some(rpc_codegen_callback(*is_async));
                                 store_fun
                                     .call1(
                                         py,
@@ -567,6 +660,11 @@ impl Nac3 {
                             }
                         }
                     }
+                    TopLevelDef::Variable { .. } => {
+                        return Err(CompileError::new_err(String::from(
+                            "Unsupported @rpc annotation on global variable",
+                        )))
+                    }
                 }
             }
         }
@@ -587,33 +685,12 @@ impl Nac3 {
         let task = CodeGenTask {
             subst: Vec::default(),
             symbol_name: "__modinit__".to_string(),
-            body: instance.body,
-            signature,
-            resolver: resolver.clone(),
-            store,
-            unifier_index: instance.unifier_id,
-            calls: instance.calls,
-            id: 0,
-        };
-
-        let mut store = ConcreteTypeStore::new();
-        let mut cache = HashMap::new();
-        let signature = store.from_signature(
-            &mut composer.unifier,
-            &self.primitive,
-            &fun_signature,
-            &mut cache,
-        );
-        let signature = store.add_cty(signature);
-        let attributes_writeback_task = CodeGenTask {
-            subst: Vec::default(),
-            symbol_name: "attributes_writeback".to_string(),
             body: Arc::new(Vec::default()),
             signature,
             resolver,
             store,
             unifier_index: instance.unifier_id,
-            calls: Arc::new(HashMap::default()),
+            calls: instance.calls,
             id: 0,
         };
 
@@ -626,7 +703,7 @@ impl Nac3 {
             let buffer = buffer.as_slice().into();
             membuffer.lock().push(buffer);
         })));
-        let size_t = Context::create()
+        let size_t = context
             .ptr_sized_int_type(&self.get_llvm_target_machine().get_target_data(), None)
             .get_bit_width();
         let num_threads = if is_multithreaded() { 4 } else { 1 };
@@ -637,19 +714,27 @@ impl Nac3 {
             .collect();
 
         let membuffer = membuffers.clone();
+        let mut has_return = false;
         py.allow_threads(|| {
             let (registry, handles) =
                 WorkerRegistry::create_workers(threads, top_level.clone(), &self.llvm_options, &f);
-            registry.add_task(task);
-            registry.wait_tasks_complete(handles);
 
-            let mut generator =
+            let mut generator = ArtiqCodeGenerator::new("main".to_string(), size_t, self.time_fns);
-                ArtiqCodeGenerator::new("attributes_writeback".to_string(), size_t, self.time_fns);
+            let context = Context::create();
-            let context = inkwell::context::Context::create();
+            let module = context.create_module("main");
-            let module = context.create_module("attributes_writeback");
             let target_machine = self.llvm_options.create_target_machine().unwrap();
             module.set_data_layout(&target_machine.get_target_data().get_data_layout());
             module.set_triple(&target_machine.get_triple());
+            module.add_basic_value_flag(
+                "Debug Info Version",
+                FlagBehavior::Warning,
+                context.i32_type().const_int(3, false),
+            );
+            module.add_basic_value_flag(
+                "Dwarf Version",
+                FlagBehavior::Warning,
+                context.i32_type().const_int(4, false),
+            );
             let builder = context.create_builder();
             let (_, module, _) = gen_func_impl(
                 &context,
@@ -657,9 +742,27 @@ impl Nac3 {
                 &registry,
                 builder,
                 module,
-                attributes_writeback_task,
+                task,
                 |generator, ctx| {
-                    attributes_writeback(ctx, generator, inner_resolver.as_ref(), &host_attributes)
+                    assert_eq!(instance.body.len(), 1, "toplevel module should have 1 statement");
+                    let StmtKind::Expr { value: ref expr, .. } = instance.body[0].node else {
+                        unreachable!("toplevel statement must be an expression")
+                    };
+                    let ExprKind::Call { .. } = expr.node else {
+                        unreachable!("toplevel expression must be a function call")
+                    };
+
+                    let return_obj =
+                        generator.gen_expr(ctx, expr)?.map(|value| (expr.custom.unwrap(), value));
+                    has_return = return_obj.is_some();
+                    registry.wait_tasks_complete(handles);
+                    attributes_writeback(
+                        ctx,
+                        generator,
+                        inner_resolver.as_ref(),
+                        &host_attributes,
+                        return_obj,
+                    )
                 },
             )
             .unwrap();
@@ -668,37 +771,24 @@ impl Nac3 {
             membuffer.lock().push(buffer);
         });
 
-        let context = inkwell::context::Context::create();
+        embedding_map.setattr("expects_return", has_return).unwrap();
+
+        // Link all modules into `main`.
         let buffers = membuffers.lock();
         let main = context
-            .create_module_from_ir(MemoryBuffer::create_from_memory_range(&buffers[0], "main"))
+            .create_module_from_ir(MemoryBuffer::create_from_memory_range(
+                buffers.last().unwrap(),
+                "main",
+            ))
             .unwrap();
-        for buffer in buffers.iter().skip(1) {
+        for buffer in buffers.iter().rev().skip(1) {
             let other = context
                 .create_module_from_ir(MemoryBuffer::create_from_memory_range(buffer, "main"))
                 .unwrap();
 
             main.link_in_module(other).map_err(|err| CompileError::new_err(err.to_string()))?;
         }
-        let builder = context.create_builder();
+        main.link_in_module(irrt).map_err(|err| CompileError::new_err(err.to_string()))?;
-        let modinit_return = main
-            .get_function("__modinit__")
-            .unwrap()
-            .get_last_basic_block()
-            .unwrap()
-            .get_terminator()
-            .unwrap();
-        builder.position_before(&modinit_return);
-        builder
-            .build_call(
-                main.get_function("attributes_writeback").unwrap(),
-                &[],
-                "attributes_writeback",
-            )
-            .unwrap();
-
-        main.link_in_module(load_irrt(&context))
-            .map_err(|err| CompileError::new_err(err.to_string()))?;
 
         let mut function_iter = main.get_first_function();
         while let Some(func) = function_iter {
@@ -732,6 +822,20 @@ impl Nac3 {
             panic!("Failed to run optimization for module `main`: {}", err.to_string());
         }
 
+        Python::with_gil(|py| {
+            let string_store = self.string_store.read();
+            let mut string_store_vec = string_store.iter().collect::<Vec<_>>();
+            string_store_vec.sort_by(|(_s1, key1), (_s2, key2)| key1.cmp(key2));
+            for (s, key) in string_store_vec {
+                let embed_key: i32 = helper.store_str.call1(py, (s,)).unwrap().extract(py).unwrap();
+                assert_eq!(
+                    embed_key, *key,
+                    "string {s} is out of sync between embedding map (key={embed_key}) and \
+                    the internal string store (key={key})"
+                );
+            }
+        });
+
         link_fn(&main)
     }
 
@@ -784,6 +888,41 @@ impl Nac3 {
     }
 }
 
+/// Retrieves the Name.id from a decorator, supports decorators with arguments.
+fn decorator_id_string(decorator: &Located<ExprKind>) -> Option<String> {
+    if let ExprKind::Name { id, .. } = decorator.node {
+        // Bare decorator
+        return Some(id.to_string());
+    } else if let ExprKind::Call { func, .. } = &decorator.node {
+        // Decorators that are calls (e.g. "@rpc()") have Call for the node,
+        // need to extract the id from within.
+        if let ExprKind::Name { id, .. } = func.node {
+            return Some(id.to_string());
+        }
+    }
+    None
+}
+
+/// Retrieves flags from a decorator, if any.
+fn decorator_get_flags(decorator: &Located<ExprKind>) -> Vec<Constant> {
+    let mut flags = vec![];
+    if let ExprKind::Call { keywords, .. } = &decorator.node {
+        for keyword in keywords {
+            if keyword.node.arg != Some("flags".into()) {
+                continue;
+            }
+            if let ExprKind::Set { elts } = &keyword.node.value.node {
+                for elt in elts {
+                    if let ExprKind::Constant { value, .. } = &elt.node {
+                        flags.push(value.clone());
+                    }
+                }
+            }
+        }
+    }
+    flags
+}
+
 fn link_with_lld(elf_filename: String, obj_filename: String) -> PyResult<()> {
     let linker_args = vec![
         "-shared".to_string(),
@@ -853,7 +992,7 @@ impl Nac3 {
             Isa::RiscV32IMA => &timeline::NOW_PINNING_TIME_FNS,
             Isa::CortexA9 | Isa::Host => &timeline::EXTERN_TIME_FNS,
         };
-        let primitive: PrimitiveStore = TopLevelComposer::make_primitives(isa.get_size_type()).0;
+        let (primitive, _) = TopLevelComposer::make_primitives(isa.get_size_type());
         let builtins = vec![
             (
                 "now_mu".into(),
@@ -869,6 +1008,7 @@ impl Nac3 {
                         name: "t".into(),
                         ty: primitive.int64,
                         default_value: None,
+                        is_vararg: false,
                     }],
                     ret: primitive.none,
                     vars: VarMap::new(),
@@ -888,6 +1028,7 @@ impl Nac3 {
                         name: "dt".into(),
                         ty: primitive.int64,
                         default_value: None,
+                        is_vararg: false,
                     }],
                     ret: primitive.none,
                     vars: VarMap::new(),
@@ -944,6 +1085,48 @@ impl Nac3 {
         let working_directory = tempfile::Builder::new().prefix("nac3-").tempdir().unwrap();
         fs::write(working_directory.path().join("kernel.ld"), include_bytes!("kernel.ld")).unwrap();
 
+        let mut string_store: HashMap<String, i32> = HashMap::default();
+
+        // Keep this list of exceptions in sync with `EXCEPTION_ID_LOOKUP` in `artiq::firmware::ksupport::eh_artiq`
+        // The exceptions declared here must be defined in `artiq.coredevice.exceptions`
+        // Verify synchronization by running the test cases in `artiq.test.coredevice.test_exceptions`
+        let runtime_exception_names = [
+            "RTIOUnderflow",
+            "RTIOOverflow",
+            "RTIODestinationUnreachable",
+            "DMAError",
+            "I2CError",
+            "CacheError",
+            "SPIError",
+            "SubkernelError",
+            "0:AssertionError",
+            "0:AttributeError",
+            "0:IndexError",
+            "0:IOError",
+            "0:KeyError",
+            "0:NotImplementedError",
+            "0:OverflowError",
+            "0:RuntimeError",
+            "0:TimeoutError",
+            "0:TypeError",
+            "0:ValueError",
+            "0:ZeroDivisionError",
+            "0:LinAlgError",
+            "UnwrapNoneError",
+        ];
+
+        // Preallocate runtime exception names
+        for (i, name) in runtime_exception_names.iter().enumerate() {
+            let exn_name = if name.find(':').is_none() {
+                format!("0:artiq.coredevice.exceptions.{name}")
+            } else {
+                (*name).to_string()
+            };
+
+            let id = i32::try_from(i).unwrap();
+            string_store.insert(exn_name, id);
+        }
+
         Ok(Nac3 {
             isa,
             time_fns,
@@ -953,7 +1136,7 @@ impl Nac3 {
             top_levels: Vec::default(),
             pyid_to_def: Arc::default(),
             working_directory,
-            string_store: Arc::default(),
+            string_store: Arc::new(string_store.into()),
             exception_ids: Arc::default(),
             deferred_eval_store: DeferredEvaluationStore::new(),
             llvm_options: CodeGenLLVMOptions {
@@ -963,7 +1146,12 @@ impl Nac3 {
         })
     }
 
-    fn analyze(&mut self, functions: &PySet, classes: &PySet) -> PyResult<()> {
+    fn analyze(
+        &mut self,
+        functions: &PySet,
+        classes: &PySet,
+        content_modules: &PySet,
+    ) -> PyResult<()> {
         let (modules, class_ids) =
             Python::with_gil(|py| -> PyResult<(HashMap<u64, PyObject>, HashSet<u64>)> {
                 let mut modules: HashMap<u64, PyObject> = HashMap::new();
@@ -973,14 +1161,22 @@ impl Nac3 {
                 let getmodule_fn = PyModule::import(py, "inspect")?.getattr("getmodule")?;
 
                 for function in functions {
-                    let module = getmodule_fn.call1((function,))?.extract()?;
+                    let module: PyObject = getmodule_fn.call1((function,))?.extract()?;
+                    if !module.is_none(py) {
                         modules.insert(id_fn.call1((&module,))?.extract()?, module);
                     }
+                }
                 for class in classes {
-                    let module = getmodule_fn.call1((class,))?.extract()?;
+                    let module: PyObject = getmodule_fn.call1((class,))?.extract()?;
+                    if !module.is_none(py) {
                         modules.insert(id_fn.call1((&module,))?.extract()?, module);
+                    }
                     class_ids.insert(id_fn.call1((class,))?.extract()?);
                 }
+                for module in content_modules {
+                    let module: PyObject = module.extract()?;
+                    modules.insert(id_fn.call1((&module,))?.extract()?, module);
+                }
                 Ok((modules, class_ids))
             })?;
 

nac3artiq/src/symbol_resolver.rs

@@ -1,14 +1,32 @@
-use inkwell::{
+use std::{
+    collections::{HashMap, HashSet},
+    sync::{
+        atomic::{AtomicBool, Ordering::Relaxed},
+        Arc,
+    },
+};
+
+use itertools::Itertools;
+use parking_lot::RwLock;
+use pyo3::{
+    types::{PyDict, PyTuple},
+    PyAny, PyErr, PyObject, PyResult, Python,
+};
+
+use super::PrimitivePythonId;
+use nac3core::{
+    codegen::{
+        types::{ndarray::NDArrayType, ProxyType},
+        values::ndarray::make_contiguous_strides,
+        CodeGenContext, CodeGenerator,
+    },
+    inkwell::{
+        module::Linkage,
         types::{BasicType, BasicTypeEnum},
         values::BasicValueEnum,
         AddressSpace,
-};
-use itertools::Itertools;
-use nac3core::{
-    codegen::{
-        classes::{NDArrayType, ProxyType},
-        CodeGenContext, CodeGenerator,
     },
+    nac3parser::ast::{self, StrRef},
     symbol_resolver::{StaticValue, SymbolResolver, SymbolValue, ValueEnum},
     toplevel::{
         helper::PrimDef,
@@ -20,21 +38,6 @@ use nac3core::{
         typedef::{into_var_map, iter_type_vars, Type, TypeEnum, TypeVar, Unifier, VarMap},
     },
 };
-use nac3parser::ast::{self, StrRef};
-use parking_lot::{Mutex, RwLock};
-use pyo3::{
-    types::{PyDict, PyTuple},
-    PyAny, PyObject, PyResult, Python,
-};
-use std::{
-    collections::{HashMap, HashSet},
-    sync::{
-        atomic::{AtomicBool, Ordering::Relaxed},
-        Arc,
-    },
-};
-
-use crate::PrimitivePythonId;
 
 pub enum PrimitiveValue {
     I32(i32),
@@ -79,7 +82,6 @@ pub struct InnerResolver {
     pub id_to_primitive: RwLock<HashMap<u64, PrimitiveValue>>,
     pub field_to_val: RwLock<HashMap<ResolverField, Option<PyFieldHandle>>>,
     pub global_value_ids: Arc<RwLock<HashMap<u64, PyObject>>>,
-    pub class_names: Mutex<HashMap<StrRef, Type>>,
     pub pyid_to_def: Arc<RwLock<HashMap<u64, DefinitionId>>>,
     pub pyid_to_type: Arc<RwLock<HashMap<u64, Type>>>,
     pub primitive_ids: PrimitivePythonId,
@@ -133,6 +135,8 @@ impl StaticValue for PythonValue {
                         format!("{}_const", self.id).as_str(),
                     );
                     global.set_constant(true);
+                    // Set linkage of global to private to avoid name collisions
+                    global.set_linkage(Linkage::Private);
                     global.set_initializer(&ctx.ctx.const_struct(
                         &[ctx.ctx.i32_type().const_int(u64::from(id), false).into()],
                         false,
@@ -163,7 +167,7 @@ impl StaticValue for PythonValue {
                 PrimitiveValue::Bool(val) => {
                     ctx.ctx.i8_type().const_int(u64::from(*val), false).into()
                 }
-                PrimitiveValue::Str(val) => ctx.ctx.const_string(val.as_bytes(), true).into(),
+                PrimitiveValue::Str(val) => ctx.gen_string(generator, val).into(),
             });
         }
         if let Some(global) = ctx.module.get_global(&self.id.to_string()) {
@@ -351,7 +355,7 @@ impl InnerResolver {
             Ok(Ok((ndarray, false)))
         } else if ty_id == self.primitive_ids.tuple {
             // do not handle type var param and concrete check here
-            Ok(Ok((unifier.add_ty(TypeEnum::TTuple { ty: vec![] }), false)))
+            Ok(Ok((unifier.add_ty(TypeEnum::TTuple { ty: vec![], is_vararg_ctx: false }), false)))
         } else if ty_id == self.primitive_ids.option {
             Ok(Ok((primitives.option, false)))
         } else if ty_id == self.primitive_ids.none {
@@ -555,7 +559,10 @@ impl InnerResolver {
                             Err(err) => return Ok(Err(err)),
                             _ => return Ok(Err("tuple type needs at least 1 type parameters".to_string()))
                         };
-                    Ok(Ok((unifier.add_ty(TypeEnum::TTuple { ty: args }), true)))
+                    Ok(Ok((
+                        unifier.add_ty(TypeEnum::TTuple { ty: args, is_vararg_ctx: false }),
+                        true,
+                    )))
                 }
                 TypeEnum::TObj { params, obj_id, .. } => {
                     let subst = {
@@ -797,7 +804,9 @@ impl InnerResolver {
                     .map(|elem| self.get_obj_type(py, elem, unifier, defs, primitives))
                     .collect();
                 let types = types?;
-                Ok(types.map(|types| unifier.add_ty(TypeEnum::TTuple { ty: types })))
+                Ok(types.map(|types| {
+                    unifier.add_ty(TypeEnum::TTuple { ty: types, is_vararg_ctx: false })
+                }))
             }
             // special handling for option type since its class member layout in python side
             // is special and cannot be mapped directly to a nac3 type as below
@@ -972,7 +981,7 @@ impl InnerResolver {
         } else if ty_id == self.primitive_ids.string || ty_id == self.primitive_ids.np_str_ {
             let val: String = obj.extract().unwrap();
             self.id_to_primitive.write().insert(id, PrimitiveValue::Str(val.clone()));
-            Ok(Some(ctx.ctx.const_string(val.as_bytes(), true).into()))
+            Ok(Some(ctx.gen_string(generator, val).into()))
         } else if ty_id == self.primitive_ids.float || ty_id == self.primitive_ids.float64 {
             let val: f64 = obj.extract().unwrap();
             self.id_to_primitive.write().insert(id, PrimitiveValue::F64(val));
@@ -1076,18 +1085,19 @@ impl InnerResolver {
             } else {
                 unreachable!("must be ndarray")
             };
-            let (ndarray_dtype, ndarray_ndims) =
+            let (ndarray_dtype, _) = unpack_ndarray_var_tys(&mut ctx.unifier, ndarray_ty);
-                unpack_ndarray_var_tys(&mut ctx.unifier, ndarray_ty);
 
+            let llvm_i8 = ctx.ctx.i8_type();
+            let llvm_pi8 = llvm_i8.ptr_type(AddressSpace::default());
             let llvm_usize = generator.get_size_type(ctx.ctx);
-            let ndarray_dtype_llvm_ty = ctx.get_llvm_type(generator, ndarray_dtype);
+            let llvm_ndarray = NDArrayType::from_unifier_type(generator, ctx, ndarray_ty);
-            let ndarray_llvm_ty = NDArrayType::new(generator, ctx.ctx, ndarray_dtype_llvm_ty);
+            let dtype = llvm_ndarray.element_type();
 
             {
                 if self.global_value_ids.read().contains_key(&id) {
                     let global = ctx.module.get_global(&id_str).unwrap_or_else(|| {
                         ctx.module.add_global(
-                            ndarray_llvm_ty.as_underlying_type(),
+                            llvm_ndarray.as_base_type().get_element_type().into_struct_type(),
                             Some(AddressSpace::default()),
                             &id_str,
                         )
@@ -1097,40 +1107,41 @@ impl InnerResolver {
                 self.global_value_ids.write().insert(id, obj.into());
             }
 
-            let TypeEnum::TLiteral { values, .. } = &*ctx.unifier.get_ty_immutable(ndarray_ndims)
+            let ndims = llvm_ndarray.ndims().unwrap();
-            else {
-                unreachable!("Expected Literal for ndarray_ndims")
-            };
-
-            let ndarray_ndims = if values.len() == 1 {
-                values[0].clone()
-            } else {
-                todo!("Unpacking literal of more than one element unimplemented")
-            };
-            let Ok(ndarray_ndims) = u64::try_from(ndarray_ndims) else {
-                unreachable!("Expected u64 value for ndarray_ndims")
-            };
 
             // Obtain the shape of the ndarray
             let shape_tuple: &PyTuple = obj.getattr("shape")?.downcast()?;
-            assert_eq!(shape_tuple.len(), ndarray_ndims as usize);
+            assert_eq!(shape_tuple.len(), ndims as usize);
-            let shape_values: Result<Option<Vec<_>>, _> = shape_tuple
+
+            // The Rust type inferencer cannot figure this out
+            let shape_values = shape_tuple
                 .iter()
                 .enumerate()
                 .map(|(i, elem)| {
-                    self.get_obj_value(py, elem, ctx, generator, ctx.primitives.usize()).map_err(
+                    let value = self
-                        |e| super::CompileError::new_err(format!("Error getting element {i}: {e}")),
+                        .get_obj_value(py, elem, ctx, generator, ctx.primitives.usize())
-                    )
+                        .map_err(|e| {
+                            super::CompileError::new_err(format!("Error getting element {i}: {e}"))
+                        })?
+                        .unwrap();
+                    let value = value.into_int_value();
+                    Ok(value)
                 })
-                .collect();
+                .collect::<Result<Vec<_>, PyErr>>()?;
-            let shape_values = shape_values?.unwrap();
+
-            let shape_values = llvm_usize.const_array(
+            // Also use this opportunity to get the constant values of `shape_values` for calculating strides.
-                &shape_values.into_iter().map(BasicValueEnum::into_int_value).collect_vec(),
+            let shape_u64s = shape_values
-            );
+                .iter()
+                .map(|dim| {
+                    assert!(dim.is_const());
+                    dim.get_zero_extended_constant().unwrap()
+                })
+                .collect_vec();
+            let shape_values = llvm_usize.const_array(&shape_values);
 
             // create a global for ndarray.shape and initialize it using the shape
             let shape_global = ctx.module.add_global(
-                llvm_usize.array_type(ndarray_ndims as u32),
+                llvm_usize.array_type(ndims as u32),
                 Some(AddressSpace::default()),
                 &(id_str.clone() + ".shape"),
             );
@@ -1138,17 +1149,25 @@ impl InnerResolver {
 
             // Obtain the (flattened) elements of the ndarray
             let sz: usize = obj.getattr("size")?.extract()?;
-            let data: Result<Option<Vec<_>>, _> = (0..sz)
+            let data: Vec<_> = (0..sz)
                 .map(|i| {
                     obj.getattr("flat")?.get_item(i).and_then(|elem| {
-                        self.get_obj_value(py, elem, ctx, generator, ndarray_dtype).map_err(|e| {
+                        let value = self
-                            super::CompileError::new_err(format!("Error getting element {i}: {e}"))
+                            .get_obj_value(py, elem, ctx, generator, ndarray_dtype)
+                            .map_err(|e| {
+                                super::CompileError::new_err(format!(
+                                    "Error getting element {i}: {e}"
+                                ))
+                            })?
+                            .unwrap();
+
+                        assert_eq!(value.get_type(), dtype);
+                        Ok(value)
                     })
                 })
-                })
+                .try_collect()?;
-                .collect();
+            let data = data.into_iter();
-            let data = data?.unwrap().into_iter();
+            let data = match dtype {
-            let data = match ndarray_dtype_llvm_ty {
                 BasicTypeEnum::ArrayType(ty) => {
                     ty.const_array(&data.map(BasicValueEnum::into_array_value).collect_vec())
                 }
@@ -1173,37 +1192,73 @@ impl InnerResolver {
             };
 
             // create a global for ndarray.data and initialize it using the elements
+            //
+            // NOTE: NDArray's `data` is `u8*`. Here, `data_global` is an array of `dtype`.
+            // We will have to cast it to an `u8*` later.
             let data_global = ctx.module.add_global(
-                ndarray_dtype_llvm_ty.array_type(sz as u32),
+                dtype.array_type(sz as u32),
                 Some(AddressSpace::default()),
                 &(id_str.clone() + ".data"),
             );
             data_global.set_initializer(&data);
 
+            // Get the constant itemsize.
+            let itemsize = dtype.size_of().unwrap();
+            let itemsize = itemsize.get_zero_extended_constant().unwrap();
+
+            // Create the strides needed for ndarray.strides
+            let strides = make_contiguous_strides(itemsize, ndims, &shape_u64s);
+            let strides =
+                strides.into_iter().map(|stride| llvm_usize.const_int(stride, false)).collect_vec();
+            let strides = llvm_usize.const_array(&strides);
+
+            // create a global for ndarray.strides and initialize it
+            let strides_global = ctx.module.add_global(
+                llvm_i8.array_type(ndims as u32),
+                Some(AddressSpace::default()),
+                &format!("${id_str}.strides"),
+            );
+            strides_global.set_initializer(&strides);
+
             // create a global for the ndarray object and initialize it
-            let value = ndarray_llvm_ty.as_underlying_type().const_named_struct(&[
+
-                llvm_usize.const_int(ndarray_ndims, false).into(),
+            // NOTE: data_global is an array of dtype, we want a `u8*`.
-                shape_global
+            let ndarray_data = data_global.as_pointer_value();
-                    .as_pointer_value()
+            let ndarray_data = ctx.builder.build_pointer_cast(ndarray_data, llvm_pi8, "").unwrap();
-                    .const_cast(llvm_usize.ptr_type(AddressSpace::default()))
+
-                    .into(),
+            let ndarray_itemsize = llvm_usize.const_int(itemsize, false);
-                data_global
+
-                    .as_pointer_value()
+            let ndarray_ndims = llvm_usize.const_int(ndims, false);
-                    .const_cast(ndarray_dtype_llvm_ty.ptr_type(AddressSpace::default()))
+
-                    .into(),
+            let ndarray_shape = shape_global.as_pointer_value();
+
+            let ndarray_strides = strides_global.as_pointer_value();
+
+            let ndarray = llvm_ndarray
+                .as_base_type()
+                .get_element_type()
+                .into_struct_type()
+                .const_named_struct(&[
+                    ndarray_itemsize.into(),
+                    ndarray_ndims.into(),
+                    ndarray_shape.into(),
+                    ndarray_strides.into(),
+                    ndarray_data.into(),
                 ]);
 
-            let ndarray = ctx.module.add_global(
+            let ndarray_global = ctx.module.add_global(
-                ndarray_llvm_ty.as_underlying_type(),
+                llvm_ndarray.as_base_type().get_element_type().into_struct_type(),
                 Some(AddressSpace::default()),
                 &id_str,
             );
-            ndarray.set_initializer(&value);
+            ndarray_global.set_initializer(&ndarray);
 
-            Ok(Some(ndarray.as_pointer_value().into()))
+            Ok(Some(ndarray_global.as_pointer_value().into()))
         } else if ty_id == self.primitive_ids.tuple {
             let expected_ty_enum = ctx.unifier.get_ty_immutable(expected_ty);
-            let TypeEnum::TTuple { ty } = expected_ty_enum.as_ref() else { unreachable!() };
+            let TypeEnum::TTuple { ty, is_vararg_ctx: false } = expected_ty_enum.as_ref() else {
+                unreachable!()
+            };
 
             let tup_tys = ty.iter();
             let elements: &PyTuple = obj.downcast()?;
@@ -1459,6 +1514,7 @@ impl SymbolResolver for Resolver {
         &self,
         id: StrRef,
         _: &mut CodeGenContext<'ctx, '_>,
+        _: &mut dyn CodeGenerator,
     ) -> Option<ValueEnum<'ctx>> {
         let sym_value = {
             let id_to_val = self.0.id_to_pyval.read();
@@ -1520,10 +1576,7 @@ impl SymbolResolver for Resolver {
         if let Some(id) = string_store.get(s) {
             *id
         } else {
-            let id = Python::with_gil(|py| -> PyResult<i32> {
+            let id = i32::try_from(string_store.len()).unwrap();
-                self.0.helper.store_str.call1(py, (s,))?.extract(py)
-            })
-            .unwrap();
             string_store.insert(s.into(), id);
             id
         }

nac3artiq/src/timeline.rs

@@ -1,9 +1,12 @@
-use inkwell::{
+use itertools::Either;
+
+use nac3core::{
+    codegen::CodeGenContext,
+    inkwell::{
         values::{BasicValueEnum, CallSiteValue},
         AddressSpace, AtomicOrdering,
+    },
 };
-use itertools::Either;
-use nac3core::codegen::CodeGenContext;
 
 /// Functions for manipulating the timeline.
 pub trait TimeFns {
@@ -31,7 +34,7 @@ impl TimeFns for NowPinningTimeFns64 {
             .unwrap_or_else(|| ctx.module.add_global(i64_type, None, "now"));
         let now_hiptr = ctx
             .builder
-            .build_bitcast(now, i32_type.ptr_type(AddressSpace::default()), "now.hi.addr")
+            .build_bit_cast(now, i32_type.ptr_type(AddressSpace::default()), "now.hi.addr")
             .map(BasicValueEnum::into_pointer_value)
             .unwrap();
 
@@ -80,7 +83,7 @@ impl TimeFns for NowPinningTimeFns64 {
             .unwrap_or_else(|| ctx.module.add_global(i64_type, None, "now"));
         let now_hiptr = ctx
             .builder
-            .build_bitcast(now, i32_type.ptr_type(AddressSpace::default()), "now.hi.addr")
+            .build_bit_cast(now, i32_type.ptr_type(AddressSpace::default()), "now.hi.addr")
             .map(BasicValueEnum::into_pointer_value)
             .unwrap();
 
@@ -109,7 +112,7 @@ impl TimeFns for NowPinningTimeFns64 {
             .unwrap_or_else(|| ctx.module.add_global(i64_type, None, "now"));
         let now_hiptr = ctx
             .builder
-            .build_bitcast(now, i32_type.ptr_type(AddressSpace::default()), "now.hi.addr")
+            .build_bit_cast(now, i32_type.ptr_type(AddressSpace::default()), "now.hi.addr")
             .map(BasicValueEnum::into_pointer_value)
             .unwrap();
 
@@ -207,7 +210,7 @@ impl TimeFns for NowPinningTimeFns {
             .unwrap_or_else(|| ctx.module.add_global(i64_type, None, "now"));
         let now_hiptr = ctx
             .builder
-            .build_bitcast(now, i32_type.ptr_type(AddressSpace::default()), "now.hi.addr")
+            .build_bit_cast(now, i32_type.ptr_type(AddressSpace::default()), "now.hi.addr")
             .map(BasicValueEnum::into_pointer_value)
             .unwrap();
 
@@ -258,7 +261,7 @@ impl TimeFns for NowPinningTimeFns {
         let time_lo = ctx.builder.build_int_truncate(time, i32_type, "time.lo").unwrap();
         let now_hiptr = ctx
             .builder
-            .build_bitcast(now, i32_type.ptr_type(AddressSpace::default()), "now.hi.addr")
+            .build_bit_cast(now, i32_type.ptr_type(AddressSpace::default()), "now.hi.addr")
             .map(BasicValueEnum::into_pointer_value)
             .unwrap();
 

nac3ast/Cargo.toml

@@ -10,7 +10,6 @@ constant-optimization = ["fold"]
 fold = []
 
 [dependencies]
-lazy_static = "1.5"
 parking_lot = "0.12"
 string-interner = "0.17"
 fxhash = "0.2"

nac3ast/src/ast_gen.rs

@@ -5,14 +5,12 @@ pub use crate::location::Location;
 
 use fxhash::FxBuildHasher;
 use parking_lot::{Mutex, MutexGuard};
-use std::{cell::RefCell, collections::HashMap, fmt};
+use std::{cell::RefCell, collections::HashMap, fmt, sync::LazyLock};
 use string_interner::{symbol::SymbolU32, DefaultBackend, StringInterner};
 
 pub type Interner = StringInterner<DefaultBackend, FxBuildHasher>;
-lazy_static! {
+static INTERNER: LazyLock<Mutex<Interner>> =
-    static ref INTERNER: Mutex<Interner> =
+    LazyLock::new(|| Mutex::new(StringInterner::with_hasher(FxBuildHasher::default())));
-        Mutex::new(StringInterner::with_hasher(FxBuildHasher::default()));
-}
 
 thread_local! {
     static LOCAL_INTERNER: RefCell<HashMap<String, StrRef>> = RefCell::default();

nac3ast/src/lib.rs

@@ -1,10 +1,4 @@
-#![deny(
+#![deny(future_incompatible, let_underscore, nonstandard_style, clippy::all)]
-    future_incompatible,
-    let_underscore,
-    nonstandard_style,
-    rust_2024_compatibility,
-    clippy::all
-)]
 #![warn(clippy::pedantic)]
 #![allow(
     clippy::missing_errors_doc,
@@ -14,9 +8,6 @@
     clippy::wildcard_imports
 )]
 
-#[macro_use]
-extern crate lazy_static;
-
 mod ast_gen;
 mod constant;
 #[cfg(feature = "fold")]

nac3core/Cargo.toml

@@ -1,26 +1,29 @@
-[features]
-test = []
-
 [package]
 name = "nac3core"
 version = "0.1.0"
 authors = ["M-Labs"]
 edition = "2021"
 
+[features]
+default = ["derive"]
+derive = ["dep:nac3core_derive"]
+no-escape-analysis = []
+
 [dependencies]
 itertools = "0.13"
 crossbeam = "0.8"
-indexmap = "2.2"
+indexmap = "2.6"
 parking_lot = "0.12"
-rayon = "1.8"
+rayon = "1.10"
+nac3core_derive = { path = "nac3core_derive", optional = true }
 nac3parser = { path = "../nac3parser" }
-strum = "0.26.2"
+strum = "0.26"
-strum_macros = "0.26.4"
+strum_macros = "0.26"
 
 [dependencies.inkwell]
-version = "0.4"
+version = "0.5"
 default-features = false
-features = ["llvm14-0", "target-x86", "target-arm", "target-riscv", "no-libffi-linking"]
+features = ["llvm14-0-prefer-dynamic", "target-x86", "target-arm", "target-riscv", "no-libffi-linking"]
 
 [dev-dependencies]
 test-case = "1.2.0"

nac3core/build.rs

@@ -1,46 +1,32 @@
-use regex::Regex;
 use std::{
     env,
     fs::File,
     io::Write,
-    path::{Path, PathBuf},
+    path::Path,
     process::{Command, Stdio},
 };
 
-const CMD_IRRT_CLANG: &str = "clang-irrt";
+use regex::Regex;
-const CMD_IRRT_CLANG_TEST: &str = "clang-irrt-test";
-const CMD_IRRT_LLVM_AS: &str = "llvm-as-irrt";
 
-fn get_out_dir() -> PathBuf {
+fn main() {
-    PathBuf::from(env::var("OUT_DIR").unwrap())
+    let out_dir = env::var("OUT_DIR").unwrap();
-}
+    let out_dir = Path::new(&out_dir);
+    let irrt_dir = Path::new("irrt");
 
-fn get_irrt_dir() -> &'static Path {
+    let irrt_cpp_path = irrt_dir.join("irrt.cpp");
-    Path::new("irrt")
-}
-
-/// Compile `irrt.cpp` for use in `src/codegen`
-fn compile_irrt_cpp() {
-    let out_dir = get_out_dir();
-    let irrt_dir = get_irrt_dir();
 
     /*
      * HACK: Sadly, clang doesn't let us emit generic LLVM bitcode.
      * Compiling for WASM32 and filtering the output with regex is the closest we can get.
      */
-    let irrt_cpp_path = irrt_dir.join("irrt.cpp");
+    let mut flags: Vec<&str> = vec![
-    let flags: &[&str] = &[
         "--target=wasm32",
         "-x",
         "c++",
+        "-std=c++20",
         "-fno-discard-value-names",
         "-fno-exceptions",
         "-fno-rtti",
-        match env::var("PROFILE").as_deref() {
-            Ok("debug") => "-O0",
-            Ok("release") => "-O3",
-            flavor => panic!("Unknown or missing build flavor {flavor:?}"),
-        },
         "-emit-llvm",
         "-S",
         "-Wall",
@@ -52,16 +38,26 @@ fn compile_irrt_cpp() {
         irrt_cpp_path.to_str().unwrap(),
     ];
 
+    match env::var("PROFILE").as_deref() {
+        Ok("debug") => {
+            flags.push("-O0");
+            flags.push("-DIRRT_DEBUG_ASSERT");
+        }
+        Ok("release") => {
+            flags.push("-O3");
+        }
+        flavor => panic!("Unknown or missing build flavor {flavor:?}"),
+    }
+
     // Tell Cargo to rerun if any file under `irrt_dir` (recursive) changes
     println!("cargo:rerun-if-changed={}", irrt_dir.to_str().unwrap());
 
     // Compile IRRT and capture the LLVM IR output
-    let output = Command::new(CMD_IRRT_CLANG)
+    let output = Command::new("clang-irrt")
         .args(flags)
         .output()
-        .map(|o| {
+        .inspect(|o| {
             assert!(o.status.success(), "{}", std::str::from_utf8(&o.stderr).unwrap());
-            o
         })
         .unwrap();
 
@@ -102,9 +98,7 @@ fn compile_irrt_cpp() {
         file.write_all(filtered_output.as_bytes()).unwrap();
     }
 
-    // Assemble the emitted and filtered IR to .bc
+    let mut llvm_as = Command::new("llvm-as-irrt")
-    // That .bc will be integrated into nac3core's codegen
-    let mut llvm_as = Command::new(CMD_IRRT_LLVM_AS)
         .stdin(Stdio::piped())
         .arg("-o")
         .arg(out_dir.join("irrt.bc"))
@@ -113,48 +107,3 @@ fn compile_irrt_cpp() {
     llvm_as.stdin.as_mut().unwrap().write_all(filtered_output.as_bytes()).unwrap();
     assert!(llvm_as.wait().unwrap().success());
 }
-
-/// Compile `irrt_test.cpp` for testing
-fn compile_irrt_test_cpp() {
-    let out_dir = get_out_dir();
-    let irrt_dir = get_irrt_dir();
-
-    let exe_path = out_dir.join("irrt_test.out"); // Output path of the compiled test executable
-    let irrt_test_cpp_path = irrt_dir.join("irrt_test.cpp");
-    let flags: &[&str] = &[
-        irrt_test_cpp_path.to_str().unwrap(),
-        "-x",
-        "c++",
-        "-I",
-        irrt_dir.to_str().unwrap(),
-        "-g",
-        "-fno-discard-value-names",
-        "-O0",
-        "-Wall",
-        "-Wextra",
-        "-Werror=return-type",
-        "-lm", // for `tgamma()`, `lgamma()`
-        "-o",
-        exe_path.to_str().unwrap(),
-    ];
-
-    Command::new(CMD_IRRT_CLANG_TEST)
-        .args(flags)
-        .output()
-        .map(|o| {
-            assert!(o.status.success(), "{}", std::str::from_utf8(&o.stderr).unwrap());
-            o
-        })
-        .unwrap();
-    println!("cargo:rerun-if-changed={}", irrt_dir.to_str().unwrap());
-}
-
-fn main() {
-    compile_irrt_cpp();
-
-    // https://github.com/rust-lang/cargo/issues/2549
-    // `cargo test -F test` to also build `irrt_test.cpp
-    if cfg!(feature = "test") {
-        compile_irrt_test_cpp();
-    }
-}

nac3core/irrt/irrt.cpp

@@ -1,10 +1,10 @@
-#define IRRT_DEFINE_TYPEDEF_INTS
+#include "irrt/exception.hpp"
-#include <irrt_everything.hpp>
+#include "irrt/list.hpp"
-
+#include "irrt/math.hpp"
-/*
+#include "irrt/ndarray.hpp"
- * All IRRT implementations.
+#include "irrt/range.hpp"
- *
+#include "irrt/slice.hpp"
- * We don't have pre-compiled objects, so we are writing all implementations in
+#include "irrt/ndarray/basic.hpp"
- * headers and concatenate them with `#include` into one massive source file that
+#include "irrt/ndarray/def.hpp"
- * contains all the IRRT stuff.
+#include "irrt/ndarray/iter.hpp"
- */
+#include "irrt/ndarray/indexing.hpp"

nac3core/irrt/irrt/artiq_defs.hpp

@@ -1,39 +0,0 @@
-#pragma once
-
-#include <irrt/int_defs.hpp>
-
-/*
-This file defines all ARTIQ-specific structures
-*/
-
-/**
- * @brief ARTIQ's `cslice` object
- *
- * See https://docs.rs/cslice/0.3.0/src/cslice/lib.rs.html#33-37
- */
-template <typename SizeT>
-struct CSlice {
-    const char *base;
-    SizeT len;
-};
-
-/**
- * @brief Int type of ARTIQ's `Exception` IDs.
- */
-typedef uint32_t ExceptionId;
-
-/**
- * @brief ARTIQ's `Exception` object
- *
- * See https://github.com/m-labs/artiq/blob/b0d2705c385f64b6e6711c1726cd9178f40b598e/artiq/firmware/libeh/eh_artiq.rs#L1C1-L17C1
- */
-template <typename SizeT>
-struct Exception {
-    ExceptionId id;
-    CSlice<SizeT> file;
-    uint32_t line;
-    uint32_t column;
-    CSlice<SizeT> function;
-    CSlice<SizeT> message;
-    uint32_t param;
-};

nac3core/irrt/irrt/core.hpp

@@ -1,347 +0,0 @@
-#pragma once
-
-#include <irrt/int_defs.hpp>
-#include <irrt/slice.hpp>
-#include <irrt/utils.hpp>
-
-// NDArray indices are always `uint32_t`.
-using NDIndexInt = uint32_t;
-
-namespace {
-// adapted from GNU Scientific Library:
-// https://git.savannah.gnu.org/cgit/gsl.git/tree/sys/pow_int.c
-// need to make sure `exp >= 0` before calling this function
-template <typename T>
-T __nac3_int_exp_impl(T base, T exp) {
-    T res = 1;
-    /* repeated squaring method */
-    do {
-        if (exp & 1) {
-            res *= base; /* for n odd */
-        }
-        exp >>= 1;
-        base *= base;
-    } while (exp);
-    return res;
-}
-
-template <typename SizeT>
-SizeT __nac3_ndarray_calc_size_impl(const SizeT* list_data, SizeT list_len,
-                                    SizeT begin_idx, SizeT end_idx) {
-    __builtin_assume(end_idx <= list_len);
-
-    SizeT num_elems = 1;
-    for (SizeT i = begin_idx; i < end_idx; ++i) {
-        SizeT val = list_data[i];
-        __builtin_assume(val > 0);
-        num_elems *= val;
-    }
-    return num_elems;
-}
-
-template <typename SizeT>
-void __nac3_ndarray_calc_nd_indices_impl(SizeT index, const SizeT* dims,
-                                         SizeT num_dims, NDIndexInt* idxs) {
-    SizeT stride = 1;
-    for (SizeT dim = 0; dim < num_dims; dim++) {
-        SizeT i = num_dims - dim - 1;
-        __builtin_assume(dims[i] > 0);
-        idxs[i] = (index / stride) % dims[i];
-        stride *= dims[i];
-    }
-}
-
-template <typename SizeT>
-SizeT __nac3_ndarray_flatten_index_impl(const SizeT* dims, SizeT num_dims,
-                                        const NDIndexInt* indices,
-                                        SizeT num_indices) {
-    SizeT idx = 0;
-    SizeT stride = 1;
-    for (SizeT i = 0; i < num_dims; ++i) {
-        SizeT ri = num_dims - i - 1;
-        if (ri < num_indices) {
-            idx += stride * indices[ri];
-        }
-
-        __builtin_assume(dims[i] > 0);
-        stride *= dims[ri];
-    }
-    return idx;
-}
-
-template <typename SizeT>
-void __nac3_ndarray_calc_broadcast_impl(const SizeT* lhs_dims, SizeT lhs_ndims,
-                                        const SizeT* rhs_dims, SizeT rhs_ndims,
-                                        SizeT* out_dims) {
-    SizeT max_ndims = lhs_ndims > rhs_ndims ? lhs_ndims : rhs_ndims;
-
-    for (SizeT i = 0; i < max_ndims; ++i) {
-        const SizeT* lhs_dim_sz =
-            i < lhs_ndims ? &lhs_dims[lhs_ndims - i - 1] : nullptr;
-        const SizeT* rhs_dim_sz =
-            i < rhs_ndims ? &rhs_dims[rhs_ndims - i - 1] : nullptr;
-
-        SizeT* out_dim = &out_dims[max_ndims - i - 1];
-
-        if (lhs_dim_sz == nullptr) {
-            *out_dim = *rhs_dim_sz;
-        } else if (rhs_dim_sz == nullptr) {
-            *out_dim = *lhs_dim_sz;
-        } else if (*lhs_dim_sz == 1) {
-            *out_dim = *rhs_dim_sz;
-        } else if (*rhs_dim_sz == 1) {
-            *out_dim = *lhs_dim_sz;
-        } else if (*lhs_dim_sz == *rhs_dim_sz) {
-            *out_dim = *lhs_dim_sz;
-        } else {
-            __builtin_unreachable();
-        }
-    }
-}
-
-template <typename SizeT>
-void __nac3_ndarray_calc_broadcast_idx_impl(const SizeT* src_dims,
-                                            SizeT src_ndims,
-                                            const NDIndexInt* in_idx,
-                                            NDIndexInt* out_idx) {
-    for (SizeT i = 0; i < src_ndims; ++i) {
-        SizeT src_i = src_ndims - i - 1;
-        out_idx[src_i] = src_dims[src_i] == 1 ? 0 : in_idx[src_i];
-    }
-}
-}  // namespace
-
-extern "C" {
-#define DEF_nac3_int_exp_(T)                   \
-    T __nac3_int_exp_##T(T base, T exp) {      \
-        return __nac3_int_exp_impl(base, exp); \
-    }
-
-DEF_nac3_int_exp_(int32_t);
-DEF_nac3_int_exp_(int64_t);
-DEF_nac3_int_exp_(uint32_t);
-DEF_nac3_int_exp_(uint64_t);
-
-SliceIndex __nac3_slice_index_bound(SliceIndex i, const SliceIndex len) {
-    if (i < 0) {
-        i = len + i;
-    }
-    if (i < 0) {
-        return 0;
-    } else if (i > len) {
-        return len;
-    }
-    return i;
-}
-
-SliceIndex __nac3_range_slice_len(const SliceIndex start, const SliceIndex end,
-                                  const SliceIndex step) {
-    SliceIndex diff = end - start;
-    if (diff > 0 && step > 0) {
-        return ((diff - 1) / step) + 1;
-    } else if (diff < 0 && step < 0) {
-        return ((diff + 1) / step) + 1;
-    } else {
-        return 0;
-    }
-}
-
-// Handle list assignment and dropping part of the list when
-// both dest_step and src_step are +1.
-// - All the index must *not* be out-of-bound or negative,
-// - The end index is *inclusive*,
-// - The length of src and dest slice size should already
-// be checked: if dest.step == 1 then len(src) <= len(dest) else
-// len(src) == len(dest)
-SliceIndex __nac3_list_slice_assign_var_size(
-    SliceIndex dest_start, SliceIndex dest_end, SliceIndex dest_step,
-    uint8_t* dest_arr, SliceIndex dest_arr_len, SliceIndex src_start,
-    SliceIndex src_end, SliceIndex src_step, uint8_t* src_arr,
-    SliceIndex src_arr_len, const SliceIndex size) {
-    /* if dest_arr_len == 0, do nothing since we do not support
-     * extending list
-     */
-    if (dest_arr_len == 0) return dest_arr_len;
-    /* if both step is 1, memmove directly, handle the dropping of
-     * the list, and shrink size */
-    if (src_step == dest_step && dest_step == 1) {
-        const SliceIndex src_len =
-            (src_end >= src_start) ? (src_end - src_start + 1) : 0;
-        const SliceIndex dest_len =
-            (dest_end >= dest_start) ? (dest_end - dest_start + 1) : 0;
-        if (src_len > 0) {
-            __builtin_memmove(dest_arr + dest_start * size,
-                              src_arr + src_start * size, src_len * size);
-        }
-        if (dest_len > 0) {
-            /* dropping */
-            __builtin_memmove(dest_arr + (dest_start + src_len) * size,
-                              dest_arr + (dest_end + 1) * size,
-                              (dest_arr_len - dest_end - 1) * size);
-        }
-        /* shrink size */
-        return dest_arr_len - (dest_len - src_len);
-    }
-    /* if two range overlaps, need alloca */
-    uint8_t need_alloca =
-        (dest_arr == src_arr) &&
-        !(max(dest_start, dest_end) < min(src_start, src_end) ||
-          max(src_start, src_end) < min(dest_start, dest_end));
-    if (need_alloca) {
-        uint8_t* tmp =
-            reinterpret_cast<uint8_t*>(__builtin_alloca(src_arr_len * size));
-        __builtin_memcpy(tmp, src_arr, src_arr_len * size);
-        src_arr = tmp;
-    }
-    SliceIndex src_ind = src_start;
-    SliceIndex dest_ind = dest_start;
-    for (; (src_step > 0) ? (src_ind <= src_end) : (src_ind >= src_end);
-         src_ind += src_step, dest_ind += dest_step) {
-        /* for constant optimization */
-        if (size == 1) {
-            __builtin_memcpy(dest_arr + dest_ind, src_arr + src_ind, 1);
-        } else if (size == 4) {
-            __builtin_memcpy(dest_arr + dest_ind * 4, src_arr + src_ind * 4, 4);
-        } else if (size == 8) {
-            __builtin_memcpy(dest_arr + dest_ind * 8, src_arr + src_ind * 8, 8);
-        } else {
-            /* memcpy for var size, cannot overlap after previous
-             * alloca */
-            __builtin_memcpy(dest_arr + dest_ind * size,
-                             src_arr + src_ind * size, size);
-        }
-    }
-    /* only dest_step == 1 can we shrink the dest list. */
-    /* size should be ensured prior to calling this function */
-    if (dest_step == 1 && dest_end >= dest_start) {
-        __builtin_memmove(
-            dest_arr + dest_ind * size, dest_arr + (dest_end + 1) * size,
-            (dest_arr_len - dest_end - 1) * size + size + size + size);
-        return dest_arr_len - (dest_end - dest_ind) - 1;
-    }
-    return dest_arr_len;
-}
-
-int32_t __nac3_isinf(double x) { return __builtin_isinf(x); }
-
-int32_t __nac3_isnan(double x) { return __builtin_isnan(x); }
-
-double tgamma(double arg);
-
-double __nac3_gamma(double z) {
-    // Handling for denormals
-    //     | x                 | Python gamma(x) | C tgamma(x) |
-    // --- | ----------------- | --------------- | ----------- |
-    // (1) | nan               | nan             | nan         |
-    // (2) | -inf              | -inf            | inf         |
-    // (3) | inf               | inf             | inf         |
-    // (4) | 0.0               | inf             | inf         |
-    // (5) | {-1.0, -2.0, ...} | inf             | nan         |
-
-    // (1)-(3)
-    if (__builtin_isinf(z) || __builtin_isnan(z)) {
-        return z;
-    }
-
-    double v = tgamma(z);
-
-    // (4)-(5)
-    return __builtin_isinf(v) || __builtin_isnan(v) ? __builtin_inf() : v;
-}
-
-double lgamma(double arg);
-
-double __nac3_gammaln(double x) {
-    // libm's handling of value overflows differs from scipy:
-    // - scipy: gammaln(-inf) -> -inf
-    // - libm : lgamma(-inf) -> inf
-
-    if (__builtin_isinf(x)) {
-        return x;
-    }
-
-    return lgamma(x);
-}
-
-double j0(double x);
-
-double __nac3_j0(double x) {
-    // libm's handling of value overflows differs from scipy:
-    // - scipy: j0(inf) -> nan
-    // - libm : j0(inf) -> 0.0
-
-    if (__builtin_isinf(x)) {
-        return __builtin_nan("");
-    }
-
-    return j0(x);
-}
-
-uint32_t __nac3_ndarray_calc_size(const uint32_t* list_data, uint32_t list_len,
-                                  uint32_t begin_idx, uint32_t end_idx) {
-    return __nac3_ndarray_calc_size_impl(list_data, list_len, begin_idx,
-                                         end_idx);
-}
-
-uint64_t __nac3_ndarray_calc_size64(const uint64_t* list_data,
-                                    uint64_t list_len, uint64_t begin_idx,
-                                    uint64_t end_idx) {
-    return __nac3_ndarray_calc_size_impl(list_data, list_len, begin_idx,
-                                         end_idx);
-}
-
-void __nac3_ndarray_calc_nd_indices(uint32_t index, const uint32_t* dims,
-                                    uint32_t num_dims, NDIndexInt* idxs) {
-    __nac3_ndarray_calc_nd_indices_impl(index, dims, num_dims, idxs);
-}
-
-void __nac3_ndarray_calc_nd_indices64(uint64_t index, const uint64_t* dims,
-                                      uint64_t num_dims, NDIndexInt* idxs) {
-    __nac3_ndarray_calc_nd_indices_impl(index, dims, num_dims, idxs);
-}
-
-uint32_t __nac3_ndarray_flatten_index(const uint32_t* dims, uint32_t num_dims,
-                                      const NDIndexInt* indices,
-                                      uint32_t num_indices) {
-    return __nac3_ndarray_flatten_index_impl(dims, num_dims, indices,
-                                             num_indices);
-}
-
-uint64_t __nac3_ndarray_flatten_index64(const uint64_t* dims, uint64_t num_dims,
-                                        const NDIndexInt* indices,
-                                        uint64_t num_indices) {
-    return __nac3_ndarray_flatten_index_impl(dims, num_dims, indices,
-                                             num_indices);
-}
-
-void __nac3_ndarray_calc_broadcast(const uint32_t* lhs_dims, uint32_t lhs_ndims,
-                                   const uint32_t* rhs_dims, uint32_t rhs_ndims,
-                                   uint32_t* out_dims) {
-    return __nac3_ndarray_calc_broadcast_impl(lhs_dims, lhs_ndims, rhs_dims,
-                                              rhs_ndims, out_dims);
-}
-
-void __nac3_ndarray_calc_broadcast64(const uint64_t* lhs_dims,
-                                     uint64_t lhs_ndims,
-                                     const uint64_t* rhs_dims,
-                                     uint64_t rhs_ndims, uint64_t* out_dims) {
-    return __nac3_ndarray_calc_broadcast_impl(lhs_dims, lhs_ndims, rhs_dims,
-                                              rhs_ndims, out_dims);
-}
-
-void __nac3_ndarray_calc_broadcast_idx(const uint32_t* src_dims,
-                                       uint32_t src_ndims,
-                                       const NDIndexInt* in_idx,
-                                       NDIndexInt* out_idx) {
-    __nac3_ndarray_calc_broadcast_idx_impl(src_dims, src_ndims, in_idx,
-                                           out_idx);
-}
-
-void __nac3_ndarray_calc_broadcast_idx64(const uint64_t* src_dims,
-                                         uint64_t src_ndims,
-                                         const NDIndexInt* in_idx,
-                                         NDIndexInt* out_idx) {
-    __nac3_ndarray_calc_broadcast_idx_impl(src_dims, src_ndims, in_idx,
-                                           out_idx);
-}
-}  // extern "C"

nac3core/irrt/irrt/cslice.hpp

@@ -0,0 +1,9 @@
+#pragma once
+
+#include "irrt/int_types.hpp"
+
+template<typename SizeT>
+struct CSlice {
+    void* base;
+    SizeT len;
+};

nac3core/irrt/irrt/debug.hpp

@@ -0,0 +1,25 @@
+#pragma once
+
+// Set in nac3core/build.rs
+#ifdef IRRT_DEBUG_ASSERT
+#define IRRT_DEBUG_ASSERT_BOOL true
+#else
+#define IRRT_DEBUG_ASSERT_BOOL false
+#endif
+
+#define raise_debug_assert(SizeT, msg, param1, param2, param3) \
+    raise_exception(SizeT, EXN_ASSERTION_ERROR, "IRRT debug assert failed: " msg, param1, param2, param3)
+
+#define debug_assert_eq(SizeT, lhs, rhs)                                           \
+    if constexpr (IRRT_DEBUG_ASSERT_BOOL) {                                        \
+        if ((lhs) != (rhs)) {                                                      \
+            raise_debug_assert(SizeT, "LHS = {0}. RHS = {1}", lhs, rhs, NO_PARAM); \
+        }                                                                          \
+    }
+
+#define debug_assert(SizeT, expr)                                                  \
+    if constexpr (IRRT_DEBUG_ASSERT_BOOL) {                                        \
+        if (!(expr)) {                                                             \
+            raise_debug_assert(SizeT, "Got false.", NO_PARAM, NO_PARAM, NO_PARAM); \
+        }                                                                          \
+    }

nac3core/irrt/irrt/error_context.hpp

@@ -1,92 +0,0 @@
-#pragma once
-
-#include <irrt/artiq_defs.hpp>
-#include <irrt/int_defs.hpp>
-#include <irrt/utils.hpp>
-
-namespace {
-/**
- * @brief A (limited) set of known Exception IDs usable in IRRT
- */
-struct ErrorContextExceptions {
-    ExceptionId index_error;
-    ExceptionId value_error;
-    ExceptionId assertion_error;
-    ExceptionId runtime_error;
-    ExceptionId type_error;
-};
-
-/**
- * @brief The IRRT error context object
- *
- * This object contains all the details needed to propagate Python-like Exceptions in
- * IRRT - within IRRT itself or propagate out of extern calls from nac3core.
- */
-struct ErrorContext {
-    const ErrorContextExceptions *exceptions;
-
-    // Exception thrown by IRRT
-    ExceptionId exception_id;
-    // Points to empty c-string if there is no thrown Exception
-    const char *msg;
-    uint64_t param1;
-    uint64_t param2;
-    uint64_t param3;
-
-    void initialize(const ErrorContextExceptions *exceptions) {
-        this->exceptions = exceptions;
-        clear_error();
-    }
-
-    void clear_error() {
-        // NOTE: Point the msg to an empty str.
-        // Don't set it to nullptr - to implement `has_exception`
-        this->msg = "";
-    }
-
-    void set_exception(ExceptionId exception_id, const char *msg,
-                       uint64_t param1 = 0, uint64_t param2 = 0,
-                       uint64_t param3 = 0) {
-        this->exception_id = exception_id;
-        this->msg = msg;
-        this->param1 = param1;
-        this->param2 = param2;
-        this->param3 = param3;
-    }
-
-    bool has_exception() { return !cstr_utils::is_empty(msg); }
-
-    template <typename SizeT>
-    void get_exception_str(CSlice<SizeT> *dst_str) {
-        dst_str->base = msg;
-        dst_str->len = (SizeT)cstr_utils::length(msg);
-    }
-};
-}  // namespace
-
-extern "C" {
-void __nac3_error_context_initialize(ErrorContext *errctx,
-                                     ErrorContextExceptions *exceptions) {
-    errctx->initialize(exceptions);
-}
-
-bool __nac3_error_context_has_exception(ErrorContext *errctx) {
-    return errctx->has_exception();
-}
-
-void __nac3_error_context_get_exception_str(ErrorContext *errctx,
-                                            CSlice<int32_t> *dst_str) {
-    errctx->get_exception_str<int32_t>(dst_str);
-}
-
-void __nac3_error_context_get_exception_str64(ErrorContext *errctx,
-                                              CSlice<int64_t> *dst_str) {
-    errctx->get_exception_str<int64_t>(dst_str);
-}
-
-// Used for testing
-void __nac3_error_dummy_raise(ErrorContext *errctx) {
-    errctx->set_exception(errctx->exceptions->runtime_error,
-                          "Error thrown from __nac3_error_dummy_raise");
-}
-}

nac3core/irrt/irrt/exception.hpp

@@ -0,0 +1,85 @@
+#pragma once
+
+#include "irrt/cslice.hpp"
+#include "irrt/int_types.hpp"
+
+/**
+ * @brief The int type of ARTIQ exception IDs.
+ */
+using ExceptionId = int32_t;
+
+/*
+ * Set of exceptions C++ IRRT can use.
+ * Must be synchronized with `setup_irrt_exceptions` in `nac3core/src/codegen/irrt/mod.rs`.
+ */
+extern "C" {
+ExceptionId EXN_INDEX_ERROR;
+ExceptionId EXN_VALUE_ERROR;
+ExceptionId EXN_ASSERTION_ERROR;
+ExceptionId EXN_TYPE_ERROR;
+}
+
+/**
+ * @brief Extern function to `__nac3_raise`
+ *
+ * The parameter `err` could be `Exception<int32_t>` or `Exception<int64_t>`. The caller
+ * must make sure to pass `Exception`s with the correct `SizeT` depending on the `size_t` of the runtime.
+ */
+extern "C" void __nac3_raise(void* err);
+
+namespace {
+/**
+ * @brief NAC3's Exception struct
+ */
+template<typename SizeT>
+struct Exception {
+    ExceptionId id;
+    CSlice<SizeT> filename;
+    int32_t line;
+    int32_t column;
+    CSlice<SizeT> function;
+    CSlice<SizeT> msg;
+    int64_t params[3];
+};
+
+constexpr int64_t NO_PARAM = 0;
+
+template<typename SizeT>
+void _raise_exception_helper(ExceptionId id,
+                             const char* filename,
+                             int32_t line,
+                             const char* function,
+                             const char* msg,
+                             int64_t param0,
+                             int64_t param1,
+                             int64_t param2) {
+    Exception<SizeT> e = {
+        .id = id,
+        .filename = {.base = reinterpret_cast<void*>(const_cast<char*>(filename)),
+                     .len = static_cast<SizeT>(__builtin_strlen(filename))},
+        .line = line,
+        .column = 0,
+        .function = {.base = reinterpret_cast<void*>(const_cast<char*>(function)),
+                     .len = static_cast<SizeT>(__builtin_strlen(function))},
+        .msg = {.base = reinterpret_cast<void*>(const_cast<char*>(msg)),
+                .len = static_cast<SizeT>(__builtin_strlen(msg))},
+    };
+    e.params[0] = param0;
+    e.params[1] = param1;
+    e.params[2] = param2;
+    __nac3_raise(reinterpret_cast<void*>(&e));
+    __builtin_unreachable();
+}
+}  // namespace
+
+/**
+ * @brief Raise an exception with location details (location in the IRRT source files).
+ * @param SizeT The runtime `size_t` type.
+ * @param id The ID of the exception to raise.
+ * @param msg A global constant C-string of the error message.
+ *
+ * `param0` to `param2` are optional format arguments of `msg`. They should be set to
+ * `NO_PARAM` to indicate they are unused.
+ */
+#define raise_exception(SizeT, id, msg, param0, param1, param2) \
+    _raise_exception_helper<SizeT>(id, __FILE__, __LINE__, __FUNCTION__, msg, param0, param1, param2)

nac3core/irrt/irrt/int_defs.hpp

@@ -1,12 +0,0 @@
-#pragma once
-
-// This is made toggleable since `irrt_test.cpp` itself would include
-// headers that define these typedefs
-#ifdef IRRT_DEFINE_TYPEDEF_INTS
-using int8_t = _BitInt(8);
-using uint8_t = unsigned _BitInt(8);
-using int32_t = _BitInt(32);
-using uint32_t = unsigned _BitInt(32);
-using int64_t = _BitInt(64);
-using uint64_t = unsigned _BitInt(64);
-#endif

nac3core/irrt/irrt/int_types.hpp

@@ -0,0 +1,27 @@
+#pragma once
+
+#if __STDC_VERSION__ >= 202000
+using int8_t = _BitInt(8);
+using uint8_t = unsigned _BitInt(8);
+using int32_t = _BitInt(32);
+using uint32_t = unsigned _BitInt(32);
+using int64_t = _BitInt(64);
+using uint64_t = unsigned _BitInt(64);
+#else
+
+#pragma clang diagnostic push
+#pragma clang diagnostic ignored "-Wdeprecated-type"
+using int8_t = _ExtInt(8);
+using uint8_t = unsigned _ExtInt(8);
+using int32_t = _ExtInt(32);
+using uint32_t = unsigned _ExtInt(32);
+using int64_t = _ExtInt(64);
+using uint64_t = unsigned _ExtInt(64);
+#pragma clang diagnostic pop
+
+#endif
+
+// NDArray indices are always `uint32_t`.
+using NDIndexInt = uint32_t;
+// The type of an index or a value describing the length of a range/slice is always `int32_t`.
+using SliceIndex = int32_t;

nac3core/irrt/irrt/list.hpp

@@ -0,0 +1,81 @@
+#pragma once
+
+#include "irrt/int_types.hpp"
+#include "irrt/math_util.hpp"
+
+extern "C" {
+// Handle list assignment and dropping part of the list when
+// both dest_step and src_step are +1.
+// - All the index must *not* be out-of-bound or negative,
+// - The end index is *inclusive*,
+// - The length of src and dest slice size should already
+// be checked: if dest.step == 1 then len(src) <= len(dest) else len(src) == len(dest)
+SliceIndex __nac3_list_slice_assign_var_size(SliceIndex dest_start,
+                                             SliceIndex dest_end,
+                                             SliceIndex dest_step,
+                                             void* dest_arr,
+                                             SliceIndex dest_arr_len,
+                                             SliceIndex src_start,
+                                             SliceIndex src_end,
+                                             SliceIndex src_step,
+                                             void* src_arr,
+                                             SliceIndex src_arr_len,
+                                             const SliceIndex size) {
+    /* if dest_arr_len == 0, do nothing since we do not support extending list */
+    if (dest_arr_len == 0)
+        return dest_arr_len;
+    /* if both step is 1, memmove directly, handle the dropping of the list, and shrink size */
+    if (src_step == dest_step && dest_step == 1) {
+        const SliceIndex src_len = (src_end >= src_start) ? (src_end - src_start + 1) : 0;
+        const SliceIndex dest_len = (dest_end >= dest_start) ? (dest_end - dest_start + 1) : 0;
+        if (src_len > 0) {
+            __builtin_memmove(static_cast<uint8_t*>(dest_arr) + dest_start * size,
+                              static_cast<uint8_t*>(src_arr) + src_start * size, src_len * size);
+        }
+        if (dest_len > 0) {
+            /* dropping */
+            __builtin_memmove(static_cast<uint8_t*>(dest_arr) + (dest_start + src_len) * size,
+                              static_cast<uint8_t*>(dest_arr) + (dest_end + 1) * size,
+                              (dest_arr_len - dest_end - 1) * size);
+        }
+        /* shrink size */
+        return dest_arr_len - (dest_len - src_len);
+    }
+    /* if two range overlaps, need alloca */
+    uint8_t need_alloca = (dest_arr == src_arr)
+                          && !(max(dest_start, dest_end) < min(src_start, src_end)
+                               || max(src_start, src_end) < min(dest_start, dest_end));
+    if (need_alloca) {
+        void* tmp = __builtin_alloca(src_arr_len * size);
+        __builtin_memcpy(tmp, src_arr, src_arr_len * size);
+        src_arr = tmp;
+    }
+    SliceIndex src_ind = src_start;
+    SliceIndex dest_ind = dest_start;
+    for (; (src_step > 0) ? (src_ind <= src_end) : (src_ind >= src_end); src_ind += src_step, dest_ind += dest_step) {
+        /* for constant optimization */
+        if (size == 1) {
+            __builtin_memcpy(static_cast<uint8_t*>(dest_arr) + dest_ind, static_cast<uint8_t*>(src_arr) + src_ind, 1);
+        } else if (size == 4) {
+            __builtin_memcpy(static_cast<uint8_t*>(dest_arr) + dest_ind * 4,
+                             static_cast<uint8_t*>(src_arr) + src_ind * 4, 4);
+        } else if (size == 8) {
+            __builtin_memcpy(static_cast<uint8_t*>(dest_arr) + dest_ind * 8,
+                             static_cast<uint8_t*>(src_arr) + src_ind * 8, 8);
+        } else {
+            /* memcpy for var size, cannot overlap after previous alloca */
+            __builtin_memcpy(static_cast<uint8_t*>(dest_arr) + dest_ind * size,
+                             static_cast<uint8_t*>(src_arr) + src_ind * size, size);
+        }
+    }
+    /* only dest_step == 1 can we shrink the dest list. */
+    /* size should be ensured prior to calling this function */
+    if (dest_step == 1 && dest_end >= dest_start) {
+        __builtin_memmove(static_cast<uint8_t*>(dest_arr) + dest_ind * size,
+                          static_cast<uint8_t*>(dest_arr) + (dest_end + 1) * size,
+                          (dest_arr_len - dest_end - 1) * size);
+        return dest_arr_len - (dest_end - dest_ind) - 1;
+    }
+    return dest_arr_len;
+}
+}  // extern "C"

nac3core/irrt/irrt/math.hpp

@@ -0,0 +1,93 @@
+#pragma once
+
+namespace {
+// adapted from GNU Scientific Library: https://git.savannah.gnu.org/cgit/gsl.git/tree/sys/pow_int.c
+// need to make sure `exp >= 0` before calling this function
+template<typename T>
+T __nac3_int_exp_impl(T base, T exp) {
+    T res = 1;
+    /* repeated squaring method */
+    do {
+        if (exp & 1) {
+            res *= base; /* for n odd */
+        }
+        exp >>= 1;
+        base *= base;
+    } while (exp);
+    return res;
+}
+}  // namespace
+
+#define DEF_nac3_int_exp_(T)                   \
+    T __nac3_int_exp_##T(T base, T exp) {      \
+        return __nac3_int_exp_impl(base, exp); \
+    }
+
+extern "C" {
+
+// Putting semicolons here to make clang-format not reformat this into
+// a stair shape.
+DEF_nac3_int_exp_(int32_t);
+DEF_nac3_int_exp_(int64_t);
+DEF_nac3_int_exp_(uint32_t);
+DEF_nac3_int_exp_(uint64_t);
+
+int32_t __nac3_isinf(double x) {
+    return __builtin_isinf(x);
+}
+
+int32_t __nac3_isnan(double x) {
+    return __builtin_isnan(x);
+}
+
+double tgamma(double arg);
+
+double __nac3_gamma(double z) {
+    // Handling for denormals
+    //     | x                 | Python gamma(x) | C tgamma(x) |
+    // --- | ----------------- | --------------- | ----------- |
+    // (1) | nan               | nan             | nan         |
+    // (2) | -inf              | -inf            | inf         |
+    // (3) | inf               | inf             | inf         |
+    // (4) | 0.0               | inf             | inf         |
+    // (5) | {-1.0, -2.0, ...} | inf             | nan         |
+
+    // (1)-(3)
+    if (__builtin_isinf(z) || __builtin_isnan(z)) {
+        return z;
+    }
+
+    double v = tgamma(z);
+
+    // (4)-(5)
+    return __builtin_isinf(v) || __builtin_isnan(v) ? __builtin_inf() : v;
+}
+
+double lgamma(double arg);
+
+double __nac3_gammaln(double x) {
+    // libm's handling of value overflows differs from scipy:
+    // - scipy: gammaln(-inf) -> -inf
+    // - libm : lgamma(-inf) -> inf
+
+    if (__builtin_isinf(x)) {
+        return x;
+    }
+
+    return lgamma(x);
+}
+
+double j0(double x);
+
+double __nac3_j0(double x) {
+    // libm's handling of value overflows differs from scipy:
+    // - scipy: j0(inf) -> nan
+    // - libm : j0(inf) -> 0.0
+
+    if (__builtin_isinf(x)) {
+        return __builtin_nan("");
+    }
+
+    return j0(x);
+}
+}  // namespace

nac3core/irrt/irrt/math_util.hpp

@@ -0,0 +1,13 @@
+#pragma once
+
+namespace {
+template<typename T>
+const T& max(const T& a, const T& b) {
+    return a > b ? a : b;
+}
+
+template<typename T>
+const T& min(const T& a, const T& b) {
+    return a > b ? b : a;
+}
+}  // namespace

nac3core/irrt/irrt/ndarray.hpp

@@ -0,0 +1,151 @@
+#pragma once
+
+#include "irrt/int_types.hpp"
+
+// TODO: To be deleted since NDArray with strides is done.
+
+namespace {
+template<typename SizeT>
+SizeT __nac3_ndarray_calc_size_impl(const SizeT* list_data, SizeT list_len, SizeT begin_idx, SizeT end_idx) {
+    __builtin_assume(end_idx <= list_len);
+
+    SizeT num_elems = 1;
+    for (SizeT i = begin_idx; i < end_idx; ++i) {
+        SizeT val = list_data[i];
+        __builtin_assume(val > 0);
+        num_elems *= val;
+    }
+    return num_elems;
+}
+
+template<typename SizeT>
+void __nac3_ndarray_calc_nd_indices_impl(SizeT index, const SizeT* dims, SizeT num_dims, NDIndexInt* idxs) {
+    SizeT stride = 1;
+    for (SizeT dim = 0; dim < num_dims; dim++) {
+        SizeT i = num_dims - dim - 1;
+        __builtin_assume(dims[i] > 0);
+        idxs[i] = (index / stride) % dims[i];
+        stride *= dims[i];
+    }
+}
+
+template<typename SizeT>
+SizeT __nac3_ndarray_flatten_index_impl(const SizeT* dims,
+                                        SizeT num_dims,
+                                        const NDIndexInt* indices,
+                                        SizeT num_indices) {
+    SizeT idx = 0;
+    SizeT stride = 1;
+    for (SizeT i = 0; i < num_dims; ++i) {
+        SizeT ri = num_dims - i - 1;
+        if (ri < num_indices) {
+            idx += stride * indices[ri];
+        }
+
+        __builtin_assume(dims[i] > 0);
+        stride *= dims[ri];
+    }
+    return idx;
+}
+
+template<typename SizeT>
+void __nac3_ndarray_calc_broadcast_impl(const SizeT* lhs_dims,
+                                        SizeT lhs_ndims,
+                                        const SizeT* rhs_dims,
+                                        SizeT rhs_ndims,
+                                        SizeT* out_dims) {
+    SizeT max_ndims = lhs_ndims > rhs_ndims ? lhs_ndims : rhs_ndims;
+
+    for (SizeT i = 0; i < max_ndims; ++i) {
+        const SizeT* lhs_dim_sz = i < lhs_ndims ? &lhs_dims[lhs_ndims - i - 1] : nullptr;
+        const SizeT* rhs_dim_sz = i < rhs_ndims ? &rhs_dims[rhs_ndims - i - 1] : nullptr;
+        SizeT* out_dim = &out_dims[max_ndims - i - 1];
+
+        if (lhs_dim_sz == nullptr) {
+            *out_dim = *rhs_dim_sz;
+        } else if (rhs_dim_sz == nullptr) {
+            *out_dim = *lhs_dim_sz;
+        } else if (*lhs_dim_sz == 1) {
+            *out_dim = *rhs_dim_sz;
+        } else if (*rhs_dim_sz == 1) {
+            *out_dim = *lhs_dim_sz;
+        } else if (*lhs_dim_sz == *rhs_dim_sz) {
+            *out_dim = *lhs_dim_sz;
+        } else {
+            __builtin_unreachable();
+        }
+    }
+}
+
+template<typename SizeT>
+void __nac3_ndarray_calc_broadcast_idx_impl(const SizeT* src_dims,
+                                            SizeT src_ndims,
+                                            const NDIndexInt* in_idx,
+                                            NDIndexInt* out_idx) {
+    for (SizeT i = 0; i < src_ndims; ++i) {
+        SizeT src_i = src_ndims - i - 1;
+        out_idx[src_i] = src_dims[src_i] == 1 ? 0 : in_idx[src_i];
+    }
+}
+}  // namespace
+
+extern "C" {
+uint32_t __nac3_ndarray_calc_size(const uint32_t* list_data, uint32_t list_len, uint32_t begin_idx, uint32_t end_idx) {
+    return __nac3_ndarray_calc_size_impl(list_data, list_len, begin_idx, end_idx);
+}
+
+uint64_t
+__nac3_ndarray_calc_size64(const uint64_t* list_data, uint64_t list_len, uint64_t begin_idx, uint64_t end_idx) {
+    return __nac3_ndarray_calc_size_impl(list_data, list_len, begin_idx, end_idx);
+}
+
+void __nac3_ndarray_calc_nd_indices(uint32_t index, const uint32_t* dims, uint32_t num_dims, NDIndexInt* idxs) {
+    __nac3_ndarray_calc_nd_indices_impl(index, dims, num_dims, idxs);
+}
+
+void __nac3_ndarray_calc_nd_indices64(uint64_t index, const uint64_t* dims, uint64_t num_dims, NDIndexInt* idxs) {
+    __nac3_ndarray_calc_nd_indices_impl(index, dims, num_dims, idxs);
+}
+
+uint32_t
+__nac3_ndarray_flatten_index(const uint32_t* dims, uint32_t num_dims, const NDIndexInt* indices, uint32_t num_indices) {
+    return __nac3_ndarray_flatten_index_impl(dims, num_dims, indices, num_indices);
+}
+
+uint64_t __nac3_ndarray_flatten_index64(const uint64_t* dims,
+                                        uint64_t num_dims,
+                                        const NDIndexInt* indices,
+                                        uint64_t num_indices) {
+    return __nac3_ndarray_flatten_index_impl(dims, num_dims, indices, num_indices);
+}
+
+void __nac3_ndarray_calc_broadcast(const uint32_t* lhs_dims,
+                                   uint32_t lhs_ndims,
+                                   const uint32_t* rhs_dims,
+                                   uint32_t rhs_ndims,
+                                   uint32_t* out_dims) {
+    return __nac3_ndarray_calc_broadcast_impl(lhs_dims, lhs_ndims, rhs_dims, rhs_ndims, out_dims);
+}
+
+void __nac3_ndarray_calc_broadcast64(const uint64_t* lhs_dims,
+                                     uint64_t lhs_ndims,
+                                     const uint64_t* rhs_dims,
+                                     uint64_t rhs_ndims,
+                                     uint64_t* out_dims) {
+    return __nac3_ndarray_calc_broadcast_impl(lhs_dims, lhs_ndims, rhs_dims, rhs_ndims, out_dims);
+}
+
+void __nac3_ndarray_calc_broadcast_idx(const uint32_t* src_dims,
+                                       uint32_t src_ndims,
+                                       const NDIndexInt* in_idx,
+                                       NDIndexInt* out_idx) {
+    __nac3_ndarray_calc_broadcast_idx_impl(src_dims, src_ndims, in_idx, out_idx);
+}
+
+void __nac3_ndarray_calc_broadcast_idx64(const uint64_t* src_dims,
+                                         uint64_t src_ndims,
+                                         const NDIndexInt* in_idx,
+                                         NDIndexInt* out_idx) {
+    __nac3_ndarray_calc_broadcast_idx_impl(src_dims, src_ndims, in_idx, out_idx);
+}
+}  // namespace

nac3core/irrt/irrt/ndarray/basic.hpp

@@ -1,36 +1,58 @@
 #pragma once
 
-#include <irrt/error_context.hpp>
+#include "irrt/debug.hpp"
-#include <irrt/int_defs.hpp>
+#include "irrt/exception.hpp"
-#include <irrt/ndarray/def.hpp>
+#include "irrt/int_types.hpp"
+#include "irrt/ndarray/def.hpp"
 
 namespace {
 namespace ndarray {
 namespace basic {
-namespace util {
 /**
- * @brief Asserts that `shape` does not contain negative dimensions.
+ * @brief Assert that `shape` does not contain negative dimensions.
  *
  * @param ndims Number of dimensions in `shape`
  * @param shape The shape to check on
  */
 template<typename SizeT>
-void assert_shape_no_negative(ErrorContext* errctx, SizeT ndims,
+void assert_shape_no_negative(SizeT ndims, const SizeT* shape) {
-                              const SizeT* shape) {
     for (SizeT axis = 0; axis < ndims; axis++) {
         if (shape[axis] < 0) {
-            errctx->set_exception(
+            raise_exception(SizeT, EXN_VALUE_ERROR,
-                errctx->exceptions->value_error,
                             "negative dimensions are not allowed; axis {0} "
                             "has dimension {1}",
-                axis, shape[axis]);
+                            axis, shape[axis], NO_PARAM);
-            return;
         }
     }
 }
 
 /**
- * @brief Returns the number of elements of an ndarray given its shape.
+ * @brief Assert that two shapes are the same in the context of writing output to an ndarray.
+ */
+template<typename SizeT>
+void assert_output_shape_same(SizeT ndarray_ndims,
+                              const SizeT* ndarray_shape,
+                              SizeT output_ndims,
+                              const SizeT* output_shape) {
+    if (ndarray_ndims != output_ndims) {
+        // There is no corresponding NumPy error message like this.
+        raise_exception(SizeT, EXN_VALUE_ERROR, "Cannot write output of ndims {0} to an ndarray with ndims {1}",
+                        output_ndims, ndarray_ndims, NO_PARAM);
+    }
+
+    for (SizeT axis = 0; axis < ndarray_ndims; axis++) {
+        if (ndarray_shape[axis] != output_shape[axis]) {
+            // There is no corresponding NumPy error message like this.
+            raise_exception(SizeT, EXN_VALUE_ERROR,
+                            "Mismatched dimensions on axis {0}, output has "
+                            "dimension {1}, but destination ndarray has dimension {2}.",
+                            axis, output_shape[axis], ndarray_shape[axis]);
+        }
+    }
+}
+
+/**
+ * @brief Return the number of elements of an ndarray given its shape.
  *
  * @param ndims Number of dimensions in `shape`
  * @param shape The shape of the ndarray
@@ -38,7 +60,8 @@ void assert_shape_no_negative(ErrorContext* errctx, SizeT ndims,
 template<typename SizeT>
 SizeT calc_size_from_shape(SizeT ndims, const SizeT* shape) {
     SizeT size = 1;
-    for (SizeT axis = 0; axis < ndims; axis++) size *= shape[axis];
+    for (SizeT axis = 0; axis < ndims; axis++)
+        size *= shape[axis];
     return size;
 }
 
@@ -51,17 +74,15 @@ SizeT calc_size_from_shape(SizeT ndims, const SizeT* shape) {
  * @param nth The index of the element of interest.
  */
 template<typename SizeT>
-void set_indices_by_nth(SizeT ndims, const SizeT* shape, SizeT* indices,
+void set_indices_by_nth(SizeT ndims, const SizeT* shape, SizeT* indices, SizeT nth) {
-                        SizeT nth) {
+    for (SizeT i = 0; i < ndims; i++) {
-    for (int32_t i = 0; i < ndims; i++) {
+        SizeT axis = ndims - i - 1;
-        int32_t axis = ndims - i - 1;
+        SizeT dim = shape[axis];
-        int32_t dim = shape[axis];
 
         indices[axis] = nth % dim;
         nth /= dim;
     }
 }
-}  // namespace util
 
 /**
  * @brief Return the number of elements of an `ndarray`
@@ -70,7 +91,7 @@ void set_indices_by_nth(SizeT ndims, const SizeT* shape, SizeT* indices,
  */
 template<typename SizeT>
 SizeT size(const NDArray<SizeT>* ndarray) {
-    return util::calc_size_from_shape(ndarray->ndims, ndarray->shape);
+    return calc_size_from_shape(ndarray->ndims, ndarray->shape);
 }
 
 /**
@@ -83,123 +104,42 @@ SizeT nbytes(const NDArray<SizeT>* ndarray) {
     return size(ndarray) * ndarray->itemsize;
 }
 
-/**
- * @brief Update the strides of an ndarray given an ndarray `shape`
- * and assuming that the ndarray is fully c-contagious.
- *
- * You might want to read https://ajcr.net/stride-guide-part-1/.
- */
-template <typename SizeT>
-void set_strides_by_shape(NDArray<SizeT>* ndarray) {
-    SizeT stride_product = 1;
-    for (SizeT i = 0; i < ndarray->ndims; i++) {
-        int axis = ndarray->ndims - i - 1;
-        ndarray->strides[axis] = stride_product * ndarray->itemsize;
-        stride_product *= ndarray->shape[axis];
-    }
-}
-
-/**
- * @brief Return the pointer to the element indexed by `indices`.
- */
-template <typename SizeT>
-uint8_t* get_pelement_by_indices(const NDArray<SizeT>* ndarray,
-                                 const SizeT* indices) {
-    uint8_t* element = ndarray->data;
-    for (SizeT dim_i = 0; dim_i < ndarray->ndims; dim_i++)
-        element += indices[dim_i] * ndarray->strides[dim_i];
-    return element;
-}
-
-/**
- * @brief Return the pointer to the nth (0-based) element in a flattened view of `ndarray`.
- */
-template <typename SizeT>
-uint8_t* get_nth_pelement(const NDArray<SizeT>* ndarray, SizeT nth) {
-    SizeT* indices = (SizeT*)__builtin_alloca(sizeof(SizeT) * ndarray->ndims);
-    util::set_indices_by_nth(ndarray->ndims, ndarray->shape, indices, nth);
-    return get_pelement_by_indices(ndarray, indices);
-}
-
-/**
- * @brief Like `get_nth_pelement` but asserts that `nth` is in bounds.
- */
-template <typename SizeT>
-uint8_t* checked_get_nth_pelement(ErrorContext* errctx,
-                                  const NDArray<SizeT>* ndarray, SizeT nth) {
-    SizeT arr_size = ndarray->size();
-    if (!(0 <= nth && nth < arr_size)) {
-        errctx->set_exception(
-            errctx->exceptions->index_error,
-            "index {0} is out of bounds, valid range is {1} <= index < {2}",
-            nth, 0, arr_size);
-        return 0;
-    }
-    return get_nth_pelement(ndarray, nth);
-}
-
-/**
- * @brief Set an element in `ndarray`.
- *
- * @param pelement Pointer to the element in `ndarray` to be set.
- * @param pvalue Pointer to the value `pelement` will be set to.
- */
-template <typename SizeT>
-void set_pelement_value(NDArray<SizeT>* ndarray, uint8_t* pelement,
-                        const uint8_t* pvalue) {
-    __builtin_memcpy(pelement, pvalue, ndarray->itemsize);
-}
-
 /**
  * @brief Get the `len()` of an ndarray, and asserts that `ndarray` is a sized object.
  *
  * This function corresponds to `<an_ndarray>.__len__`.
  *
- * @param dst_length The returned result
+ * @param dst_length The length.
  */
 template<typename SizeT>
-void len(ErrorContext* errctx, const NDArray<SizeT>* ndarray,
+SizeT len(const NDArray<SizeT>* ndarray) {
-         SliceIndex* dst_length) {
+    if (ndarray->ndims != 0) {
+        return ndarray->shape[0];
+    }
+
     // numpy prohibits `__len__` on unsized objects
-    if (ndarray->ndims == 0) {
+    raise_exception(SizeT, EXN_TYPE_ERROR, "len() of unsized object", NO_PARAM, NO_PARAM, NO_PARAM);
-        errctx->set_exception(errctx->exceptions->type_error,
+    __builtin_unreachable();
-                              "len() of unsized object");
-        return;
-    }
-
-    *dst_length = (SliceIndex)ndarray->shape[0];
-}
-
-/**
- * @brief Copy data from one ndarray to another of the exact same size and itemsize.
- *
- * Both ndarrays will be viewed in their flatten views when copying the elements.
- */
-template <typename SizeT>
-void copy_data(const NDArray<SizeT>* src_ndarray, NDArray<SizeT>* dst_ndarray) {
-    __builtin_assume(src_ndarray->itemsize == dst_ndarray->itemsize);
-
-    for (SizeT i = 0; i < size(src_ndarray); i++) {
-        auto src_element = ndarray::basic::get_nth_pelement(src_ndarray, i);
-        auto dst_element = ndarray::basic::get_nth_pelement(dst_ndarray, i);
-        ndarray::basic::set_pelement_value(dst_ndarray, dst_element,
-                                           src_element);
-    }
 }
 
 /**
  * @brief Return a boolean indicating if `ndarray` is (C-)contiguous.
  *
- * You may want to see: ndarray's rules for C-contiguity: https://github.com/numpy/numpy/blob/df256d0d2f3bc6833699529824781c58f9c6e697/numpy/core/src/multiarray/flagsobject.c#L95C1-L99C45
+ * You may want to see ndarray's rules for C-contiguity:
+ * https://github.com/numpy/numpy/blob/df256d0d2f3bc6833699529824781c58f9c6e697/numpy/core/src/multiarray/flagsobject.c#L95C1-L99C45
  */
 template<typename SizeT>
 bool is_c_contiguous(const NDArray<SizeT>* ndarray) {
-    // Other references:
+    // References:
-    // - tinynumpy's implementation: https://github.com/wadetb/tinynumpy/blob/0d23d22e07062ffab2afa287374c7b366eebdda1/tinynumpy/tinynumpy.py#L102
+    // - tinynumpy's implementation:
-    // - ndarray's flags["C_CONTIGUOUS"]: https://numpy.org/doc/stable/reference/generated/numpy.ndarray.flags.html#numpy.ndarray.flags
+    // https://github.com/wadetb/tinynumpy/blob/0d23d22e07062ffab2afa287374c7b366eebdda1/tinynumpy/tinynumpy.py#L102
-    // - ndarray's rules for C-contiguity: https://github.com/numpy/numpy/blob/df256d0d2f3bc6833699529824781c58f9c6e697/numpy/core/src/multiarray/flagsobject.c#L95C1-L99C45
+    // - ndarray's flags["C_CONTIGUOUS"]:
+    // https://numpy.org/doc/stable/reference/generated/numpy.ndarray.flags.html#numpy.ndarray.flags
+    // - ndarray's rules for C-contiguity:
+    // https://github.com/numpy/numpy/blob/df256d0d2f3bc6833699529824781c58f9c6e697/numpy/core/src/multiarray/flagsobject.c#L95C1-L99C45
 
-    // From https://github.com/numpy/numpy/blob/df256d0d2f3bc6833699529824781c58f9c6e697/numpy/core/src/multiarray/flagsobject.c#L95C1-L99C45:
+    // From
+    // https://github.com/numpy/numpy/blob/df256d0d2f3bc6833699529824781c58f9c6e697/numpy/core/src/multiarray/flagsobject.c#L95C1-L99C45:
     //
     // The traditional rule is that for an array to be flagged as C contiguous,
     // the following must hold:
@@ -223,15 +163,90 @@ bool is_c_contiguous(const NDArray<SizeT>* ndarray) {
         return false;
     }
 
-    for (SizeT i = 0; i < ndarray->ndims - 1; i++) {
+    for (SizeT i = 1; i < ndarray->ndims; i++) {
-        if (ndarray->strides[i] !=
+        SizeT axis_i = ndarray->ndims - i - 1;
-            ndarray->shape[i + 1] + ndarray->strides[i + 1]) {
+        if (ndarray->strides[axis_i] != ndarray->shape[axis_i + 1] * ndarray->strides[axis_i + 1]) {
             return false;
         }
     }
 
     return true;
 }
+
+/**
+ * @brief Return the pointer to the element indexed by `indices` along the ndarray's axes.
+ *
+ * This function does no bound check.
+ */
+template<typename SizeT>
+void* get_pelement_by_indices(const NDArray<SizeT>* ndarray, const SizeT* indices) {
+    void* element = ndarray->data;
+    for (SizeT dim_i = 0; dim_i < ndarray->ndims; dim_i++)
+        element = static_cast<uint8_t*>(element) + indices[dim_i] * ndarray->strides[dim_i];
+    return element;
+}
+
+/**
+ * @brief Return the pointer to the nth (0-based) element of `ndarray` in flattened view.
+ *
+ * This function does no bound check.
+ */
+template<typename SizeT>
+void* get_nth_pelement(const NDArray<SizeT>* ndarray, SizeT nth) {
+    void* element = ndarray->data;
+    for (SizeT i = 0; i < ndarray->ndims; i++) {
+        SizeT axis = ndarray->ndims - i - 1;
+        SizeT dim = ndarray->shape[axis];
+        element = static_cast<uint8_t*>(element) + ndarray->strides[axis] * (nth % dim);
+        nth /= dim;
+    }
+    return element;
+}
+
+/**
+ * @brief Update the strides of an ndarray given an ndarray `shape` to be contiguous.
+ *
+ * You might want to read https://ajcr.net/stride-guide-part-1/.
+ */
+template<typename SizeT>
+void set_strides_by_shape(NDArray<SizeT>* ndarray) {
+    SizeT stride_product = 1;
+    for (SizeT i = 0; i < ndarray->ndims; i++) {
+        SizeT axis = ndarray->ndims - i - 1;
+        ndarray->strides[axis] = stride_product * ndarray->itemsize;
+        stride_product *= ndarray->shape[axis];
+    }
+}
+
+/**
+ * @brief Set an element in `ndarray`.
+ *
+ * @param pelement Pointer to the element in `ndarray` to be set.
+ * @param pvalue Pointer to the value `pelement` will be set to.
+ */
+template<typename SizeT>
+void set_pelement_value(NDArray<SizeT>* ndarray, void* pelement, const void* pvalue) {
+    __builtin_memcpy(pelement, pvalue, ndarray->itemsize);
+}
+
+/**
+ * @brief Copy data from one ndarray to another of the exact same size and itemsize.
+ *
+ * Both ndarrays will be viewed in their flatten views when copying the elements.
+ */
+template<typename SizeT>
+void copy_data(const NDArray<SizeT>* src_ndarray, NDArray<SizeT>* dst_ndarray) {
+    // TODO: Make this faster with memcpy when we see a contiguous segment.
+    // TODO: Handle overlapping.
+
+    debug_assert_eq(SizeT, src_ndarray->itemsize, dst_ndarray->itemsize);
+
+    for (SizeT i = 0; i < size(src_ndarray); i++) {
+        auto src_element = ndarray::basic::get_nth_pelement(src_ndarray, i);
+        auto dst_element = ndarray::basic::get_nth_pelement(dst_ndarray, i);
+        ndarray::basic::set_pelement_value(dst_ndarray, dst_element, src_element);
+    }
+}
 }  // namespace basic
 }  // namespace ndarray
 }  // namespace
@@ -239,6 +254,28 @@ bool is_c_contiguous(const NDArray<SizeT>* ndarray) {
 extern "C" {
 using namespace ndarray::basic;
 
+void __nac3_ndarray_util_assert_shape_no_negative(int32_t ndims, int32_t* shape) {
+    assert_shape_no_negative(ndims, shape);
+}
+
+void __nac3_ndarray_util_assert_shape_no_negative64(int64_t ndims, int64_t* shape) {
+    assert_shape_no_negative(ndims, shape);
+}
+
+void __nac3_ndarray_util_assert_output_shape_same(int32_t ndarray_ndims,
+                                                  const int32_t* ndarray_shape,
+                                                  int32_t output_ndims,
+                                                  const int32_t* output_shape) {
+    assert_output_shape_same(ndarray_ndims, ndarray_shape, output_ndims, output_shape);
+}
+
+void __nac3_ndarray_util_assert_output_shape_same64(int64_t ndarray_ndims,
+                                                    const int64_t* ndarray_shape,
+                                                    int64_t output_ndims,
+                                                    const int64_t* output_shape) {
+    assert_output_shape_same(ndarray_ndims, ndarray_shape, output_ndims, output_shape);
+}
+
 uint32_t __nac3_ndarray_size(NDArray<int32_t>* ndarray) {
     return size(ndarray);
 }
@@ -255,34 +292,12 @@ uint64_t __nac3_ndarray_nbytes64(NDArray<int64_t>* ndarray) {
     return nbytes(ndarray);
 }
 
-void __nac3_ndarray_len(ErrorContext* errctx, NDArray<int32_t>* ndarray,
+int32_t __nac3_ndarray_len(NDArray<int32_t>* ndarray) {
-                        SliceIndex* dst_len) {
+    return len(ndarray);
-    return len(errctx, ndarray, dst_len);
 }
 
-void __nac3_ndarray_len64(ErrorContext* errctx, NDArray<int64_t>* ndarray,
+int64_t __nac3_ndarray_len64(NDArray<int64_t>* ndarray) {
-                          SliceIndex* dst_len) {
+    return len(ndarray);
-    return len(errctx, ndarray, dst_len);
-}
-
-void __nac3_ndarray_util_assert_shape_no_negative(ErrorContext* errctx,
-                                                  int32_t ndims,
-                                                  int32_t* shape) {
-    util::assert_shape_no_negative(errctx, ndims, shape);
-}
-
-void __nac3_ndarray_util_assert_shape_no_negative64(ErrorContext* errctx,
-                                                    int64_t ndims,
-                                                    int64_t* shape) {
-    util::assert_shape_no_negative(errctx, ndims, shape);
-}
-
-void __nac3_ndarray_set_strides_by_shape(NDArray<int32_t>* ndarray) {
-    set_strides_by_shape(ndarray);
-}
-
-void __nac3_ndarray_set_strides_by_shape64(NDArray<int64_t>* ndarray) {
-    set_strides_by_shape(ndarray);
 }
 
 bool __nac3_ndarray_is_c_contiguous(NDArray<int32_t>* ndarray) {
@@ -293,23 +308,35 @@ bool __nac3_ndarray_is_c_contiguous64(NDArray<int64_t>* ndarray) {
     return is_c_contiguous(ndarray);
 }
 
-void __nac3_ndarray_copy_data(NDArray<int32_t>* src_ndarray,
+void* __nac3_ndarray_get_nth_pelement(const NDArray<int32_t>* ndarray, int32_t nth) {
-                              NDArray<int32_t>* dst_ndarray) {
+    return get_nth_pelement(ndarray, nth);
+}
+
+void* __nac3_ndarray_get_nth_pelement64(const NDArray<int64_t>* ndarray, int64_t nth) {
+    return get_nth_pelement(ndarray, nth);
+}
+
+void* __nac3_ndarray_get_pelement_by_indices(const NDArray<int32_t>* ndarray, int32_t* indices) {
+    return get_pelement_by_indices(ndarray, indices);
+}
+
+void* __nac3_ndarray_get_pelement_by_indices64(const NDArray<int64_t>* ndarray, int64_t* indices) {
+    return get_pelement_by_indices(ndarray, indices);
+}
+
+void __nac3_ndarray_set_strides_by_shape(NDArray<int32_t>* ndarray) {
+    set_strides_by_shape(ndarray);
+}
+
+void __nac3_ndarray_set_strides_by_shape64(NDArray<int64_t>* ndarray) {
+    set_strides_by_shape(ndarray);
+}
+
+void __nac3_ndarray_copy_data(NDArray<int32_t>* src_ndarray, NDArray<int32_t>* dst_ndarray) {
     copy_data(src_ndarray, dst_ndarray);
 }
 
-void __nac3_ndarray_copy_data64(NDArray<int64_t>* src_ndarray,
+void __nac3_ndarray_copy_data64(NDArray<int64_t>* src_ndarray, NDArray<int64_t>* dst_ndarray) {
-                                NDArray<int64_t>* dst_ndarray) {
     copy_data(src_ndarray, dst_ndarray);
 }
-
-uint8_t* __nac3_ndarray_get_nth_pelement(NDArray<int32_t>* ndarray,
-                                         int32_t index) {
-    return get_nth_pelement(ndarray, index);
-}
-
-uint8_t* __nac3_ndarray_get_nth_pelement64(NDArray<int64_t>* ndarray,
-                                           int64_t index) {
-    return get_nth_pelement(ndarray, index);
-}
 }

nac3core/irrt/irrt/ndarray/broadcast.hpp

@@ -1,221 +0,0 @@
-#pragma once
-
-#include <irrt/error_context.hpp>
-#include <irrt/int_defs.hpp>
-#include <irrt/ndarray/def.hpp>
-#include <irrt/slice.hpp>
-
-namespace {
-template <typename SizeT>
-struct ShapeEntry {
-    SizeT ndims;
-    SizeT* shape;
-};
-}  // namespace
-
-namespace {
-namespace ndarray {
-namespace broadcast {
-namespace util {
-/**
- * @brief Return true if `src_shape` can broadcast to `dst_shape`.
- */
-template <typename SizeT>
-bool can_broadcast_shape_to(SizeT target_ndims, const SizeT* target_shape,
-                            SizeT src_ndims, const SizeT* src_shape) {
-    /*
-     *  // See https://numpy.org/doc/stable/user/basics.broadcasting.html
-
-     *  This function handles this example:
-     *  ```
-     *  Image  (3d array): 256 x 256 x 3
-     *  Scale  (1d array):             3
-     *  Result (3d array): 256 x 256 x 3
-     *  ```
-
-     *  Other interesting examples to consider:
-     *  - `can_broadcast_shape_to([3], [1, 1, 1, 1, 3]) == true`
-     *  - `can_broadcast_shape_to([3], [3, 1]) == false`
-     *  - `can_broadcast_shape_to([256, 256, 3], [256, 1, 3]) == true`
-
-     *  In cases when the shapes contain zero(es):
-     *  - `can_broadcast_shape_to([0], [1]) == true`
-     *  - `can_broadcast_shape_to([0], [2]) == false`
-     *  - `can_broadcast_shape_to([0, 4, 0, 0], [1]) == true`
-     *  - `can_broadcast_shape_to([0, 4, 0, 0], [1, 1, 1, 1]) == true`
-     *  - `can_broadcast_shape_to([0, 4, 0, 0], [1, 4, 1, 1]) == true`
-     *  - `can_broadcast_shape_to([4, 3], [0, 3]) == false`
-     *  - `can_broadcast_shape_to([4, 3], [0, 0]) == false`
-     */
-
-    // This is essentially doing the following in Python:
-    // `for target_dim, src_dim in itertools.zip_longest(target_shape[::-1], src_shape[::-1], fillvalue=1)`
-    for (SizeT i = 0; i < max(target_ndims, src_ndims); i++) {
-        SizeT target_dim_i = target_ndims - i - 1;
-        SizeT src_dim_i = src_ndims - i - 1;
-
-        bool target_dim_exists = target_dim_i >= 0;
-        bool src_dim_exists = src_dim_i >= 0;
-
-        SizeT target_dim = target_dim_exists ? target_shape[target_dim_i] : 1;
-        SizeT src_dim = src_dim_exists ? src_shape[src_dim_i] : 1;
-
-        bool ok = src_dim == 1 || target_dim == src_dim;
-        if (!ok) return false;
-    }
-
-    return true;
-}
-
-/**
- * @brief Performs `np.broadcast_shapes`
- */
-template <typename SizeT>
-void broadcast_shapes(ErrorContext* errctx, SizeT num_shapes,
-                      const ShapeEntry<SizeT>* shapes, SizeT dst_ndims,
-                      SizeT* dst_shape) {
-    // `dst_ndims` must be `max([shape.ndims for shape in shapes])`, but the caller has to calculate it/provide it
-    //   for this function since it should already know in order to allocate `dst_shape` in the first place.
-    // `dst_shape` must be pre-allocated.
-    // `dst_shape` does not have to be initialized
-
-    // TODO: Implementation is not obvious
-
-    // This is essentially a `mconcat` where the neutral element is `[1, 1, 1, 1, ...]`, and the operation is commutative.
-
-    // Set `dst_shape` to all `1`s.
-    for (SizeT dst_axis = 0; dst_axis < dst_ndims; dst_axis++) {
-        dst_shape[dst_axis] = 0;
-    }
-
-    for (SizeT i = 0; i < num_shapes; i++) {
-        ShapeEntry<SizeT> entry = shapes[i];
-        SizeT entry_axis = entry.ndims - i;
-        SizeT dst_axis = dst_ndims - i;
-
-        SizeT entry_dim = entry.shape[entry_axis];
-        SizeT dst_dim = dst_shape[dst_axis];
-
-        if (dst_dim == 1) {
-            dst_shape[dst_axis] = entry_dim;
-        } else if (entry_dim == 1) {
-            // Do nothing
-        } else if (entry_dim == dst_dim) {
-            // Do nothing
-        } else {
-            errctx->set_exception(errctx->exceptions->value_error,
-                                  "shape mismatch: objects cannot be broadcast "
-                                  "to a single shape.");
-            return;
-        }
-    }
-}
-}  // namespace util
-
-/**
- * @brief Perform `np.broadcast_to(<ndarray>, <target_shape>)` and appropriate assertions.
- *
- * Cautious note on https://github.com/numpy/numpy/issues/21744..
- *
- * This function attempts to broadcast `src_ndarray` to a new shape defined by `dst_ndarray.shape`,
- * and return the result by modifying `dst_ndarray`.
- *
- * # Notes on `dst_ndarray`
- * The caller is responsible for allocating space for the resulting ndarray.
- * Here is what this function expects from `dst_ndarray` when called:
- *   - `dst_ndarray->data` does not have to be initialized.
- *   - `dst_ndarray->itemsize` does not have to be initialized.
- *   - `dst_ndarray->ndims` must be initialized, determining the length of `dst_ndarray->shape`
- *   - `dst_ndarray->shape` must be allocated, and must contain the desired target broadcast shape.
- *   - `dst_ndarray->strides` must be allocated, through it can contain uninitialized values.
- * When this function call ends:
- *   - `dst_ndarray->data` is set to `src_ndarray->data` (`dst_ndarray` is just a view to `src_ndarray`)
- *   - `dst_ndarray->itemsize` is set to `src_ndarray->itemsize`
- *   - `dst_ndarray->ndims` is unchanged.
- *   - `dst_ndarray->shape` is unchanged.
- *   - `dst_ndarray->strides` is updated accordingly by how ndarray broadcast_to works.
- */
-template <typename SizeT>
-void broadcast_to(ErrorContext* errctx, const NDArray<SizeT>* src_ndarray,
-                  NDArray<SizeT>* dst_ndarray) {
-    /*
-     * Cautions:
-     *   ```
-     *   xs = np.zeros((4,))
-     *   ys = np.zero((4, 1))
-     *   ys[:] = xs # ok
-     *
-     *   xs = np.zeros((1, 4))
-     *   ys = np.zero((4,))
-     *   ys[:] = xs # allowed
-     *   # However `np.broadcast_to(xs, (4,))` would fails, as per numpy's broadcasting rule.
-     *   # and apparently numpy will "deprecate" this? SEE https://github.com/numpy/numpy/issues/21744
-     *   # This implementation will NOT support this assignment.
-     *   ```
-    */
-
-    if (!ndarray::broadcast::util::can_broadcast_shape_to(
-            dst_ndarray->ndims, dst_ndarray->shape, src_ndarray->ndims,
-            src_ndarray->shape)) {
-        errctx->set_exception(errctx->exceptions->value_error,
-                              "operands could not be broadcast together");
-        return;
-    }
-
-    dst_ndarray->data = src_ndarray->data;
-    dst_ndarray->itemsize = src_ndarray->itemsize;
-
-    // TODO: Implementation is not obvious
-    SizeT stride_product = 1;
-    for (SizeT i = 0; i < max(src_ndarray->ndims, dst_ndarray->ndims); i++) {
-        SizeT src_ndarray_dim_i = src_ndarray->ndims - i - 1;
-        SizeT dst_dim_i = dst_ndarray->ndims - i - 1;
-
-        bool src_ndarray_dim_exists = src_ndarray_dim_i >= 0;
-        bool dst_dim_exists = dst_dim_i >= 0;
-
-        bool c1 = src_ndarray_dim_exists &&
-                  src_ndarray->shape[src_ndarray_dim_i] == 1;
-        bool c2 = dst_dim_exists && dst_ndarray->shape[dst_dim_i] != 1;
-        if (!src_ndarray_dim_exists || (c1 && c2)) {
-            dst_ndarray->strides[dst_dim_i] = 0;  // Freeze it in-place
-        } else {
-            dst_ndarray->strides[dst_dim_i] =
-                stride_product * src_ndarray->itemsize;
-            stride_product *= src_ndarray->shape[src_ndarray_dim_i];
-        }
-    }
-}
-}  // namespace broadcast
-}  // namespace ndarray
-}  // namespace
-
-extern "C" {
-using namespace ndarray::broadcast;
-
-void __nac3_ndarray_broadcast_to(ErrorContext* errctx,
-                                 NDArray<int32_t>* src_ndarray,
-                                 NDArray<int32_t>* dst_ndarray) {
-    broadcast_to(errctx, src_ndarray, dst_ndarray);
-}
-
-void __nac3_ndarray_broadcast_to64(ErrorContext* errctx,
-                                   NDArray<int64_t>* src_ndarray,
-                                   NDArray<int64_t>* dst_ndarray) {
-    broadcast_to(errctx, src_ndarray, dst_ndarray);
-}
-
-void __nac3_ndarray_broadcast_shapes(ErrorContext* errctx, int32_t num_shapes,
-                                     const ShapeEntry<int32_t>* shapes,
-                                     int32_t dst_ndims, int32_t* dst_shape) {
-    ndarray::broadcast::util::broadcast_shapes(errctx, num_shapes, shapes,
-                                               dst_ndims, dst_shape);
-}
-
-void __nac3_ndarray_broadcast_shapes64(ErrorContext* errctx, int64_t num_shapes,
-                                       const ShapeEntry<int64_t>* shapes,
-                                       int64_t dst_ndims, int64_t* dst_shape) {
-    ndarray::broadcast::util::broadcast_shapes(errctx, num_shapes, shapes,
-                                               dst_ndims, dst_shape);
-}
-}

nac3core/irrt/irrt/ndarray/def.hpp

@@ -1,20 +1,22 @@
 #pragma once
 
+#include "irrt/int_types.hpp"
+
 namespace {
 /**
  * @brief The NDArray object
  *
- * The official numpy implementations: https://github.com/numpy/numpy/blob/735a477f0bc2b5b84d0e72d92f224bde78d4e069/doc/source/reference/c-api/types-and-structures.rst
+ * Official numpy implementation:
+ * https://github.com/numpy/numpy/blob/735a477f0bc2b5b84d0e72d92f224bde78d4e069/doc/source/reference/c-api/types-and-structures.rst#pyarrayinterface
+ *
+ * Note that this implementation is based on `PyArrayInterface` rather of `PyArrayObject`. The
+ * difference between `PyArrayInterface` and `PyArrayObject` (relevant to our implementation) is
+ * that `PyArrayInterface` *has* `itemsize` and uses `void*` for its `data`, whereas `PyArrayObject`
+ * does not require `itemsize` (probably using `strides[-1]` instead) and uses `char*` for its
+ * `data`. There are also minor differences in the struct layout.
  */
 template<typename SizeT>
 struct NDArray {
-    /**
-     * @brief The underlying data this `ndarray` is pointing to.
-     *
-     * Must be set to `nullptr` to indicate that this NDArray's `data` is uninitialized.
-     */
-    uint8_t* data;
-
     /**
      * @brief The number of bytes of a single element in `data`.
      */
@@ -37,8 +39,13 @@ struct NDArray {
      *
      * The stride values are in units of bytes, not number of elements.
      *
-     * Note that `strides` can have negative values.
+     * Note that `strides` can have negative values or contain 0.
      */
     SizeT* strides;
+
+    /**
+     * @brief The underlying data this `ndarray` is pointing to.
+     */
+    void* data;
 };
 }  // namespace

nac3core/irrt/irrt/ndarray/indexing.hpp

@@ -1,9 +1,11 @@
 #pragma once
 
-#include <irrt/error_context.hpp>
+#include "irrt/exception.hpp"
-#include <irrt/ndarray/basic.hpp>
+#include "irrt/int_types.hpp"
-#include <irrt/ndarray/def.hpp>
+#include "irrt/ndarray/basic.hpp"
-#include <irrt/slice.hpp>
+#include "irrt/ndarray/def.hpp"
+#include "irrt/range.hpp"
+#include "irrt/slice.hpp"
 
 namespace {
 typedef uint8_t NDIndexType;
@@ -11,35 +13,52 @@ typedef uint8_t NDIndexType;
 /**
  * @brief A single element index
  *
- * See https://numpy.org/doc/stable/user/basics.indexing.html#single-element-indexing
+ * `data` points to a `int32_t`.
- *
- * `data` points to a `SliceIndex`.
  */
 const NDIndexType ND_INDEX_TYPE_SINGLE_ELEMENT = 0;
+
 /**
  * @brief A slice index
  *
- * See https://numpy.org/doc/stable/user/basics.indexing.html#slicing-and-striding
+ * `data` points to a `Slice<int32_t>`.
- *
- * `data` points to a `UserRange`.
  */
 const NDIndexType ND_INDEX_TYPE_SLICE = 1;
 
+/**
+ * @brief `np.newaxis` / `None`
+ *
+ * `data` is unused.
+ */
+const NDIndexType ND_INDEX_TYPE_NEWAXIS = 2;
+
+/**
+ * @brief `Ellipsis` / `...`
+ *
+ * `data` is unused.
+ */
+const NDIndexType ND_INDEX_TYPE_ELLIPSIS = 3;
+
 /**
  * @brief An index used in ndarray indexing
+ *
+ * That is:
+ * ```
+ * my_ndarray[::-1, 3, ..., np.newaxis]
+ *            ^^^^  ^  ^^^  ^^^^^^^^^^ each of these is represented by an NDIndex.
+ * ```
  */
 struct NDIndex {
     /**
      * @brief Enum tag to specify the type of index.
      *
-     * Please see comments of each enum constant.
+     * Please see the comment of each enum constant.
      */
     NDIndexType type;
 
     /**
      * @brief The accompanying data associated with `type`.
      *
-     * Please see comments of each enum constant.
+     * Please see the comment of each enum constant.
      */
     uint8_t* data;
 };
@@ -48,44 +67,12 @@ struct NDIndex {
 namespace {
 namespace ndarray {
 namespace indexing {
-namespace util {
-
-/**
- * @brief Return the expected rank of the resulting ndarray
- * created by indexing an ndarray of rank `ndims` using `indexes`.
- */
-template <typename SizeT>
-void deduce_ndims_after_indexing(ErrorContext* errctx, SizeT* final_ndims,
-                                 SizeT ndims, SizeT num_indexes,
-                                 const NDIndex* indexes) {
-    if (num_indexes > ndims) {
-        errctx->set_exception(errctx->exceptions->index_error,
-                              "too many indices for array: array is "
-                              "{0}-dimensional, but {1} were indexed",
-                              ndims, num_indexes);
-        return;
-    }
-
-    *final_ndims = ndims;
-    for (SizeT i = 0; i < num_indexes; i++) {
-        if (indexes[i].type == ND_INDEX_TYPE_SINGLE_ELEMENT) {
-            // An index demotes the rank by 1
-            (*final_ndims)--;
-        }
-    }
-}
-}  // namespace util
-
 /**
  * @brief Perform ndarray "basic indexing" (https://numpy.org/doc/stable/user/basics.indexing.html#basic-indexing)
  *
- * This is function very similar to performing `dst_ndarray = src_ndarray[indexes]` in Python (where the variables
+ * This function is very similar to performing `dst_ndarray = src_ndarray[indices]` in Python.
- * can all be found in the parameter of this function).
  *
- * In other words, this function takes in an ndarray (`src_ndarray`), index it with `indexes`, and return the
+ * This function also does proper assertions on `indices` to check for out of bounds access and more.
- * indexed array (by writing the result to `dst_ndarray`).
- *
- * This function also does proper assertions on `indexes`.
  *
  * # Notes on `dst_ndarray`
  * The caller is responsible for allocating space for the resulting ndarray.
@@ -93,68 +80,110 @@ void deduce_ndims_after_indexing(ErrorContext* errctx, SizeT* final_ndims,
  *   - `dst_ndarray->data` does not have to be initialized.
  *   - `dst_ndarray->itemsize` does not have to be initialized.
  *   - `dst_ndarray->ndims` must be initialized, and it must be equal to the expected `ndims` of the `dst_ndarray` after
- *       indexing `src_ndarray` with `indexes`.
+ *       indexing `src_ndarray` with `indices`.
  *   - `dst_ndarray->shape` must be allocated, through it can contain uninitialized values.
  *   - `dst_ndarray->strides` must be allocated, through it can contain uninitialized values.
  * When this function call ends:
- *   - `dst_ndarray->data` is set to `src_ndarray->data` (`dst_ndarray` is just a view to `src_ndarray`)
+ *   - `dst_ndarray->data` is set to `src_ndarray->data`.
- *   - `dst_ndarray->itemsize` is set to `src_ndarray->itemsize`
+ *   - `dst_ndarray->itemsize` is set to `src_ndarray->itemsize`.
  *   - `dst_ndarray->ndims` is unchanged.
  *   - `dst_ndarray->shape` is updated according to how `src_ndarray` is indexed.
  *   - `dst_ndarray->strides` is updated accordingly by how ndarray indexing works.
  *
- * @param indexes Indexes to index `src_ndarray`, ordered in the same way you would write them in Python.
+ * @param indices indices to index `src_ndarray`, ordered in the same way you would write them in Python.
  * @param src_ndarray The NDArray to be indexed.
  * @param dst_ndarray The resulting NDArray after indexing. Further details in the comments above,
  */
 template<typename SizeT>
-void index(ErrorContext* errctx, SizeT num_indexes, const NDIndex* indexes,
+void index(SizeT num_indices, const NDIndex* indices, const NDArray<SizeT>* src_ndarray, NDArray<SizeT>* dst_ndarray) {
-           const NDArray<SizeT>* src_ndarray, NDArray<SizeT>* dst_ndarray) {
+    // Validate `indices`.
-    // Reference code: https://github.com/wadetb/tinynumpy/blob/0d23d22e07062ffab2afa287374c7b366eebdda1/tinynumpy/tinynumpy.py#L652
+
+    // Expected value of `dst_ndarray->ndims`.
+    SizeT expected_dst_ndims = src_ndarray->ndims;
+    // To check for "too many indices for array: array is ?-dimensional, but ? were indexed"
+    SizeT num_indexed = 0;
+    // There may be ellipsis `...` in `indices`. There can only be 0 or 1 ellipsis.
+    SizeT num_ellipsis = 0;
+
+    for (SizeT i = 0; i < num_indices; i++) {
+        if (indices[i].type == ND_INDEX_TYPE_SINGLE_ELEMENT) {
+            expected_dst_ndims--;
+            num_indexed++;
+        } else if (indices[i].type == ND_INDEX_TYPE_SLICE) {
+            num_indexed++;
+        } else if (indices[i].type == ND_INDEX_TYPE_NEWAXIS) {
+            expected_dst_ndims++;
+        } else if (indices[i].type == ND_INDEX_TYPE_ELLIPSIS) {
+            num_ellipsis++;
+            if (num_ellipsis > 1) {
+                raise_exception(SizeT, EXN_INDEX_ERROR, "an index can only have a single ellipsis ('...')", NO_PARAM,
+                                NO_PARAM, NO_PARAM);
+            }
+        } else {
+            __builtin_unreachable();
+        }
+    }
+
+    debug_assert_eq(SizeT, expected_dst_ndims, dst_ndarray->ndims);
+
+    if (src_ndarray->ndims - num_indexed < 0) {
+        raise_exception(SizeT, EXN_INDEX_ERROR,
+                        "too many indices for array: array is {0}-dimensional, "
+                        "but {1} were indexed",
+                        src_ndarray->ndims, num_indices, NO_PARAM);
+    }
 
     dst_ndarray->data = src_ndarray->data;
     dst_ndarray->itemsize = src_ndarray->itemsize;
 
+    // Reference code:
+    // https://github.com/wadetb/tinynumpy/blob/0d23d22e07062ffab2afa287374c7b366eebdda1/tinynumpy/tinynumpy.py#L652
     SizeT src_axis = 0;
     SizeT dst_axis = 0;
 
-    for (SliceIndex i = 0; i < num_indexes; i++) {
+    for (int32_t i = 0; i < num_indices; i++) {
-        const NDIndex* index = &indexes[i];
+        const NDIndex* index = &indices[i];
         if (index->type == ND_INDEX_TYPE_SINGLE_ELEMENT) {
-            SliceIndex input = *((SliceIndex*)index->data);
+            SizeT input = (SizeT) * ((int32_t*)index->data);
-            SliceIndex k = slice::resolve_index_in_length(
-                src_ndarray->shape[src_axis], input);
 
-            if (k == slice::OUT_OF_BOUNDS) {
+            SizeT k = slice::resolve_index_in_length(src_ndarray->shape[src_axis], input);
-                errctx->set_exception(errctx->exceptions->index_error,
+            if (k == -1) {
+                raise_exception(SizeT, EXN_INDEX_ERROR,
                                 "index {0} is out of bounds for axis {1} "
                                 "with size {2}",
-                                      input, src_axis,
+                                input, src_axis, src_ndarray->shape[src_axis]);
-                                      src_ndarray->shape[src_axis]);
-                return;
             }
 
-            dst_ndarray->data += k * src_ndarray->strides[src_axis];
+            dst_ndarray->data = static_cast<uint8_t*>(dst_ndarray->data) + k * src_ndarray->strides[src_axis];
 
             src_axis++;
         } else if (index->type == ND_INDEX_TYPE_SLICE) {
-            UserSlice* input = (UserSlice*)index->data;
+            Slice<int32_t>* slice = (Slice<int32_t>*)index->data;
 
-            Slice slice;
+            Range<int32_t> range = slice->indices_checked<SizeT>(src_ndarray->shape[src_axis]);
-            input->indices_checked(errctx, src_ndarray->shape[src_axis],
-                                   &slice);
-            if (errctx->has_exception()) {
-                return;
-            }
 
-            dst_ndarray->data +=
+            dst_ndarray->data = static_cast<uint8_t*>(dst_ndarray->data) + (SizeT)range.start * src_ndarray->strides[src_axis];
-                (SizeT)slice.start * src_ndarray->strides[src_axis];
+            dst_ndarray->strides[dst_axis] = ((SizeT)range.step) * src_ndarray->strides[src_axis];
-            dst_ndarray->strides[dst_axis] =
+            dst_ndarray->shape[dst_axis] = (SizeT)range.len<SizeT>();
-                ((SizeT)slice.step) * src_ndarray->strides[src_axis];
-            dst_ndarray->shape[dst_axis] = (SizeT)slice.len();
 
             dst_axis++;
             src_axis++;
+        } else if (index->type == ND_INDEX_TYPE_NEWAXIS) {
+            dst_ndarray->strides[dst_axis] = 0;
+            dst_ndarray->shape[dst_axis] = 1;
+
+            dst_axis++;
+        } else if (index->type == ND_INDEX_TYPE_ELLIPSIS) {
+            // The number of ':' entries this '...' implies.
+            SizeT ellipsis_size = src_ndarray->ndims - num_indexed;
+
+            for (SizeT j = 0; j < ellipsis_size; j++) {
+                dst_ndarray->strides[dst_axis] = src_ndarray->strides[src_axis];
+                dst_ndarray->shape[dst_axis] = src_ndarray->shape[src_axis];
+
+                dst_axis++;
+                src_axis++;
+            }
         } else {
             __builtin_unreachable();
         }
@@ -164,6 +193,9 @@ void index(ErrorContext* errctx, SizeT num_indexes, const NDIndex* indexes,
         dst_ndarray->shape[dst_axis] = src_ndarray->shape[src_axis];
         dst_ndarray->strides[dst_axis] = src_ndarray->strides[src_axis];
     }
+
+    debug_assert_eq(SizeT, src_ndarray->ndims, src_axis);
+    debug_assert_eq(SizeT, dst_ndarray->ndims, dst_axis);
 }
 }  // namespace indexing
 }  // namespace ndarray
@@ -172,29 +204,17 @@ void index(ErrorContext* errctx, SizeT num_indexes, const NDIndex* indexes,
 extern "C" {
 using namespace ndarray::indexing;
 
-void __nac3_ndarray_indexing_deduce_ndims_after_indexing(
+void __nac3_ndarray_index(int32_t num_indices,
-    ErrorContext* errctx, int32_t* result, int32_t ndims, int32_t num_indexes,
+                          NDIndex* indices,
-    const NDIndex* indexes) {
+                          NDArray<int32_t>* src_ndarray,
-    ndarray::indexing::util::deduce_ndims_after_indexing(errctx, result, ndims,
-                                                         num_indexes, indexes);
-}
-
-void __nac3_ndarray_indexing_deduce_ndims_after_indexing64(
-    ErrorContext* errctx, int64_t* result, int64_t ndims, int64_t num_indexes,
-    const NDIndex* indexes) {
-    ndarray::indexing::util::deduce_ndims_after_indexing(errctx, result, ndims,
-                                                         num_indexes, indexes);
-}
-
-void __nac3_ndarray_index(ErrorContext* errctx, int32_t num_indexes,
-                          NDIndex* indexes, NDArray<int32_t>* src_ndarray,
                           NDArray<int32_t>* dst_ndarray) {
-    index(errctx, num_indexes, indexes, src_ndarray, dst_ndarray);
+    index(num_indices, indices, src_ndarray, dst_ndarray);
 }
 
-void __nac3_ndarray_index64(ErrorContext* errctx, int64_t num_indexes,
+void __nac3_ndarray_index64(int64_t num_indices,
-                            NDIndex* indexes, NDArray<int64_t>* src_ndarray,
+                            NDIndex* indices,
+                            NDArray<int64_t>* src_ndarray,
                             NDArray<int64_t>* dst_ndarray) {
-    index(errctx, num_indexes, indexes, src_ndarray, dst_ndarray);
+    index(num_indices, indices, src_ndarray, dst_ndarray);
 }
 }

nac3core/irrt/irrt/ndarray/iter.hpp

@@ -0,0 +1,146 @@
+#pragma once
+
+#include "irrt/int_types.hpp"
+#include "irrt/ndarray/def.hpp"
+
+namespace {
+/**
+ * @brief Helper struct to enumerate through an ndarray *efficiently*.
+ *
+ * Example usage (in pseudo-code):
+ * ```
+ * // Suppose my_ndarray has been initialized, with shape [2, 3] and dtype `double`
+ * NDIter nditer;
+ * nditer.initialize(my_ndarray);
+ * while (nditer.has_element()) {
+ *    // This body is run 6 (= my_ndarray.size) times.
+ *
+ *    // [0, 0] -> [0, 1] -> [0, 2] -> [1, 0] -> [1, 1] -> [1, 2] -> end
+ *    print(nditer.indices);
+ *
+ *    // 0 -> 1 -> 2 -> 3 -> 4 -> 5
+ *    print(nditer.nth);
+ *
+ *    // <1st element> -> <2nd element> -> ... -> <6th element> -> end
+ *    print(*((double *) nditer.element))
+ *
+ *    nditer.next(); // Go to next element.
+ * }
+ * ```
+ *
+ * Interesting cases:
+ * - If `my_ndarray.ndims` == 0, there is one iteration.
+ * - If `my_ndarray.shape` contains zeroes, there are no iterations.
+ */
+template<typename SizeT>
+struct NDIter {
+    // Information about the ndarray being iterated over.
+    SizeT ndims;
+    SizeT* shape;
+    SizeT* strides;
+
+    /**
+     * @brief The current indices.
+     *
+     * Must be allocated by the caller.
+     */
+    SizeT* indices;
+
+    /**
+     * @brief The nth (0-based) index of the current indices.
+     *
+     * Initially this is 0.
+     */
+    SizeT nth;
+
+    /**
+     * @brief Pointer to the current element.
+     *
+     * Initially this points to first element of the ndarray.
+     */
+    void* element;
+
+    /**
+     * @brief Cache for the product of shape.
+     *
+     * Could be 0 if `shape` has 0s in it.
+     */
+    SizeT size;
+
+    void initialize(SizeT ndims, SizeT* shape, SizeT* strides, void* element, SizeT* indices) {
+        this->ndims = ndims;
+        this->shape = shape;
+        this->strides = strides;
+
+        this->indices = indices;
+        this->element = element;
+
+        // Compute size
+        this->size = 1;
+        for (SizeT i = 0; i < ndims; i++) {
+            this->size *= shape[i];
+        }
+
+        // `indices` starts on all 0s.
+        for (SizeT axis = 0; axis < ndims; axis++)
+            indices[axis] = 0;
+        nth = 0;
+    }
+
+    void initialize_by_ndarray(NDArray<SizeT>* ndarray, SizeT* indices) {
+        // NOTE: ndarray->data is pointing to the first element, and `NDIter`'s `element` should also point to the first
+        // element as well.
+        this->initialize(ndarray->ndims, ndarray->shape, ndarray->strides, ndarray->data, indices);
+    }
+
+    // Is the current iteration valid?
+    // If true, then `element`, `indices` and `nth` contain details about the current element.
+    bool has_element() { return nth < size; }
+
+    // Go to the next element.
+    void next() {
+        for (SizeT i = 0; i < ndims; i++) {
+            SizeT axis = ndims - i - 1;
+            indices[axis]++;
+            if (indices[axis] >= shape[axis]) {
+                indices[axis] = 0;
+
+                // TODO: There is something called backstrides to speedup iteration.
+                // See https://ajcr.net/stride-guide-part-1/, and
+                // https://docs.scipy.org/doc/numpy-1.13.0/reference/c-api.types-and-structures.html#c.PyArrayIterObject.PyArrayIterObject.backstrides.
+                element = static_cast<void*>(reinterpret_cast<uint8_t*>(element) - strides[axis] * (shape[axis] - 1));
+            } else {
+                element = static_cast<void*>(reinterpret_cast<uint8_t*>(element) + strides[axis]);
+                break;
+            }
+        }
+        nth++;
+    }
+};
+}  // namespace
+
+extern "C" {
+void __nac3_nditer_initialize(NDIter<int32_t>* iter, NDArray<int32_t>* ndarray, int32_t* indices) {
+    iter->initialize_by_ndarray(ndarray, indices);
+}
+
+void __nac3_nditer_initialize64(NDIter<int64_t>* iter, NDArray<int64_t>* ndarray, int64_t* indices) {
+    iter->initialize_by_ndarray(ndarray, indices);
+}
+
+bool __nac3_nditer_has_element(NDIter<int32_t>* iter) {
+    return iter->has_element();
+}
+
+bool __nac3_nditer_has_element64(NDIter<int64_t>* iter) {
+    return iter->has_element();
+}
+
+void __nac3_nditer_next(NDIter<int32_t>* iter) {
+    iter->next();
+}
+
+void __nac3_nditer_next64(NDIter<int64_t>* iter) {
+    iter->next();
+}
+}

nac3core/irrt/irrt/ndarray/reshape.hpp

@@ -1,117 +0,0 @@
-#pragma once
-
-#include <irrt/error_context.hpp>
-#include <irrt/int_defs.hpp>
-#include <irrt/ndarray/def.hpp>
-
-namespace {
-namespace ndarray {
-namespace reshape {
-namespace util {
-
-/**
- * @brief Perform assertions on and resolve unknown dimensions in `new_shape` in `np.reshape(<ndarray>, new_shape)`
- *
- * If `new_shape` indeed contains unknown dimensions (specified with `-1`, just like numpy), `new_shape` will be
- * modified to contain the resolved dimension.
- *
- * To perform assertions on and resolve unknown dimensions in `new_shape`, we don't need the actual
- * `<ndarray>` object itself, but only the `.size` of the `<ndarray>`.
- *
- * @param size The `.size` of `<ndarray>`
- * @param new_ndims Number of elements in `new_shape`
- * @param new_shape Target shape to reshape to
- */
-template <typename SizeT>
-void resolve_and_check_new_shape(ErrorContext* errctx, SizeT size,
-                                 SizeT new_ndims, SizeT* new_shape) {
-    // Is there a -1 in `new_shape`?
-    bool neg1_exists = false;
-    // Location of -1, only initialized if `neg1_exists` is true
-    SizeT neg1_axis_i;
-    // The computed ndarray size of `new_shape`
-    SizeT new_size = 1;
-
-    for (SizeT axis_i = 0; axis_i < new_ndims; axis_i++) {
-        SizeT dim = new_shape[axis_i];
-        if (dim < 0) {
-            if (dim == -1) {
-                if (neg1_exists) {
-                    // Multiple `-1` found. Throw an error.
-                    errctx->set_exception(
-                        errctx->exceptions->value_error,
-                        "can only specify one unknown dimension");
-                    return;
-                } else {
-                    neg1_exists = true;
-                    neg1_axis_i = axis_i;
-                }
-            } else {
-                // TODO: What? In `np.reshape` any negative dimensions is
-                // treated like its `-1`.
-                //
-                // Try running `np.zeros((3, 4)).reshape((-999, 2))`
-                //
-                // It is not documented by numpy.
-                // Throw an error for now...
-
-                errctx->set_exception(
-                    errctx->exceptions->value_error,
-                    "Found negative dimension {0} on axis {1}", dim, axis_i);
-                return;
-            }
-        } else {
-            new_size *= dim;
-        }
-    }
-
-    bool can_reshape;
-    if (neg1_exists) {
-        // Let `x` be the unknown dimension
-        // solve `x * <new_size> = <size>`
-        if (new_size == 0 && size == 0) {
-            // `x` has infinitely many solutions
-            can_reshape = false;
-        } else if (new_size == 0 && size != 0) {
-            // `x` has no solutions
-            can_reshape = false;
-        } else if (size % new_size != 0) {
-            // `x` has no integer solutions
-            can_reshape = false;
-        } else {
-            can_reshape = true;
-            new_shape[neg1_axis_i] = size / new_size;  // Resolve dimension
-        }
-    } else {
-        can_reshape = (new_size == size);
-    }
-
-    if (!can_reshape) {
-        errctx->set_exception(
-            errctx->exceptions->value_error,
-            "cannot reshape array of size {0} into given shape", size);
-        return;
-    }
-}
-}  // namespace util
-}  // namespace reshape
-}  // namespace ndarray
-}  // namespace
-
-extern "C" {
-
-void __nac3_ndarray_resolve_and_check_new_shape(ErrorContext* errctx,
-                                                int32_t size, int32_t new_ndims,
-                                                int32_t* new_shape) {
-    ndarray::reshape::util::resolve_and_check_new_shape(errctx, size, new_ndims,
-                                                        new_shape);
-}
-
-void __nac3_ndarray_resolve_and_check_new_shape64(ErrorContext* errctx,
-                                                  int64_t size,
-                                                  int64_t new_ndims,
-                                                  int64_t* new_shape) {
-    ndarray::reshape::util::resolve_and_check_new_shape(errctx, size, new_ndims,
-                                                        new_shape);
-}
-}

nac3core/irrt/irrt/range.hpp

@@ -0,0 +1,47 @@
+#pragma once
+
+#include "irrt/debug.hpp"
+#include "irrt/int_types.hpp"
+
+namespace {
+namespace range {
+template<typename T>
+T len(T start, T stop, T step) {
+    // Reference:
+    // https://github.com/python/cpython/blob/9dbd12375561a393eaec4b21ee4ac568a407cdb0/Objects/rangeobject.c#L933
+    if (step > 0 && start < stop)
+        return 1 + (stop - 1 - start) / step;
+    else if (step < 0 && start > stop)
+        return 1 + (start - 1 - stop) / (-step);
+    else
+        return 0;
+}
+}  // namespace range
+
+/**
+ * @brief A Python range.
+ */
+template<typename T>
+struct Range {
+    T start;
+    T stop;
+    T step;
+
+    /**
+     * @brief Calculate the `len()` of this range.
+     */
+    template<typename SizeT>
+    T len() {
+        debug_assert(SizeT, step != 0);
+        return range::len(start, stop, step);
+    }
+};
+}  // namespace
+
+extern "C" {
+using namespace range;
+
+SliceIndex __nac3_range_slice_len(const SliceIndex start, const SliceIndex end, const SliceIndex step) {
+    return len(start, end, step);
+}
+}

nac3core/irrt/irrt/slice.hpp

@@ -1,78 +1,67 @@
 #pragma once
 
-#include <irrt/error_context.hpp>
+#include "irrt/debug.hpp"
-#include <irrt/int_defs.hpp>
+#include "irrt/exception.hpp"
-#include <irrt/slice.hpp>
+#include "irrt/int_types.hpp"
-#include <irrt/utils.hpp>
+#include "irrt/math_util.hpp"
-
+#include "irrt/range.hpp"
-// The type of an index or a value describing the length of a
-// range/slice is always `int32_t`.
-using SliceIndex = int32_t;
 
 namespace {
-
-/**
- * @brief A Python-like slice with resolved indices.
- *
- * "Resolved indices" means that `start` and `stop` must be positive and are
- * bound to a known length.
- */
-struct Slice {
-    SliceIndex start;
-    SliceIndex stop;
-    SliceIndex step;
-
-    /**
-     * @brief Calculate and return the length / the number of the slice.
-     * 
-     * If this were a Python range, this function would be `len(range(start, stop, step))`.
-     */
-    SliceIndex len() {
-        SliceIndex diff = stop - start;
-        if (diff > 0 && step > 0) {
-            return ((diff - 1) / step) + 1;
-        } else if (diff < 0 && step < 0) {
-            return ((diff + 1) / step) + 1;
-        } else {
-            return 0;
-        }
-    }
-};
-
 namespace slice {
 /**
- * @brief Resolve a slice index under a given length like Python indexing.
+ * @brief Resolve a possibly negative index in a list of a known length.
- *
- * In Python, if you have a `list` of length 100, `list[-1]` resolves to
- * `list[99]`, so `resolve_index_in_length_clamped(100, -1)` returns `99`.
- *
- * If `length` is 0, 0 is returned for any value of `index`.
- *
- * If `index` is out of bounds, clamps the returned value between `0` and
- * `length - 1` (inclusive).
  *
+ * Returns -1 if the resolved index is out of the list's bounds.
  */
-SliceIndex resolve_index_in_length_clamped(SliceIndex length,
+template<typename T>
-                                           SliceIndex index) {
+T resolve_index_in_length(T length, T index) {
-    if (index < 0) {
+    T resolved = index < 0 ? length + index : index;
-        return max<SliceIndex>(length + index, 0);
-    } else {
-        return min<SliceIndex>(length, index);
-    }
-}
-
-const SliceIndex OUT_OF_BOUNDS = -1;
-
-/**
- * @brief Like `resolve_index_in_length_clamped`, but returns `OUT_OF_BOUNDS`
- * if `index` is out of bounds.
- */
-SliceIndex resolve_index_in_length(SliceIndex length, SliceIndex index) {
-    SliceIndex resolved = index < 0 ? length + index : index;
     if (0 <= resolved && resolved < length) {
         return resolved;
     } else {
-        return OUT_OF_BOUNDS;
+        return -1;
+    }
+}
+
+/**
+ * @brief Resolve a slice as a range.
+ *
+ * This is equivalent to `range(*slice(start, stop, step).indices(length))` in Python.
+ */
+template<typename T>
+void indices(bool start_defined,
+             T start,
+             bool stop_defined,
+             T stop,
+             bool step_defined,
+             T step,
+             T length,
+             T* range_start,
+             T* range_stop,
+             T* range_step) {
+    // Reference: https://github.com/python/cpython/blob/main/Objects/sliceobject.c#L388
+    *range_step = step_defined ? step : 1;
+    bool step_is_negative = *range_step < 0;
+
+    T lower, upper;
+    if (step_is_negative) {
+        lower = -1;
+        upper = length - 1;
+    } else {
+        lower = 0;
+        upper = length;
+    }
+
+    if (start_defined) {
+        *range_start = start < 0 ? max(lower, start + length) : min(upper, start);
+    } else {
+        *range_start = step_is_negative ? upper : lower;
+    }
+
+    if (stop_defined) {
+        *range_stop = stop < 0 ? max(lower, stop + length) : min(upper, stop);
+    } else {
+        *range_stop = step_is_negative ? lower : upper;
     }
 }
 }  // namespace slice
@@ -80,17 +69,18 @@ SliceIndex resolve_index_in_length(SliceIndex length, SliceIndex index) {
 /**
  * @brief A Python-like slice with **unresolved** indices.
  */
-struct UserSlice {
+template<typename T>
+struct Slice {
     bool start_defined;
-    SliceIndex start;
+    T start;
 
     bool stop_defined;
-    SliceIndex stop;
+    T stop;
 
     bool step_defined;
-    SliceIndex step;
+    T step;
 
-    UserSlice() { this->reset(); }
+    Slice() { this->reset(); }
 
     void reset() {
         this->start_defined = false;
@@ -98,69 +88,69 @@ struct UserSlice {
         this->step_defined = false;
     }
 
-    void set_start(SliceIndex start) {
+    void set_start(T start) {
         this->start_defined = true;
         this->start = start;
     }
 
-    void set_stop(SliceIndex stop) {
+    void set_stop(T stop) {
         this->stop_defined = true;
         this->stop = stop;
     }
 
-    void set_step(SliceIndex step) {
+    void set_step(T step) {
         this->step_defined = true;
         this->step = step;
     }
 
     /**
-     * @brief Resolve this slice.
+     * @brief Resolve this slice as a range.
      *
-     * In Python, this would be `slice(start, stop, step).indices(length)`.
+     * In Python, this would be `range(*slice(start, stop, step).indices(length))`.
-     *
-     * @return A `Slice` with the resolved indices.
      */
-    Slice indices(SliceIndex length) {
+    template<typename SizeT>
-        Slice result;
+    Range<T> indices(T length) {
-
+        // Reference:
-        result.step = step_defined ? step : 1;
+        // https://github.com/python/cpython/blob/main/Objects/sliceobject.c#L388
-        bool step_is_negative = result.step < 0;
+        debug_assert(SizeT, length >= 0);
-
-        if (start_defined) {
-            result.start =
-                slice::resolve_index_in_length_clamped(length, start);
-        } else {
-            result.start = step_is_negative ? length - 1 : 0;
-        }
-
-        if (stop_defined) {
-            result.stop = slice::resolve_index_in_length_clamped(length, stop);
-        } else {
-            result.stop = step_is_negative ? -1 : length;
-        }
 
+        Range<T> result;
+        slice::indices(start_defined, start, stop_defined, stop, step_defined, step, length, &result.start,
+                       &result.stop, &result.step);
         return result;
     }
 
     /**
      * @brief Like `.indices()` but with assertions.
      */
-    void indices_checked(ErrorContext* errctx, SliceIndex length,
+    template<typename SizeT>
-                         Slice* result) {
+    Range<T> indices_checked(T length) {
+        // TODO: Switch to `SizeT length`
+
         if (length < 0) {
-            errctx->set_exception(errctx->exceptions->value_error,
+            raise_exception(SizeT, EXN_VALUE_ERROR, "length should not be negative, got {0}", length, NO_PARAM,
-                                  "length should not be negative, got {0}",
+                            NO_PARAM);
-                                  length);
-            return;
         }
 
         if (this->step_defined && this->step == 0) {
-            errctx->set_exception(errctx->exceptions->value_error,
+            raise_exception(SizeT, EXN_VALUE_ERROR, "slice step cannot be zero", NO_PARAM, NO_PARAM, NO_PARAM);
-                                  "slice step cannot be zero");
-            return;
         }
 
-        *result = this->indices(length);
+        return this->indices<SizeT>(length);
     }
 };
 }  // namespace
+
+extern "C" {
+SliceIndex __nac3_slice_index_bound(SliceIndex i, const SliceIndex len) {
+    if (i < 0) {
+        i = len + i;
+    }
+    if (i < 0) {
+        return 0;
+    } else if (i > len) {
+        return len;
+    }
+    return i;
+}
+}

nac3core/irrt/irrt/utils.hpp

@@ -1,104 +0,0 @@
-#pragma once
-
-namespace {
-template <typename T>
-const T& max(const T& a, const T& b) {
-    return a > b ? a : b;
-}
-
-template <typename T>
-const T& min(const T& a, const T& b) {
-    return a > b ? b : a;
-}
-
-/**
- * @brief Compare contents of two arrays with the same length.
- */
-template <typename T>
-bool arrays_match(int len, T* as, T* bs) {
-    for (int i = 0; i < len; i++) {
-        if (as[i] != bs[i]) return false;
-    }
-    return true;
-}
-
-namespace cstr_utils {
-/**
- * @brief Return true if `str` is empty.
- */
-bool is_empty(const char* str) { return str[0] == '\0'; }
-
-/**
- * @brief Implementation of `strcmp()`
- */
-int8_t compare(const char* a, const char* b) {
-    uint32_t i = 0;
-    while (true) {
-        if (a[i] < b[i]) {
-            return -1;
-        } else if (a[i] > b[i]) {
-            return 1;
-        } else {
-            if (a[i] == '\0') {
-                return 0;
-            } else {
-                i++;
-            }
-        }
-    }
-}
-
-/**
- * @brief Return true two strings have the same content.
- */
-int8_t equal(const char* a, const char* b) { return compare(a, b) == 0; }
-
-/**
- * @brief Implementation of `strlen()`.
- */
-uint32_t length(const char* str) {
-    uint32_t length = 0;
-    while (*str != '\0') {
-        length++;
-        str++;
-    }
-    return length;
-}
-
-/**
- * @brief Copy a null-terminated string to a buffer with limited size and guaranteed null-termination.
- *
- * `dst_max_size` must be greater than 0, otherwise this function has undefined behavior.
- *
- * This function attempts to copy everything from `src` from `dst`, and *always* null-terminates `dst`.
- *
- * If the size of `dst` is too small, the final byte (`dst[dst_max_size - 1]`) of `dst` will be set to
- * the null terminator.
- *
- * @param src String to copy from.
- * @param dst Buffer to copy string to.
- * @param dst_max_size
- *   Number of bytes of this buffer, including the space needed for the null terminator.
- *   Must be greater than 0.
- * @return If `dst` is too small to contain everything in `src`.
- */
-bool copy(const char* src, char* dst, uint32_t dst_max_size) {
-    for (uint32_t i = 0; i < dst_max_size; i++) {
-        bool is_last = i + 1 == dst_max_size;
-        if (is_last && src[i] != '\0') {
-            dst[i] = '\0';
-            return false;
-        }
-
-        if (src[i] == '\0') {
-            dst[i] = '\0';
-            return true;
-        }
-
-        dst[i] = src[i];
-    }
-
-    __builtin_unreachable();
-}
-}  // namespace cstr_utils
-}  // namespace

nac3core/irrt/irrt_everything.hpp

@@ -1,13 +0,0 @@
-#pragma once
-
-#include <irrt/artiq_defs.hpp>
-#include <irrt/core.hpp>
-#include <irrt/error_context.hpp>
-#include <irrt/int_defs.hpp>
-#include <irrt/ndarray/basic.hpp>
-#include <irrt/ndarray/broadcast.hpp>
-#include <irrt/ndarray/def.hpp>
-#include <irrt/ndarray/indexing.hpp>
-#include <irrt/ndarray/reshape.hpp>
-#include <irrt/slice.hpp>
-#include <irrt/utils.hpp>

nac3core/irrt/irrt_test.cpp

@@ -1,20 +0,0 @@
-// This file will be compiled like a real C++ program,
-// and we do have the luxury to use the standard libraries.
-// That is if the nix flakes do not have issues... especially on msys2...
-#include <cstdint>
-#include <cstdio>
-#include <cstdlib>
-#include <test/test_core.hpp>
-#include <test/test_ndarray_basic.hpp>
-#include <test/test_ndarray_broadcast.hpp>
-#include <test/test_ndarray_indexing.hpp>
-#include <test/test_slice.hpp>
-
-int main() {
-    test::core::run();
-    test::slice::run();
-    test::ndarray_basic::run();
-    test::ndarray_indexing::run();
-    test::ndarray_broadcast::run();
-    return 0;
-}

nac3core/irrt/test/includes.hpp

@@ -1,11 +0,0 @@
-#pragma once
-
-#include <cstdint>
-#include <cstdio>
-#include <cstdlib>
-#include <irrt_everything.hpp>
-#include <test/util.hpp>
-
-/*
-    Include this header for every test_*.cpp
-*/

nac3core/irrt/test/test_core.hpp

@@ -1,16 +0,0 @@
-#pragma once
-
-#include <test/includes.hpp>
-
-namespace test {
-namespace core {
-void test_int_exp() {
-    BEGIN_TEST();
-
-    assert_values_match(125, __nac3_int_exp_impl<int32_t>(5, 3));
-    assert_values_match(3125, __nac3_int_exp_impl<int32_t>(5, 5));
-}
-
-void run() { test_int_exp(); }
-}  // namespace core
-}  // namespace test

nac3core/irrt/test/test_ndarray_basic.hpp

@@ -1,30 +0,0 @@
-#pragma once
-
-#include <test/includes.hpp>
-
-namespace test {
-namespace ndarray_basic {
-void test_calc_size_from_shape_normal() {
-    // Test shapes with normal values
-    BEGIN_TEST();
-
-    int32_t shape[4] = {2, 3, 5, 7};
-    assert_values_match(
-        210, ndarray::basic::util::calc_size_from_shape<int32_t>(4, shape));
-}
-
-void test_calc_size_from_shape_has_zero() {
-    // Test shapes with 0 in them
-    BEGIN_TEST();
-
-    int32_t shape[4] = {2, 0, 5, 7};
-    assert_values_match(
-        0, ndarray::basic::util::calc_size_from_shape<int32_t>(4, shape));
-}
-
-void run() {
-    test_calc_size_from_shape_normal();
-    test_calc_size_from_shape_has_zero();
-}
-}  // namespace ndarray_basic
-}  // namespace test

nac3core/irrt/test/test_ndarray_broadcast.hpp

@@ -1,129 +0,0 @@
-#pragma once
-
-#include <test/includes.hpp>
-
-namespace test {
-namespace ndarray_broadcast {
-void test_can_broadcast_shape() {
-    BEGIN_TEST();
-
-    assert_values_match(true,
-                        ndarray::broadcast::util::can_broadcast_shape_to(
-                            1, (int32_t[]){3}, 5, (int32_t[]){1, 1, 1, 1, 3}));
-    assert_values_match(false, ndarray::broadcast::util::can_broadcast_shape_to(
-                                   1, (int32_t[]){3}, 2, (int32_t[]){3, 1}));
-    assert_values_match(true, ndarray::broadcast::util::can_broadcast_shape_to(
-                                  1, (int32_t[]){3}, 1, (int32_t[]){3}));
-    assert_values_match(false, ndarray::broadcast::util::can_broadcast_shape_to(
-                                   1, (int32_t[]){1}, 1, (int32_t[]){3}));
-    assert_values_match(true, ndarray::broadcast::util::can_broadcast_shape_to(
-                                  1, (int32_t[]){1}, 1, (int32_t[]){1}));
-    assert_values_match(
-        true, ndarray::broadcast::util::can_broadcast_shape_to(
-                  3, (int32_t[]){256, 256, 3}, 3, (int32_t[]){256, 1, 3}));
-    assert_values_match(true,
-                        ndarray::broadcast::util::can_broadcast_shape_to(
-                            3, (int32_t[]){256, 256, 3}, 1, (int32_t[]){3}));
-    assert_values_match(false,
-                        ndarray::broadcast::util::can_broadcast_shape_to(
-                            3, (int32_t[]){256, 256, 3}, 1, (int32_t[]){2}));
-    assert_values_match(true,
-                        ndarray::broadcast::util::can_broadcast_shape_to(
-                            3, (int32_t[]){256, 256, 3}, 1, (int32_t[]){1}));
-
-    // In cases when the shapes contain zero(es)
-    assert_values_match(true, ndarray::broadcast::util::can_broadcast_shape_to(
-                                  1, (int32_t[]){0}, 1, (int32_t[]){1}));
-    assert_values_match(false, ndarray::broadcast::util::can_broadcast_shape_to(
-                                   1, (int32_t[]){0}, 1, (int32_t[]){2}));
-    assert_values_match(true,
-                        ndarray::broadcast::util::can_broadcast_shape_to(
-                            4, (int32_t[]){0, 4, 0, 0}, 1, (int32_t[]){1}));
-    assert_values_match(
-        true, ndarray::broadcast::util::can_broadcast_shape_to(
-                  4, (int32_t[]){0, 4, 0, 0}, 4, (int32_t[]){1, 1, 1, 1}));
-    assert_values_match(
-        true, ndarray::broadcast::util::can_broadcast_shape_to(
-                  4, (int32_t[]){0, 4, 0, 0}, 4, (int32_t[]){1, 4, 1, 1}));
-    assert_values_match(false, ndarray::broadcast::util::can_broadcast_shape_to(
-                                   2, (int32_t[]){4, 3}, 2, (int32_t[]){0, 3}));
-    assert_values_match(false, ndarray::broadcast::util::can_broadcast_shape_to(
-                                   2, (int32_t[]){4, 3}, 2, (int32_t[]){0, 0}));
-}
-
-void test_ndarray_broadcast() {
-    /*
-    # array = np.array([[19.9, 29.9, 39.9, 49.9]], dtype=np.float64)
-    # >>> [[19.9 29.9 39.9 49.9]]
-    #
-    # array = np.broadcast_to(array, (2, 3, 4))
-    # >>> [[[19.9 29.9 39.9 49.9]
-    # >>>   [19.9 29.9 39.9 49.9]
-    # >>>   [19.9 29.9 39.9 49.9]]
-    # >>>  [[19.9 29.9 39.9 49.9]
-    # >>>   [19.9 29.9 39.9 49.9]
-    # >>>   [19.9 29.9 39.9 49.9]]]
-    #
-    # assery array.strides == (0, 0, 8)
-
-    */
-    BEGIN_TEST();
-
-    double in_data[4] = {19.9, 29.9, 39.9, 49.9};
-    const int32_t in_ndims = 2;
-    int32_t in_shape[in_ndims] = {1, 4};
-    int32_t in_strides[in_ndims] = {};
-    NDArray<int32_t> ndarray = {.data = (uint8_t*)in_data,
-                                .itemsize = sizeof(double),
-                                .ndims = in_ndims,
-                                .shape = in_shape,
-                                .strides = in_strides};
-    ndarray::basic::set_strides_by_shape(&ndarray);
-
-    const int32_t dst_ndims = 3;
-    int32_t dst_shape[dst_ndims] = {2, 3, 4};
-    int32_t dst_strides[dst_ndims] = {};
-    NDArray<int32_t> dst_ndarray = {
-        .ndims = dst_ndims, .shape = dst_shape, .strides = dst_strides};
-
-    ErrorContext errctx = create_testing_errctx();
-    ndarray::broadcast::broadcast_to(&errctx, &ndarray, &dst_ndarray);
-    assert_errctx_no_exception(&errctx);
-
-    assert_arrays_match(dst_ndims, ((int32_t[]){0, 0, 8}), dst_ndarray.strides);
-
-    assert_values_match(19.9,
-                        *((double*)ndarray::basic::get_pelement_by_indices(
-                            &dst_ndarray, ((int32_t[]){0, 0, 0}))));
-    assert_values_match(29.9,
-                        *((double*)ndarray::basic::get_pelement_by_indices(
-                            &dst_ndarray, ((int32_t[]){0, 0, 1}))));
-    assert_values_match(39.9,
-                        *((double*)ndarray::basic::get_pelement_by_indices(
-                            &dst_ndarray, ((int32_t[]){0, 0, 2}))));
-    assert_values_match(49.9,
-                        *((double*)ndarray::basic::get_pelement_by_indices(
-                            &dst_ndarray, ((int32_t[]){0, 0, 3}))));
-    assert_values_match(19.9,
-                        *((double*)ndarray::basic::get_pelement_by_indices(
-                            &dst_ndarray, ((int32_t[]){0, 1, 0}))));
-    assert_values_match(29.9,
-                        *((double*)ndarray::basic::get_pelement_by_indices(
-                            &dst_ndarray, ((int32_t[]){0, 1, 1}))));
-    assert_values_match(39.9,
-                        *((double*)ndarray::basic::get_pelement_by_indices(
-                            &dst_ndarray, ((int32_t[]){0, 1, 2}))));
-    assert_values_match(49.9,
-                        *((double*)ndarray::basic::get_pelement_by_indices(
-                            &dst_ndarray, ((int32_t[]){0, 1, 3}))));
-    assert_values_match(49.9,
-                        *((double*)ndarray::basic::get_pelement_by_indices(
-                            &dst_ndarray, ((int32_t[]){1, 2, 3}))));
-}
-
-void run() {
-    test_can_broadcast_shape();
-    test_ndarray_broadcast();
-}
-}  // namespace ndarray_broadcast
-}  // namespace test

nac3core/irrt/test/test_ndarray_indexing.hpp

@@ -1,220 +0,0 @@
-#pragma once
-
-#include <test/includes.hpp>
-
-namespace test {
-namespace ndarray_indexing {
-void test_normal_1() {
-    /*
-        Reference Python code:
-        ```python
-        ndarray = np.arange(12, dtype=np.float64).reshape((3, 4));
-        # array([[ 0.,  1.,  2.,  3.],
-        #        [ 4.,  5.,  6.,  7.],
-        #        [ 8.,  9., 10., 11.]])
-
-        dst_ndarray = ndarray[-2:, 1::2]
-        # array([[ 5.,  7.],
-        #        [ 9., 11.]])
-
-        assert dst_ndarray.shape == (2, 2)
-        assert dst_ndarray.strides == (32, 16)
-        assert dst_ndarray[0, 0] == 5.0
-        assert dst_ndarray[0, 1] == 7.0
-        assert dst_ndarray[1, 0] == 9.0
-        assert dst_ndarray[1, 1] == 11.0
-        ```
-    */
-    BEGIN_TEST();
-
-    // Prepare src_ndarray
-    double src_data[12] = {0.0, 1.0, 2.0, 3.0, 4.0,  5.0,
-                           6.0, 7.0, 8.0, 9.0, 10.0, 11.0};
-    int32_t src_itemsize = sizeof(double);
-    const int32_t src_ndims = 2;
-    int32_t src_shape[src_ndims] = {3, 4};
-    int32_t src_strides[src_ndims] = {};
-    NDArray<int32_t> src_ndarray = {.data = (uint8_t *)src_data,
-                                    .itemsize = src_itemsize,
-                                    .ndims = src_ndims,
-                                    .shape = src_shape,
-                                    .strides = src_strides};
-    ndarray::basic::set_strides_by_shape(&src_ndarray);
-
-    // Prepare dst_ndarray
-    const int32_t dst_ndims = 2;
-    int32_t dst_shape[dst_ndims] = {999, 999};    // Empty values
-    int32_t dst_strides[dst_ndims] = {999, 999};  // Empty values
-    NDArray<int32_t> dst_ndarray = {.data = nullptr,
-                                    .ndims = dst_ndims,
-                                    .shape = dst_shape,
-                                    .strides = dst_strides};
-
-    // Create the subscripts in `ndarray[-2::, 1::2]`
-    UserSlice subscript_1;
-    subscript_1.set_start(-2);
-
-    UserSlice subscript_2;
-    subscript_2.set_start(1);
-    subscript_2.set_step(2);
-
-    const int32_t num_indexes = 2;
-    NDIndex indexes[num_indexes] = {
-        {.type = ND_INDEX_TYPE_SLICE, .data = (uint8_t *)&subscript_1},
-        {.type = ND_INDEX_TYPE_SLICE, .data = (uint8_t *)&subscript_2}};
-
-    ErrorContext errctx = create_testing_errctx();
-    ndarray::indexing::index(&errctx, num_indexes, indexes, &src_ndarray,
-                             &dst_ndarray);
-    assert_errctx_no_exception(&errctx);
-
-    int32_t expected_shape[dst_ndims] = {2, 2};
-    int32_t expected_strides[dst_ndims] = {32, 16};
-
-    assert_arrays_match(dst_ndims, expected_shape, dst_ndarray.shape);
-    assert_arrays_match(dst_ndims, expected_strides, dst_ndarray.strides);
-
-    // dst_ndarray[0, 0]
-    assert_values_match(5.0,
-                        *((double *)ndarray::basic::get_pelement_by_indices(
-                            &dst_ndarray, (int32_t[dst_ndims]){0, 0})));
-    // dst_ndarray[0, 1]
-    assert_values_match(7.0,
-                        *((double *)ndarray::basic::get_pelement_by_indices(
-                            &dst_ndarray, (int32_t[dst_ndims]){0, 1})));
-    // dst_ndarray[1, 0]
-    assert_values_match(9.0,
-                        *((double *)ndarray::basic::get_pelement_by_indices(
-                            &dst_ndarray, (int32_t[dst_ndims]){1, 0})));
-    // dst_ndarray[1, 1]
-    assert_values_match(11.0,
-                        *((double *)ndarray::basic::get_pelement_by_indices(
-                            &dst_ndarray, (int32_t[dst_ndims]){1, 1})));
-}
-
-void test_normal_2() {
-    /*
-        ```python
-        ndarray = np.arange(12, dtype=np.float64).reshape((3, 4))
-        # array([[ 0.,  1.,  2.,  3.],
-        #        [ 4.,  5.,  6.,  7.],
-        #        [ 8.,  9., 10., 11.]])
-
-        dst_ndarray = ndarray[2, ::-2]
-        # array([11.,  9.])
-
-        assert dst_ndarray.shape == (2,)
-        assert dst_ndarray.strides == (-16,)
-        assert dst_ndarray[0] == 11.0
-        assert dst_ndarray[1] == 9.0
-        ```
-    */
-    BEGIN_TEST();
-
-    // Prepare src_ndarray
-    double src_data[12] = {0.0, 1.0, 2.0, 3.0, 4.0,  5.0,
-                           6.0, 7.0, 8.0, 9.0, 10.0, 11.0};
-    int32_t src_itemsize = sizeof(double);
-    const int32_t src_ndims = 2;
-    int32_t src_shape[src_ndims] = {3, 4};
-    int32_t src_strides[src_ndims] = {};
-    NDArray<int32_t> src_ndarray = {.data = (uint8_t *)src_data,
-                                    .itemsize = src_itemsize,
-                                    .ndims = src_ndims,
-                                    .shape = src_shape,
-                                    .strides = src_strides};
-    ndarray::basic::set_strides_by_shape(&src_ndarray);
-
-    // Prepare dst_ndarray
-    const int32_t dst_ndims = 1;
-    int32_t dst_shape[dst_ndims] = {999};    // Empty values
-    int32_t dst_strides[dst_ndims] = {999};  // Empty values
-    NDArray<int32_t> dst_ndarray = {.data = nullptr,
-                                    .ndims = dst_ndims,
-                                    .shape = dst_shape,
-                                    .strides = dst_strides};
-
-    // Create the subscripts in `ndarray[2, ::-2]`
-    int32_t subscript_1 = 2;
-
-    UserSlice subscript_2;
-    subscript_2.set_step(-2);
-
-    const int32_t num_indexes = 2;
-    NDIndex indexes[num_indexes] = {
-        {.type = ND_INDEX_TYPE_SINGLE_ELEMENT, .data = (uint8_t *)&subscript_1},
-        {.type = ND_INDEX_TYPE_SLICE, .data = (uint8_t *)&subscript_2}};
-
-    ErrorContext errctx = create_testing_errctx();
-    ndarray::indexing::index(&errctx, num_indexes, indexes, &src_ndarray,
-                             &dst_ndarray);
-    assert_errctx_no_exception(&errctx);
-
-    int32_t expected_shape[dst_ndims] = {2};
-    int32_t expected_strides[dst_ndims] = {-16};
-    assert_arrays_match(dst_ndims, expected_shape, dst_ndarray.shape);
-    assert_arrays_match(dst_ndims, expected_strides, dst_ndarray.strides);
-
-    assert_values_match(11.0,
-                        *((double *)ndarray::basic::get_pelement_by_indices(
-                            &dst_ndarray, (int32_t[dst_ndims]){0})));
-    assert_values_match(9.0,
-                        *((double *)ndarray::basic::get_pelement_by_indices(
-                            &dst_ndarray, (int32_t[dst_ndims]){1})));
-}
-
-void test_index_subscript_out_of_bounds() {
-    /*
-        # Consider `my_array`
-
-        print(my_array.shape)
-        # (4, 5, 6)
-
-        my_array[2, 100] # error, index subscript at axis 1 is out of bounds
-    */
-    BEGIN_TEST();
-
-    // Prepare src_ndarray
-    const int32_t src_ndims = 2;
-    int32_t src_shape[src_ndims] = {3, 4};
-    int32_t src_strides[src_ndims] = {};
-    NDArray<int32_t> src_ndarray = {
-        .data = (uint8_t *)nullptr,  // placeholder, we wouldn't access it
-        .itemsize = sizeof(double),  // placeholder
-        .ndims = src_ndims,
-        .shape = src_shape,
-        .strides = src_strides};
-    ndarray::basic::set_strides_by_shape(&src_ndarray);
-
-    // Create the subscripts in `my_array[2, 100]`
-    int32_t subscript_1 = 2;
-    int32_t subscript_2 = 100;
-
-    const int32_t num_indexes = 2;
-    NDIndex indexes[num_indexes] = {
-        {.type = ND_INDEX_TYPE_SINGLE_ELEMENT, .data = (uint8_t *)&subscript_1},
-        {.type = ND_INDEX_TYPE_SINGLE_ELEMENT,
-         .data = (uint8_t *)&subscript_2}};
-
-    // Prepare dst_ndarray
-    const int32_t dst_ndims = 0;
-    int32_t dst_shape[dst_ndims] = {};
-    int32_t dst_strides[dst_ndims] = {};
-    NDArray<int32_t> dst_ndarray = {.data = nullptr,  // placehloder
-                                    .ndims = dst_ndims,
-                                    .shape = dst_shape,
-                                    .strides = dst_strides};
-
-    ErrorContext errctx = create_testing_errctx();
-    ndarray::indexing::index(&errctx, num_indexes, indexes, &src_ndarray,
-                             &dst_ndarray);
-    assert_errctx_has_exception(&errctx, errctx.exceptions->index_error);
-}
-
-void run() {
-    test_normal_1();
-    test_normal_2();
-    test_index_subscript_out_of_bounds();
-}
-}  // namespace ndarray_indexing
-}  // namespace test

nac3core/irrt/test/test_slice.hpp

@@ -1,92 +0,0 @@
-#pragma once
-
-#include <irrt_everything.hpp>
-#include <test/includes.hpp>
-
-namespace test {
-namespace slice {
-void test_slice_normal() {
-    // Normal situation
-    BEGIN_TEST();
-
-    UserSlice user_slice;
-    user_slice.set_stop(5);
-
-    Slice slice = user_slice.indices(100);
-
-    printf("%d, %d, %d\n", slice.start, slice.stop, slice.step);
-
-    assert_values_match(0, slice.start);
-    assert_values_match(5, slice.stop);
-    assert_values_match(1, slice.step);
-}
-
-void test_slice_start_too_large() {
-    // Start is too large and should be clamped to length
-    BEGIN_TEST();
-
-    UserSlice user_slice;
-    user_slice.set_start(400);
-
-    Slice slice = user_slice.indices(100);
-
-    assert_values_match(100, slice.start);
-    assert_values_match(100, slice.stop);
-    assert_values_match(1, slice.step);
-}
-
-void test_slice_negative_start_stop() {
-    // Negative start/stop should be resolved
-    BEGIN_TEST();
-
-    UserSlice user_slice;
-    user_slice.set_start(-10);
-    user_slice.set_stop(-5);
-
-    Slice slice = user_slice.indices(100);
-
-    assert_values_match(90, slice.start);
-    assert_values_match(95, slice.stop);
-    assert_values_match(1, slice.step);
-}
-
-void test_slice_only_negative_step() {
-    // Things like `[::-5]` should be handled correctly
-    BEGIN_TEST();
-
-    UserSlice user_slice;
-    user_slice.set_step(-5);
-
-    Slice slice = user_slice.indices(100);
-
-    assert_values_match(99, slice.start);
-    assert_values_match(-1, slice.stop);
-    assert_values_match(-5, slice.step);
-}
-
-void test_slice_step_zero() {
-    // Step = 0 is a value error
-    BEGIN_TEST();
-
-    ErrorContext errctx = create_testing_errctx();
-
-    UserSlice user_slice;
-    user_slice.set_start(2);
-    user_slice.set_stop(12);
-    user_slice.set_step(0);
-
-    Slice slice;
-    user_slice.indices_checked(&errctx, 100, &slice);
-
-    assert_errctx_has_exception(&errctx, errctx.exceptions->value_error);
-}
-
-void run() {
-    test_slice_normal();
-    test_slice_start_too_large();
-    test_slice_negative_start_stop();
-    test_slice_only_negative_step();
-    test_slice_step_zero();
-}
-}  // namespace slice
-}  // namespace test

nac3core/irrt/test/util.hpp

@@ -1,188 +0,0 @@
-#pragma once
-
-#include <cstdio>
-#include <cstdlib>
-
-template <class T>
-void print_value(const T& value);
-
-template <>
-void print_value(const bool& value) {
-    printf("%s", value ? "true" : "false");
-}
-
-template <>
-void print_value(const int8_t& value) {
-    printf("%d", value);
-}
-
-template <>
-void print_value(const int32_t& value) {
-    printf("%d", value);
-}
-
-template <>
-void print_value(const uint8_t& value) {
-    printf("%u", value);
-}
-
-template <>
-void print_value(const uint32_t& value) {
-    printf("%u", value);
-}
-
-template <>
-void print_value(const float& value) {
-    printf("%f", value);
-}
-
-template <>
-void print_value(const double& value) {
-    printf("%f", value);
-}
-
-void __begin_test(const char* function_name, const char* file, int line) {
-    printf("######### Running %s @ %s:%d\n", function_name, file, line);
-}
-
-#define BEGIN_TEST() __begin_test(__FUNCTION__, __FILE__, __LINE__)
-
-void test_fail() {
-    printf("[!] Test failed. Exiting with status code 1.\n");
-    exit(1);
-}
-
-template <typename T>
-void debug_print_array(int len, const T* as) {
-    printf("[");
-    for (int i = 0; i < len; i++) {
-        if (i != 0) printf(", ");
-        print_value(as[i]);
-    }
-    printf("]");
-}
-
-void print_assertion_passed(const char* file, int line) {
-    printf("[*] Assertion passed on %s:%d\n", file, line);
-}
-
-void print_assertion_failed(const char* file, int line) {
-    printf("[!] Assertion failed on %s:%d\n", file, line);
-}
-
-void __assert_true(const char* file, int line, bool cond) {
-    if (cond) {
-        print_assertion_passed(file, line);
-    } else {
-        print_assertion_failed(file, line);
-        test_fail();
-    }
-}
-
-#define assert_true(cond) __assert_true(__FILE__, __LINE__, cond)
-
-template <typename T>
-void __assert_arrays_match(const char* file, int line, int len,
-                           const T* expected, const T* got) {
-    if (arrays_match(len, expected, got)) {
-        print_assertion_passed(file, line);
-    } else {
-        print_assertion_failed(file, line);
-        printf("Expect = ");
-        debug_print_array(len, expected);
-        printf("\n");
-        printf("   Got = ");
-        debug_print_array(len, got);
-        printf("\n");
-        test_fail();
-    }
-}
-
-#define assert_arrays_match(len, expected, got) \
-    __assert_arrays_match(__FILE__, __LINE__, len, expected, got)
-
-template <typename T>
-void __assert_values_match(const char* file, int line, T expected, T got) {
-    if (expected == got) {
-        print_assertion_passed(file, line);
-    } else {
-        print_assertion_failed(file, line);
-        printf("Expect = ");
-        print_value(expected);
-        printf("\n");
-        printf("   Got = ");
-        print_value(got);
-        printf("\n");
-        test_fail();
-    }
-}
-
-#define assert_values_match(expected, got) \
-    __assert_values_match(__FILE__, __LINE__, expected, got)
-
-// A fake set of ExceptionIds for testing only
-const ErrorContextExceptions TEST_ERROR_CONTEXT_EXCEPTIONS = {
-    .index_error = 0,
-    .value_error = 1,
-    .assertion_error = 2,
-    .runtime_error = 3,
-    .type_error = 4,
-};
-
-ErrorContext create_testing_errctx() {
-    // Everything is global so it is fine to directly return a struct
-    // ErrorContext
-    ErrorContext errctx;
-    errctx.initialize(&TEST_ERROR_CONTEXT_EXCEPTIONS);
-    return errctx;
-}
-
-void print_errctx_content(ErrorContext* errctx) {
-    if (errctx->has_exception()) {
-        printf(
-            "(Exception ID %d): %s ... where param1 = %ld, param2 = %ld, "
-            "param3 = "
-            "%ld\n",
-            errctx->exception_id, errctx->msg, errctx->param1, errctx->param2,
-            errctx->param3);
-    } else {
-        printf("<no exception>\n");
-    }
-}
-
-void __assert_errctx_no_exception(const char* file, int line,
-                                  ErrorContext* errctx) {
-    if (errctx->has_exception()) {
-        print_assertion_failed(file, line);
-        printf("Expecting no exception but caught the following:\n\n");
-        print_errctx_content(errctx);
-        test_fail();
-    }
-}
-
-#define assert_errctx_no_exception(errctx) \
-    __assert_errctx_no_exception(__FILE__, __LINE__, errctx)
-
-void __assert_errctx_has_exception(const char* file, int line,
-                                   ErrorContext* errctx,
-                                   ExceptionId expected_exception_id) {
-    if (errctx->has_exception()) {
-        if (errctx->exception_id != expected_exception_id) {
-            print_assertion_failed(file, line);
-            printf(
-                "Expecting exception id %d but got exception id %d. Error "
-                "caught:\n\n",
-                expected_exception_id, errctx->exception_id);
-            print_errctx_content(errctx);
-            test_fail();
-        }
-    } else {
-        print_assertion_failed(file, line);
-        printf("Expecting an exception, but there is none.");
-        test_fail();
-    }
-}
-
-#define assert_errctx_has_exception(errctx, expected_exception_id) \
-    __assert_errctx_has_exception(__FILE__, __LINE__, errctx,      \
-                                  expected_exception_id)

nac3core/nac3core_derive/Cargo.toml

@@ -0,0 +1,21 @@
+[package]
+name = "nac3core_derive"
+version = "0.1.0"
+edition = "2021"
+
+[lib]
+proc-macro = true
+
+[[test]]
+name = "structfields_tests"
+path = "tests/structfields_test.rs"
+
+[dev-dependencies]
+nac3core = { path = ".." }
+trybuild = { version = "1.0", features = ["diff"] }
+
+[dependencies]
+proc-macro2 = "1.0"
+proc-macro-error = "1.0"
+syn = "2.0"
+quote = "1.0"

nac3core/nac3core_derive/src/lib.rs

@@ -0,0 +1,320 @@
+use proc_macro::TokenStream;
+use proc_macro_error::{abort, proc_macro_error};
+use quote::quote;
+use syn::{
+    parse_macro_input, spanned::Spanned, Data, DataStruct, Expr, ExprField, ExprMethodCall,
+    ExprPath, GenericArgument, Ident, LitStr, Path, PathArguments, Type, TypePath,
+};
+
+/// Extracts all generic arguments of a [`Type`] into a [`Vec`].
+///
+/// Returns [`Some`] of a possibly-empty [`Vec`] if the path of `ty` matches with
+/// `expected_ty_name`, otherwise returns [`None`].
+fn extract_generic_args(expected_ty_name: &'static str, ty: &Type) -> Option<Vec<GenericArgument>> {
+    let Type::Path(TypePath { qself: None, path, .. }) = ty else {
+        return None;
+    };
+
+    let segments = &path.segments;
+    if segments.len() != 1 {
+        return None;
+    };
+
+    let segment = segments.iter().next().unwrap();
+    if segment.ident != expected_ty_name {
+        return None;
+    }
+
+    let PathArguments::AngleBracketed(path_args) = &segment.arguments else {
+        return Some(Vec::new());
+    };
+    let args = &path_args.args;
+
+    Some(args.iter().cloned().collect::<Vec<_>>())
+}
+
+/// Maps a `path` matching one of the `target_idents` into the `replacement` [`Ident`].
+fn map_path_to_ident(path: &Path, target_idents: &[&str], replacement: &str) -> Option<Ident> {
+    path.require_ident()
+        .ok()
+        .filter(|ident| target_idents.iter().any(|target| ident == target))
+        .map(|ident| Ident::new(replacement, ident.span()))
+}
+
+/// Extracts the left-hand side of a dot-expression.
+fn extract_dot_operand(expr: &Expr) -> Option<&Expr> {
+    match expr {
+        Expr::MethodCall(ExprMethodCall { receiver: operand, .. })
+        | Expr::Field(ExprField { base: operand, .. }) => Some(operand),
+        _ => None,
+    }
+}
+
+/// Replaces the top-level receiver of a dot-expression with an [`Ident`], returning `Some(&mut expr)` if the
+/// replacement is performed.
+///
+/// The top-level receiver is the left-most receiver expression, e.g. the top-level receiver of `a.b.c.foo()` is `a`.
+fn replace_top_level_receiver(expr: &mut Expr, ident: Ident) -> Option<&mut Expr> {
+    if let Expr::MethodCall(ExprMethodCall { receiver: operand, .. })
+    | Expr::Field(ExprField { base: operand, .. }) = expr
+    {
+        return if extract_dot_operand(operand).is_some() {
+            if replace_top_level_receiver(operand, ident).is_some() {
+                Some(expr)
+            } else {
+                None
+            }
+        } else {
+            *operand = Box::new(Expr::Path(ExprPath {
+                attrs: Vec::default(),
+                qself: None,
+                path: ident.into(),
+            }));
+
+            Some(expr)
+        };
+    }
+
+    None
+}
+
+/// Iterates all operands to the left-hand side of the `.` of an [expression][`Expr`], i.e. the container operand of all
+/// [`Expr::Field`] and the receiver operand of all [`Expr::MethodCall`].
+///
+/// The iterator will return the operand expressions in reverse order of appearance. For example, `a.b.c.func()` will
+/// return `vec![c, b, a]`.
+fn iter_dot_operands(expr: &Expr) -> impl Iterator<Item = &Expr> {
+    let mut o = extract_dot_operand(expr);
+
+    std::iter::from_fn(move || {
+        let this = o;
+        o = o.as_ref().and_then(|o| extract_dot_operand(o));
+
+        this
+    })
+}
+
+/// Normalizes a value expression for use when creating an instance of this structure, returning a
+/// [`proc_macro2::TokenStream`] of tokens representing the normalized expression.
+fn normalize_value_expr(expr: &Expr) -> proc_macro2::TokenStream {
+    match &expr {
+        Expr::Path(ExprPath { qself: None, path, .. }) => {
+            if let Some(ident) = map_path_to_ident(path, &["usize", "size_t"], "llvm_usize") {
+                quote! { #ident }
+            } else {
+                abort!(
+                    path,
+                    format!(
+                        "Expected one of `size_t`, `usize`, or an implicit call expression in #[value_type(...)], found {}", 
+                        quote!(#expr).to_string(),
+                    )
+                )
+            }
+        }
+
+        Expr::Call(_) => {
+            quote! { ctx.#expr }
+        }
+
+        Expr::MethodCall(_) => {
+            let base_receiver = iter_dot_operands(expr).last();
+
+            match base_receiver {
+                // `usize.{...}`, `size_t.{...}` -> Rewrite the identifiers to `llvm_usize`
+                Some(Expr::Path(ExprPath { qself: None, path, .. }))
+                    if map_path_to_ident(path, &["usize", "size_t"], "llvm_usize").is_some() =>
+                {
+                    let ident =
+                        map_path_to_ident(path, &["usize", "size_t"], "llvm_usize").unwrap();
+
+                    let mut expr = expr.clone();
+                    let expr = replace_top_level_receiver(&mut expr, ident).unwrap();
+
+                    quote!(#expr)
+                }
+
+                // `ctx.{...}`, `context.{...}` -> Rewrite the identifiers to `ctx`
+                Some(Expr::Path(ExprPath { qself: None, path, .. }))
+                    if map_path_to_ident(path, &["ctx", "context"], "ctx").is_some() =>
+                {
+                    let ident = map_path_to_ident(path, &["ctx", "context"], "ctx").unwrap();
+
+                    let mut expr = expr.clone();
+                    let expr = replace_top_level_receiver(&mut expr, ident).unwrap();
+
+                    quote!(#expr)
+                }
+
+                // No reserved identifier prefix -> Prepend `ctx.` to the entire expression
+                _ => quote! { ctx.#expr },
+            }
+        }
+
+        _ => {
+            abort!(
+                expr,
+                format!(
+                    "Expected one of `size_t`, `usize`, or an implicit call expression in #[value_type(...)], found {}", 
+                    quote!(#expr).to_string(),
+                )
+            )
+        }
+    }
+}
+
+/// Derives an implementation of `codegen::types::structure::StructFields`.
+///
+/// The benefit of using `#[derive(StructFields)]` is that all index- or order-dependent logic required by
+/// `impl StructFields` is automatically generated by this implementation, including the field index as required by
+/// `StructField::new` and the fields as returned by `StructFields::to_vec`.
+///
+/// # Prerequisites
+///
+/// In order to derive from [`StructFields`], you must implement (or derive) [`Eq`] and [`Copy`] as required by
+/// `StructFields`.
+///
+/// Moreover, `#[derive(StructFields)]` can only be used for `struct`s with named fields, and may only contain fields
+/// with either `StructField` or [`PhantomData`] types.
+///
+/// # Attributes for [`StructFields`]
+///
+/// Each `StructField` field must be declared with the `#[value_type(...)]` attribute. The argument of `value_type`
+/// accepts one of the following:
+///
+/// - An expression returning an instance of `inkwell::types::BasicType` (with or without the receiver `ctx`/`context`).
+/// For example, `context.i8_type()`, `ctx.i8_type()`, and `i8_type()` all refer to `i8`.
+/// - The reserved identifiers `usize` and `size_t` referring to an `inkwell::types::IntType` of the platform-dependent
+/// integer size. `usize` and `size_t` can also be used as the receiver to other method calls, e.g.
+/// `usize.array_type(3)`.
+///
+/// # Example
+///
+/// The following is an example of an LLVM slice implemented using `#[derive(StructFields)]`.
+///
+/// ```rust,ignore
+/// use nac3core::{
+///     codegen::types::structure::StructField,
+///     inkwell::{
+///         values::{IntValue, PointerValue},
+///         AddressSpace,
+///     },
+/// };
+/// use nac3core_derive::StructFields;
+///
+/// // All classes that implement StructFields must also implement Eq and Copy
+/// #[derive(PartialEq, Eq, Clone, Copy, StructFields)]
+/// pub struct SliceValue<'ctx> {
+///     // Declares ptr have a value type of i8*
+///     //
+///     // Can also be written as `ctx.i8_type().ptr_type(...)` or `context.i8_type().ptr_type(...)`
+///     #[value_type(i8_type().ptr_type(AddressSpace::default()))]
+///     ptr: StructField<'ctx, PointerValue<'ctx>>,
+///
+///     // Declares len have a value type of usize, depending on the target compilation platform
+///     #[value_type(usize)]
+///     len: StructField<'ctx, IntValue<'ctx>>,
+/// }
+/// ```
+#[proc_macro_derive(StructFields, attributes(value_type))]
+#[proc_macro_error]
+pub fn derive(input: TokenStream) -> TokenStream {
+    let input = parse_macro_input!(input as syn::DeriveInput);
+    let ident = &input.ident;
+
+    let Data::Struct(DataStruct { fields, .. }) = &input.data else {
+        abort!(input, "Only structs with named fields are supported");
+    };
+    if let Err(err_span) =
+        fields
+            .iter()
+            .try_for_each(|field| if field.ident.is_some() { Ok(()) } else { Err(field.span()) })
+    {
+        abort!(err_span, "Only structs with named fields are supported");
+    };
+
+    // Check if struct<'ctx>
+    if input.generics.params.len() != 1 {
+        abort!(input.generics, "Expected exactly 1 generic parameter")
+    }
+
+    let phantom_info = fields
+        .iter()
+        .filter(|field| extract_generic_args("PhantomData", &field.ty).is_some())
+        .map(|field| field.ident.as_ref().unwrap())
+        .cloned()
+        .collect::<Vec<_>>();
+
+    let field_info = fields
+        .iter()
+        .filter(|field| extract_generic_args("PhantomData", &field.ty).is_none())
+        .map(|field| {
+            let ident = field.ident.as_ref().unwrap();
+            let ty = &field.ty;
+
+            let Some(_) = extract_generic_args("StructField", ty) else {
+                abort!(field, "Only StructField and PhantomData are allowed")
+            };
+
+            let attrs = &field.attrs;
+            let Some(value_type_attr) =
+                attrs.iter().find(|attr| attr.path().is_ident("value_type"))
+            else {
+                abort!(field, "Expected #[value_type(...)] attribute for field");
+            };
+
+            let Ok(value_type_expr) = value_type_attr.parse_args::<Expr>() else {
+                abort!(value_type_attr, "Expected expression in #[value_type(...)]");
+            };
+
+            let value_expr_toks = normalize_value_expr(&value_type_expr);
+
+            (ident.clone(), value_expr_toks)
+        })
+        .collect::<Vec<_>>();
+
+    // `<*>::new` impl of `StructField` and `PhantomData` for `StructFields::new`
+    let phantoms_create = phantom_info
+        .iter()
+        .map(|id| quote! { #id: ::std::marker::PhantomData })
+        .collect::<Vec<_>>();
+    let fields_create = field_info
+        .iter()
+        .map(|(id, ty)| {
+            let id_lit = LitStr::new(&id.to_string(), id.span());
+            quote! {
+                #id: ::nac3core::codegen::types::structure::StructField::create(
+                    &mut counter,
+                    #id_lit,
+                    #ty,
+                )
+            }
+        })
+        .collect::<Vec<_>>();
+
+    // `.into()` impl of `StructField` for `StructFields::to_vec`
+    let fields_into =
+        field_info.iter().map(|(id, _)| quote! { self.#id.into() }).collect::<Vec<_>>();
+
+    let impl_block = quote! {
+        impl<'ctx> ::nac3core::codegen::types::structure::StructFields<'ctx> for #ident<'ctx> {
+            fn new(ctx: impl ::nac3core::inkwell::context::AsContextRef<'ctx>, llvm_usize: ::nac3core::inkwell::types::IntType<'ctx>) -> Self {
+                let ctx = unsafe { ::nac3core::inkwell::context::ContextRef::new(ctx.as_ctx_ref()) };
+
+                let mut counter = ::nac3core::codegen::types::structure::FieldIndexCounter::default();
+
+                #ident {
+                    #(#fields_create),*
+                    #(#phantoms_create),*
+                }
+            }
+
+            fn to_vec(&self) -> ::std::vec::Vec<(&'static str, ::nac3core::inkwell::types::BasicTypeEnum<'ctx>)> {
+                vec![
+                    #(#fields_into),*
+                ]
+            }
+        }
+    };
+
+    impl_block.into()
+}

nac3core/nac3core_derive/tests/structfields_empty.rs

@@ -0,0 +1,9 @@
+use nac3core_derive::StructFields;
+use std::marker::PhantomData;
+
+#[derive(PartialEq, Eq, Clone, Copy, StructFields)]
+pub struct EmptyValue<'ctx> {
+    _phantom: PhantomData<&'ctx ()>,
+}
+
+fn main() {}

nac3core/nac3core_derive/tests/structfields_ndarray.rs

@@ -0,0 +1,20 @@
+use nac3core::{
+    codegen::types::structure::StructField,
+    inkwell::{
+        values::{IntValue, PointerValue},
+        AddressSpace,
+    },
+};
+use nac3core_derive::StructFields;
+
+#[derive(PartialEq, Eq, Clone, Copy, StructFields)]
+pub struct NDArrayValue<'ctx> {
+    #[value_type(usize)]
+    ndims: StructField<'ctx, IntValue<'ctx>>,
+    #[value_type(usize.ptr_type(AddressSpace::default()))]
+    shape: StructField<'ctx, PointerValue<'ctx>>,
+    #[value_type(i8_type().ptr_type(AddressSpace::default()))]
+    data: StructField<'ctx, PointerValue<'ctx>>,
+}
+
+fn main() {}

nac3core/nac3core_derive/tests/structfields_slice.rs

@@ -0,0 +1,18 @@
+use nac3core::{
+    codegen::types::structure::StructField,
+    inkwell::{
+        values::{IntValue, PointerValue},
+        AddressSpace,
+    },
+};
+use nac3core_derive::StructFields;
+
+#[derive(PartialEq, Eq, Clone, Copy, StructFields)]
+pub struct SliceValue<'ctx> {
+    #[value_type(i8_type().ptr_type(AddressSpace::default()))]
+    ptr: StructField<'ctx, PointerValue<'ctx>>,
+    #[value_type(usize)]
+    len: StructField<'ctx, IntValue<'ctx>>,
+}
+
+fn main() {}

nac3core/nac3core_derive/tests/structfields_slice_context.rs

@@ -0,0 +1,18 @@
+use nac3core::{
+    codegen::types::structure::StructField,
+    inkwell::{
+        values::{IntValue, PointerValue},
+        AddressSpace,
+    },
+};
+use nac3core_derive::StructFields;
+
+#[derive(PartialEq, Eq, Clone, Copy, StructFields)]
+pub struct SliceValue<'ctx> {
+    #[value_type(context.i8_type().ptr_type(AddressSpace::default()))]
+    ptr: StructField<'ctx, PointerValue<'ctx>>,
+    #[value_type(usize)]
+    len: StructField<'ctx, IntValue<'ctx>>,
+}
+
+fn main() {}

nac3core/nac3core_derive/tests/structfields_slice_ctx.rs

@@ -0,0 +1,18 @@
+use nac3core::{
+    codegen::types::structure::StructField,
+    inkwell::{
+        values::{IntValue, PointerValue},
+        AddressSpace,
+    },
+};
+use nac3core_derive::StructFields;
+
+#[derive(PartialEq, Eq, Clone, Copy, StructFields)]
+pub struct SliceValue<'ctx> {
+    #[value_type(ctx.i8_type().ptr_type(AddressSpace::default()))]
+    ptr: StructField<'ctx, PointerValue<'ctx>>,
+    #[value_type(usize)]
+    len: StructField<'ctx, IntValue<'ctx>>,
+}
+
+fn main() {}

nac3core/nac3core_derive/tests/structfields_slice_sizet.rs

@@ -0,0 +1,18 @@
+use nac3core::{
+    codegen::types::structure::StructField,
+    inkwell::{
+        values::{IntValue, PointerValue},
+        AddressSpace,
+    },
+};
+use nac3core_derive::StructFields;
+
+#[derive(PartialEq, Eq, Clone, Copy, StructFields)]
+pub struct SliceValue<'ctx> {
+    #[value_type(i8_type().ptr_type(AddressSpace::default()))]
+    ptr: StructField<'ctx, PointerValue<'ctx>>,
+    #[value_type(size_t)]
+    len: StructField<'ctx, IntValue<'ctx>>,
+}
+
+fn main() {}

nac3core/nac3core_derive/tests/structfields_test.rs

@@ -0,0 +1,10 @@
+#[test]
+fn test_parse_empty() {
+    let t = trybuild::TestCases::new();
+    t.pass("tests/structfields_empty.rs");
+    t.pass("tests/structfields_slice.rs");
+    t.pass("tests/structfields_slice_ctx.rs");
+    t.pass("tests/structfields_slice_context.rs");
+    t.pass("tests/structfields_slice_sizet.rs");
+    t.pass("tests/structfields_ndarray.rs");
+}

nac3core/src/codegen/concrete_type.rs

@@ -1,3 +1,9 @@
+use std::collections::HashMap;
+
+use indexmap::IndexMap;
+
+use nac3parser::ast::StrRef;
+
 use crate::{
     symbol_resolver::SymbolValue,
     toplevel::DefinitionId,
@@ -9,10 +15,6 @@ use crate::{
     },
 };
 
-use indexmap::IndexMap;
-use nac3parser::ast::StrRef;
-use std::collections::HashMap;
-
 pub struct ConcreteTypeStore {
     store: Vec<ConcreteTypeEnum>,
 }
@@ -25,6 +27,7 @@ pub struct ConcreteFuncArg {
     pub name: StrRef,
     pub ty: ConcreteType,
     pub default_value: Option<SymbolValue>,
+    pub is_vararg: bool,
 }
 
 #[derive(Clone, Debug)]
@@ -46,6 +49,7 @@ pub enum ConcreteTypeEnum {
     TPrimitive(Primitive),
     TTuple {
         ty: Vec<ConcreteType>,
+        is_vararg_ctx: bool,
     },
     TObj {
         obj_id: DefinitionId,
@@ -102,8 +106,16 @@ impl ConcreteTypeStore {
                 .iter()
                 .map(|arg| ConcreteFuncArg {
                     name: arg.name,
-                    ty: self.from_unifier_type(unifier, primitives, arg.ty, cache),
+                    ty: if arg.is_vararg {
+                        let tuple_ty = unifier
+                            .add_ty(TypeEnum::TTuple { ty: vec![arg.ty], is_vararg_ctx: true });
+
+                        self.from_unifier_type(unifier, primitives, tuple_ty, cache)
+                    } else {
+                        self.from_unifier_type(unifier, primitives, arg.ty, cache)
+                    },
                     default_value: arg.default_value.clone(),
+                    is_vararg: arg.is_vararg,
                 })
                 .collect(),
             ret: self.from_unifier_type(unifier, primitives, signature.ret, cache),
@@ -158,11 +170,12 @@ impl ConcreteTypeStore {
             cache.insert(ty, None);
             let ty_enum = unifier.get_ty(ty);
             let result = match &*ty_enum {
-                TypeEnum::TTuple { ty } => ConcreteTypeEnum::TTuple {
+                TypeEnum::TTuple { ty, is_vararg_ctx } => ConcreteTypeEnum::TTuple {
                     ty: ty
                         .iter()
                         .map(|t| self.from_unifier_type(unifier, primitives, *t, cache))
                         .collect(),
+                    is_vararg_ctx: *is_vararg_ctx,
                 },
                 TypeEnum::TObj { obj_id, fields, params } => ConcreteTypeEnum::TObj {
                     obj_id: *obj_id,
@@ -248,11 +261,12 @@ impl ConcreteTypeStore {
                 *cache.get_mut(&cty).unwrap() = Some(ty);
                 return ty;
             }
-            ConcreteTypeEnum::TTuple { ty } => TypeEnum::TTuple {
+            ConcreteTypeEnum::TTuple { ty, is_vararg_ctx } => TypeEnum::TTuple {
                 ty: ty
                     .iter()
                     .map(|cty| self.to_unifier_type(unifier, primitives, *cty, cache))
                     .collect(),
+                is_vararg_ctx: *is_vararg_ctx,
             },
             ConcreteTypeEnum::TVirtual { ty } => {
                 TypeEnum::TVirtual { ty: self.to_unifier_type(unifier, primitives, *ty, cache) }
@@ -277,6 +291,7 @@ impl ConcreteTypeStore {
                         name: arg.name,
                         ty: self.to_unifier_type(unifier, primitives, arg.ty, cache),
                         default_value: arg.default_value.clone(),
+                        is_vararg: false,
                     })
                     .collect(),
                 ret: self.to_unifier_type(unifier, primitives, *ret, cache),

nac3core/src/codegen/extern_fns.rs

@@ -1,8 +1,10 @@
-use inkwell::attributes::{Attribute, AttributeLoc};
+use inkwell::{
-use inkwell::values::{BasicValueEnum, CallSiteValue, FloatValue, IntValue};
+    attributes::{Attribute, AttributeLoc},
+    values::{BasicValueEnum, CallSiteValue, FloatValue, IntValue},
+};
 use itertools::Either;
 
-use crate::codegen::CodeGenContext;
+use super::CodeGenContext;
 
 /// Macro to generate extern function
 /// Both function return type and function parameter type are `FloatValue`
@@ -13,8 +15,8 @@ use crate::codegen::CodeGenContext;
 /// * `$extern_fn:literal`: Name of underlying extern function
 ///
 /// Optional Arguments:
-/// * `$(,$attributes:literal)*)`: Attributes linked with the extern function
+/// * `$(,$attributes:literal)*)`: Attributes linked with the extern function.
-/// The default attributes are "mustprogress", "nofree", "nounwind", "willreturn", and "writeonly"
+///   The default attributes are "mustprogress", "nofree", "nounwind", "willreturn", and "writeonly".
 ///   These will be used unless other attributes are specified
 /// * `$(,$args:ident)*`: Operands of the extern function
 ///   The data type of these operands will be set to `FloatValue`
@@ -130,3 +132,62 @@ pub fn call_ldexp<'ctx>(
         .map(Either::unwrap_left)
         .unwrap()
 }
+
+/// Macro to generate `np_linalg` and `sp_linalg` functions
+/// The function takes as input `NDArray` and returns ()
+///
+/// Arguments:
+/// * `$fn_name:ident`: The identifier of the rust function to be generated
+/// * `$extern_fn:literal`: Name of underlying extern function
+/// * (2/3/4): Number of `NDArray` that function takes as input
+///
+/// Note:
+/// The operands and resulting `NDArray` are both passed as input to the funcion
+/// It is the responsibility of caller to ensure that output `NDArray` is properly allocated on stack
+/// The function changes the content of the output `NDArray` in-place
+macro_rules! generate_linalg_extern_fn {
+    ($fn_name:ident, $extern_fn:literal, 2) => {
+        generate_linalg_extern_fn!($fn_name, $extern_fn, mat1, mat2);
+    };
+    ($fn_name:ident, $extern_fn:literal, 3) => {
+        generate_linalg_extern_fn!($fn_name, $extern_fn, mat1, mat2, mat3);
+    };
+    ($fn_name:ident, $extern_fn:literal, 4) => {
+        generate_linalg_extern_fn!($fn_name, $extern_fn, mat1, mat2, mat3, mat4);
+    };
+    ($fn_name:ident, $extern_fn:literal $(,$input_matrix:ident)*) => {
+        #[doc = concat!("Invokes the linalg `", stringify!($extern_fn), " function." )]
+        pub fn $fn_name<'ctx>(
+            ctx: &mut CodeGenContext<'ctx, '_>
+            $(,$input_matrix: BasicValueEnum<'ctx>)*,
+            name: Option<&str>,
+        ){
+            const FN_NAME: &str = $extern_fn;
+            let extern_fn = ctx.module.get_function(FN_NAME).unwrap_or_else(|| {
+                let fn_type = ctx.ctx.void_type().fn_type(&[$($input_matrix.get_type().into()),*], false);
+
+                let func = ctx.module.add_function(FN_NAME, fn_type, None);
+                for attr in ["mustprogress", "nofree", "nounwind", "willreturn", "writeonly"] {
+                    func.add_attribute(
+                        AttributeLoc::Function,
+                        ctx.ctx.create_enum_attribute(Attribute::get_named_enum_kind_id(attr), 0),
+                    );
+                }
+                func
+            });
+
+            ctx.builder.build_call(extern_fn, &[$($input_matrix.into(),)*], name.unwrap_or_default()).unwrap();
+        }
+    };
+}
+
+generate_linalg_extern_fn!(call_np_linalg_cholesky, "np_linalg_cholesky", 2);
+generate_linalg_extern_fn!(call_np_linalg_qr, "np_linalg_qr", 3);
+generate_linalg_extern_fn!(call_np_linalg_svd, "np_linalg_svd", 4);
+generate_linalg_extern_fn!(call_np_linalg_inv, "np_linalg_inv", 2);
+generate_linalg_extern_fn!(call_np_linalg_pinv, "np_linalg_pinv", 2);
+generate_linalg_extern_fn!(call_np_linalg_matrix_power, "np_linalg_matrix_power", 3);
+generate_linalg_extern_fn!(call_np_linalg_det, "np_linalg_det", 2);
+generate_linalg_extern_fn!(call_sp_linalg_lu, "sp_linalg_lu", 3);
+generate_linalg_extern_fn!(call_sp_linalg_schur, "sp_linalg_schur", 3);
+generate_linalg_extern_fn!(call_sp_linalg_hessenberg, "sp_linalg_hessenberg", 3);

nac3core/src/codegen/generator.rs

@@ -1,16 +1,18 @@
-use crate::{
-    codegen::{bool_to_i1, bool_to_i8, classes::ArraySliceValue, expr::*, stmt::*, CodeGenContext},
-    symbol_resolver::ValueEnum,
-    toplevel::{DefinitionId, TopLevelDef},
-    typecheck::typedef::{FunSignature, Type},
-};
 use inkwell::{
     context::Context,
     types::{BasicTypeEnum, IntType},
     values::{BasicValueEnum, IntValue, PointerValue},
 };
+
 use nac3parser::ast::{Expr, Stmt, StrRef};
 
+use super::{bool_to_i1, bool_to_i8, expr::*, stmt::*, values::ArraySliceValue, CodeGenContext};
+use crate::{
+    symbol_resolver::ValueEnum,
+    toplevel::{DefinitionId, TopLevelDef},
+    typecheck::typedef::{FunSignature, Type},
+};
+
 pub trait CodeGenerator {
     /// Return the module name for the code generator.
     fn get_name(&self) -> &str;
@@ -57,6 +59,7 @@ pub trait CodeGenerator {
     /// - fun: Function signature, definition ID and the substitution key.
     /// - params: Function parameters. Note that this does not include the object even if the
     ///   function is a class method.
+    ///
     /// Note that this function should check if the function is generated in another thread (due to
     /// possible race condition), see the default implementation for an example.
     fn gen_func_instance<'ctx>(
@@ -131,6 +134,39 @@ pub trait CodeGenerator {
         gen_assign(self, ctx, target, value, value_ty)
     }
 
+    /// Generate code for an assignment expression where LHS is a `"target_list"`.
+    ///
+    /// See <https://docs.python.org/3/reference/simple_stmts.html#assignment-statements>.
+    fn gen_assign_target_list<'ctx>(
+        &mut self,
+        ctx: &mut CodeGenContext<'ctx, '_>,
+        targets: &Vec<Expr<Option<Type>>>,
+        value: ValueEnum<'ctx>,
+        value_ty: Type,
+    ) -> Result<(), String>
+    where
+        Self: Sized,
+    {
+        gen_assign_target_list(self, ctx, targets, value, value_ty)
+    }
+
+    /// Generate code for an item assignment.
+    ///
+    /// i.e., `target[key] = value`
+    fn gen_setitem<'ctx>(
+        &mut self,
+        ctx: &mut CodeGenContext<'ctx, '_>,
+        target: &Expr<Option<Type>>,
+        key: &Expr<Option<Type>>,
+        value: ValueEnum<'ctx>,
+        value_ty: Type,
+    ) -> Result<(), String>
+    where
+        Self: Sized,
+    {
+        gen_setitem(self, ctx, target, key, value, value_ty)
+    }
+
     /// Generate code for a while expression.
     /// Return true if the while loop must early return
     fn gen_while(

nac3core/src/codegen/irrt/error_context.rs

@@ -1,198 +0,0 @@
-use super::util::{function::CallFunction, get_sizet_dependent_function_name};
-use crate::codegen::{
-    model::*,
-    structure::{cslice::CSlice, exception::ExceptionId},
-    CodeGenContext, CodeGenerator,
-};
-
-#[allow(clippy::struct_field_names)]
-pub struct ErrorContextExceptionsFields<F: FieldVisitor> {
-    pub index_error: F::Field<IntModel<ExceptionId>>,
-    pub value_error: F::Field<IntModel<ExceptionId>>,
-    pub assertion_error: F::Field<IntModel<ExceptionId>>,
-    pub runtime_error: F::Field<IntModel<ExceptionId>>,
-    pub type_error: F::Field<IntModel<ExceptionId>>,
-}
-
-/// Corresponds to IRRT's `struct ErrorContextExceptions`
-#[derive(Debug, Clone, Copy, Default, PartialEq, Eq)]
-pub struct ErrorContextExceptions;
-
-impl StructKind for ErrorContextExceptions {
-    type Fields<F: FieldVisitor> = ErrorContextExceptionsFields<F>;
-
-    fn visit_fields<F: FieldVisitor>(&self, visitor: &mut F) -> Self::Fields<F> {
-        Self::Fields {
-            index_error: visitor.add("index_error"),
-            value_error: visitor.add("value_error"),
-            assertion_error: visitor.add("assertion_error"),
-            runtime_error: visitor.add("runtime_error"),
-            type_error: visitor.add("type_error"),
-        }
-    }
-}
-
-pub struct ErrorContextFields<F: FieldVisitor> {
-    pub exceptions: F::Field<PtrModel<StructModel<ErrorContextExceptions>>>,
-    pub exception_id: F::Field<IntModel<ExceptionId>>,
-    pub msg: F::Field<PtrModel<IntModel<Byte>>>,
-    pub param1: F::Field<IntModel<Int64>>,
-    pub param2: F::Field<IntModel<Int64>>,
-    pub param3: F::Field<IntModel<Int64>>,
-}
-
-/// Corresponds to IRRT's `struct ErrorContext`
-#[derive(Debug, Clone, Copy, Default, PartialEq, Eq)]
-pub struct ErrorContext;
-
-impl StructKind for ErrorContext {
-    type Fields<F: FieldVisitor> = ErrorContextFields<F>;
-
-    fn visit_fields<F: FieldVisitor>(&self, visitor: &mut F) -> Self::Fields<F> {
-        Self::Fields {
-            exceptions: visitor.add("exceptions"),
-            exception_id: visitor.add("exception_id"),
-            msg: visitor.add("msg"),
-            param1: visitor.add("param1"),
-            param2: visitor.add("param2"),
-            param3: visitor.add("param3"),
-        }
-    }
-}
-
-/// Build an [`ErrorContextExceptions`] loaded with resolved [`ExceptionID`]s according to the [`SymbolResolver`].
-fn build_error_context_exceptions<'ctx>(
-    tyctx: TypeContext<'ctx>,
-    ctx: &CodeGenContext<'ctx, '_>,
-) -> Ptr<'ctx, StructModel<ErrorContextExceptions>> {
-    let exceptions =
-        StructModel(ErrorContextExceptions).alloca(tyctx, ctx, "error_context_exceptions");
-    let i32_model = IntModel(Int32);
-
-    let get_string_id = |string_id| {
-        i32_model.constant(tyctx, ctx.ctx, ctx.resolver.get_string_id(string_id) as u64)
-    };
-
-    exceptions.gep(ctx, |f| f.index_error).store(ctx, get_string_id("0:IndexError"));
-    exceptions.gep(ctx, |f| f.value_error).store(ctx, get_string_id("0:ValueError"));
-    exceptions.gep(ctx, |f| f.assertion_error).store(ctx, get_string_id("0:AssertionError"));
-    exceptions.gep(ctx, |f| f.runtime_error).store(ctx, get_string_id("0:RuntimeError"));
-    exceptions.gep(ctx, |f| f.type_error).store(ctx, get_string_id("0:TypeError"));
-
-    exceptions
-}
-
-pub fn call_nac3_error_context_initialize<'ctx>(
-    tyctx: TypeContext<'ctx>,
-    ctx: &CodeGenContext<'ctx, '_>,
-    perrctx: Ptr<'ctx, StructModel<ErrorContext>>,
-    pexceptions: Ptr<'ctx, StructModel<ErrorContextExceptions>>,
-) {
-    CallFunction::begin(tyctx, ctx, "__nac3_error_context_initialize")
-        .arg("errctx", perrctx)
-        .arg("exceptions", pexceptions)
-        .returning_void();
-}
-
-pub fn call_nac3_error_context_has_exception<'ctx>(
-    tyctx: TypeContext<'ctx>,
-    ctx: &CodeGenContext<'ctx, '_>,
-    perrctx: Ptr<'ctx, StructModel<ErrorContext>>,
-) -> Int<'ctx, Bool> {
-    CallFunction::begin(tyctx, ctx, "__nac3_error_context_has_exception")
-        .arg("errctx", perrctx)
-        .returning("has_exception")
-}
-
-pub fn call_nac3_error_context_get_exception_str<'ctx>(
-    tyctx: TypeContext<'ctx>,
-    ctx: &CodeGenContext<'ctx, '_>,
-    perrctx: Ptr<'ctx, StructModel<ErrorContext>>,
-    dst_str: Ptr<'ctx, StructModel<CSlice>>,
-) {
-    CallFunction::begin(
-        tyctx,
-        ctx,
-        &get_sizet_dependent_function_name(tyctx, "__nac3_error_context_get_exception_str"),
-    )
-    .arg("errctx", perrctx)
-    .arg("dst_str", dst_str)
-    .returning_void();
-}
-
-/// Setup a [`ErrorContext`] that could be passed to IRRT functions taking in a `ErrorContext* errctx`
-/// for error reporting purposes.
-///
-/// Also see: [`check_error_context`]
-pub fn setup_error_context<'ctx>(
-    tyctx: TypeContext<'ctx>,
-    ctx: &CodeGenContext<'ctx, '_>,
-) -> Ptr<'ctx, StructModel<ErrorContext>> {
-    let errctx_model = StructModel(ErrorContext);
-
-    let exceptions = build_error_context_exceptions(tyctx, ctx);
-    let errctx_ptr = errctx_model.alloca(tyctx, ctx, "errctx");
-
-    call_nac3_error_context_initialize(tyctx, ctx, errctx_ptr, exceptions);
-
-    errctx_ptr
-}
-
-/// Check a [`ErrorContext`] to see if it contains error. **If there is an error,
-/// a Pythonic exception will be raised in the firmware**.
-pub fn check_error_context<'ctx, G: CodeGenerator + ?Sized>(
-    generator: &mut G,
-    ctx: &mut CodeGenContext<'ctx, '_>,
-    perrctx: Ptr<'ctx, StructModel<ErrorContext>>,
-) {
-    let tyctx = generator.type_context(ctx.ctx);
-    let cslice_model = StructModel(CSlice);
-
-    let current_bb = ctx.builder.get_insert_block().unwrap();
-    let irrt_has_exception_bb = ctx.ctx.insert_basic_block_after(current_bb, "irrt_has_exception");
-    let end_bb = ctx.ctx.insert_basic_block_after(irrt_has_exception_bb, "end");
-
-    // Inserting into `current_bb`
-    let has_exception = call_nac3_error_context_has_exception(tyctx, ctx, perrctx);
-    ctx.builder
-        .build_conditional_branch(has_exception.value, irrt_has_exception_bb, end_bb)
-        .unwrap();
-
-    // Inserting into `irrt_has_exception_bb`
-    ctx.builder.position_at_end(irrt_has_exception_bb);
-
-    // Load all the values for `ctx.make_assert_impl_by_id`
-    let pexception_str = cslice_model.alloca(tyctx, ctx, "exception_str");
-    call_nac3_error_context_get_exception_str(tyctx, ctx, perrctx, pexception_str);
-
-    let exception_id = perrctx.gep(ctx, |f| f.exception_id).load(tyctx, ctx, "exception_id");
-    let msg = pexception_str.load(tyctx, ctx, "msg");
-    let param1 = perrctx.gep(ctx, |f| f.param1).load(tyctx, ctx, "param1");
-    let param2 = perrctx.gep(ctx, |f| f.param2).load(tyctx, ctx, "param2");
-    let param3 = perrctx.gep(ctx, |f| f.param3).load(tyctx, ctx, "param3");
-
-    ctx.raise_exn_impl(
-        generator,
-        exception_id,
-        msg,
-        [Some(param1), Some(param2), Some(param3)],
-        ctx.current_loc,
-    );
-
-    // Position to `end_bb` for continuation
-    ctx.builder.position_at_end(end_bb);
-}
-
-pub fn call_nac3_dummy_raise<G: CodeGenerator + ?Sized>(
-    generator: &mut G,
-    ctx: &mut CodeGenContext,
-) {
-    let tyctx = generator.type_context(ctx.ctx);
-
-    let errctx = setup_error_context(tyctx, ctx);
-    CallFunction::begin(tyctx, ctx, "__nac3_error_dummy_raise")
-        .arg("errctx", errctx)
-        .returning_void();
-
-    check_error_context(generator, ctx, errctx);
-}

nac3core/src/codegen/irrt/list.rs

@@ -0,0 +1,162 @@
+use inkwell::{
+    types::BasicTypeEnum,
+    values::{BasicValueEnum, CallSiteValue, IntValue},
+    AddressSpace, IntPredicate,
+};
+use itertools::Either;
+
+use super::calculate_len_for_slice_range;
+use crate::codegen::{
+    macros::codegen_unreachable,
+    values::{ArrayLikeValue, ListValue},
+    CodeGenContext, CodeGenerator,
+};
+
+/// This function handles 'end' **inclusively**.
+/// Order of tuples `assign_idx` and `value_idx` is ('start', 'end', 'step').
+/// Negative index should be handled before entering this function
+pub fn list_slice_assignment<'ctx, G: CodeGenerator + ?Sized>(
+    generator: &mut G,
+    ctx: &mut CodeGenContext<'ctx, '_>,
+    ty: BasicTypeEnum<'ctx>,
+    dest_arr: ListValue<'ctx>,
+    dest_idx: (IntValue<'ctx>, IntValue<'ctx>, IntValue<'ctx>),
+    src_arr: ListValue<'ctx>,
+    src_idx: (IntValue<'ctx>, IntValue<'ctx>, IntValue<'ctx>),
+) {
+    let size_ty = generator.get_size_type(ctx.ctx);
+    let int8_ptr = ctx.ctx.i8_type().ptr_type(AddressSpace::default());
+    let int32 = ctx.ctx.i32_type();
+    let (fun_symbol, elem_ptr_type) = ("__nac3_list_slice_assign_var_size", int8_ptr);
+    let slice_assign_fun = {
+        let ty_vec = vec![
+            int32.into(),         // dest start idx
+            int32.into(),         // dest end idx
+            int32.into(),         // dest step
+            elem_ptr_type.into(), // dest arr ptr
+            int32.into(),         // dest arr len
+            int32.into(),         // src start idx
+            int32.into(),         // src end idx
+            int32.into(),         // src step
+            elem_ptr_type.into(), // src arr ptr
+            int32.into(),         // src arr len
+            int32.into(),         // size
+        ];
+        ctx.module.get_function(fun_symbol).unwrap_or_else(|| {
+            let fn_t = int32.fn_type(ty_vec.as_slice(), false);
+            ctx.module.add_function(fun_symbol, fn_t, None)
+        })
+    };
+
+    let zero = int32.const_zero();
+    let one = int32.const_int(1, false);
+    let dest_arr_ptr = dest_arr.data().base_ptr(ctx, generator);
+    let dest_arr_ptr =
+        ctx.builder.build_pointer_cast(dest_arr_ptr, elem_ptr_type, "dest_arr_ptr_cast").unwrap();
+    let dest_len = dest_arr.load_size(ctx, Some("dest.len"));
+    let dest_len = ctx.builder.build_int_truncate_or_bit_cast(dest_len, int32, "srclen32").unwrap();
+    let src_arr_ptr = src_arr.data().base_ptr(ctx, generator);
+    let src_arr_ptr =
+        ctx.builder.build_pointer_cast(src_arr_ptr, elem_ptr_type, "src_arr_ptr_cast").unwrap();
+    let src_len = src_arr.load_size(ctx, Some("src.len"));
+    let src_len = ctx.builder.build_int_truncate_or_bit_cast(src_len, int32, "srclen32").unwrap();
+
+    // index in bound and positive should be done
+    // assert if dest.step == 1 then len(src) <= len(dest) else len(src) == len(dest), and
+    // throw exception if not satisfied
+    let src_end = ctx
+        .builder
+        .build_select(
+            ctx.builder.build_int_compare(IntPredicate::SLT, src_idx.2, zero, "is_neg").unwrap(),
+            ctx.builder.build_int_sub(src_idx.1, one, "e_min_one").unwrap(),
+            ctx.builder.build_int_add(src_idx.1, one, "e_add_one").unwrap(),
+            "final_e",
+        )
+        .map(BasicValueEnum::into_int_value)
+        .unwrap();
+    let dest_end = ctx
+        .builder
+        .build_select(
+            ctx.builder.build_int_compare(IntPredicate::SLT, dest_idx.2, zero, "is_neg").unwrap(),
+            ctx.builder.build_int_sub(dest_idx.1, one, "e_min_one").unwrap(),
+            ctx.builder.build_int_add(dest_idx.1, one, "e_add_one").unwrap(),
+            "final_e",
+        )
+        .map(BasicValueEnum::into_int_value)
+        .unwrap();
+    let src_slice_len =
+        calculate_len_for_slice_range(generator, ctx, src_idx.0, src_end, src_idx.2);
+    let dest_slice_len =
+        calculate_len_for_slice_range(generator, ctx, dest_idx.0, dest_end, dest_idx.2);
+    let src_eq_dest = ctx
+        .builder
+        .build_int_compare(IntPredicate::EQ, src_slice_len, dest_slice_len, "slice_src_eq_dest")
+        .unwrap();
+    let src_slt_dest = ctx
+        .builder
+        .build_int_compare(IntPredicate::SLT, src_slice_len, dest_slice_len, "slice_src_slt_dest")
+        .unwrap();
+    let dest_step_eq_one = ctx
+        .builder
+        .build_int_compare(
+            IntPredicate::EQ,
+            dest_idx.2,
+            dest_idx.2.get_type().const_int(1, false),
+            "slice_dest_step_eq_one",
+        )
+        .unwrap();
+    let cond_1 = ctx.builder.build_and(dest_step_eq_one, src_slt_dest, "slice_cond_1").unwrap();
+    let cond = ctx.builder.build_or(src_eq_dest, cond_1, "slice_cond").unwrap();
+    ctx.make_assert(
+        generator,
+        cond,
+        "0:ValueError",
+        "attempt to assign sequence of size {0} to slice of size {1} with step size {2}",
+        [Some(src_slice_len), Some(dest_slice_len), Some(dest_idx.2)],
+        ctx.current_loc,
+    );
+
+    let new_len = {
+        let args = vec![
+            dest_idx.0.into(),   // dest start idx
+            dest_idx.1.into(),   // dest end idx
+            dest_idx.2.into(),   // dest step
+            dest_arr_ptr.into(), // dest arr ptr
+            dest_len.into(),     // dest arr len
+            src_idx.0.into(),    // src start idx
+            src_idx.1.into(),    // src end idx
+            src_idx.2.into(),    // src step
+            src_arr_ptr.into(),  // src arr ptr
+            src_len.into(),      // src arr len
+            {
+                let s = match ty {
+                    BasicTypeEnum::FloatType(t) => t.size_of(),
+                    BasicTypeEnum::IntType(t) => t.size_of(),
+                    BasicTypeEnum::PointerType(t) => t.size_of(),
+                    BasicTypeEnum::StructType(t) => t.size_of().unwrap(),
+                    _ => codegen_unreachable!(ctx),
+                };
+                ctx.builder.build_int_truncate_or_bit_cast(s, int32, "size").unwrap()
+            }
+            .into(),
+        ];
+        ctx.builder
+            .build_call(slice_assign_fun, args.as_slice(), "slice_assign")
+            .map(CallSiteValue::try_as_basic_value)
+            .map(|v| v.map_left(BasicValueEnum::into_int_value))
+            .map(Either::unwrap_left)
+            .unwrap()
+    };
+    // update length
+    let need_update =
+        ctx.builder.build_int_compare(IntPredicate::NE, new_len, dest_len, "need_update").unwrap();
+    let current = ctx.builder.get_insert_block().unwrap().get_parent().unwrap();
+    let update_bb = ctx.ctx.append_basic_block(current, "update");
+    let cont_bb = ctx.ctx.append_basic_block(current, "cont");
+    ctx.builder.build_conditional_branch(need_update, update_bb, cont_bb).unwrap();
+    ctx.builder.position_at_end(update_bb);
+    let new_len = ctx.builder.build_int_z_extend_or_bit_cast(new_len, size_ty, "new_len").unwrap();
+    dest_arr.store_size(ctx, generator, new_len);
+    ctx.builder.build_unconditional_branch(cont_bb).unwrap();
+    ctx.builder.position_at_end(cont_bb);
+}

nac3core/src/codegen/irrt/math.rs

@@ -0,0 +1,152 @@
+use inkwell::{
+    values::{BasicValueEnum, CallSiteValue, FloatValue, IntValue},
+    IntPredicate,
+};
+use itertools::Either;
+
+use crate::codegen::{
+    macros::codegen_unreachable,
+    {CodeGenContext, CodeGenerator},
+};
+
+// repeated squaring method adapted from GNU Scientific Library:
+// https://git.savannah.gnu.org/cgit/gsl.git/tree/sys/pow_int.c
+pub fn integer_power<'ctx, G: CodeGenerator + ?Sized>(
+    generator: &mut G,
+    ctx: &mut CodeGenContext<'ctx, '_>,
+    base: IntValue<'ctx>,
+    exp: IntValue<'ctx>,
+    signed: bool,
+) -> IntValue<'ctx> {
+    let symbol = match (base.get_type().get_bit_width(), exp.get_type().get_bit_width(), signed) {
+        (32, 32, true) => "__nac3_int_exp_int32_t",
+        (64, 64, true) => "__nac3_int_exp_int64_t",
+        (32, 32, false) => "__nac3_int_exp_uint32_t",
+        (64, 64, false) => "__nac3_int_exp_uint64_t",
+        _ => codegen_unreachable!(ctx),
+    };
+    let base_type = base.get_type();
+    let pow_fun = ctx.module.get_function(symbol).unwrap_or_else(|| {
+        let fn_type = base_type.fn_type(&[base_type.into(), base_type.into()], false);
+        ctx.module.add_function(symbol, fn_type, None)
+    });
+    // throw exception when exp < 0
+    let ge_zero = ctx
+        .builder
+        .build_int_compare(
+            IntPredicate::SGE,
+            exp,
+            exp.get_type().const_zero(),
+            "assert_int_pow_ge_0",
+        )
+        .unwrap();
+    ctx.make_assert(
+        generator,
+        ge_zero,
+        "0:ValueError",
+        "integer power must be positive or zero",
+        [None, None, None],
+        ctx.current_loc,
+    );
+    ctx.builder
+        .build_call(pow_fun, &[base.into(), exp.into()], "call_int_pow")
+        .map(CallSiteValue::try_as_basic_value)
+        .map(|v| v.map_left(BasicValueEnum::into_int_value))
+        .map(Either::unwrap_left)
+        .unwrap()
+}
+
+/// Generates a call to `isinf` in IR. Returns an `i1` representing the result.
+pub fn call_isinf<'ctx, G: CodeGenerator + ?Sized>(
+    generator: &mut G,
+    ctx: &CodeGenContext<'ctx, '_>,
+    v: FloatValue<'ctx>,
+) -> IntValue<'ctx> {
+    let intrinsic_fn = ctx.module.get_function("__nac3_isinf").unwrap_or_else(|| {
+        let fn_type = ctx.ctx.i32_type().fn_type(&[ctx.ctx.f64_type().into()], false);
+        ctx.module.add_function("__nac3_isinf", fn_type, None)
+    });
+
+    let ret = ctx
+        .builder
+        .build_call(intrinsic_fn, &[v.into()], "isinf")
+        .map(CallSiteValue::try_as_basic_value)
+        .map(|v| v.map_left(BasicValueEnum::into_int_value))
+        .map(Either::unwrap_left)
+        .unwrap();
+
+    generator.bool_to_i1(ctx, ret)
+}
+
+/// Generates a call to `isnan` in IR. Returns an `i1` representing the result.
+pub fn call_isnan<'ctx, G: CodeGenerator + ?Sized>(
+    generator: &mut G,
+    ctx: &CodeGenContext<'ctx, '_>,
+    v: FloatValue<'ctx>,
+) -> IntValue<'ctx> {
+    let intrinsic_fn = ctx.module.get_function("__nac3_isnan").unwrap_or_else(|| {
+        let fn_type = ctx.ctx.i32_type().fn_type(&[ctx.ctx.f64_type().into()], false);
+        ctx.module.add_function("__nac3_isnan", fn_type, None)
+    });
+
+    let ret = ctx
+        .builder
+        .build_call(intrinsic_fn, &[v.into()], "isnan")
+        .map(CallSiteValue::try_as_basic_value)
+        .map(|v| v.map_left(BasicValueEnum::into_int_value))
+        .map(Either::unwrap_left)
+        .unwrap();
+
+    generator.bool_to_i1(ctx, ret)
+}
+
+/// Generates a call to `gamma` in IR. Returns an `f64` representing the result.
+pub fn call_gamma<'ctx>(ctx: &CodeGenContext<'ctx, '_>, v: FloatValue<'ctx>) -> FloatValue<'ctx> {
+    let llvm_f64 = ctx.ctx.f64_type();
+
+    let intrinsic_fn = ctx.module.get_function("__nac3_gamma").unwrap_or_else(|| {
+        let fn_type = llvm_f64.fn_type(&[llvm_f64.into()], false);
+        ctx.module.add_function("__nac3_gamma", fn_type, None)
+    });
+
+    ctx.builder
+        .build_call(intrinsic_fn, &[v.into()], "gamma")
+        .map(CallSiteValue::try_as_basic_value)
+        .map(|v| v.map_left(BasicValueEnum::into_float_value))
+        .map(Either::unwrap_left)
+        .unwrap()
+}
+
+/// Generates a call to `gammaln` in IR. Returns an `f64` representing the result.
+pub fn call_gammaln<'ctx>(ctx: &CodeGenContext<'ctx, '_>, v: FloatValue<'ctx>) -> FloatValue<'ctx> {
+    let llvm_f64 = ctx.ctx.f64_type();
+
+    let intrinsic_fn = ctx.module.get_function("__nac3_gammaln").unwrap_or_else(|| {
+        let fn_type = llvm_f64.fn_type(&[llvm_f64.into()], false);
+        ctx.module.add_function("__nac3_gammaln", fn_type, None)
+    });
+
+    ctx.builder
+        .build_call(intrinsic_fn, &[v.into()], "gammaln")
+        .map(CallSiteValue::try_as_basic_value)
+        .map(|v| v.map_left(BasicValueEnum::into_float_value))
+        .map(Either::unwrap_left)
+        .unwrap()
+}
+
+/// Generates a call to `j0` in IR. Returns an `f64` representing the result.
+pub fn call_j0<'ctx>(ctx: &CodeGenContext<'ctx, '_>, v: FloatValue<'ctx>) -> FloatValue<'ctx> {
+    let llvm_f64 = ctx.ctx.f64_type();
+
+    let intrinsic_fn = ctx.module.get_function("__nac3_j0").unwrap_or_else(|| {
+        let fn_type = llvm_f64.fn_type(&[llvm_f64.into()], false);
+        ctx.module.add_function("__nac3_j0", fn_type, None)
+    });
+
+    ctx.builder
+        .build_call(intrinsic_fn, &[v.into()], "j0")
+        .map(CallSiteValue::try_as_basic_value)
+        .map(|v| v.map_left(BasicValueEnum::into_float_value))
+        .map(Either::unwrap_left)
+        .unwrap()
+}

nac3core/src/codegen/irrt/mod.rs

@@ -1,35 +1,29 @@
-use crate::typecheck::typedef::Type;
-
-pub mod error_context;
-pub mod ndarray;
-pub mod slice;
-mod test;
-mod util;
-
-use super::model::*;
-use super::{
-    classes::{
-        ArrayLikeIndexer, ArrayLikeValue, ArraySliceValue, ListValue, NDArrayValue,
-        TypedArrayLikeAdapter, UntypedArrayLikeAccessor,
-    },
-    llvm_intrinsics, CodeGenContext, CodeGenerator,
-};
-use crate::codegen::classes::TypedArrayLikeAccessor;
-use crate::codegen::stmt::gen_for_callback_incrementing;
 use inkwell::{
     attributes::{Attribute, AttributeLoc},
     context::Context,
     memory_buffer::MemoryBuffer,
     module::Module,
-    types::{BasicTypeEnum, IntType},
+    values::{BasicValue, BasicValueEnum, IntValue},
-    values::{BasicValueEnum, CallSiteValue, FloatValue, IntValue},
+    IntPredicate,
-    AddressSpace, IntPredicate,
 };
-use itertools::Either;
+
 use nac3parser::ast::Expr;
 
+use super::{CodeGenContext, CodeGenerator};
+use crate::{symbol_resolver::SymbolResolver, typecheck::typedef::Type};
+pub use list::*;
+pub use math::*;
+pub use range::*;
+pub use slice::*;
+
+mod list;
+mod math;
+pub mod ndarray;
+mod range;
+mod slice;
+
 #[must_use]
-pub fn load_irrt(ctx: &Context) -> Module {
+pub fn load_irrt<'ctx>(ctx: &'ctx Context, symbol_resolver: &dyn SymbolResolver) -> Module<'ctx> {
     let bitcode_buf = MemoryBuffer::create_from_memory_range(
         include_bytes!(concat!(env!("OUT_DIR"), "/irrt.bc")),
         "irrt_bitcode_buffer",
@@ -45,89 +39,47 @@ pub fn load_irrt(ctx: &Context) -> Module {
         let function = irrt_mod.get_function(symbol).unwrap();
         function.add_attribute(AttributeLoc::Function, ctx.create_enum_attribute(inline_attr, 0));
     }
+
+    // Initialize all global `EXN_*` exception IDs in IRRT with the [`SymbolResolver`].
+    let exn_id_type = ctx.i32_type();
+    let errors = &[
+        ("EXN_INDEX_ERROR", "0:IndexError"),
+        ("EXN_VALUE_ERROR", "0:ValueError"),
+        ("EXN_ASSERTION_ERROR", "0:AssertionError"),
+        ("EXN_TYPE_ERROR", "0:TypeError"),
+    ];
+    for (irrt_name, symbol_name) in errors {
+        let exn_id = symbol_resolver.get_string_id(symbol_name);
+        let exn_id = exn_id_type.const_int(exn_id as u64, false).as_basic_value_enum();
+
+        let global = irrt_mod.get_global(irrt_name).unwrap_or_else(|| {
+            panic!("Exception symbol name '{irrt_name}' should exist in the IRRT LLVM module")
+        });
+        global.set_initializer(&exn_id);
+    }
+
     irrt_mod
 }
 
-// repeated squaring method adapted from GNU Scientific Library:
+/// Returns the name of a function which contains variants for 32-bit and 64-bit `size_t`.
-// https://git.savannah.gnu.org/cgit/gsl.git/tree/sys/pow_int.c
+///
-pub fn integer_power<'ctx, G: CodeGenerator + ?Sized>(
+/// - When [`TypeContext::size_type`] is 32-bits, the function name is `fn_name}`.
-    generator: &mut G,
+/// - When [`TypeContext::size_type`] is 64-bits, the function name is `{fn_name}64`.
-    ctx: &mut CodeGenContext<'ctx, '_>,
+#[must_use]
-    base: IntValue<'ctx>,
+pub fn get_usize_dependent_function_name<G: CodeGenerator + ?Sized>(
-    exp: IntValue<'ctx>,
+    generator: &G,
-    signed: bool,
+    ctx: &CodeGenContext<'_, '_>,
-) -> IntValue<'ctx> {
+    name: &str,
-    let symbol = match (base.get_type().get_bit_width(), exp.get_type().get_bit_width(), signed) {
+) -> String {
-        (32, 32, true) => "__nac3_int_exp_int32_t",
+    let mut name = name.to_owned();
-        (64, 64, true) => "__nac3_int_exp_int64_t",
+    match generator.get_size_type(ctx.ctx).get_bit_width() {
-        (32, 32, false) => "__nac3_int_exp_uint32_t",
+        32 => {}
-        (64, 64, false) => "__nac3_int_exp_uint64_t",
+        64 => name.push_str("64"),
-        _ => unreachable!(),
+        bit_width => {
-    };
+            panic!("Unsupported int type bit width {bit_width}, must be either 32-bits or 64-bits")
-    let base_type = base.get_type();
-    let pow_fun = ctx.module.get_function(symbol).unwrap_or_else(|| {
-        let fn_type = base_type.fn_type(&[base_type.into(), base_type.into()], false);
-        ctx.module.add_function(symbol, fn_type, None)
-    });
-    // throw exception when exp < 0
-    let ge_zero = ctx
-        .builder
-        .build_int_compare(
-            IntPredicate::SGE,
-            exp,
-            exp.get_type().const_zero(),
-            "assert_int_pow_ge_0",
-        )
-        .unwrap();
-    ctx.make_assert(
-        generator,
-        ge_zero,
-        "0:ValueError",
-        "integer power must be positive or zero",
-        [None, None, None],
-        ctx.current_loc,
-    );
-    ctx.builder
-        .build_call(pow_fun, &[base.into(), exp.into()], "call_int_pow")
-        .map(CallSiteValue::try_as_basic_value)
-        .map(|v| v.map_left(BasicValueEnum::into_int_value))
-        .map(Either::unwrap_left)
-        .unwrap()
         }
-
+    }
-pub fn calculate_len_for_slice_range<'ctx, G: CodeGenerator + ?Sized>(
+    name
-    generator: &mut G,
-    ctx: &mut CodeGenContext<'ctx, '_>,
-    start: IntValue<'ctx>,
-    end: IntValue<'ctx>,
-    step: IntValue<'ctx>,
-) -> IntValue<'ctx> {
-    const SYMBOL: &str = "__nac3_range_slice_len";
-    let len_func = ctx.module.get_function(SYMBOL).unwrap_or_else(|| {
-        let i32_t = ctx.ctx.i32_type();
-        let fn_t = i32_t.fn_type(&[i32_t.into(), i32_t.into(), i32_t.into()], false);
-        ctx.module.add_function(SYMBOL, fn_t, None)
-    });
-
-    // assert step != 0, throw exception if not
-    let not_zero = ctx
-        .builder
-        .build_int_compare(IntPredicate::NE, step, step.get_type().const_zero(), "range_step_ne")
-        .unwrap();
-    ctx.make_assert(
-        generator,
-        not_zero,
-        "0:ValueError",
-        "step must not be zero",
-        [None, None, None],
-        ctx.current_loc,
-    );
-    ctx.builder
-        .build_call(len_func, &[start.into(), end.into(), step.into()], "calc_len")
-        .map(CallSiteValue::try_as_basic_value)
-        .map(|v| v.map_left(BasicValueEnum::into_int_value))
-        .map(Either::unwrap_left)
-        .unwrap()
 }
 
 /// NOTE: the output value of the end index of this function should be compared ***inclusively***,
@@ -295,658 +247,3 @@ pub fn handle_slice_indices<'ctx, G: CodeGenerator>(
         }
     }))
 }
-
-/// this function allows index out of range, since python
-/// allows index out of range in slice (`a = [1,2,3]; a[1:10] == [2,3]`).
-pub fn handle_slice_index_bound<'ctx, G: CodeGenerator>(
-    i: &Expr<Option<Type>>,
-    ctx: &mut CodeGenContext<'ctx, '_>,
-    generator: &mut G,
-    length: IntValue<'ctx>,
-) -> Result<Option<IntValue<'ctx>>, String> {
-    const SYMBOL: &str = "__nac3_slice_index_bound";
-    let func = ctx.module.get_function(SYMBOL).unwrap_or_else(|| {
-        let i32_t = ctx.ctx.i32_type();
-        let fn_t = i32_t.fn_type(&[i32_t.into(), i32_t.into()], false);
-        ctx.module.add_function(SYMBOL, fn_t, None)
-    });
-
-    let i = if let Some(v) = generator.gen_expr(ctx, i)? {
-        v.to_basic_value_enum(ctx, generator, i.custom.unwrap())?
-    } else {
-        return Ok(None);
-    };
-    Ok(Some(
-        ctx.builder
-            .build_call(func, &[i.into(), length.into()], "bounded_ind")
-            .map(CallSiteValue::try_as_basic_value)
-            .map(|v| v.map_left(BasicValueEnum::into_int_value))
-            .map(Either::unwrap_left)
-            .unwrap(),
-    ))
-}
-
-/// This function handles 'end' **inclusively**.
-/// Order of tuples `assign_idx` and `value_idx` is ('start', 'end', 'step').
-/// Negative index should be handled before entering this function
-pub fn list_slice_assignment<'ctx, G: CodeGenerator + ?Sized>(
-    generator: &mut G,
-    ctx: &mut CodeGenContext<'ctx, '_>,
-    ty: BasicTypeEnum<'ctx>,
-    dest_arr: ListValue<'ctx>,
-    dest_idx: (IntValue<'ctx>, IntValue<'ctx>, IntValue<'ctx>),
-    src_arr: ListValue<'ctx>,
-    src_idx: (IntValue<'ctx>, IntValue<'ctx>, IntValue<'ctx>),
-) {
-    let size_ty = generator.get_size_type(ctx.ctx);
-    let int8_ptr = ctx.ctx.i8_type().ptr_type(AddressSpace::default());
-    let int32 = ctx.ctx.i32_type();
-    let (fun_symbol, elem_ptr_type) = ("__nac3_list_slice_assign_var_size", int8_ptr);
-    let slice_assign_fun = {
-        let ty_vec = vec![
-            int32.into(),         // dest start idx
-            int32.into(),         // dest end idx
-            int32.into(),         // dest step
-            elem_ptr_type.into(), // dest arr ptr
-            int32.into(),         // dest arr len
-            int32.into(),         // src start idx
-            int32.into(),         // src end idx
-            int32.into(),         // src step
-            elem_ptr_type.into(), // src arr ptr
-            int32.into(),         // src arr len
-            int32.into(),         // size
-        ];
-        ctx.module.get_function(fun_symbol).unwrap_or_else(|| {
-            let fn_t = int32.fn_type(ty_vec.as_slice(), false);
-            ctx.module.add_function(fun_symbol, fn_t, None)
-        })
-    };
-
-    let zero = int32.const_zero();
-    let one = int32.const_int(1, false);
-    let dest_arr_ptr = dest_arr.data().base_ptr(ctx, generator);
-    let dest_arr_ptr =
-        ctx.builder.build_pointer_cast(dest_arr_ptr, elem_ptr_type, "dest_arr_ptr_cast").unwrap();
-    let dest_len = dest_arr.load_size(ctx, Some("dest.len"));
-    let dest_len = ctx.builder.build_int_truncate_or_bit_cast(dest_len, int32, "srclen32").unwrap();
-    let src_arr_ptr = src_arr.data().base_ptr(ctx, generator);
-    let src_arr_ptr =
-        ctx.builder.build_pointer_cast(src_arr_ptr, elem_ptr_type, "src_arr_ptr_cast").unwrap();
-    let src_len = src_arr.load_size(ctx, Some("src.len"));
-    let src_len = ctx.builder.build_int_truncate_or_bit_cast(src_len, int32, "srclen32").unwrap();
-
-    // index in bound and positive should be done
-    // assert if dest.step == 1 then len(src) <= len(dest) else len(src) == len(dest), and
-    // throw exception if not satisfied
-    let src_end = ctx
-        .builder
-        .build_select(
-            ctx.builder.build_int_compare(IntPredicate::SLT, src_idx.2, zero, "is_neg").unwrap(),
-            ctx.builder.build_int_sub(src_idx.1, one, "e_min_one").unwrap(),
-            ctx.builder.build_int_add(src_idx.1, one, "e_add_one").unwrap(),
-            "final_e",
-        )
-        .map(BasicValueEnum::into_int_value)
-        .unwrap();
-    let dest_end = ctx
-        .builder
-        .build_select(
-            ctx.builder.build_int_compare(IntPredicate::SLT, dest_idx.2, zero, "is_neg").unwrap(),
-            ctx.builder.build_int_sub(dest_idx.1, one, "e_min_one").unwrap(),
-            ctx.builder.build_int_add(dest_idx.1, one, "e_add_one").unwrap(),
-            "final_e",
-        )
-        .map(BasicValueEnum::into_int_value)
-        .unwrap();
-    let src_slice_len =
-        calculate_len_for_slice_range(generator, ctx, src_idx.0, src_end, src_idx.2);
-    let dest_slice_len =
-        calculate_len_for_slice_range(generator, ctx, dest_idx.0, dest_end, dest_idx.2);
-    let src_eq_dest = ctx
-        .builder
-        .build_int_compare(IntPredicate::EQ, src_slice_len, dest_slice_len, "slice_src_eq_dest")
-        .unwrap();
-    let src_slt_dest = ctx
-        .builder
-        .build_int_compare(IntPredicate::SLT, src_slice_len, dest_slice_len, "slice_src_slt_dest")
-        .unwrap();
-    let dest_step_eq_one = ctx
-        .builder
-        .build_int_compare(
-            IntPredicate::EQ,
-            dest_idx.2,
-            dest_idx.2.get_type().const_int(1, false),
-            "slice_dest_step_eq_one",
-        )
-        .unwrap();
-    let cond_1 = ctx.builder.build_and(dest_step_eq_one, src_slt_dest, "slice_cond_1").unwrap();
-    let cond = ctx.builder.build_or(src_eq_dest, cond_1, "slice_cond").unwrap();
-
-    // TODO: Temporary fix. Rewrite `list_slice_assignment` later
-    // Exception params should have been i64
-    {
-        let type_context = generator.type_context(ctx.ctx);
-        let param_model = IntModel(Int64);
-
-        let src_slice_len =
-            param_model.s_extend_or_bit_cast(type_context, ctx, src_slice_len, "src_slice_len");
-        let dest_slice_len =
-            param_model.s_extend_or_bit_cast(type_context, ctx, dest_slice_len, "dest_slice_len");
-        let dest_idx_2 =
-            param_model.s_extend_or_bit_cast(type_context, ctx, dest_idx.2, "dest_idx_2");
-
-        ctx.make_assert(
-            generator,
-            cond,
-            "0:ValueError",
-            "attempt to assign sequence of size {0} to slice of size {1} with step size {2}",
-            [Some(src_slice_len.value), Some(dest_slice_len.value), Some(dest_idx_2.value)],
-            ctx.current_loc,
-        );
-    }
-
-    let new_len = {
-        let args = vec![
-            dest_idx.0.into(),   // dest start idx
-            dest_idx.1.into(),   // dest end idx
-            dest_idx.2.into(),   // dest step
-            dest_arr_ptr.into(), // dest arr ptr
-            dest_len.into(),     // dest arr len
-            src_idx.0.into(),    // src start idx
-            src_idx.1.into(),    // src end idx
-            src_idx.2.into(),    // src step
-            src_arr_ptr.into(),  // src arr ptr
-            src_len.into(),      // src arr len
-            {
-                let s = match ty {
-                    BasicTypeEnum::FloatType(t) => t.size_of(),
-                    BasicTypeEnum::IntType(t) => t.size_of(),
-                    BasicTypeEnum::PointerType(t) => t.size_of(),
-                    BasicTypeEnum::StructType(t) => t.size_of().unwrap(),
-                    _ => unreachable!(),
-                };
-                ctx.builder.build_int_truncate_or_bit_cast(s, int32, "size").unwrap()
-            }
-            .into(),
-        ];
-        ctx.builder
-            .build_call(slice_assign_fun, args.as_slice(), "slice_assign")
-            .map(CallSiteValue::try_as_basic_value)
-            .map(|v| v.map_left(BasicValueEnum::into_int_value))
-            .map(Either::unwrap_left)
-            .unwrap()
-    };
-    // update length
-    let need_update =
-        ctx.builder.build_int_compare(IntPredicate::NE, new_len, dest_len, "need_update").unwrap();
-    let current = ctx.builder.get_insert_block().unwrap().get_parent().unwrap();
-    let update_bb = ctx.ctx.append_basic_block(current, "update");
-    let cont_bb = ctx.ctx.append_basic_block(current, "cont");
-    ctx.builder.build_conditional_branch(need_update, update_bb, cont_bb).unwrap();
-    ctx.builder.position_at_end(update_bb);
-    let new_len = ctx.builder.build_int_z_extend_or_bit_cast(new_len, size_ty, "new_len").unwrap();
-    dest_arr.store_size(ctx, generator, new_len);
-    ctx.builder.build_unconditional_branch(cont_bb).unwrap();
-    ctx.builder.position_at_end(cont_bb);
-}
-
-/// Generates a call to `isinf` in IR. Returns an `i1` representing the result.
-pub fn call_isinf<'ctx, G: CodeGenerator + ?Sized>(
-    generator: &mut G,
-    ctx: &CodeGenContext<'ctx, '_>,
-    v: FloatValue<'ctx>,
-) -> IntValue<'ctx> {
-    let intrinsic_fn = ctx.module.get_function("__nac3_isinf").unwrap_or_else(|| {
-        let fn_type = ctx.ctx.i32_type().fn_type(&[ctx.ctx.f64_type().into()], false);
-        ctx.module.add_function("__nac3_isinf", fn_type, None)
-    });
-
-    let ret = ctx
-        .builder
-        .build_call(intrinsic_fn, &[v.into()], "isinf")
-        .map(CallSiteValue::try_as_basic_value)
-        .map(|v| v.map_left(BasicValueEnum::into_int_value))
-        .map(Either::unwrap_left)
-        .unwrap();
-
-    generator.bool_to_i1(ctx, ret)
-}
-
-/// Generates a call to `isnan` in IR. Returns an `i1` representing the result.
-pub fn call_isnan<'ctx, G: CodeGenerator + ?Sized>(
-    generator: &mut G,
-    ctx: &CodeGenContext<'ctx, '_>,
-    v: FloatValue<'ctx>,
-) -> IntValue<'ctx> {
-    let intrinsic_fn = ctx.module.get_function("__nac3_isnan").unwrap_or_else(|| {
-        let fn_type = ctx.ctx.i32_type().fn_type(&[ctx.ctx.f64_type().into()], false);
-        ctx.module.add_function("__nac3_isnan", fn_type, None)
-    });
-
-    let ret = ctx
-        .builder
-        .build_call(intrinsic_fn, &[v.into()], "isnan")
-        .map(CallSiteValue::try_as_basic_value)
-        .map(|v| v.map_left(BasicValueEnum::into_int_value))
-        .map(Either::unwrap_left)
-        .unwrap();
-
-    generator.bool_to_i1(ctx, ret)
-}
-
-/// Generates a call to `gamma` in IR. Returns an `f64` representing the result.
-pub fn call_gamma<'ctx>(ctx: &CodeGenContext<'ctx, '_>, v: FloatValue<'ctx>) -> FloatValue<'ctx> {
-    let llvm_f64 = ctx.ctx.f64_type();
-
-    let intrinsic_fn = ctx.module.get_function("__nac3_gamma").unwrap_or_else(|| {
-        let fn_type = llvm_f64.fn_type(&[llvm_f64.into()], false);
-        ctx.module.add_function("__nac3_gamma", fn_type, None)
-    });
-
-    ctx.builder
-        .build_call(intrinsic_fn, &[v.into()], "gamma")
-        .map(CallSiteValue::try_as_basic_value)
-        .map(|v| v.map_left(BasicValueEnum::into_float_value))
-        .map(Either::unwrap_left)
-        .unwrap()
-}
-
-/// Generates a call to `gammaln` in IR. Returns an `f64` representing the result.
-pub fn call_gammaln<'ctx>(ctx: &CodeGenContext<'ctx, '_>, v: FloatValue<'ctx>) -> FloatValue<'ctx> {
-    let llvm_f64 = ctx.ctx.f64_type();
-
-    let intrinsic_fn = ctx.module.get_function("__nac3_gammaln").unwrap_or_else(|| {
-        let fn_type = llvm_f64.fn_type(&[llvm_f64.into()], false);
-        ctx.module.add_function("__nac3_gammaln", fn_type, None)
-    });
-
-    ctx.builder
-        .build_call(intrinsic_fn, &[v.into()], "gammaln")
-        .map(CallSiteValue::try_as_basic_value)
-        .map(|v| v.map_left(BasicValueEnum::into_float_value))
-        .map(Either::unwrap_left)
-        .unwrap()
-}
-
-/// Generates a call to `j0` in IR. Returns an `f64` representing the result.
-pub fn call_j0<'ctx>(ctx: &CodeGenContext<'ctx, '_>, v: FloatValue<'ctx>) -> FloatValue<'ctx> {
-    let llvm_f64 = ctx.ctx.f64_type();
-
-    let intrinsic_fn = ctx.module.get_function("__nac3_j0").unwrap_or_else(|| {
-        let fn_type = llvm_f64.fn_type(&[llvm_f64.into()], false);
-        ctx.module.add_function("__nac3_j0", fn_type, None)
-    });
-
-    ctx.builder
-        .build_call(intrinsic_fn, &[v.into()], "j0")
-        .map(CallSiteValue::try_as_basic_value)
-        .map(|v| v.map_left(BasicValueEnum::into_float_value))
-        .map(Either::unwrap_left)
-        .unwrap()
-}
-
-/// Generates a call to `__nac3_ndarray_calc_size`. Returns an [`IntValue`] representing the
-/// calculated total size.
-///
-/// * `dims` - An [`ArrayLikeIndexer`] containing the size of each dimension.
-/// * `range` - The dimension index to begin and end (exclusively) calculating the dimensions for,
-/// or [`None`] if starting from the first dimension and ending at the last dimension respectively.
-pub fn call_ndarray_calc_size<'ctx, G, Dims>(
-    generator: &G,
-    ctx: &CodeGenContext<'ctx, '_>,
-    dims: &Dims,
-    (begin, end): (Option<IntValue<'ctx>>, Option<IntValue<'ctx>>),
-) -> IntValue<'ctx>
-where
-    G: CodeGenerator + ?Sized,
-    Dims: ArrayLikeIndexer<'ctx>,
-{
-    let llvm_usize = generator.get_size_type(ctx.ctx);
-    let llvm_pusize = llvm_usize.ptr_type(AddressSpace::default());
-
-    let ndarray_calc_size_fn_name = match llvm_usize.get_bit_width() {
-        32 => "__nac3_ndarray_calc_size",
-        64 => "__nac3_ndarray_calc_size64",
-        bw => unreachable!("Unsupported size type bit width: {}", bw),
-    };
-    let ndarray_calc_size_fn_t = llvm_usize.fn_type(
-        &[llvm_pusize.into(), llvm_usize.into(), llvm_usize.into(), llvm_usize.into()],
-        false,
-    );
-    let ndarray_calc_size_fn =
-        ctx.module.get_function(ndarray_calc_size_fn_name).unwrap_or_else(|| {
-            ctx.module.add_function(ndarray_calc_size_fn_name, ndarray_calc_size_fn_t, None)
-        });
-
-    let begin = begin.unwrap_or_else(|| llvm_usize.const_zero());
-    let end = end.unwrap_or_else(|| dims.size(ctx, generator));
-    ctx.builder
-        .build_call(
-            ndarray_calc_size_fn,
-            &[
-                dims.base_ptr(ctx, generator).into(),
-                dims.size(ctx, generator).into(),
-                begin.into(),
-                end.into(),
-            ],
-            "",
-        )
-        .map(CallSiteValue::try_as_basic_value)
-        .map(|v| v.map_left(BasicValueEnum::into_int_value))
-        .map(Either::unwrap_left)
-        .unwrap()
-}
-
-/// Generates a call to `__nac3_ndarray_calc_nd_indices`. Returns a [`TypeArrayLikeAdpater`]
-/// containing `i32` indices of the flattened index.
-///
-/// * `index` - The index to compute the multidimensional index for.
-/// * `ndarray` - LLVM pointer to the `NDArray`. This value must be the LLVM representation of an
-/// `NDArray`.
-pub fn call_ndarray_calc_nd_indices<'ctx, G: CodeGenerator + ?Sized>(
-    generator: &G,
-    ctx: &mut CodeGenContext<'ctx, '_>,
-    index: IntValue<'ctx>,
-    ndarray: NDArrayValue<'ctx>,
-) -> TypedArrayLikeAdapter<'ctx, IntValue<'ctx>> {
-    let llvm_void = ctx.ctx.void_type();
-    let llvm_i32 = ctx.ctx.i32_type();
-    let llvm_usize = generator.get_size_type(ctx.ctx);
-    let llvm_pi32 = llvm_i32.ptr_type(AddressSpace::default());
-    let llvm_pusize = llvm_usize.ptr_type(AddressSpace::default());
-
-    let ndarray_calc_nd_indices_fn_name = match llvm_usize.get_bit_width() {
-        32 => "__nac3_ndarray_calc_nd_indices",
-        64 => "__nac3_ndarray_calc_nd_indices64",
-        bw => unreachable!("Unsupported size type bit width: {}", bw),
-    };
-    let ndarray_calc_nd_indices_fn =
-        ctx.module.get_function(ndarray_calc_nd_indices_fn_name).unwrap_or_else(|| {
-            let fn_type = llvm_void.fn_type(
-                &[llvm_usize.into(), llvm_pusize.into(), llvm_usize.into(), llvm_pi32.into()],
-                false,
-            );
-
-            ctx.module.add_function(ndarray_calc_nd_indices_fn_name, fn_type, None)
-        });
-
-    let ndarray_num_dims = ndarray.load_ndims(ctx);
-    let ndarray_dims = ndarray.dim_sizes();
-
-    let indices = ctx.builder.build_array_alloca(llvm_i32, ndarray_num_dims, "").unwrap();
-
-    ctx.builder
-        .build_call(
-            ndarray_calc_nd_indices_fn,
-            &[
-                index.into(),
-                ndarray_dims.base_ptr(ctx, generator).into(),
-                ndarray_num_dims.into(),
-                indices.into(),
-            ],
-            "",
-        )
-        .unwrap();
-
-    TypedArrayLikeAdapter::from(
-        ArraySliceValue::from_ptr_val(indices, ndarray_num_dims, None),
-        Box::new(|_, v| v.into_int_value()),
-        Box::new(|_, v| v.into()),
-    )
-}
-
-fn call_ndarray_flatten_index_impl<'ctx, G, Indices>(
-    generator: &G,
-    ctx: &CodeGenContext<'ctx, '_>,
-    ndarray: NDArrayValue<'ctx>,
-    indices: &Indices,
-) -> IntValue<'ctx>
-where
-    G: CodeGenerator + ?Sized,
-    Indices: ArrayLikeIndexer<'ctx>,
-{
-    let llvm_i32 = ctx.ctx.i32_type();
-    let llvm_usize = generator.get_size_type(ctx.ctx);
-
-    let llvm_pi32 = llvm_i32.ptr_type(AddressSpace::default());
-    let llvm_pusize = llvm_usize.ptr_type(AddressSpace::default());
-
-    debug_assert_eq!(
-        IntType::try_from(indices.element_type(ctx, generator))
-            .map(IntType::get_bit_width)
-            .unwrap_or_default(),
-        llvm_i32.get_bit_width(),
-        "Expected i32 value for argument `indices` to `call_ndarray_flatten_index_impl`"
-    );
-    debug_assert_eq!(
-        indices.size(ctx, generator).get_type().get_bit_width(),
-        llvm_usize.get_bit_width(),
-        "Expected usize integer value for argument `indices_size` to `call_ndarray_flatten_index_impl`"
-    );
-
-    let ndarray_flatten_index_fn_name = match llvm_usize.get_bit_width() {
-        32 => "__nac3_ndarray_flatten_index",
-        64 => "__nac3_ndarray_flatten_index64",
-        bw => unreachable!("Unsupported size type bit width: {}", bw),
-    };
-    let ndarray_flatten_index_fn =
-        ctx.module.get_function(ndarray_flatten_index_fn_name).unwrap_or_else(|| {
-            let fn_type = llvm_usize.fn_type(
-                &[llvm_pusize.into(), llvm_usize.into(), llvm_pi32.into(), llvm_usize.into()],
-                false,
-            );
-
-            ctx.module.add_function(ndarray_flatten_index_fn_name, fn_type, None)
-        });
-
-    let ndarray_num_dims = ndarray.load_ndims(ctx);
-    let ndarray_dims = ndarray.dim_sizes();
-
-    let index = ctx
-        .builder
-        .build_call(
-            ndarray_flatten_index_fn,
-            &[
-                ndarray_dims.base_ptr(ctx, generator).into(),
-                ndarray_num_dims.into(),
-                indices.base_ptr(ctx, generator).into(),
-                indices.size(ctx, generator).into(),
-            ],
-            "",
-        )
-        .map(CallSiteValue::try_as_basic_value)
-        .map(|v| v.map_left(BasicValueEnum::into_int_value))
-        .map(Either::unwrap_left)
-        .unwrap();
-
-    index
-}
-
-/// Generates a call to `__nac3_ndarray_flatten_index`. Returns the flattened index for the
-/// multidimensional index.
-///
-/// * `ndarray` - LLVM pointer to the `NDArray`. This value must be the LLVM representation of an
-/// `NDArray`.
-/// * `indices` - The multidimensional index to compute the flattened index for.
-pub fn call_ndarray_flatten_index<'ctx, G, Index>(
-    generator: &mut G,
-    ctx: &mut CodeGenContext<'ctx, '_>,
-    ndarray: NDArrayValue<'ctx>,
-    indices: &Index,
-) -> IntValue<'ctx>
-where
-    G: CodeGenerator + ?Sized,
-    Index: ArrayLikeIndexer<'ctx>,
-{
-    call_ndarray_flatten_index_impl(generator, ctx, ndarray, indices)
-}
-
-/// Generates a call to `__nac3_ndarray_calc_broadcast`. Returns a tuple containing the number of
-/// dimension and size of each dimension of the resultant `ndarray`.
-pub fn call_ndarray_calc_broadcast<'ctx, G: CodeGenerator + ?Sized>(
-    generator: &mut G,
-    ctx: &mut CodeGenContext<'ctx, '_>,
-    lhs: NDArrayValue<'ctx>,
-    rhs: NDArrayValue<'ctx>,
-) -> TypedArrayLikeAdapter<'ctx, IntValue<'ctx>> {
-    let llvm_usize = generator.get_size_type(ctx.ctx);
-    let llvm_pusize = llvm_usize.ptr_type(AddressSpace::default());
-
-    let ndarray_calc_broadcast_fn_name = match llvm_usize.get_bit_width() {
-        32 => "__nac3_ndarray_calc_broadcast",
-        64 => "__nac3_ndarray_calc_broadcast64",
-        bw => unreachable!("Unsupported size type bit width: {}", bw),
-    };
-    let ndarray_calc_broadcast_fn =
-        ctx.module.get_function(ndarray_calc_broadcast_fn_name).unwrap_or_else(|| {
-            let fn_type = llvm_usize.fn_type(
-                &[
-                    llvm_pusize.into(),
-                    llvm_usize.into(),
-                    llvm_pusize.into(),
-                    llvm_usize.into(),
-                    llvm_pusize.into(),
-                ],
-                false,
-            );
-
-            ctx.module.add_function(ndarray_calc_broadcast_fn_name, fn_type, None)
-        });
-
-    let lhs_ndims = lhs.load_ndims(ctx);
-    let rhs_ndims = rhs.load_ndims(ctx);
-    let min_ndims = llvm_intrinsics::call_int_umin(ctx, lhs_ndims, rhs_ndims, None);
-
-    gen_for_callback_incrementing(
-        generator,
-        ctx,
-        None,
-        llvm_usize.const_zero(),
-        (min_ndims, false),
-        |generator, ctx, _, idx| {
-            let idx = ctx.builder.build_int_sub(min_ndims, idx, "").unwrap();
-            let (lhs_dim_sz, rhs_dim_sz) = unsafe {
-                (
-                    lhs.dim_sizes().get_typed_unchecked(ctx, generator, &idx, None),
-                    rhs.dim_sizes().get_typed_unchecked(ctx, generator, &idx, None),
-                )
-            };
-
-            let llvm_usize_const_one = llvm_usize.const_int(1, false);
-            let lhs_eqz = ctx
-                .builder
-                .build_int_compare(IntPredicate::EQ, lhs_dim_sz, llvm_usize_const_one, "")
-                .unwrap();
-            let rhs_eqz = ctx
-                .builder
-                .build_int_compare(IntPredicate::EQ, rhs_dim_sz, llvm_usize_const_one, "")
-                .unwrap();
-            let lhs_or_rhs_eqz = ctx.builder.build_or(lhs_eqz, rhs_eqz, "").unwrap();
-
-            let lhs_eq_rhs = ctx
-                .builder
-                .build_int_compare(IntPredicate::EQ, lhs_dim_sz, rhs_dim_sz, "")
-                .unwrap();
-
-            let is_compatible = ctx.builder.build_or(lhs_or_rhs_eqz, lhs_eq_rhs, "").unwrap();
-
-            ctx.make_assert(
-                generator,
-                is_compatible,
-                "0:ValueError",
-                "operands could not be broadcast together",
-                [None, None, None],
-                ctx.current_loc,
-            );
-
-            Ok(())
-        },
-        llvm_usize.const_int(1, false),
-    )
-    .unwrap();
-
-    let max_ndims = llvm_intrinsics::call_int_umax(ctx, lhs_ndims, rhs_ndims, None);
-    let lhs_dims = lhs.dim_sizes().base_ptr(ctx, generator);
-    let lhs_ndims = lhs.load_ndims(ctx);
-    let rhs_dims = rhs.dim_sizes().base_ptr(ctx, generator);
-    let rhs_ndims = rhs.load_ndims(ctx);
-    let out_dims = ctx.builder.build_array_alloca(llvm_usize, max_ndims, "").unwrap();
-    let out_dims = ArraySliceValue::from_ptr_val(out_dims, max_ndims, None);
-
-    ctx.builder
-        .build_call(
-            ndarray_calc_broadcast_fn,
-            &[
-                lhs_dims.into(),
-                lhs_ndims.into(),
-                rhs_dims.into(),
-                rhs_ndims.into(),
-                out_dims.base_ptr(ctx, generator).into(),
-            ],
-            "",
-        )
-        .unwrap();
-
-    TypedArrayLikeAdapter::from(
-        out_dims,
-        Box::new(|_, v| v.into_int_value()),
-        Box::new(|_, v| v.into()),
-    )
-}
-
-/// Generates a call to `__nac3_ndarray_calc_broadcast_idx`. Returns an [`ArrayAllocaValue`]
-/// containing the indices used for accessing `array` corresponding to the index of the broadcasted
-/// array `broadcast_idx`.
-pub fn call_ndarray_calc_broadcast_index<
-    'ctx,
-    G: CodeGenerator + ?Sized,
-    BroadcastIdx: UntypedArrayLikeAccessor<'ctx>,
->(
-    generator: &mut G,
-    ctx: &mut CodeGenContext<'ctx, '_>,
-    array: NDArrayValue<'ctx>,
-    broadcast_idx: &BroadcastIdx,
-) -> TypedArrayLikeAdapter<'ctx, IntValue<'ctx>> {
-    let llvm_i32 = ctx.ctx.i32_type();
-    let llvm_usize = generator.get_size_type(ctx.ctx);
-    let llvm_pi32 = llvm_i32.ptr_type(AddressSpace::default());
-    let llvm_pusize = llvm_usize.ptr_type(AddressSpace::default());
-
-    let ndarray_calc_broadcast_fn_name = match llvm_usize.get_bit_width() {
-        32 => "__nac3_ndarray_calc_broadcast_idx",
-        64 => "__nac3_ndarray_calc_broadcast_idx64",
-        bw => unreachable!("Unsupported size type bit width: {}", bw),
-    };
-    let ndarray_calc_broadcast_fn =
-        ctx.module.get_function(ndarray_calc_broadcast_fn_name).unwrap_or_else(|| {
-            let fn_type = llvm_usize.fn_type(
-                &[llvm_pusize.into(), llvm_usize.into(), llvm_pi32.into(), llvm_pi32.into()],
-                false,
-            );
-
-            ctx.module.add_function(ndarray_calc_broadcast_fn_name, fn_type, None)
-        });
-
-    let broadcast_size = broadcast_idx.size(ctx, generator);
-    let out_idx = ctx.builder.build_array_alloca(llvm_i32, broadcast_size, "").unwrap();
-
-    let array_dims = array.dim_sizes().base_ptr(ctx, generator);
-    let array_ndims = array.load_ndims(ctx);
-    let broadcast_idx_ptr = unsafe {
-        broadcast_idx.ptr_offset_unchecked(ctx, generator, &llvm_usize.const_zero(), None)
-    };
-
-    ctx.builder
-        .build_call(
-            ndarray_calc_broadcast_fn,
-            &[array_dims.into(), array_ndims.into(), broadcast_idx_ptr.into(), out_idx.into()],
-            "",
-        )
-        .unwrap();
-
-    TypedArrayLikeAdapter::from(
-        ArraySliceValue::from_ptr_val(out_idx, broadcast_size, None),
-        Box::new(|_, v| v.into_int_value()),
-        Box::new(|_, v| v.into()),
-    )
-}

nac3core/src/codegen/irrt/ndarray/basic.rs

@@ -1,153 +1,250 @@
-use crate::codegen::irrt::error_context::{check_error_context, setup_error_context};
+use inkwell::{
-use crate::codegen::irrt::slice::SliceIndex;
+    values::{BasicValueEnum, IntValue, PointerValue},
-use crate::codegen::irrt::util::function::CallFunction;
+    AddressSpace,
-use crate::codegen::irrt::util::get_sizet_dependent_function_name;
+};
-use crate::codegen::model::*;
+
-use crate::codegen::structure::ndarray::NpArray;
+use crate::codegen::{
-use crate::codegen::{CodeGenContext, CodeGenerator};
+    expr::{create_and_call_function, infer_and_call_function},
+    irrt::get_usize_dependent_function_name,
+    types::ProxyType,
+    values::{ndarray::NDArrayValue, ProxyValue},
+    CodeGenContext, CodeGenerator,
+};
+
+pub fn call_nac3_ndarray_util_assert_shape_no_negative<'ctx, G: CodeGenerator + ?Sized>(
+    generator: &G,
+    ctx: &CodeGenContext<'ctx, '_>,
+    ndims: IntValue<'ctx>,
+    shape: PointerValue<'ctx>,
+) {
+    let llvm_usize = generator.get_size_type(ctx.ctx);
+    let llvm_pusize = llvm_usize.ptr_type(AddressSpace::default());
+
+    let name = get_usize_dependent_function_name(
+        generator,
+        ctx,
+        "__nac3_ndarray_util_assert_shape_no_negative",
+    );
+
+    create_and_call_function(
+        ctx,
+        &name,
+        Some(llvm_usize.into()),
+        &[(llvm_usize.into(), ndims.into()), (llvm_pusize.into(), shape.into())],
+        None,
+        None,
+    );
+}
+
+pub fn call_nac3_ndarray_util_assert_output_shape_same<'ctx, G: CodeGenerator + ?Sized>(
+    generator: &G,
+    ctx: &CodeGenContext<'ctx, '_>,
+    ndarray_ndims: IntValue<'ctx>,
+    ndarray_shape: PointerValue<'ctx>,
+    output_ndims: IntValue<'ctx>,
+    output_shape: IntValue<'ctx>,
+) {
+    let llvm_usize = generator.get_size_type(ctx.ctx);
+    let llvm_pusize = llvm_usize.ptr_type(AddressSpace::default());
+
+    let name = get_usize_dependent_function_name(
+        generator,
+        ctx,
+        "__nac3_ndarray_util_assert_output_shape_same",
+    );
+
+    create_and_call_function(
+        ctx,
+        &name,
+        Some(llvm_usize.into()),
+        &[
+            (llvm_usize.into(), ndarray_ndims.into()),
+            (llvm_pusize.into(), ndarray_shape.into()),
+            (llvm_usize.into(), output_ndims.into()),
+            (llvm_pusize.into(), output_shape.into()),
+        ],
+        None,
+        None,
+    );
+}
 
 pub fn call_nac3_ndarray_size<'ctx, G: CodeGenerator + ?Sized>(
-    generator: &mut G,
+    generator: &G,
-    ctx: &mut CodeGenContext<'ctx, '_>,
+    ctx: &CodeGenContext<'ctx, '_>,
-    ndarray_ptr: Ptr<'ctx, StructModel<NpArray>>,
+    ndarray: NDArrayValue<'ctx>,
-) -> Int<'ctx, SizeT> {
+) -> IntValue<'ctx> {
-    let tyctx = generator.type_context(ctx.ctx);
+    let llvm_usize = generator.get_size_type(ctx.ctx);
+    let llvm_ndarray = ndarray.get_type().as_base_type();
 
-    CallFunction::begin(
+    let name = get_usize_dependent_function_name(generator, ctx, "__nac3_ndarray_size");
-        tyctx,
+
+    create_and_call_function(
         ctx,
-        &get_sizet_dependent_function_name(tyctx, "__nac3_ndarray_size"),
+        &name,
+        Some(llvm_usize.into()),
+        &[(llvm_ndarray.into(), ndarray.as_base_value().into())],
+        Some("size"),
+        None,
     )
-    .arg("ndarray", ndarray_ptr)
+    .map(BasicValueEnum::into_int_value)
-    .returning("size")
+    .unwrap()
 }
 
 pub fn call_nac3_ndarray_nbytes<'ctx, G: CodeGenerator + ?Sized>(
-    generator: &mut G,
+    generator: &G,
-    ctx: &mut CodeGenContext<'ctx, '_>,
+    ctx: &CodeGenContext<'ctx, '_>,
-    ndarray_ptr: Ptr<'ctx, StructModel<NpArray>>,
+    ndarray: NDArrayValue<'ctx>,
-) -> Int<'ctx, SizeT> {
+) -> IntValue<'ctx> {
-    let tyctx = generator.type_context(ctx.ctx);
+    let llvm_usize = generator.get_size_type(ctx.ctx);
+    let llvm_ndarray = ndarray.get_type().as_base_type();
 
-    CallFunction::begin(
+    let name = get_usize_dependent_function_name(generator, ctx, "__nac3_ndarray_nbytes");
-        tyctx,
+
+    create_and_call_function(
         ctx,
-        &get_sizet_dependent_function_name(tyctx, "__nac3_ndarray_nbytes"),
+        &name,
+        Some(llvm_usize.into()),
+        &[(llvm_ndarray.into(), ndarray.as_base_value().into())],
+        Some("nbytes"),
+        None,
     )
-    .arg("ndarray", ndarray_ptr)
+    .map(BasicValueEnum::into_int_value)
-    .returning("nbytes")
+    .unwrap()
 }
 
 pub fn call_nac3_ndarray_len<'ctx, G: CodeGenerator + ?Sized>(
-    generator: &mut G,
+    generator: &G,
-    ctx: &mut CodeGenContext<'ctx, '_>,
+    ctx: &CodeGenContext<'ctx, '_>,
-    ndarray_ptr: Ptr<'ctx, StructModel<NpArray>>,
+    ndarray: NDArrayValue<'ctx>,
-) -> Int<'ctx, SliceIndex> {
+) -> IntValue<'ctx> {
-    let tyctx = generator.type_context(ctx.ctx);
+    let llvm_usize = generator.get_size_type(ctx.ctx);
-    let slice_index_model = IntModel(SliceIndex::default());
+    let llvm_ndarray = ndarray.get_type().as_base_type();
 
-    let dst_len = slice_index_model.alloca(tyctx, ctx, "dst_len");
+    let name = get_usize_dependent_function_name(generator, ctx, "__nac3_ndarray_len");
 
-    let errctx = setup_error_context(tyctx, ctx);
+    create_and_call_function(
-    CallFunction::begin(
-        tyctx,
         ctx,
-        &get_sizet_dependent_function_name(tyctx, "__nac3_ndarray_len"),
+        &name,
+        Some(llvm_usize.into()),
+        &[(llvm_ndarray.into(), ndarray.as_base_value().into())],
+        Some("len"),
+        None,
     )
-    .arg("errctx", errctx)
+    .map(BasicValueEnum::into_int_value)
-    .arg("ndarray", ndarray_ptr)
+    .unwrap()
-    .arg("dst_len", dst_len)
-    .returning_void();
-    check_error_context(generator, ctx, errctx);
-
-    dst_len.load(tyctx, ctx, "len")
-}
-
-pub fn call_nac3_ndarray_util_assert_shape_no_negative<'ctx, G: CodeGenerator + ?Sized>(
-    generator: &mut G,
-    ctx: &mut CodeGenContext<'ctx, '_>,
-    ndims: Int<'ctx, SizeT>,
-    shape: Ptr<'ctx, IntModel<SizeT>>,
-) {
-    let tyctx = generator.type_context(ctx.ctx);
-
-    let errctx = setup_error_context(tyctx, ctx);
-    CallFunction::begin(
-        tyctx,
-        ctx,
-        &get_sizet_dependent_function_name(tyctx, "__nac3_ndarray_util_assert_shape_no_negative"),
-    )
-    .arg("errctx", errctx)
-    .arg("ndims", ndims)
-    .arg("shape", shape)
-    .returning_void();
-    check_error_context(generator, ctx, errctx);
-}
-
-pub fn call_nac3_ndarray_set_strides_by_shape<'ctx, G: CodeGenerator + ?Sized>(
-    generator: &mut G,
-    ctx: &mut CodeGenContext<'ctx, '_>,
-    ndarray_ptr: Ptr<'ctx, StructModel<NpArray>>,
-) {
-    let tyctx = generator.type_context(ctx.ctx);
-
-    CallFunction::begin(
-        tyctx,
-        ctx,
-        &get_sizet_dependent_function_name(tyctx, "__nac3_ndarray_set_strides_by_shape"),
-    )
-    .arg("ndarray", ndarray_ptr)
-    .returning_void();
 }
 
 pub fn call_nac3_ndarray_is_c_contiguous<'ctx, G: CodeGenerator + ?Sized>(
-    generator: &mut G,
+    generator: &G,
-    ctx: &mut CodeGenContext<'ctx, '_>,
+    ctx: &CodeGenContext<'ctx, '_>,
-    ndarray_ptr: Ptr<'ctx, StructModel<NpArray>>,
+    ndarray: NDArrayValue<'ctx>,
-) -> Int<'ctx, Bool> {
+) -> IntValue<'ctx> {
-    let tyctx = generator.type_context(ctx.ctx);
+    let llvm_i1 = ctx.ctx.bool_type();
+    let llvm_ndarray = ndarray.get_type().as_base_type();
 
-    CallFunction::begin(
+    let name = get_usize_dependent_function_name(generator, ctx, "__nac3_ndarray_is_c_contiguous");
-        tyctx,
+
+    create_and_call_function(
         ctx,
-        &get_sizet_dependent_function_name(tyctx, "__nac3_ndarray_is_c_contiguous"),
+        &name,
+        Some(llvm_i1.into()),
+        &[(llvm_ndarray.into(), ndarray.as_base_value().into())],
+        Some("is_c_contiguous"),
+        None,
     )
-    .arg("ndarray", ndarray_ptr)
+    .map(BasicValueEnum::into_int_value)
-    .returning("is_c_contiguous")
+    .unwrap()
-}
-
-pub fn call_nac3_ndarray_copy_data<'ctx, G: CodeGenerator + ?Sized>(
-    generator: &mut G,
-    ctx: &mut CodeGenContext<'ctx, '_>,
-    src_ndarray: Ptr<'ctx, StructModel<NpArray>>,
-    dst_ndarray: Ptr<'ctx, StructModel<NpArray>>,
-) {
-    let tyctx = generator.type_context(ctx.ctx);
-
-    CallFunction::begin(
-        tyctx,
-        ctx,
-        &get_sizet_dependent_function_name(tyctx, "__nac3_ndarray_copy_data"),
-    )
-    .arg("src_ndarray", src_ndarray)
-    .arg("dst_ndarray", dst_ndarray)
-    .returning_void();
 }
 
 pub fn call_nac3_ndarray_get_nth_pelement<'ctx, G: CodeGenerator + ?Sized>(
-    generator: &mut G,
+    generator: &G,
-    ctx: &mut CodeGenContext<'ctx, '_>,
+    ctx: &CodeGenContext<'ctx, '_>,
-    pndarray: Ptr<'ctx, StructModel<NpArray>>,
+    ndarray: NDArrayValue<'ctx>,
-    index: Int<'ctx, SizeT>,
+    index: IntValue<'ctx>,
-) -> Ptr<'ctx, IntModel<Byte>> {
+) -> PointerValue<'ctx> {
-    let tyctx = generator.type_context(ctx.ctx);
+    let llvm_i8 = ctx.ctx.i8_type();
+    let llvm_pi8 = llvm_i8.ptr_type(AddressSpace::default());
+    let llvm_usize = generator.get_size_type(ctx.ctx);
+    let llvm_ndarray = ndarray.get_type().as_base_type();
 
-    CallFunction::begin(
+    let name = get_usize_dependent_function_name(generator, ctx, "__nac3_ndarray_get_nth_pelement");
-        tyctx,
+
+    create_and_call_function(
         ctx,
-        &get_sizet_dependent_function_name(tyctx, "__nac3_ndarray_get_nth_pelement"),
+        &name,
+        Some(llvm_pi8.into()),
+        &[(llvm_ndarray.into(), ndarray.as_base_value().into()), (llvm_usize.into(), index.into())],
+        Some("pelement"),
+        None,
     )
-    .arg("ndarray", pndarray)
+    .map(BasicValueEnum::into_pointer_value)
-    .arg("index", index)
+    .unwrap()
-    .returning("pelement")
+}
+
+pub fn call_nac3_ndarray_get_pelement_by_indices<'ctx, G: CodeGenerator + ?Sized>(
+    generator: &G,
+    ctx: &CodeGenContext<'ctx, '_>,
+    ndarray: NDArrayValue<'ctx>,
+    indices: PointerValue<'ctx>,
+) -> PointerValue<'ctx> {
+    let llvm_i8 = ctx.ctx.i8_type();
+    let llvm_pi8 = llvm_i8.ptr_type(AddressSpace::default());
+    let llvm_usize = generator.get_size_type(ctx.ctx);
+    let llvm_pusize = llvm_usize.ptr_type(AddressSpace::default());
+    let llvm_ndarray = ndarray.get_type().as_base_type();
+
+    let name =
+        get_usize_dependent_function_name(generator, ctx, "__nac3_ndarray_get_pelement_by_indices");
+
+    create_and_call_function(
+        ctx,
+        &name,
+        Some(llvm_pi8.into()),
+        &[
+            (llvm_ndarray.into(), ndarray.as_base_value().into()),
+            (llvm_pusize.into(), indices.into()),
+        ],
+        Some("pelement"),
+        None,
+    )
+    .map(BasicValueEnum::into_pointer_value)
+    .unwrap()
+}
+
+pub fn call_nac3_ndarray_set_strides_by_shape<'ctx, G: CodeGenerator + ?Sized>(
+    generator: &G,
+    ctx: &CodeGenContext<'ctx, '_>,
+    ndarray: NDArrayValue<'ctx>,
+) {
+    let llvm_ndarray = ndarray.get_type().as_base_type();
+
+    let name =
+        get_usize_dependent_function_name(generator, ctx, "__nac3_ndarray_set_strides_by_shape");
+
+    create_and_call_function(
+        ctx,
+        &name,
+        None,
+        &[(llvm_ndarray.into(), ndarray.as_base_value().into())],
+        None,
+        None,
+    );
+}
+
+pub fn call_nac3_ndarray_copy_data<'ctx, G: CodeGenerator + ?Sized>(
+    generator: &G,
+    ctx: &CodeGenContext<'ctx, '_>,
+    src_ndarray: NDArrayValue<'ctx>,
+    dst_ndarray: NDArrayValue<'ctx>,
+) {
+    let name = get_usize_dependent_function_name(generator, ctx, "__nac3_ndarray_copy_data");
+
+    infer_and_call_function(
+        ctx,
+        &name,
+        None,
+        &[src_ndarray.as_base_value().into(), dst_ndarray.as_base_value().into()],
+        None,
+        None,
+    );
 }

nac3core/src/codegen/irrt/ndarray/broadcast.rs

@@ -1,74 +0,0 @@
-use crate::codegen::{
-    irrt::{
-        error_context::{check_error_context, setup_error_context},
-        util::{function::CallFunction, get_sizet_dependent_function_name},
-    },
-    model::*,
-    structure::ndarray::NpArray,
-    CodeGenContext, CodeGenerator,
-};
-
-pub fn call_nac3_ndarray_broadcast_to<'ctx, G: CodeGenerator + ?Sized>(
-    generator: &mut G,
-    ctx: &mut CodeGenContext<'ctx, '_>,
-    src_ndarray: Ptr<'ctx, StructModel<NpArray>>,
-    dst_ndarray: Ptr<'ctx, StructModel<NpArray>>,
-) {
-    let tyctx = generator.type_context(ctx.ctx);
-
-    let perrctx = setup_error_context(tyctx, ctx);
-    CallFunction::begin(
-        tyctx,
-        ctx,
-        &get_sizet_dependent_function_name(tyctx, "__nac3_ndarray_broadcast_to"),
-    )
-    .arg("errctx", perrctx)
-    .arg("src_ndarray", src_ndarray)
-    .arg("dst_ndarray", dst_ndarray)
-    .returning_void();
-
-    check_error_context(generator, ctx, perrctx);
-}
-
-/// Fields of [`ShapeEntry`]
-pub struct ShapeEntryFields<F: FieldVisitor> {
-    pub ndims: F::Field<IntModel<SizeT>>,
-    pub shape: F::Field<PtrModel<IntModel<SizeT>>>,
-}
-
-#[derive(Debug, Clone, Copy, Default)]
-pub struct ShapeEntry;
-
-impl StructKind for ShapeEntry {
-    type Fields<F: FieldVisitor> = ShapeEntryFields<F>;
-
-    fn visit_fields<F: FieldVisitor>(&self, visitor: &mut F) -> Self::Fields<F> {
-        Self::Fields { ndims: visitor.add("ndims"), shape: visitor.add("shape") }
-    }
-}
-
-pub fn call_nac3_ndarray_broadcast_shapes<'ctx, G: CodeGenerator + ?Sized>(
-    generator: &mut G,
-    ctx: &mut CodeGenContext<'ctx, '_>,
-    num_shape_entries: Int<'ctx, SizeT>,
-    shape_entries: Ptr<'ctx, StructModel<ShapeEntry>>,
-    dst_ndims: Int<'ctx, SizeT>,
-    dst_shape: Ptr<'ctx, IntModel<SizeT>>,
-) {
-    let tyctx = generator.type_context(ctx.ctx);
-
-    let perrctx = setup_error_context(tyctx, ctx);
-    CallFunction::begin(
-        tyctx,
-        ctx,
-        &get_sizet_dependent_function_name(tyctx, "__nac3_ndarray_broadcast_shapes"),
-    )
-    .arg("errctx", perrctx)
-    .arg("num_shapes", num_shape_entries)
-    .arg("shapes", shape_entries)
-    .arg("dst_ndims", dst_ndims)
-    .arg("dst_shape", dst_shape)
-    .returning_void();
-
-    check_error_context(generator, ctx, perrctx);
-}

nac3core/src/codegen/irrt/ndarray/indexing.rs

@@ -1,170 +1,29 @@
 use crate::codegen::{
-    irrt::{
+    expr::infer_and_call_function,
-        error_context::{check_error_context, setup_error_context},
+    irrt::get_usize_dependent_function_name,
-        slice::{RustUserSlice, SliceIndex, UserSlice},
+    values::{ndarray::NDArrayValue, ArrayLikeValue, ArraySliceValue, ProxyValue},
-        util::{function::CallFunction, get_sizet_dependent_function_name},
-    },
-    model::*,
-    structure::ndarray::NpArray,
     CodeGenContext, CodeGenerator,
 };
 
-pub type NDIndexType = Byte;
-
-#[derive(Debug, Clone, Copy)]
-pub struct NDIndexFields<F: FieldVisitor> {
-    pub type_: F::Field<IntModel<NDIndexType>>, // Defined to be uint8_t in IRRT
-    pub data: F::Field<PtrModel<IntModel<Byte>>>,
-}
-
-#[derive(Debug, Clone, Copy, Default, PartialEq, Eq)]
-pub struct NDIndex;
-
-impl StructKind for NDIndex {
-    type Fields<F: FieldVisitor> = NDIndexFields<F>;
-
-    fn visit_fields<F: FieldVisitor>(&self, visitor: &mut F) -> Self::Fields<F> {
-        Self::Fields { type_: visitor.add("type"), data: visitor.add("data") }
-    }
-}
-
-// An enum variant to store the content
-// and type of an NDIndex in high level.
-#[derive(Debug, Clone)]
-pub enum RustNDIndex<'ctx> {
-    SingleElement(Int<'ctx, SliceIndex>),
-    Slice(RustUserSlice<'ctx>),
-}
-
-impl<'ctx> RustNDIndex<'ctx> {
-    fn get_type_id(&self) -> u64 {
-        // Defined in IRRT, must be in sync
-        match self {
-            RustNDIndex::SingleElement(_) => 0,
-            RustNDIndex::Slice(_) => 1,
-        }
-    }
-
-    fn write_to_ndindex(
-        &self,
-        tyctx: TypeContext<'ctx>,
-        ctx: &CodeGenContext<'ctx, '_>,
-        dst_ndindex_ptr: Ptr<'ctx, StructModel<NDIndex>>,
-    ) {
-        let ndindex_type_model = IntModel(NDIndexType::default());
-        let slice_index_model = IntModel(SliceIndex::default());
-        let user_slice_model = StructModel(UserSlice);
-
-        // Set `dst_ndindex_ptr->type`
-        dst_ndindex_ptr
-            .gep(ctx, |f| f.type_)
-            .store(ctx, ndindex_type_model.constant(tyctx, ctx.ctx, self.get_type_id()));
-
-        // Set `dst_ndindex_ptr->data`
-        let data = match self {
-            RustNDIndex::SingleElement(in_index) => {
-                let index_ptr = slice_index_model.alloca(tyctx, ctx, "index");
-                index_ptr.store(ctx, *in_index);
-                index_ptr.transmute(tyctx, ctx, IntModel(Byte), "")
-            }
-            RustNDIndex::Slice(in_rust_slice) => {
-                let user_slice_ptr = user_slice_model.alloca(tyctx, ctx, "user_slice");
-                in_rust_slice.write_to_user_slice(tyctx, ctx, user_slice_ptr);
-                user_slice_ptr.transmute(tyctx, ctx, IntModel(Byte), "")
-            }
-        };
-        dst_ndindex_ptr.gep(ctx, |f| f.data).store(ctx, data);
-    }
-
-    /// Allocate an array of `NDIndex`es on the stack and return its stack pointer.
-    pub fn alloca_ndindexes(
-        tyctx: TypeContext<'ctx>,
-        ctx: &CodeGenContext<'ctx, '_>,
-        in_ndindexes: &[RustNDIndex<'ctx>],
-    ) -> (Int<'ctx, SizeT>, Ptr<'ctx, StructModel<NDIndex>>) {
-        let sizet_model = IntModel(SizeT);
-        let ndindex_model = StructModel(NDIndex);
-
-        let num_ndindexes = sizet_model.constant(tyctx, ctx.ctx, in_ndindexes.len() as u64);
-        let ndindexes = ndindex_model.array_alloca(tyctx, ctx, num_ndindexes.value, "ndindexes");
-        for (i, in_ndindex) in in_ndindexes.iter().enumerate() {
-            let i = sizet_model.constant(tyctx, ctx.ctx, i as u64);
-            let pndindex = ndindexes.offset(tyctx, ctx, i.value, "");
-            in_ndindex.write_to_ndindex(tyctx, ctx, pndindex);
-        }
-
-        (num_ndindexes, ndindexes)
-    }
-
-    #[must_use]
-    pub fn deduce_ndims_after_indexing(indices: &[RustNDIndex], original_ndims: u64) -> u64 {
-        let mut final_ndims = original_ndims;
-        for index in indices {
-            match index {
-                RustNDIndex::SingleElement(_) => {
-                    final_ndims -= 1;
-                }
-                RustNDIndex::Slice(_) => {}
-            }
-        }
-        final_ndims
-    }
-}
-
-pub fn call_nac3_ndarray_indexing_deduce_ndims_after_indexing<'ctx, G: CodeGenerator + ?Sized>(
-    generator: &mut G,
-    ctx: &mut CodeGenContext<'ctx, '_>,
-    ndims: Int<'ctx, SizeT>,
-    num_ndindexes: Int<'ctx, SizeT>,
-    ndindexs: Ptr<'ctx, StructModel<NDIndex>>,
-) -> Int<'ctx, SizeT> {
-    let tyctx = generator.type_context(ctx.ctx);
-    let sizet_model = IntModel(SizeT);
-
-    let pfinal_ndims = sizet_model.alloca(tyctx, ctx, "pfinal_ndims");
-
-    let errctx_ptr = setup_error_context(tyctx, ctx);
-    CallFunction::begin(
-        tyctx,
-        ctx,
-        &get_sizet_dependent_function_name(
-            tyctx,
-            "__nac3_ndarray_indexing_deduce_ndims_after_indexing",
-        ),
-    )
-    .arg("errctx", errctx_ptr)
-    .arg("result", pfinal_ndims)
-    .arg("ndims", ndims)
-    .arg("num_ndindexs", num_ndindexes)
-    .arg("ndindexs", ndindexs)
-    .returning_void();
-    check_error_context(generator, ctx, errctx_ptr);
-
-    pfinal_ndims.load(tyctx, ctx, "final_ndims")
-}
-
 pub fn call_nac3_ndarray_index<'ctx, G: CodeGenerator + ?Sized>(
-    generator: &mut G,
+    generator: &G,
-    ctx: &mut CodeGenContext<'ctx, '_>,
+    ctx: &CodeGenContext<'ctx, '_>,
-    num_indexes: Int<'ctx, SizeT>,
+    indices: ArraySliceValue<'ctx>,
-    indexes: Ptr<'ctx, StructModel<NDIndex>>,
+    src_ndarray: NDArrayValue<'ctx>,
-    src_ndarray: Ptr<'ctx, StructModel<NpArray>>,
+    dst_ndarray: NDArrayValue<'ctx>,
-    dst_ndarray: Ptr<'ctx, StructModel<NpArray>>,
 ) {
-    let tyctx = generator.type_context(ctx.ctx);
+    let name = get_usize_dependent_function_name(generator, ctx, "__nac3_ndarray_index");
-
+    infer_and_call_function(
-    let perrctx = setup_error_context(tyctx, ctx);
-    CallFunction::begin(
-        tyctx,
         ctx,
-        &get_sizet_dependent_function_name(tyctx, "__nac3_ndarray_index"),
+        &name,
-    )
+        None,
-    .arg("errctx", perrctx)
+        &[
-    .arg("num_indexes", num_indexes)
+            indices.size(ctx, generator).into(),
-    .arg("indexes", indexes)
+            indices.base_ptr(ctx, generator).into(),
-    .arg("src_ndarray", src_ndarray)
+            src_ndarray.as_base_value().into(),
-    .arg("dst_ndarray", dst_ndarray)
+            dst_ndarray.as_base_value().into(),
-    .returning_void();
+        ],
-
+        None,
-    check_error_context(generator, ctx, perrctx);
+        None,
+    );
 }

nac3core/src/codegen/irrt/ndarray/iter.rs

@@ -0,0 +1,70 @@
+use inkwell::{
+    values::{BasicValueEnum, IntValue},
+    AddressSpace,
+};
+
+use crate::codegen::{
+    expr::{create_and_call_function, infer_and_call_function},
+    irrt::get_usize_dependent_function_name,
+    types::ProxyType,
+    values::{
+        ndarray::{NDArrayValue, NDIterValue},
+        ArrayLikeValue, ArraySliceValue, ProxyValue,
+    },
+    CodeGenContext, CodeGenerator,
+};
+
+pub fn call_nac3_nditer_initialize<'ctx, G: CodeGenerator + ?Sized>(
+    generator: &G,
+    ctx: &CodeGenContext<'ctx, '_>,
+    iter: NDIterValue<'ctx>,
+    ndarray: NDArrayValue<'ctx>,
+    indices: ArraySliceValue<'ctx>,
+) {
+    let llvm_usize = generator.get_size_type(ctx.ctx);
+    let llvm_pusize = llvm_usize.ptr_type(AddressSpace::default());
+
+    let name = get_usize_dependent_function_name(generator, ctx, "__nac3_nditer_initialize");
+
+    create_and_call_function(
+        ctx,
+        &name,
+        None,
+        &[
+            (iter.get_type().as_base_type().into(), iter.as_base_value().into()),
+            (ndarray.get_type().as_base_type().into(), ndarray.as_base_value().into()),
+            (llvm_pusize.into(), indices.base_ptr(ctx, generator).into()),
+        ],
+        None,
+        None,
+    );
+}
+
+pub fn call_nac3_nditer_has_element<'ctx, G: CodeGenerator + ?Sized>(
+    generator: &G,
+    ctx: &CodeGenContext<'ctx, '_>,
+    iter: NDIterValue<'ctx>,
+) -> IntValue<'ctx> {
+    let name = get_usize_dependent_function_name(generator, ctx, "__nac3_nditer_has_element");
+
+    infer_and_call_function(
+        ctx,
+        &name,
+        Some(ctx.ctx.bool_type().into()),
+        &[iter.as_base_value().into()],
+        None,
+        None,
+    )
+    .map(BasicValueEnum::into_int_value)
+    .unwrap()
+}
+
+pub fn call_nac3_nditer_next<'ctx, G: CodeGenerator + ?Sized>(
+    generator: &G,
+    ctx: &CodeGenContext<'ctx, '_>,
+    iter: NDIterValue<'ctx>,
+) {
+    let name = get_usize_dependent_function_name(generator, ctx, "__nac3_nditer_next");
+
+    infer_and_call_function(ctx, &name, None, &[iter.as_base_value().into()], None, None);
+}

nac3core/src/codegen/irrt/ndarray/mod.rs

@@ -1,4 +1,391 @@
-pub mod basic;
+use inkwell::{
-pub mod broadcast;
+    types::IntType,
-pub mod indexing;
+    values::{BasicValueEnum, CallSiteValue, IntValue},
-pub mod reshape;
+    AddressSpace, IntPredicate,
+};
+use itertools::Either;
+
+use crate::codegen::{
+    llvm_intrinsics,
+    macros::codegen_unreachable,
+    stmt::gen_for_callback_incrementing,
+    values::{
+        ndarray::NDArrayValue, ArrayLikeIndexer, ArrayLikeValue, ArraySliceValue,
+        TypedArrayLikeAccessor, TypedArrayLikeAdapter, UntypedArrayLikeAccessor,
+    },
+    CodeGenContext, CodeGenerator,
+};
+pub use basic::*;
+pub use indexing::*;
+pub use iter::*;
+
+mod basic;
+mod indexing;
+mod iter;
+
+/// Generates a call to `__nac3_ndarray_calc_size`. Returns an [`IntValue`] representing the
+/// calculated total size.
+///
+/// * `dims` - An [`ArrayLikeIndexer`] containing the size of each dimension.
+/// * `range` - The dimension index to begin and end (exclusively) calculating the dimensions for,
+///   or [`None`] if starting from the first dimension and ending at the last dimension
+///   respectively.
+pub fn call_ndarray_calc_size<'ctx, G, Dims>(
+    generator: &G,
+    ctx: &CodeGenContext<'ctx, '_>,
+    dims: &Dims,
+    (begin, end): (Option<IntValue<'ctx>>, Option<IntValue<'ctx>>),
+) -> IntValue<'ctx>
+where
+    G: CodeGenerator + ?Sized,
+    Dims: ArrayLikeIndexer<'ctx>,
+{
+    let llvm_usize = generator.get_size_type(ctx.ctx);
+    let llvm_pusize = llvm_usize.ptr_type(AddressSpace::default());
+
+    let ndarray_calc_size_fn_name = match llvm_usize.get_bit_width() {
+        32 => "__nac3_ndarray_calc_size",
+        64 => "__nac3_ndarray_calc_size64",
+        bw => codegen_unreachable!(ctx, "Unsupported size type bit width: {}", bw),
+    };
+    let ndarray_calc_size_fn_t = llvm_usize.fn_type(
+        &[llvm_pusize.into(), llvm_usize.into(), llvm_usize.into(), llvm_usize.into()],
+        false,
+    );
+    let ndarray_calc_size_fn =
+        ctx.module.get_function(ndarray_calc_size_fn_name).unwrap_or_else(|| {
+            ctx.module.add_function(ndarray_calc_size_fn_name, ndarray_calc_size_fn_t, None)
+        });
+
+    let begin = begin.unwrap_or_else(|| llvm_usize.const_zero());
+    let end = end.unwrap_or_else(|| dims.size(ctx, generator));
+    ctx.builder
+        .build_call(
+            ndarray_calc_size_fn,
+            &[
+                dims.base_ptr(ctx, generator).into(),
+                dims.size(ctx, generator).into(),
+                begin.into(),
+                end.into(),
+            ],
+            "",
+        )
+        .map(CallSiteValue::try_as_basic_value)
+        .map(|v| v.map_left(BasicValueEnum::into_int_value))
+        .map(Either::unwrap_left)
+        .unwrap()
+}
+
+/// Generates a call to `__nac3_ndarray_calc_nd_indices`. Returns a [`TypeArrayLikeAdpater`]
+/// containing `i32` indices of the flattened index.
+///
+/// * `index` - The index to compute the multidimensional index for.
+/// * `ndarray` - LLVM pointer to the `NDArray`. This value must be the LLVM representation of an
+///   `NDArray`.
+pub fn call_ndarray_calc_nd_indices<'ctx, G: CodeGenerator + ?Sized>(
+    generator: &G,
+    ctx: &CodeGenContext<'ctx, '_>,
+    index: IntValue<'ctx>,
+    ndarray: NDArrayValue<'ctx>,
+) -> TypedArrayLikeAdapter<'ctx, IntValue<'ctx>> {
+    let llvm_void = ctx.ctx.void_type();
+    let llvm_i32 = ctx.ctx.i32_type();
+    let llvm_usize = generator.get_size_type(ctx.ctx);
+    let llvm_pi32 = llvm_i32.ptr_type(AddressSpace::default());
+    let llvm_pusize = llvm_usize.ptr_type(AddressSpace::default());
+
+    let ndarray_calc_nd_indices_fn_name = match llvm_usize.get_bit_width() {
+        32 => "__nac3_ndarray_calc_nd_indices",
+        64 => "__nac3_ndarray_calc_nd_indices64",
+        bw => codegen_unreachable!(ctx, "Unsupported size type bit width: {}", bw),
+    };
+    let ndarray_calc_nd_indices_fn =
+        ctx.module.get_function(ndarray_calc_nd_indices_fn_name).unwrap_or_else(|| {
+            let fn_type = llvm_void.fn_type(
+                &[llvm_usize.into(), llvm_pusize.into(), llvm_usize.into(), llvm_pi32.into()],
+                false,
+            );
+
+            ctx.module.add_function(ndarray_calc_nd_indices_fn_name, fn_type, None)
+        });
+
+    let ndarray_num_dims = ndarray.load_ndims(ctx);
+    let ndarray_dims = ndarray.shape();
+
+    let indices = ctx.builder.build_array_alloca(llvm_i32, ndarray_num_dims, "").unwrap();
+
+    ctx.builder
+        .build_call(
+            ndarray_calc_nd_indices_fn,
+            &[
+                index.into(),
+                ndarray_dims.base_ptr(ctx, generator).into(),
+                ndarray_num_dims.into(),
+                indices.into(),
+            ],
+            "",
+        )
+        .unwrap();
+
+    TypedArrayLikeAdapter::from(
+        ArraySliceValue::from_ptr_val(indices, ndarray_num_dims, None),
+        Box::new(|_, v| v.into_int_value()),
+        Box::new(|_, v| v.into()),
+    )
+}
+
+fn call_ndarray_flatten_index_impl<'ctx, G, Indices>(
+    generator: &G,
+    ctx: &CodeGenContext<'ctx, '_>,
+    ndarray: NDArrayValue<'ctx>,
+    indices: &Indices,
+) -> IntValue<'ctx>
+where
+    G: CodeGenerator + ?Sized,
+    Indices: ArrayLikeIndexer<'ctx>,
+{
+    let llvm_i32 = ctx.ctx.i32_type();
+    let llvm_usize = generator.get_size_type(ctx.ctx);
+
+    let llvm_pi32 = llvm_i32.ptr_type(AddressSpace::default());
+    let llvm_pusize = llvm_usize.ptr_type(AddressSpace::default());
+
+    debug_assert_eq!(
+        IntType::try_from(indices.element_type(ctx, generator))
+            .map(IntType::get_bit_width)
+            .unwrap_or_default(),
+        llvm_i32.get_bit_width(),
+        "Expected i32 value for argument `indices` to `call_ndarray_flatten_index_impl`"
+    );
+    debug_assert_eq!(
+        indices.size(ctx, generator).get_type().get_bit_width(),
+        llvm_usize.get_bit_width(),
+        "Expected usize integer value for argument `indices_size` to `call_ndarray_flatten_index_impl`"
+    );
+
+    let ndarray_flatten_index_fn_name = match llvm_usize.get_bit_width() {
+        32 => "__nac3_ndarray_flatten_index",
+        64 => "__nac3_ndarray_flatten_index64",
+        bw => codegen_unreachable!(ctx, "Unsupported size type bit width: {}", bw),
+    };
+    let ndarray_flatten_index_fn =
+        ctx.module.get_function(ndarray_flatten_index_fn_name).unwrap_or_else(|| {
+            let fn_type = llvm_usize.fn_type(
+                &[llvm_pusize.into(), llvm_usize.into(), llvm_pi32.into(), llvm_usize.into()],
+                false,
+            );
+
+            ctx.module.add_function(ndarray_flatten_index_fn_name, fn_type, None)
+        });
+
+    let ndarray_num_dims = ndarray.load_ndims(ctx);
+    let ndarray_dims = ndarray.shape();
+
+    let index = ctx
+        .builder
+        .build_call(
+            ndarray_flatten_index_fn,
+            &[
+                ndarray_dims.base_ptr(ctx, generator).into(),
+                ndarray_num_dims.into(),
+                indices.base_ptr(ctx, generator).into(),
+                indices.size(ctx, generator).into(),
+            ],
+            "",
+        )
+        .map(CallSiteValue::try_as_basic_value)
+        .map(|v| v.map_left(BasicValueEnum::into_int_value))
+        .map(Either::unwrap_left)
+        .unwrap();
+
+    index
+}
+
+/// Generates a call to `__nac3_ndarray_flatten_index`. Returns the flattened index for the
+/// multidimensional index.
+///
+/// * `ndarray` - LLVM pointer to the `NDArray`. This value must be the LLVM representation of an
+///   `NDArray`.
+/// * `indices` - The multidimensional index to compute the flattened index for.
+pub fn call_ndarray_flatten_index<'ctx, G, Index>(
+    generator: &G,
+    ctx: &CodeGenContext<'ctx, '_>,
+    ndarray: NDArrayValue<'ctx>,
+    indices: &Index,
+) -> IntValue<'ctx>
+where
+    G: CodeGenerator + ?Sized,
+    Index: ArrayLikeIndexer<'ctx>,
+{
+    call_ndarray_flatten_index_impl(generator, ctx, ndarray, indices)
+}
+
+/// Generates a call to `__nac3_ndarray_calc_broadcast`. Returns a tuple containing the number of
+/// dimension and size of each dimension of the resultant `ndarray`.
+pub fn call_ndarray_calc_broadcast<'ctx, G: CodeGenerator + ?Sized>(
+    generator: &mut G,
+    ctx: &mut CodeGenContext<'ctx, '_>,
+    lhs: NDArrayValue<'ctx>,
+    rhs: NDArrayValue<'ctx>,
+) -> TypedArrayLikeAdapter<'ctx, IntValue<'ctx>> {
+    let llvm_usize = generator.get_size_type(ctx.ctx);
+    let llvm_pusize = llvm_usize.ptr_type(AddressSpace::default());
+
+    let ndarray_calc_broadcast_fn_name = match llvm_usize.get_bit_width() {
+        32 => "__nac3_ndarray_calc_broadcast",
+        64 => "__nac3_ndarray_calc_broadcast64",
+        bw => codegen_unreachable!(ctx, "Unsupported size type bit width: {}", bw),
+    };
+    let ndarray_calc_broadcast_fn =
+        ctx.module.get_function(ndarray_calc_broadcast_fn_name).unwrap_or_else(|| {
+            let fn_type = llvm_usize.fn_type(
+                &[
+                    llvm_pusize.into(),
+                    llvm_usize.into(),
+                    llvm_pusize.into(),
+                    llvm_usize.into(),
+                    llvm_pusize.into(),
+                ],
+                false,
+            );
+
+            ctx.module.add_function(ndarray_calc_broadcast_fn_name, fn_type, None)
+        });
+
+    let lhs_ndims = lhs.load_ndims(ctx);
+    let rhs_ndims = rhs.load_ndims(ctx);
+    let min_ndims = llvm_intrinsics::call_int_umin(ctx, lhs_ndims, rhs_ndims, None);
+
+    gen_for_callback_incrementing(
+        generator,
+        ctx,
+        None,
+        llvm_usize.const_zero(),
+        (min_ndims, false),
+        |generator, ctx, _, idx| {
+            let idx = ctx.builder.build_int_sub(min_ndims, idx, "").unwrap();
+            let (lhs_dim_sz, rhs_dim_sz) = unsafe {
+                (
+                    lhs.shape().get_typed_unchecked(ctx, generator, &idx, None),
+                    rhs.shape().get_typed_unchecked(ctx, generator, &idx, None),
+                )
+            };
+
+            let llvm_usize_const_one = llvm_usize.const_int(1, false);
+            let lhs_eqz = ctx
+                .builder
+                .build_int_compare(IntPredicate::EQ, lhs_dim_sz, llvm_usize_const_one, "")
+                .unwrap();
+            let rhs_eqz = ctx
+                .builder
+                .build_int_compare(IntPredicate::EQ, rhs_dim_sz, llvm_usize_const_one, "")
+                .unwrap();
+            let lhs_or_rhs_eqz = ctx.builder.build_or(lhs_eqz, rhs_eqz, "").unwrap();
+
+            let lhs_eq_rhs = ctx
+                .builder
+                .build_int_compare(IntPredicate::EQ, lhs_dim_sz, rhs_dim_sz, "")
+                .unwrap();
+
+            let is_compatible = ctx.builder.build_or(lhs_or_rhs_eqz, lhs_eq_rhs, "").unwrap();
+
+            ctx.make_assert(
+                generator,
+                is_compatible,
+                "0:ValueError",
+                "operands could not be broadcast together",
+                [None, None, None],
+                ctx.current_loc,
+            );
+
+            Ok(())
+        },
+        llvm_usize.const_int(1, false),
+    )
+    .unwrap();
+
+    let max_ndims = llvm_intrinsics::call_int_umax(ctx, lhs_ndims, rhs_ndims, None);
+    let lhs_dims = lhs.shape().base_ptr(ctx, generator);
+    let lhs_ndims = lhs.load_ndims(ctx);
+    let rhs_dims = rhs.shape().base_ptr(ctx, generator);
+    let rhs_ndims = rhs.load_ndims(ctx);
+    let out_dims = ctx.builder.build_array_alloca(llvm_usize, max_ndims, "").unwrap();
+    let out_dims = ArraySliceValue::from_ptr_val(out_dims, max_ndims, None);
+
+    ctx.builder
+        .build_call(
+            ndarray_calc_broadcast_fn,
+            &[
+                lhs_dims.into(),
+                lhs_ndims.into(),
+                rhs_dims.into(),
+                rhs_ndims.into(),
+                out_dims.base_ptr(ctx, generator).into(),
+            ],
+            "",
+        )
+        .unwrap();
+
+    TypedArrayLikeAdapter::from(
+        out_dims,
+        Box::new(|_, v| v.into_int_value()),
+        Box::new(|_, v| v.into()),
+    )
+}
+
+/// Generates a call to `__nac3_ndarray_calc_broadcast_idx`. Returns an [`ArrayAllocaValue`]
+/// containing the indices used for accessing `array` corresponding to the index of the broadcasted
+/// array `broadcast_idx`.
+pub fn call_ndarray_calc_broadcast_index<
+    'ctx,
+    G: CodeGenerator + ?Sized,
+    BroadcastIdx: UntypedArrayLikeAccessor<'ctx>,
+>(
+    generator: &mut G,
+    ctx: &mut CodeGenContext<'ctx, '_>,
+    array: NDArrayValue<'ctx>,
+    broadcast_idx: &BroadcastIdx,
+) -> TypedArrayLikeAdapter<'ctx, IntValue<'ctx>> {
+    let llvm_i32 = ctx.ctx.i32_type();
+    let llvm_usize = generator.get_size_type(ctx.ctx);
+    let llvm_pi32 = llvm_i32.ptr_type(AddressSpace::default());
+    let llvm_pusize = llvm_usize.ptr_type(AddressSpace::default());
+
+    let ndarray_calc_broadcast_fn_name = match llvm_usize.get_bit_width() {
+        32 => "__nac3_ndarray_calc_broadcast_idx",
+        64 => "__nac3_ndarray_calc_broadcast_idx64",
+        bw => codegen_unreachable!(ctx, "Unsupported size type bit width: {}", bw),
+    };
+    let ndarray_calc_broadcast_fn =
+        ctx.module.get_function(ndarray_calc_broadcast_fn_name).unwrap_or_else(|| {
+            let fn_type = llvm_usize.fn_type(
+                &[llvm_pusize.into(), llvm_usize.into(), llvm_pi32.into(), llvm_pi32.into()],
+                false,
+            );
+
+            ctx.module.add_function(ndarray_calc_broadcast_fn_name, fn_type, None)
+        });
+
+    let broadcast_size = broadcast_idx.size(ctx, generator);
+    let out_idx = ctx.builder.build_array_alloca(llvm_i32, broadcast_size, "").unwrap();
+
+    let array_dims = array.shape().base_ptr(ctx, generator);
+    let array_ndims = array.load_ndims(ctx);
+    let broadcast_idx_ptr = unsafe {
+        broadcast_idx.ptr_offset_unchecked(ctx, generator, &llvm_usize.const_zero(), None)
+    };
+
+    ctx.builder
+        .build_call(
+            ndarray_calc_broadcast_fn,
+            &[array_dims.into(), array_ndims.into(), broadcast_idx_ptr.into(), out_idx.into()],
+            "",
+        )
+        .unwrap();
+
+    TypedArrayLikeAdapter::from(
+        ArraySliceValue::from_ptr_val(out_idx, broadcast_size, None),
+        Box::new(|_, v| v.into_int_value()),
+        Box::new(|_, v| v.into()),
+    )
+}

nac3core/src/codegen/irrt/ndarray/reshape.rs

@@ -1,31 +0,0 @@
-use crate::codegen::{
-    irrt::{
-        error_context::{check_error_context, setup_error_context},
-        util::{function::CallFunction, get_sizet_dependent_function_name},
-    },
-    model::*,
-    CodeGenContext, CodeGenerator,
-};
-
-pub fn call_nac3_ndarray_resolve_and_check_new_shape<'ctx, G: CodeGenerator + ?Sized>(
-    generator: &mut G,
-    ctx: &mut CodeGenContext<'ctx, '_>,
-    size: Int<'ctx, SizeT>,
-    new_ndims: Int<'ctx, SizeT>,
-    new_shape: Ptr<'ctx, IntModel<SizeT>>,
-) {
-    let tyctx = generator.type_context(ctx.ctx);
-
-    let perrctx = setup_error_context(tyctx, ctx);
-    CallFunction::begin(
-        tyctx,
-        ctx,
-        &get_sizet_dependent_function_name(tyctx, "__nac3_ndarray_resolve_and_check_new_shape"),
-    )
-    .arg("errctx", perrctx)
-    .arg("size", size)
-    .arg("new_ndims", new_ndims)
-    .arg("new_shape", new_shape)
-    .returning_void();
-    check_error_context(generator, ctx, perrctx);
-}

nac3core/src/codegen/irrt/range.rs

@@ -0,0 +1,42 @@
+use inkwell::{
+    values::{BasicValueEnum, CallSiteValue, IntValue},
+    IntPredicate,
+};
+use itertools::Either;
+
+use crate::codegen::{CodeGenContext, CodeGenerator};
+
+pub fn calculate_len_for_slice_range<'ctx, G: CodeGenerator + ?Sized>(
+    generator: &mut G,
+    ctx: &mut CodeGenContext<'ctx, '_>,
+    start: IntValue<'ctx>,
+    end: IntValue<'ctx>,
+    step: IntValue<'ctx>,
+) -> IntValue<'ctx> {
+    const SYMBOL: &str = "__nac3_range_slice_len";
+    let len_func = ctx.module.get_function(SYMBOL).unwrap_or_else(|| {
+        let i32_t = ctx.ctx.i32_type();
+        let fn_t = i32_t.fn_type(&[i32_t.into(), i32_t.into(), i32_t.into()], false);
+        ctx.module.add_function(SYMBOL, fn_t, None)
+    });
+
+    // assert step != 0, throw exception if not
+    let not_zero = ctx
+        .builder
+        .build_int_compare(IntPredicate::NE, step, step.get_type().const_zero(), "range_step_ne")
+        .unwrap();
+    ctx.make_assert(
+        generator,
+        not_zero,
+        "0:ValueError",
+        "step must not be zero",
+        [None, None, None],
+        ctx.current_loc,
+    );
+    ctx.builder
+        .build_call(len_func, &[start.into(), end.into(), step.into()], "calc_len")
+        .map(CallSiteValue::try_as_basic_value)
+        .map(|v| v.map_left(BasicValueEnum::into_int_value))
+        .map(Either::unwrap_left)
+        .unwrap()
+}

nac3core/src/codegen/irrt/slice.rs

@@ -1,81 +1,39 @@
-use crate::codegen::{model::*, CodeGenContext};
+use inkwell::values::{BasicValueEnum, CallSiteValue, IntValue};
+use itertools::Either;
 
-// nac3core's slicing index/length values are always int32_t
+use nac3parser::ast::Expr;
-pub type SliceIndex = Int32;
 
-#[derive(Debug, Clone)]
+use crate::{
-pub struct UserSliceFields<F: FieldVisitor> {
+    codegen::{CodeGenContext, CodeGenerator},
-    pub start_defined: F::Field<IntModel<Bool>>,
+    typecheck::typedef::Type,
-    pub start: F::Field<IntModel<SliceIndex>>,
+};
-    pub stop_defined: F::Field<IntModel<Bool>>,
-    pub stop: F::Field<IntModel<SliceIndex>>,
-    pub step_defined: F::Field<IntModel<Bool>>,
-    pub step: F::Field<IntModel<SliceIndex>>,
-}
 
-#[derive(Debug, Clone, Copy, Default, PartialEq, Eq)]
+/// this function allows index out of range, since python
-pub struct UserSlice;
+/// allows index out of range in slice (`a = [1,2,3]; a[1:10] == [2,3]`).
+pub fn handle_slice_index_bound<'ctx, G: CodeGenerator>(
+    i: &Expr<Option<Type>>,
+    ctx: &mut CodeGenContext<'ctx, '_>,
+    generator: &mut G,
+    length: IntValue<'ctx>,
+) -> Result<Option<IntValue<'ctx>>, String> {
+    const SYMBOL: &str = "__nac3_slice_index_bound";
+    let func = ctx.module.get_function(SYMBOL).unwrap_or_else(|| {
+        let i32_t = ctx.ctx.i32_type();
+        let fn_t = i32_t.fn_type(&[i32_t.into(), i32_t.into()], false);
+        ctx.module.add_function(SYMBOL, fn_t, None)
+    });
 
-impl StructKind for UserSlice {
+    let i = if let Some(v) = generator.gen_expr(ctx, i)? {
-    type Fields<F: FieldVisitor> = UserSliceFields<F>;
+        v.to_basic_value_enum(ctx, generator, i.custom.unwrap())?
-
+    } else {
-    fn visit_fields<F: FieldVisitor>(&self, visitor: &mut F) -> Self::Fields<F> {
+        return Ok(None);
-        Self::Fields {
+    };
-            start_defined: visitor.add("start_defined"),
+    Ok(Some(
-            start: visitor.add("start"),
+        ctx.builder
-            stop_defined: visitor.add("stop_defined"),
+            .build_call(func, &[i.into(), length.into()], "bounded_ind")
-            stop: visitor.add("stop"),
+            .map(CallSiteValue::try_as_basic_value)
-            step_defined: visitor.add("step_defined"),
+            .map(|v| v.map_left(BasicValueEnum::into_int_value))
-            step: visitor.add("step"),
+            .map(Either::unwrap_left)
-        }
+            .unwrap(),
-    }
+    ))
-}
-
-#[derive(Debug, Clone)]
-pub struct RustUserSlice<'ctx> {
-    pub start: Option<Int<'ctx, SliceIndex>>,
-    pub stop: Option<Int<'ctx, SliceIndex>>,
-    pub step: Option<Int<'ctx, SliceIndex>>,
-}
-
-impl<'ctx> RustUserSlice<'ctx> {
-    // Set the values of an LLVM UserSlice
-    // in the format of Python's `slice()`
-    pub fn write_to_user_slice(
-        &self,
-        tyctx: TypeContext<'ctx>,
-        ctx: &CodeGenContext<'ctx, '_>,
-        dst_slice_ptr: Ptr<'ctx, StructModel<UserSlice>>,
-    ) {
-        let bool_model = IntModel(Bool);
-
-        let false_ = bool_model.constant(tyctx, ctx.ctx, 0);
-        let true_ = bool_model.constant(tyctx, ctx.ctx, 1);
-
-        // TODO: Code duplication. Probably okay...?
-
-        match self.start {
-            Some(start) => {
-                dst_slice_ptr.gep(ctx, |f| f.start_defined).store(ctx, true_);
-                dst_slice_ptr.gep(ctx, |f| f.start).store(ctx, start);
-            }
-            None => dst_slice_ptr.gep(ctx, |f| f.start_defined).store(ctx, false_),
-        }
-
-        match self.stop {
-            Some(stop) => {
-                dst_slice_ptr.gep(ctx, |f| f.stop_defined).store(ctx, true_);
-                dst_slice_ptr.gep(ctx, |f| f.stop).store(ctx, stop);
-            }
-            None => dst_slice_ptr.gep(ctx, |f| f.stop_defined).store(ctx, false_),
-        }
-
-        match self.step {
-            Some(step) => {
-                dst_slice_ptr.gep(ctx, |f| f.step_defined).store(ctx, true_);
-                dst_slice_ptr.gep(ctx, |f| f.step).store(ctx, step);
-            }
-            None => dst_slice_ptr.gep(ctx, |f| f.step_defined).store(ctx, false_),
-        }
-    }
 }

nac3core/src/codegen/irrt/test.rs

@@ -1,26 +0,0 @@
-#[cfg(test)]
-mod tests {
-    use std::{path::Path, process::Command};
-
-    #[test]
-    fn run_irrt_test() {
-        assert!(
-            cfg!(feature = "test"),
-            "Please do `cargo test -F test` to compile `irrt_test.out` and run test"
-        );
-
-        let irrt_test_out_path = Path::new(concat!(env!("OUT_DIR"), "/irrt_test.out"));
-        let output = Command::new(irrt_test_out_path.to_str().unwrap()).output().unwrap();
-
-        if !output.status.success() {
-            eprintln!("irrt_test failed with status {}:", output.status);
-            eprintln!("====== stdout ======");
-            eprintln!("{}", String::from_utf8(output.stdout).unwrap());
-            eprintln!("====== stderr ======");
-            eprintln!("{}", String::from_utf8(output.stderr).unwrap());
-            eprintln!("====================");
-
-            panic!("irrt_test failed");
-        }
-    }
-}

nac3core/src/codegen/irrt/util.rs

@@ -1,103 +0,0 @@
-use crate::codegen::model::*;
-
-// When [`TypeContext::size_type`] is 32-bits, the function name is "{fn_name}".
-// When [`TypeContext::size_type`] is 64-bits, the function name is "{fn_name}64".
-#[must_use]
-pub fn get_sizet_dependent_function_name(tyctx: TypeContext<'_>, name: &str) -> String {
-    let mut name = name.to_owned();
-    match tyctx.size_type.get_bit_width() {
-        32 => {}
-        64 => name.push_str("64"),
-        bit_width => {
-            panic!("Unsupported int type bit width {bit_width}, must be either 32-bits or 64-bits")
-        }
-    }
-    name
-}
-
-pub mod function {
-    use crate::codegen::{model::*, CodeGenContext};
-    use inkwell::{
-        types::{BasicMetadataTypeEnum, BasicType, FunctionType},
-        values::{AnyValue, BasicMetadataValueEnum, BasicValue, BasicValueEnum, CallSiteValue},
-    };
-    use itertools::Itertools;
-
-    #[derive(Debug, Clone, Copy)]
-    struct Arg<'ctx> {
-        ty: BasicMetadataTypeEnum<'ctx>,
-        val: BasicMetadataValueEnum<'ctx>,
-    }
-
-    /// Helper structure to reduce IRRT Inkwell function call boilerplate
-    /// TODO: Optimize
-    pub struct CallFunction<'ctx, 'a, 'b, 'c> {
-        tyctx: TypeContext<'ctx>,
-        ctx: &'b CodeGenContext<'ctx, 'a>,
-        /// Function name
-        name: &'c str,
-        /// Call arguments
-        args: Vec<Arg<'ctx>>,
-    }
-
-    impl<'ctx, 'a, 'b, 'c> CallFunction<'ctx, 'a, 'b, 'c> {
-        pub fn begin(
-            tyctx: TypeContext<'ctx>,
-            ctx: &'b CodeGenContext<'ctx, 'a>,
-            name: &'c str,
-        ) -> Self {
-            CallFunction { tyctx, ctx, name, args: Vec::new() }
-        }
-
-        /// Push a call argument to the function call.
-        ///
-        /// The `_name` parameter is there for self-documentation purposes.
-        #[allow(clippy::needless_pass_by_value)]
-        pub fn arg<M: Model>(mut self, _name: &str, arg: Instance<'ctx, M>) -> Self {
-            let arg = Arg {
-                ty: arg.model.get_type(self.tyctx, self.ctx.ctx).as_basic_type_enum().into(),
-                val: arg.value.as_basic_value_enum().into(),
-            };
-            self.args.push(arg);
-            self
-        }
-
-        /// Like [`CallFunction::returning_`] but `return_model` is automatically inferred.
-        pub fn returning<M: Model>(self, name: &str) -> Instance<'ctx, M> {
-            self.returning_(name, M::default())
-        }
-
-        /// Call the function and expect the function to return a value of type of `return_model`.
-        pub fn returning_<M: Model>(self, name: &str, return_model: M) -> Instance<'ctx, M> {
-            let ret_ty = return_model.get_type(self.tyctx, self.ctx.ctx);
-
-            let ret = self.get_function(|tys| ret_ty.fn_type(tys, false), name);
-            let ret = BasicValueEnum::try_from(ret.as_any_value_enum()).unwrap(); // Must work
-            let ret = return_model.check_value(self.tyctx, self.ctx.ctx, ret).unwrap(); // Must work
-            ret
-        }
-
-        /// Call the function and expect the function to return a void-type.
-        pub fn returning_void(self) {
-            let ret_ty = self.ctx.ctx.void_type();
-
-            let _ = self.get_function(|tys| ret_ty.fn_type(tys, false), "");
-        }
-
-        fn get_function<F>(&self, make_fn_type: F, return_value_name: &str) -> CallSiteValue<'ctx>
-        where
-            F: FnOnce(&[BasicMetadataTypeEnum<'ctx>]) -> FunctionType<'ctx>,
-        {
-            // Get the LLVM function, declare the function if it doesn't exist - it will be defined by other
-            // components of NAC3.
-            let func = self.ctx.module.get_function(self.name).unwrap_or_else(|| {
-                let tys = self.args.iter().map(|arg| arg.ty).collect_vec();
-                let fn_type = make_fn_type(&tys);
-                self.ctx.module.add_function(self.name, fn_type, None)
-            });
-
-            let vals = self.args.iter().map(|arg| arg.val).collect_vec();
-            self.ctx.builder.build_call(func, &vals, return_value_name).unwrap()
-        }
-    }
-}

nac3core/src/codegen/llvm_intrinsics.rs

@@ -1,12 +1,14 @@
-use crate::codegen::CodeGenContext;
+use inkwell::{
-use inkwell::context::Context;
+    context::Context,
-use inkwell::intrinsics::Intrinsic;
+    intrinsics::Intrinsic,
-use inkwell::types::AnyTypeEnum::IntType;
+    types::{AnyTypeEnum::IntType, FloatType},
-use inkwell::types::FloatType;
+    values::{BasicValueEnum, CallSiteValue, FloatValue, IntValue, PointerValue},
-use inkwell::values::{BasicValueEnum, CallSiteValue, FloatValue, IntValue, PointerValue};
+    AddressSpace,
-use inkwell::AddressSpace;
+};
 use itertools::Either;
 
+use super::CodeGenContext;
+
 /// Returns the string representation for the floating-point type `ft` when used in intrinsic
 /// functions.
 fn get_float_intrinsic_repr(ctx: &Context, ft: FloatType) -> &'static str {
@@ -35,6 +37,40 @@ fn get_float_intrinsic_repr(ctx: &Context, ft: FloatType) -> &'static str {
     unreachable!()
 }
 
+/// Invokes the [`llvm.va_start`](https://llvm.org/docs/LangRef.html#llvm-va-start-intrinsic)
+/// intrinsic.
+pub fn call_va_start<'ctx>(ctx: &CodeGenContext<'ctx, '_>, arglist: PointerValue<'ctx>) {
+    const FN_NAME: &str = "llvm.va_start";
+
+    let intrinsic_fn = ctx.module.get_function(FN_NAME).unwrap_or_else(|| {
+        let llvm_void = ctx.ctx.void_type();
+        let llvm_i8 = ctx.ctx.i8_type();
+        let llvm_p0i8 = llvm_i8.ptr_type(AddressSpace::default());
+        let fn_type = llvm_void.fn_type(&[llvm_p0i8.into()], false);
+
+        ctx.module.add_function(FN_NAME, fn_type, None)
+    });
+
+    ctx.builder.build_call(intrinsic_fn, &[arglist.into()], "").unwrap();
+}
+
+/// Invokes the [`llvm.va_start`](https://llvm.org/docs/LangRef.html#llvm-va-start-intrinsic)
+/// intrinsic.
+pub fn call_va_end<'ctx>(ctx: &CodeGenContext<'ctx, '_>, arglist: PointerValue<'ctx>) {
+    const FN_NAME: &str = "llvm.va_end";
+
+    let intrinsic_fn = ctx.module.get_function(FN_NAME).unwrap_or_else(|| {
+        let llvm_void = ctx.ctx.void_type();
+        let llvm_i8 = ctx.ctx.i8_type();
+        let llvm_p0i8 = llvm_i8.ptr_type(AddressSpace::default());
+        let fn_type = llvm_void.fn_type(&[llvm_p0i8.into()], false);
+
+        ctx.module.add_function(FN_NAME, fn_type, None)
+    });
+
+    ctx.builder.build_call(intrinsic_fn, &[arglist.into()], "").unwrap();
+}
+
 /// Invokes the [`llvm.stacksave`](https://llvm.org/docs/LangRef.html#llvm-stacksave-intrinsic)
 /// intrinsic.
 pub fn call_stacksave<'ctx>(
@@ -149,7 +185,7 @@ pub fn call_memcpy_generic<'ctx>(
         dest
     } else {
         ctx.builder
-            .build_bitcast(dest, llvm_p0i8, "")
+            .build_bit_cast(dest, llvm_p0i8, "")
             .map(BasicValueEnum::into_pointer_value)
             .unwrap()
     };
@@ -157,7 +193,7 @@ pub fn call_memcpy_generic<'ctx>(
         src
     } else {
         ctx.builder
-            .build_bitcast(src, llvm_p0i8, "")
+            .build_bit_cast(src, llvm_p0i8, "")
             .map(BasicValueEnum::into_pointer_value)
             .unwrap()
     };
@@ -165,14 +201,58 @@ pub fn call_memcpy_generic<'ctx>(
     call_memcpy(ctx, dest, src, len, is_volatile);
 }
 
+/// Invokes the `llvm.memcpy` intrinsic.
+///
+/// Unlike [`call_memcpy`], this function accepts any type of pointer value. If `dest` or `src` is
+/// not a pointer to an integer, the pointer(s) will be cast to `i8*` before invoking `memcpy`.
+/// Moreover, `len` now refers to the number of elements to copy (rather than number of bytes to
+/// copy).
+pub fn call_memcpy_generic_array<'ctx>(
+    ctx: &CodeGenContext<'ctx, '_>,
+    dest: PointerValue<'ctx>,
+    src: PointerValue<'ctx>,
+    len: IntValue<'ctx>,
+    is_volatile: IntValue<'ctx>,
+) {
+    let llvm_i8 = ctx.ctx.i8_type();
+    let llvm_p0i8 = llvm_i8.ptr_type(AddressSpace::default());
+    let llvm_sizeof_expr_t = llvm_i8.size_of().get_type();
+
+    let dest_elem_t = dest.get_type().get_element_type();
+    let src_elem_t = src.get_type().get_element_type();
+
+    let dest = if matches!(dest_elem_t, IntType(t) if t.get_bit_width() == 8) {
+        dest
+    } else {
+        ctx.builder
+            .build_bit_cast(dest, llvm_p0i8, "")
+            .map(BasicValueEnum::into_pointer_value)
+            .unwrap()
+    };
+    let src = if matches!(src_elem_t, IntType(t) if t.get_bit_width() == 8) {
+        src
+    } else {
+        ctx.builder
+            .build_bit_cast(src, llvm_p0i8, "")
+            .map(BasicValueEnum::into_pointer_value)
+            .unwrap()
+    };
+
+    let len = ctx.builder.build_int_z_extend_or_bit_cast(len, llvm_sizeof_expr_t, "").unwrap();
+    let len = ctx.builder.build_int_mul(len, src_elem_t.size_of().unwrap(), "").unwrap();
+
+    call_memcpy(ctx, dest, src, len, is_volatile);
+}
+
 /// Macro to find and generate build call for llvm intrinsic (body of llvm intrinsic function)
 ///
 /// Arguments:
 /// * `$ctx:ident`: Reference to the current Code Generation Context
 /// * `$name:ident`: Optional name to be assigned to the llvm build call (Option<&str>)
 /// * `$llvm_name:literal`: Name of underlying llvm intrinsic function
-/// * `$map_fn:ident`: Mapping function to be applied on `BasicValue` (`BasicValue` -> Function Return Type)
+/// * `$map_fn:ident`: Mapping function to be applied on `BasicValue` (`BasicValue` -> Function Return Type).
-/// Use `BasicValueEnum::into_int_value` for Integer return type and `BasicValueEnum::into_float_value` for Float return type
+///   Use `BasicValueEnum::into_int_value` for Integer return type and
+///   `BasicValueEnum::into_float_value` for Float return type
 /// * `$llvm_ty:ident`: Type of first operand
 /// * `,($val:ident)*`: Comma separated list of operands
 macro_rules! generate_llvm_intrinsic_fn_body {
@@ -188,7 +268,7 @@ macro_rules! generate_llvm_intrinsic_fn_body {
 /// Arguments:
 /// * `float/int`: Indicates the return and argument type of the function
 /// * `$fn_name:ident`: The identifier of the rust function to be generated
-/// * `$llvm_name:literal`: Name of underlying llvm intrinsic function
+/// * `$llvm_name:literal`: Name of underlying llvm intrinsic function.
 ///   Omit "llvm." prefix from the function name i.e. use "ceil" instead of "llvm.ceil"
 /// * `$val:ident`: The operand for unary operations
 /// * `$val1:ident`, `$val2:ident`: The operands for binary operations
@@ -306,3 +386,25 @@ pub fn call_float_powi<'ctx>(
         .map(Either::unwrap_left)
         .unwrap()
 }
+
+/// Invokes the [`llvm.ctpop`](https://llvm.org/docs/LangRef.html#llvm-ctpop-intrinsic) intrinsic.
+pub fn call_int_ctpop<'ctx>(
+    ctx: &CodeGenContext<'ctx, '_>,
+    src: IntValue<'ctx>,
+    name: Option<&str>,
+) -> IntValue<'ctx> {
+    const FN_NAME: &str = "llvm.ctpop";
+
+    let llvm_src_t = src.get_type();
+
+    let intrinsic_fn = Intrinsic::find(FN_NAME)
+        .and_then(|intrinsic| intrinsic.get_declaration(&ctx.module, &[llvm_src_t.into()]))
+        .unwrap();
+
+    ctx.builder
+        .build_call(intrinsic_fn, &[src.into()], name.unwrap_or_default())
+        .map(CallSiteValue::try_as_basic_value)
+        .map(|v| v.map_left(BasicValueEnum::into_int_value))
+        .map(Either::unwrap_left)
+        .unwrap()
+}

nac3core/src/codegen/mod.rs

@@ -1,12 +1,12 @@
-use crate::{
+use std::{
-    codegen::classes::{ListType, ProxyType, RangeType},
+    collections::{HashMap, HashSet},
-    symbol_resolver::{StaticValue, SymbolResolver},
+    sync::{
-    toplevel::{helper::PrimDef, TopLevelContext, TopLevelDef},
+        atomic::{AtomicBool, Ordering},
-    typecheck::{
+        Arc,
-        type_inferencer::{CodeLocation, PrimitiveStore},
-        typedef::{CallId, FuncArg, Type, TypeEnum, Unifier},
     },
+    thread,
 };
+
 use crossbeam::channel::{unbounded, Receiver, Sender};
 use inkwell::{
     attributes::{Attribute, AttributeLoc},
@@ -24,37 +24,56 @@ use inkwell::{
     AddressSpace, IntPredicate, OptimizationLevel,
 };
 use itertools::Itertools;
-use model::*;
-use nac3parser::ast::{Location, Stmt, StrRef};
 use parking_lot::{Condvar, Mutex};
-use std::collections::{HashMap, HashSet};
+
-use std::sync::{
+use nac3parser::ast::{Location, Stmt, StrRef};
-    atomic::{AtomicBool, Ordering},
+
-    Arc,
+use crate::{
+    symbol_resolver::{StaticValue, SymbolResolver},
+    toplevel::{
+        helper::{extract_ndims, PrimDef},
+        numpy::unpack_ndarray_var_tys,
+        TopLevelContext, TopLevelDef,
+    },
+    typecheck::{
+        type_inferencer::{CodeLocation, PrimitiveStore},
+        typedef::{CallId, FuncArg, Type, TypeEnum, Unifier},
+    },
 };
-use std::thread;
+use concrete_type::{ConcreteType, ConcreteTypeEnum, ConcreteTypeStore};
-use structure::{cslice::CSlice, exception::Exception, ndarray::NpArray};
+pub use generator::{CodeGenerator, DefaultCodeGenerator};
+use types::{ndarray::NDArrayType, ListType, ProxyType, RangeType};
 
 pub mod builtin_fns;
-pub mod classes;
 pub mod concrete_type;
 pub mod expr;
 pub mod extern_fns;
 mod generator;
 pub mod irrt;
 pub mod llvm_intrinsics;
-pub mod model;
 pub mod numpy;
-pub mod numpy_new;
 pub mod stmt;
-pub mod structure;
+pub mod types;
-pub mod util;
+pub mod values;
 
 #[cfg(test)]
 mod test;
 
-use concrete_type::{ConcreteType, ConcreteTypeEnum, ConcreteTypeStore};
+mod macros {
-pub use generator::{CodeGenerator, DefaultCodeGenerator};
+    /// Codegen-variant of [`std::unreachable`] which accepts an instance of [`CodeGenContext`] as
+    /// its first argument to provide Python source information to indicate the codegen location
+    /// causing the assertion.
+    macro_rules! codegen_unreachable {
+        ($ctx:expr $(,)?) => {
+            std::unreachable!("unreachable code while processing {}", &$ctx.current_loc)
+        };
+        ($ctx:expr, $($arg:tt)*) => {
+            std::unreachable!("unreachable code while processing {}: {}", &$ctx.current_loc, std::format!("{}", std::format_args!($($arg)+)))
+        };
+    }
+
+    pub(crate) use codegen_unreachable;
+}
 
 #[derive(Default)]
 pub struct StaticValueStore {
@@ -174,11 +193,11 @@ pub struct CodeGenContext<'ctx, 'a> {
     pub registry: &'a WorkerRegistry,
 
     /// Cache for constant strings.
-    pub const_strings: HashMap<String, Struct<'ctx, CSlice>>,
+    pub const_strings: HashMap<String, BasicValueEnum<'ctx>>,
 
     /// [`BasicBlock`] containing all `alloca` statements for the current function.
     pub init_bb: BasicBlock<'ctx>,
-    pub exception_val: Option<Ptr<'ctx, StructModel<Exception>>>,
+    pub exception_val: Option<PointerValue<'ctx>>,
 
     /// The header and exit basic blocks of a loop in this context. See
     /// <https://llvm.org/docs/LoopTerminology.html> for explanation of these terminology.
@@ -450,7 +469,7 @@ pub struct CodeGenTask {
 fn get_llvm_type<'ctx, G: CodeGenerator + ?Sized>(
     ctx: &'ctx Context,
     module: &Module<'ctx>,
-    generator: &mut G,
+    generator: &G,
     unifier: &mut Unifier,
     top_level: &TopLevelContext,
     type_cache: &mut HashMap<Type, BasicTypeEnum<'ctx>>,
@@ -495,9 +514,13 @@ fn get_llvm_type<'ctx, G: CodeGenerator + ?Sized>(
                         }
 
                         TObj { obj_id, .. } if *obj_id == PrimDef::NDArray.id() => {
-                            let tyctx = generator.type_context(ctx);
+                            let (dtype, ndims) = unpack_ndarray_var_tys(unifier, ty);
-                            let pndarray_model = PtrModel(StructModel(NpArray));
+                            let ndims = extract_ndims(unifier, ndims);
-                            pndarray_model.get_type(tyctx, ctx).into()
+                            let element_type = get_llvm_type(
+                                ctx, module, generator, unifier, top_level, type_cache, dtype,
+                            );
+
+                            NDArrayType::new(generator, ctx, element_type, Some(ndims)).as_base_type().into()
                         }
 
                         _ => unreachable!(
@@ -541,8 +564,10 @@ fn get_llvm_type<'ctx, G: CodeGenerator + ?Sized>(
                 };
                 return ty;
             }
-            TTuple { ty } => {
+            TTuple { ty, is_vararg_ctx } => {
                 // a struct with fields in the order present in the tuple
+                assert!(!is_vararg_ctx, "Tuples in vararg context must be instantiated with the correct number of arguments before calling get_llvm_type");
+
                 let fields = ty
                     .iter()
                     .map(|ty| {
@@ -572,7 +597,7 @@ fn get_llvm_type<'ctx, G: CodeGenerator + ?Sized>(
 fn get_llvm_abi_type<'ctx, G: CodeGenerator + ?Sized>(
     ctx: &'ctx Context,
     module: &Module<'ctx>,
-    generator: &mut G,
+    generator: &G,
     unifier: &mut Unifier,
     top_level: &TopLevelContext,
     type_cache: &mut HashMap<Type, BasicTypeEnum<'ctx>>,
@@ -581,11 +606,11 @@ fn get_llvm_abi_type<'ctx, G: CodeGenerator + ?Sized>(
 ) -> BasicTypeEnum<'ctx> {
     // If the type is used in the definition of a function, return `i1` instead of `i8` for ABI
     // consistency.
-    return if unifier.unioned(ty, primitives.bool) {
+    if unifier.unioned(ty, primitives.bool) {
         ctx.bool_type().into()
     } else {
         get_llvm_type(ctx, module, generator, unifier, top_level, type_cache, ty)
-    };
+    }
 }
 
 /// Whether `sret` is needed for a return value with type `ty`.
@@ -610,6 +635,40 @@ fn need_sret(ty: BasicTypeEnum) -> bool {
     need_sret_impl(ty, true)
 }
 
+/// Returns the [`BasicTypeEnum`] representing a `va_list` struct for variadic arguments.
+fn get_llvm_valist_type<'ctx>(ctx: &'ctx Context, triple: &TargetTriple) -> BasicTypeEnum<'ctx> {
+    let triple = TargetMachine::normalize_triple(triple);
+    let triple = triple.as_str().to_str().unwrap();
+    let arch = triple.split('-').next().unwrap();
+
+    let llvm_pi8 = ctx.i8_type().ptr_type(AddressSpace::default());
+
+    // Referenced from parseArch() in llvm/lib/Support/Triple.cpp
+    match arch {
+        "i386" | "i486" | "i586" | "i686" | "riscv32" => {
+            ctx.i8_type().ptr_type(AddressSpace::default()).into()
+        }
+        "amd64" | "x86_64" | "x86_64h" => {
+            let llvm_i32 = ctx.i32_type();
+
+            let va_list_tag = ctx.opaque_struct_type("struct.__va_list_tag");
+            va_list_tag.set_body(
+                &[llvm_i32.into(), llvm_i32.into(), llvm_pi8.into(), llvm_pi8.into()],
+                false,
+            );
+            va_list_tag.into()
+        }
+        "armv7" => {
+            let va_list = ctx.opaque_struct_type("struct.__va_list");
+            va_list.set_body(&[llvm_pi8.into()], false);
+            va_list.into()
+        }
+        triple => {
+            todo!("Unsupported platform for varargs: {triple}")
+        }
+    }
+}
+
 /// Implementation for generating LLVM IR for a function.
 pub fn gen_func_impl<
     'ctx,
@@ -667,20 +726,43 @@ pub fn gen_func_impl<
         ..primitives
     };
 
-    let type_context = generator.type_context(context);
+    let mut type_cache: HashMap<_, _> = [
-    let cslice_model = StructModel(CSlice);
-    let pexn_model = PtrModel(StructModel(Exception));
-
-    let mut type_cache: HashMap<_, BasicTypeEnum<'ctx>> = [
         (primitives.int32, context.i32_type().into()),
         (primitives.int64, context.i64_type().into()),
         (primitives.uint32, context.i32_type().into()),
         (primitives.uint64, context.i64_type().into()),
         (primitives.float, context.f64_type().into()),
         (primitives.bool, context.i8_type().into()),
-        (primitives.str, cslice_model.get_type(type_context, context).into()),
+        (primitives.str, {
+            let name = "str";
+            match module.get_struct_type(name) {
+                None => {
+                    let str_type = context.opaque_struct_type("str");
+                    let fields = [
+                        context.i8_type().ptr_type(AddressSpace::default()).into(),
+                        generator.get_size_type(context).into(),
+                    ];
+                    str_type.set_body(&fields, false);
+                    str_type.into()
+                }
+                Some(t) => t.as_basic_type_enum(),
+            }
+        }),
         (primitives.range, RangeType::new(context).as_base_type().into()),
-        (primitives.exception, pexn_model.get_type(type_context, context).into()),
+        (primitives.exception, {
+            let name = "Exception";
+            if let Some(t) = module.get_struct_type(name) {
+                t.ptr_type(AddressSpace::default()).as_basic_type_enum()
+            } else {
+                let exception = context.opaque_struct_type("Exception");
+                let int32 = context.i32_type().into();
+                let int64 = context.i64_type().into();
+                let str_ty = module.get_struct_type("str").unwrap().as_basic_type_enum();
+                let fields = [int32, str_ty, int32, int32, str_ty, str_ty, int64, int64, int64];
+                exception.set_body(&fields, false);
+                exception.ptr_type(AddressSpace::default()).as_basic_type_enum()
+            }
+        }),
     ]
     .iter()
     .copied()
@@ -698,6 +780,7 @@ pub fn gen_func_impl<
                 name: arg.name,
                 ty: task.store.to_unifier_type(&mut unifier, &primitives, arg.ty, &mut cache),
                 default_value: arg.default_value.clone(),
+                is_vararg: arg.is_vararg,
             })
             .collect_vec(),
         task.store.to_unifier_type(&mut unifier, &primitives, *ret, &mut cache),
@@ -720,7 +803,10 @@ pub fn gen_func_impl<
     let has_sret = ret_type.map_or(false, |ty| need_sret(ty));
     let mut params = args
         .iter()
+        .filter(|arg| !arg.is_vararg)
         .map(|arg| {
+            debug_assert!(!arg.is_vararg);
+
             get_llvm_abi_type(
                 context,
                 &module,
@@ -739,9 +825,12 @@ pub fn gen_func_impl<
         params.insert(0, ret_type.unwrap().ptr_type(AddressSpace::default()).into());
     }
 
+    debug_assert!(matches!(args.iter().filter(|arg| arg.is_vararg).count(), 0..=1));
+    let vararg_arg = args.iter().find(|arg| arg.is_vararg);
+
     let fn_type = match ret_type {
-        Some(ret_type) if !has_sret => ret_type.fn_type(&params, false),
+        Some(ret_type) if !has_sret => ret_type.fn_type(&params, vararg_arg.is_some()),
-        _ => context.void_type().fn_type(&params, false),
+        _ => context.void_type().fn_type(&params, vararg_arg.is_some()),
     };
 
     let symbol = &task.symbol_name;
@@ -769,9 +858,10 @@ pub fn gen_func_impl<
     builder.position_at_end(init_bb);
     let body_bb = context.append_basic_block(fn_val, "body");
 
+    // Store non-vararg argument values into local variables
     let mut var_assignment = HashMap::new();
     let offset = u32::from(has_sret);
-    for (n, arg) in args.iter().enumerate() {
+    for (n, arg) in args.iter().enumerate().filter(|(_, arg)| !arg.is_vararg) {
         let param = fn_val.get_nth_param((n as u32) + offset).unwrap();
         let local_type = get_llvm_type(
             context,
@@ -804,6 +894,8 @@ pub fn gen_func_impl<
         var_assignment.insert(arg.name, (alloca, None, 0));
     }
 
+    // TODO: Save vararg parameters as list
+
     let return_buffer = if has_sret {
         Some(fn_val.get_nth_param(0).unwrap().into_pointer_value())
     } else {
@@ -1026,3 +1118,112 @@ fn gen_in_range_check<'ctx>(
 
     ctx.builder.build_int_compare(IntPredicate::SLT, lo, hi, "cmp").unwrap()
 }
+
+/// Returns the internal name for the `va_count` argument, used to indicate the number of arguments
+/// passed to the variadic function.
+fn get_va_count_arg_name(arg_name: StrRef) -> StrRef {
+    format!("__{}_va_count", &arg_name).into()
+}
+
+/// Returns the alignment of the type.
+///
+/// This is necessary as `get_alignment` is not implemented as part of [`BasicType`].
+pub fn get_type_alignment<'ctx>(ty: impl Into<BasicTypeEnum<'ctx>>) -> IntValue<'ctx> {
+    match ty.into() {
+        BasicTypeEnum::ArrayType(ty) => ty.get_alignment(),
+        BasicTypeEnum::FloatType(ty) => ty.get_alignment(),
+        BasicTypeEnum::IntType(ty) => ty.get_alignment(),
+        BasicTypeEnum::PointerType(ty) => ty.get_alignment(),
+        BasicTypeEnum::StructType(ty) => ty.get_alignment(),
+        BasicTypeEnum::VectorType(ty) => ty.get_alignment(),
+    }
+}
+
+/// Inserts an `alloca` instruction with allocation `size` given in bytes and the alignment of the
+/// given type.
+///
+/// The returned [`PointerValue`] will have a type of `i8*`, a size of at least `size`, and will be
+/// aligned with the alignment of `align_ty`.
+pub fn type_aligned_alloca<'ctx, G: CodeGenerator + ?Sized>(
+    generator: &mut G,
+    ctx: &mut CodeGenContext<'ctx, '_>,
+    align_ty: impl Into<BasicTypeEnum<'ctx>>,
+    size: IntValue<'ctx>,
+    name: Option<&str>,
+) -> PointerValue<'ctx> {
+    /// Round `val` up to its modulo `power_of_two`.
+    fn round_up<'ctx>(
+        ctx: &CodeGenContext<'ctx, '_>,
+        val: IntValue<'ctx>,
+        power_of_two: IntValue<'ctx>,
+    ) -> IntValue<'ctx> {
+        debug_assert_eq!(
+            val.get_type().get_bit_width(),
+            power_of_two.get_type().get_bit_width(),
+            "`val` ({}) and `power_of_two` ({}) must be the same type",
+            val.get_type(),
+            power_of_two.get_type(),
+        );
+
+        let llvm_val_t = val.get_type();
+
+        let max_rem =
+            ctx.builder.build_int_sub(power_of_two, llvm_val_t.const_int(1, false), "").unwrap();
+        ctx.builder
+            .build_and(
+                ctx.builder.build_int_add(val, max_rem, "").unwrap(),
+                ctx.builder.build_not(max_rem, "").unwrap(),
+                "",
+            )
+            .unwrap()
+    }
+
+    let llvm_i8 = ctx.ctx.i8_type();
+    let llvm_pi8 = llvm_i8.ptr_type(AddressSpace::default());
+    let llvm_usize = generator.get_size_type(ctx.ctx);
+    let align_ty = align_ty.into();
+
+    let size = ctx.builder.build_int_truncate_or_bit_cast(size, llvm_usize, "").unwrap();
+
+    debug_assert_eq!(
+        size.get_type().get_bit_width(),
+        llvm_usize.get_bit_width(),
+        "Expected size_t ({}) for parameter `size` of `aligned_alloca`, got {}",
+        llvm_usize,
+        size.get_type(),
+    );
+
+    let alignment = get_type_alignment(align_ty);
+    let alignment = ctx.builder.build_int_truncate_or_bit_cast(alignment, llvm_usize, "").unwrap();
+
+    if ctx.registry.llvm_options.opt_level == OptimizationLevel::None {
+        let alignment_bitcount = llvm_intrinsics::call_int_ctpop(ctx, alignment, None);
+
+        ctx.make_assert(
+            generator,
+            ctx.builder
+                .build_int_compare(
+                    IntPredicate::EQ,
+                    alignment_bitcount,
+                    alignment_bitcount.get_type().const_int(1, false),
+                    "",
+                )
+                .unwrap(),
+            "0:AssertionError",
+            "Expected power-of-two alignment for aligned_alloca, got {0}",
+            [Some(alignment), None, None],
+            ctx.current_loc,
+        );
+    }
+
+    let buffer_size = round_up(ctx, size, alignment);
+    let aligned_slices = ctx.builder.build_int_unsigned_div(buffer_size, alignment, "").unwrap();
+
+    // Just to be absolutely sure, alloca in [i8 x alignment] slices
+    let buffer = ctx.builder.build_array_alloca(align_ty, aligned_slices, "").unwrap();
+
+    ctx.builder
+        .build_bit_cast(buffer, llvm_pi8, name.unwrap_or_default())
+        .map(BasicValueEnum::into_pointer_value)
+        .unwrap()
+}

nac3core/src/codegen/model/core.rs

@@ -1,161 +0,0 @@
-use std::fmt;
-
-use inkwell::{context::Context, types::*, values::*};
-
-use super::*;
-use crate::codegen::{CodeGenContext, CodeGenerator};
-
-#[derive(Clone, Copy)]
-pub struct TypeContext<'ctx> {
-    pub size_type: IntType<'ctx>,
-}
-
-pub trait HasTypeContext {
-    fn type_context<'ctx>(&self, ctx: &'ctx Context) -> TypeContext<'ctx>;
-}
-
-impl<T: CodeGenerator + ?Sized> HasTypeContext for T {
-    fn type_context<'ctx>(&self, ctx: &'ctx Context) -> TypeContext<'ctx> {
-        TypeContext { size_type: self.get_size_type(ctx) }
-    }
-}
-
-#[derive(Debug, Clone)]
-pub struct ModelError(pub String);
-
-impl ModelError {
-    pub(super) fn under_context(mut self, context: &str) -> Self {
-        self.0.push_str(" ... in ");
-        self.0.push_str(context);
-        self
-    }
-}
-
-/// A [`Model`] is a singleton object that uniquely identifies a [`BasicType`]
-/// solely from a [`CodeGenerator`] and a [`Context`].
-pub trait Model: CheckType + fmt::Debug + Clone + Copy + Default {
-    type Value<'ctx>: BasicValue<'ctx> + TryFrom<BasicValueEnum<'ctx>>;
-    type Type<'ctx>: BasicType<'ctx>;
-
-    /// Return the [`BasicType`] of this model.
-    fn get_type<'ctx>(&self, tyctx: TypeContext<'ctx>, ctx: &'ctx Context) -> Self::Type<'ctx>;
-
-    /// Check if a [`BasicType`] is the same type of this model.
-    fn check_type<'ctx, T: BasicType<'ctx>>(
-        &self,
-        tyctx: TypeContext<'ctx>,
-        ctx: &'ctx Context,
-        ty: T,
-    ) -> Result<(), ModelError> {
-        let ty = ty.as_basic_type_enum();
-        self.check_type_impl(tyctx, ctx, ty.as_basic_type_enum())
-    }
-
-    /// Create an instance from a value with [`Instance::model`] being this model.
-    ///
-    /// Caller must make sure the type of `value` and the type of this `model` are equivalent.
-    fn believe_value<'ctx>(&self, value: Self::Value<'ctx>) -> Instance<'ctx, Self> {
-        Instance { model: *self, value }
-    }
-
-    /// Check if a [`BasicValue`]'s type is equivalent to the type of this model.
-    /// Wrap it into an [`Instance`] if it is.
-    fn check_value<'ctx, V: BasicValue<'ctx>>(
-        &self,
-        tyctx: TypeContext<'ctx>,
-        ctx: &'ctx Context,
-        value: V,
-    ) -> Result<Instance<'ctx, Self>, ModelError> {
-        let value = value.as_basic_value_enum();
-        self.check_type(tyctx, ctx, value.get_type())
-            .map_err(|err| err.under_context("the value {value:?}"))?;
-
-        let Ok(value) = Self::Value::try_from(value) else {
-            unreachable!("check_type() has bad implementation")
-        };
-        Ok(self.believe_value(value))
-    }
-
-    // Allocate a value on the stack and return its pointer.
-    fn alloca<'ctx>(
-        &self,
-        tyctx: TypeContext<'ctx>,
-        ctx: &CodeGenContext<'ctx, '_>,
-        name: &str,
-    ) -> Ptr<'ctx, Self> {
-        let pmodel = PtrModel(*self);
-        let p = ctx.builder.build_alloca(self.get_type(tyctx, ctx.ctx), name).unwrap();
-        pmodel.believe_value(p)
-    }
-
-    // Allocate an array on the stack and return its pointer.
-    fn array_alloca<'ctx>(
-        &self,
-        tyctx: TypeContext<'ctx>,
-        ctx: &CodeGenContext<'ctx, '_>,
-        len: IntValue<'ctx>,
-        name: &str,
-    ) -> Ptr<'ctx, Self> {
-        let pmodel = PtrModel(*self);
-        let p = ctx.builder.build_array_alloca(self.get_type(tyctx, ctx.ctx), len, name).unwrap();
-        pmodel.believe_value(p)
-    }
-
-    fn var_alloca<'ctx, G: CodeGenerator + ?Sized>(
-        &self,
-        generator: &mut G,
-        ctx: &mut CodeGenContext<'ctx, '_>,
-        name: Option<&str>,
-    ) -> Result<Ptr<'ctx, Self>, String> {
-        let tyctx = generator.type_context(ctx.ctx);
-
-        let pmodel = PtrModel(*self);
-        let p = generator.gen_var_alloc(
-            ctx,
-            self.get_type(tyctx, ctx.ctx).as_basic_type_enum(),
-            name,
-        )?;
-        Ok(pmodel.believe_value(p))
-    }
-
-    fn array_var_alloca<'ctx, G: CodeGenerator + ?Sized>(
-        &self,
-        generator: &mut G,
-        ctx: &mut CodeGenContext<'ctx, '_>,
-        len: IntValue<'ctx>,
-        name: Option<&'ctx str>,
-    ) -> Result<Ptr<'ctx, Self>, String> {
-        let tyctx = generator.type_context(ctx.ctx);
-
-        // TODO: Remove ArraySliceValue
-        let pmodel = PtrModel(*self);
-        let p = generator.gen_array_var_alloc(
-            ctx,
-            self.get_type(tyctx, ctx.ctx).as_basic_type_enum(),
-            len,
-            name,
-        )?;
-        Ok(pmodel.believe_value(PointerValue::from(p)))
-    }
-}
-
-#[derive(Debug, Clone, Copy)]
-pub struct Instance<'ctx, M: Model> {
-    /// The model of this instance.
-    pub model: M,
-    /// The value of this instance.
-    ///
-    /// Caller must make sure the type of `value` and the type of this `model` are equivalent,
-    /// down to having the same [`IntType::get_bit_width`] in case of [`IntType`] for example.
-    pub value: M::Value<'ctx>,
-}
-
-// NOTE: Must be Rust object-safe - This must be typeable for a Rust trait object.
-pub trait CheckType {
-    fn check_type_impl<'ctx>(
-        &self,
-        tyctx: TypeContext<'ctx>,
-        ctx: &'ctx Context,
-        ty: BasicTypeEnum<'ctx>,
-    ) -> Result<(), ModelError>;
-}

nac3core/src/codegen/model/int.rs

@@ -1,228 +0,0 @@
-use std::fmt;
-
-use inkwell::{
-    context::Context,
-    types::{BasicTypeEnum, IntType},
-    values::IntValue,
-    IntPredicate,
-};
-
-use crate::codegen::{CodeGenContext, CodeGenerator};
-
-use super::*;
-
-pub trait IntKind: fmt::Debug + Clone + Copy + Default {
-    fn get_int_type<'ctx>(&self, tyctx: TypeContext<'ctx>, ctx: &'ctx Context) -> IntType<'ctx>;
-}
-
-#[derive(Debug, Clone, Copy, Default)]
-pub struct Bool;
-#[derive(Debug, Clone, Copy, Default)]
-pub struct Byte;
-#[derive(Debug, Clone, Copy, Default)]
-pub struct Int32;
-#[derive(Debug, Clone, Copy, Default)]
-pub struct Int64;
-#[derive(Debug, Clone, Copy, Default)]
-pub struct SizeT;
-
-impl IntKind for Bool {
-    fn get_int_type<'ctx>(&self, _tyctx: TypeContext<'ctx>, ctx: &'ctx Context) -> IntType<'ctx> {
-        ctx.bool_type()
-    }
-}
-
-impl IntKind for Byte {
-    fn get_int_type<'ctx>(&self, _tyctx: TypeContext<'ctx>, ctx: &'ctx Context) -> IntType<'ctx> {
-        ctx.i8_type()
-    }
-}
-
-impl IntKind for Int32 {
-    fn get_int_type<'ctx>(&self, _tyctx: TypeContext<'ctx>, ctx: &'ctx Context) -> IntType<'ctx> {
-        ctx.i32_type()
-    }
-}
-
-impl IntKind for Int64 {
-    fn get_int_type<'ctx>(&self, _tyctx: TypeContext<'ctx>, ctx: &'ctx Context) -> IntType<'ctx> {
-        ctx.i64_type()
-    }
-}
-
-impl IntKind for SizeT {
-    fn get_int_type<'ctx>(&self, tyctx: TypeContext<'ctx>, _ctx: &'ctx Context) -> IntType<'ctx> {
-        tyctx.size_type
-    }
-}
-
-#[derive(Debug, Clone, Copy, Default)]
-pub struct IntModel<N: IntKind>(pub N);
-pub type Int<'ctx, N> = Instance<'ctx, IntModel<N>>;
-
-impl<N: IntKind> CheckType for IntModel<N> {
-    fn check_type_impl<'ctx>(
-        &self,
-        tyctx: TypeContext<'ctx>,
-        ctx: &'ctx Context,
-        ty: BasicTypeEnum<'ctx>,
-    ) -> Result<(), ModelError> {
-        let Ok(ty) = IntType::try_from(ty) else {
-            return Err(ModelError(format!("Expecting IntType, but got {ty:?}")));
-        };
-
-        let exp_ty = self.0.get_int_type(tyctx, ctx);
-        if ty.get_bit_width() != exp_ty.get_bit_width() {
-            return Err(ModelError(format!(
-                "Expecting IntType to have {} bit(s), but got {} bit(s)",
-                exp_ty.get_bit_width(),
-                ty.get_bit_width()
-            )));
-        }
-
-        Ok(())
-    }
-}
-
-impl<N: IntKind> Model for IntModel<N> {
-    type Value<'ctx> = IntValue<'ctx>;
-    type Type<'ctx> = IntType<'ctx>;
-
-    #[must_use]
-    fn get_type<'ctx>(&self, tyctx: TypeContext<'ctx>, ctx: &'ctx Context) -> Self::Type<'ctx> {
-        self.0.get_int_type(tyctx, ctx)
-    }
-}
-
-impl<N: IntKind> IntModel<N> {
-    pub fn constant<'ctx>(
-        &self,
-        tyctx: TypeContext<'ctx>,
-        ctx: &'ctx Context,
-        value: u64,
-    ) -> Int<'ctx, N> {
-        let value = self.get_type(tyctx, ctx).const_int(value, false);
-        self.believe_value(value)
-    }
-
-    pub fn const_0<'ctx>(&self, tyctx: TypeContext<'ctx>, ctx: &'ctx Context) -> Int<'ctx, N> {
-        self.constant(tyctx, ctx, 0)
-    }
-
-    pub fn const_1<'ctx>(&self, tyctx: TypeContext<'ctx>, ctx: &'ctx Context) -> Int<'ctx, N> {
-        self.constant(tyctx, ctx, 1)
-    }
-
-    pub fn s_extend_or_bit_cast<'ctx>(
-        &self,
-        tyctx: TypeContext<'ctx>,
-        ctx: &CodeGenContext<'ctx, '_>,
-        value: IntValue<'ctx>,
-        name: &str,
-    ) -> Int<'ctx, N> {
-        let value = ctx
-            .builder
-            .build_int_s_extend_or_bit_cast(value, self.get_type(tyctx, ctx.ctx), name)
-            .unwrap();
-        self.believe_value(value)
-    }
-
-    pub fn truncate<'ctx>(
-        &self,
-        tyctx: TypeContext<'ctx>,
-        ctx: &CodeGenContext<'ctx, '_>,
-        value: IntValue<'ctx>,
-        name: &str,
-    ) -> Int<'ctx, N> {
-        let value =
-            ctx.builder.build_int_truncate(value, self.get_type(tyctx, ctx.ctx), name).unwrap();
-        self.believe_value(value)
-    }
-}
-
-impl IntModel<Bool> {
-    #[must_use]
-    pub fn const_false<'ctx>(
-        &self,
-        tyctx: TypeContext<'ctx>,
-        ctx: &'ctx Context,
-    ) -> Int<'ctx, Bool> {
-        self.constant(tyctx, ctx, 0)
-    }
-
-    #[must_use]
-    pub fn const_true<'ctx>(
-        &self,
-        tyctx: TypeContext<'ctx>,
-        ctx: &'ctx Context,
-    ) -> Int<'ctx, Bool> {
-        self.constant(tyctx, ctx, 1)
-    }
-}
-
-impl<'ctx, N: IntKind> Int<'ctx, N> {
-    pub fn s_extend_or_bit_cast<NewN: IntKind, G: CodeGenerator + ?Sized>(
-        &self,
-        tyctx: TypeContext<'ctx>,
-        ctx: &CodeGenContext<'ctx, '_>,
-        to_int_kind: NewN,
-        name: &str,
-    ) -> Int<'ctx, NewN> {
-        IntModel(to_int_kind).s_extend_or_bit_cast(tyctx, ctx, self.value, name)
-    }
-
-    pub fn truncate<NewN: IntKind, G: CodeGenerator + ?Sized>(
-        &self,
-        tyctx: TypeContext<'ctx>,
-        ctx: &CodeGenContext<'ctx, '_>,
-        to_int_kind: NewN,
-        name: &str,
-    ) -> Int<'ctx, NewN> {
-        IntModel(to_int_kind).truncate(tyctx, ctx, self.value, name)
-    }
-
-    #[must_use]
-    pub fn add<G: CodeGenerator + ?Sized>(
-        &self,
-        ctx: &CodeGenContext<'ctx, '_>,
-        other: Int<'ctx, N>,
-        name: &str,
-    ) -> Int<'ctx, N> {
-        let value = ctx.builder.build_int_add(self.value, other.value, name).unwrap();
-        self.model.believe_value(value)
-    }
-
-    #[must_use]
-    pub fn sub<G: CodeGenerator + ?Sized>(
-        &self,
-        ctx: &CodeGenContext<'ctx, '_>,
-        other: Int<'ctx, N>,
-        name: &str,
-    ) -> Int<'ctx, N> {
-        let value = ctx.builder.build_int_sub(self.value, other.value, name).unwrap();
-        self.model.believe_value(value)
-    }
-
-    #[must_use]
-    pub fn mul<G: CodeGenerator + ?Sized>(
-        &self,
-        ctx: &CodeGenContext<'ctx, '_>,
-        other: Int<'ctx, N>,
-        name: &str,
-    ) -> Int<'ctx, N> {
-        let value = ctx.builder.build_int_mul(self.value, other.value, name).unwrap();
-        self.model.believe_value(value)
-    }
-
-    pub fn compare<G: CodeGenerator + ?Sized>(
-        &self,
-        ctx: &CodeGenContext<'ctx, '_>,
-        op: IntPredicate,
-        other: Int<'ctx, N>,
-        name: &str,
-    ) -> Int<'ctx, Bool> {
-        let bool_model = IntModel(Bool);
-        let value = ctx.builder.build_int_compare(op, self.value, other.value, name).unwrap();
-        bool_model.believe_value(value)
-    }
-}

nac3core/src/codegen/model/mod.rs

@@ -1,12 +0,0 @@
-mod core;
-mod int;
-mod ptr;
-mod slice;
-mod structure;
-pub mod util;
-
-pub use core::*;
-pub use int::*;
-pub use ptr::*;
-pub use slice::*;
-pub use structure::*;

nac3core/src/codegen/model/ptr.rs

@@ -1,142 +0,0 @@
-use inkwell::{
-    context::Context,
-    types::{BasicType, BasicTypeEnum, PointerType},
-    values::{IntValue, PointerValue},
-    AddressSpace,
-};
-
-use crate::codegen::CodeGenContext;
-
-use super::*;
-
-#[derive(Debug, Clone, Copy, Default)]
-pub struct PtrModel<Element>(pub Element);
-pub type Ptr<'ctx, Element> = Instance<'ctx, PtrModel<Element>>;
-
-impl<Element: CheckType> CheckType for PtrModel<Element> {
-    fn check_type_impl<'ctx>(
-        &self,
-        tyctx: TypeContext<'ctx>,
-        ctx: &'ctx Context,
-        ty: BasicTypeEnum<'ctx>,
-    ) -> Result<(), super::ModelError> {
-        let Ok(ty) = PointerType::try_from(ty) else {
-            return Err(ModelError(format!("Expecting PointerType, but got {ty:?}")));
-        };
-
-        let elem_ty = ty.get_element_type();
-        let Ok(elem_ty) = BasicTypeEnum::try_from(elem_ty) else {
-            return Err(ModelError(format!(
-                "Expecting pointer element type to be a BasicTypeEnum, but got {elem_ty:?}"
-            )));
-        };
-
-        // TODO: inkwell `get_element_type()` will be deprecated.
-        // Remove the check for `get_element_type()` when the time comes.
-        self.0
-            .check_type_impl(tyctx, ctx, elem_ty)
-            .map_err(|err| err.under_context("a PointerType"))?;
-
-        Ok(())
-    }
-}
-
-impl<Element: Model> Model for PtrModel<Element> {
-    type Value<'ctx> = PointerValue<'ctx>;
-    type Type<'ctx> = PointerType<'ctx>;
-
-    fn get_type<'ctx>(&self, tyctx: TypeContext<'ctx>, ctx: &'ctx Context) -> Self::Type<'ctx> {
-        self.0.get_type(tyctx, ctx).ptr_type(AddressSpace::default())
-    }
-}
-
-impl<Element: Model> PtrModel<Element> {
-    /// Return a ***constant*** nullptr.
-    pub fn nullptr<'ctx>(
-        &self,
-        tyctx: TypeContext<'ctx>,
-        ctx: &'ctx Context,
-    ) -> Ptr<'ctx, Element> {
-        let ptr = self.get_type(tyctx, ctx).const_null();
-        self.believe_value(ptr)
-    }
-
-    pub fn transmute<'ctx>(
-        &self,
-        tyctx: TypeContext<'ctx>,
-        ctx: &CodeGenContext<'ctx, '_>,
-        ptr: PointerValue<'ctx>,
-        name: &str,
-    ) -> Ptr<'ctx, Element> {
-        let ptr = ctx.builder.build_pointer_cast(ptr, self.get_type(tyctx, ctx.ctx), name).unwrap();
-        self.believe_value(ptr)
-    }
-}
-
-impl<'ctx, Element: Model> Ptr<'ctx, Element> {
-    /// Offset the pointer by [`inkwell::builder::Builder::build_in_bounds_gep`].
-    #[must_use]
-    pub fn offset(
-        &self,
-        tyctx: TypeContext<'ctx>,
-        ctx: &CodeGenContext<'ctx, '_>,
-        offset: IntValue<'ctx>,
-        name: &str,
-    ) -> Ptr<'ctx, Element> {
-        let new_ptr =
-            unsafe { ctx.builder.build_in_bounds_gep(self.value, &[offset], name).unwrap() };
-        self.model.check_value(tyctx, ctx.ctx, new_ptr).unwrap()
-    }
-
-    // Load the `i`-th element (0-based) on the array with [`inkwell::builder::Builder::build_in_bounds_gep`].
-    pub fn ix(
-        &self,
-        tyctx: TypeContext<'ctx>,
-        ctx: &CodeGenContext<'ctx, '_>,
-        i: IntValue<'ctx>,
-        name: &str,
-    ) -> Instance<'ctx, Element> {
-        self.offset(tyctx, ctx, i, name).load(tyctx, ctx, name)
-    }
-
-    /// Load the value with [`inkwell::builder::Builder::build_load`].
-    pub fn load(
-        &self,
-        tyctx: TypeContext<'ctx>,
-        ctx: &CodeGenContext<'ctx, '_>,
-        name: &str,
-    ) -> Instance<'ctx, Element> {
-        let value = ctx.builder.build_load(self.value, name).unwrap();
-        self.model.0.check_value(tyctx, ctx.ctx, value).unwrap() // If unwrap() panics, there is a logic error.
-    }
-
-    /// Store a value with [`inkwell::builder::Builder::build_store`].
-    pub fn store(&self, ctx: &CodeGenContext<'ctx, '_>, value: Instance<'ctx, Element>) {
-        ctx.builder.build_store(self.value, value.value).unwrap();
-    }
-
-    /// Return a casted pointer of element type `NewElement` with [`inkwell::builder::Builder::build_pointer_cast`].
-    pub fn transmute<NewElement: Model>(
-        &self,
-        tyctx: TypeContext<'ctx>,
-        ctx: &CodeGenContext<'ctx, '_>,
-        new_model: NewElement,
-        name: &str,
-    ) -> Ptr<'ctx, NewElement> {
-        PtrModel(new_model).transmute(tyctx, ctx, self.value, name)
-    }
-
-    /// Check if the pointer is null with [`inkwell::builder::Builder::build_is_null`].
-    pub fn is_null(&self, ctx: &CodeGenContext<'ctx, '_>, name: &str) -> Int<'ctx, Bool> {
-        let bool_model = IntModel(Bool);
-        let value = ctx.builder.build_is_null(self.value, name).unwrap();
-        bool_model.believe_value(value)
-    }
-
-    /// Check if the pointer is not null with [`inkwell::builder::Builder::build_is_not_null`].
-    pub fn is_not_null(&self, ctx: &CodeGenContext<'ctx, '_>, name: &str) -> Int<'ctx, Bool> {
-        let bool_model = IntModel(Bool);
-        let value = ctx.builder.build_is_not_null(self.value, name).unwrap();
-        bool_model.believe_value(value)
-    }
-}

nac3core/src/codegen/model/slice.rs

@@ -1,72 +0,0 @@
-use crate::codegen::{CodeGenContext, CodeGenerator};
-
-use super::*;
-
-/// A slice - literally just a pointer and a length value.
-///
-/// NOTE: This is NOT a [`Model`].
-pub struct ArraySlice<'ctx, Len: IntKind, Item: Model> {
-    pub base: Ptr<'ctx, Item>,
-    pub len: Int<'ctx, Len>,
-}
-
-impl<'ctx, Len: IntKind, Item: Model> ArraySlice<'ctx, Len, Item> {
-    /// Get the `idx`-nth element of this [`ArraySlice`], but doesn't do an assertion to see if `idx` is out of bounds or not.
-    ///
-    /// Also see [`ArraySlice::ix`].
-    pub fn ix_unchecked(
-        &self,
-        tyctx: TypeContext<'ctx>,
-        ctx: &CodeGenContext<'ctx, '_>,
-        idx: Int<'ctx, Len>,
-        name: &str,
-    ) -> Ptr<'ctx, Item> {
-        let element_ptr = unsafe {
-            ctx.builder.build_in_bounds_gep(self.base.value, &[idx.value], name).unwrap()
-        };
-        self.base.model.check_value(tyctx, ctx.ctx, element_ptr).unwrap()
-    }
-
-    /// Call [`ArraySlice::ix_unchecked`], but checks if `idx` is in bounds, otherwise a runtime `IndexError` will be thrown.
-    pub fn ix<G: CodeGenerator + ?Sized>(
-        &self,
-        generator: &mut G,
-        ctx: &mut CodeGenContext<'ctx, '_>,
-        idx: Int<'ctx, Len>,
-        name: &str,
-    ) -> Ptr<'ctx, Item> {
-        let tyctx = generator.type_context(ctx.ctx);
-        let len_model = IntModel(Len::default());
-
-        // Assert `0 <= idx < length` and throw an Exception if `idx` is out of bounds
-        let lower_bounded = ctx
-            .builder
-            .build_int_compare(
-                inkwell::IntPredicate::SLE,
-                len_model.constant(tyctx, ctx.ctx, 0).value,
-                idx.value,
-                "lower_bounded",
-            )
-            .unwrap();
-        let upper_bounded = ctx
-            .builder
-            .build_int_compare(
-                inkwell::IntPredicate::SLT,
-                idx.value,
-                self.len.value,
-                "upper_bounded",
-            )
-            .unwrap();
-        let bounded = ctx.builder.build_and(lower_bounded, upper_bounded, "bounded").unwrap();
-        ctx.make_assert(
-            generator,
-            bounded,
-            "0:IndexError",
-            "nac3core LLVM codegen attempting to access out of bounds array index {0}. Must satisfy 0 <= index < {2}",
-            [ Some(idx.value), Some(self.len.value), None],
-            ctx.current_loc
-        );
-
-        self.ix_unchecked(tyctx, ctx, idx, name)
-    }
-}

nac3core/src/codegen/model/structure.rs

@@ -1,174 +0,0 @@
-use std::fmt;
-
-use inkwell::{
-    context::Context,
-    types::{BasicType, BasicTypeEnum, StructType},
-    values::StructValue,
-};
-use itertools::izip;
-
-use crate::codegen::CodeGenContext;
-
-use super::*;
-
-#[derive(Debug, Clone, Copy)]
-pub struct GepField<M: Model> {
-    pub gep_index: u64,
-    pub name: &'static str,
-    pub model: M,
-}
-
-pub trait FieldVisitor {
-    type Field<M: Model + 'static>;
-
-    fn add<M: Model + 'static>(&mut self, name: &'static str) -> Self::Field<M>;
-}
-
-pub struct GepFieldVisitor {
-    gep_index_counter: u64,
-}
-
-impl FieldVisitor for GepFieldVisitor {
-    type Field<M: Model + 'static> = GepField<M>;
-
-    fn add<M: Model + 'static>(&mut self, name: &'static str) -> Self::Field<M> {
-        let gep_index = self.gep_index_counter;
-        self.gep_index_counter += 1;
-        Self::Field { gep_index, name, model: M::default() }
-    }
-}
-
-struct TypeFieldVisitor<'ctx> {
-    tyctx: TypeContext<'ctx>,
-    ctx: &'ctx Context,
-    field_types: Vec<BasicTypeEnum<'ctx>>,
-}
-
-impl<'ctx> FieldVisitor for TypeFieldVisitor<'ctx> {
-    type Field<M: Model + 'static> = ();
-
-    fn add<M: Model + 'static>(&mut self, _name: &'static str) -> Self::Field<M> {
-        self.field_types.push(M::default().get_type(self.tyctx, self.ctx).as_basic_type_enum());
-    }
-}
-
-struct CheckTypeEntry {
-    check_type: Box<dyn CheckType + 'static>,
-    name: &'static str,
-}
-
-struct CheckTypeFieldVisitor<'ctx> {
-    tyctx: TypeContext<'ctx>,
-    ctx: &'ctx Context,
-    check_types: Vec<CheckTypeEntry>,
-}
-
-impl<'ctx> FieldVisitor for CheckTypeFieldVisitor<'ctx> {
-    type Field<M: Model + 'static> = ();
-
-    fn add<M: Model + 'static>(&mut self, name: &'static str) -> Self::Field<M> {
-        self.check_types.push(CheckTypeEntry { check_type: Box::<M>::default(), name });
-    }
-}
-
-pub trait StructKind: fmt::Debug + Clone + Copy + Default {
-    type Fields<F: FieldVisitor>;
-
-    fn visit_fields<F: FieldVisitor>(&self, visitor: &mut F) -> Self::Fields<F>;
-
-    fn fields(&self) -> Self::Fields<GepFieldVisitor> {
-        self.visit_fields(&mut GepFieldVisitor { gep_index_counter: 0 })
-    }
-
-    fn get_struct_type<'ctx>(
-        &self,
-        tyctx: TypeContext<'ctx>,
-        ctx: &'ctx Context,
-    ) -> StructType<'ctx> {
-        let mut visitor = TypeFieldVisitor { tyctx, ctx, field_types: Vec::new() };
-        self.visit_fields(&mut visitor);
-
-        ctx.struct_type(&visitor.field_types, false)
-    }
-}
-
-#[derive(Debug, Clone, Copy, Default)]
-pub struct StructModel<S: StructKind>(pub S);
-pub type Struct<'ctx, S> = Instance<'ctx, StructModel<S>>;
-
-impl<S: StructKind> CheckType for StructModel<S> {
-    fn check_type_impl<'ctx>(
-        &self,
-        tyctx: TypeContext<'ctx>,
-        ctx: &'ctx Context,
-        ty: BasicTypeEnum<'ctx>,
-    ) -> Result<(), ModelError> {
-        let ty = ty.as_basic_type_enum();
-        let Ok(ty) = StructType::try_from(ty) else {
-            return Err(ModelError(format!("Expecting StructType, but got {ty:?}")));
-        };
-
-        let field_types = ty.get_field_types();
-
-        let check_types = {
-            let mut builder = CheckTypeFieldVisitor { tyctx, ctx, check_types: Vec::new() };
-            self.0.visit_fields(&mut builder);
-            builder.check_types
-        };
-
-        if check_types.len() != field_types.len() {
-            return Err(ModelError(format!(
-                "Expecting StructType to have {} field(s), but got {} field(s)",
-                check_types.len(),
-                field_types.len()
-            )));
-        }
-
-        for (field_i, (entry, field_type)) in izip!(check_types, field_types).enumerate() {
-            let field_at = field_i + 1;
-
-            entry.check_type.check_type_impl(tyctx, ctx, field_type).map_err(|err| {
-                err.under_context(format!("struct field #{field_at} '{}'", entry.name).as_str())
-            })?;
-        }
-
-        Ok(())
-    }
-}
-
-impl<S: StructKind> Model for StructModel<S> {
-    type Value<'ctx> = StructValue<'ctx>;
-    type Type<'ctx> = StructType<'ctx>;
-
-    fn get_type<'ctx>(&self, tyctx: TypeContext<'ctx>, ctx: &'ctx Context) -> Self::Type<'ctx> {
-        self.0.get_struct_type(tyctx, ctx)
-    }
-}
-
-impl<'ctx, S: StructKind> Ptr<'ctx, StructModel<S>> {
-    pub fn gep<M, GetField>(
-        &self,
-        ctx: &CodeGenContext<'ctx, '_>,
-        get_field: GetField,
-    ) -> Ptr<'ctx, M>
-    where
-        M: Model,
-        GetField: FnOnce(S::Fields<GepFieldVisitor>) -> GepField<M>,
-    {
-        let field = get_field(self.model.0 .0.fields());
-        let llvm_i32 = ctx.ctx.i32_type(); // must be i32, if its i64 then rust segfaults
-
-        let ptr = unsafe {
-            ctx.builder
-                .build_in_bounds_gep(
-                    self.value,
-                    &[llvm_i32.const_zero(), llvm_i32.const_int(field.gep_index, false)],
-                    field.name,
-                )
-                .unwrap()
-        };
-
-        let ptr_model = PtrModel(field.model);
-        ptr_model.believe_value(ptr)
-    }
-}

nac3core/src/codegen/model/util.rs

@@ -1,23 +0,0 @@
-use inkwell::{types::BasicType, values::IntValue};
-
-use crate::codegen::{llvm_intrinsics::call_memcpy_generic, CodeGenContext};
-
-use super::*;
-
-pub fn gen_model_memcpy<'ctx, M: Model>(
-    tyctx: TypeContext<'ctx>,
-    ctx: &CodeGenContext<'ctx, '_>,
-    dst: Ptr<'ctx, M>,
-    src: Ptr<'ctx, M>,
-    num_elements: IntValue<'ctx>,
-    volatile: bool,
-) {
-    let bool_model = IntModel(Bool);
-
-    let itemsize = M::default().get_type(tyctx, ctx.ctx).size_of().unwrap();
-    let totalsize =
-        ctx.builder.build_int_mul(itemsize, num_elements, "model_memcpy_totalsize").unwrap();
-    let is_volatile = bool_model.constant(tyctx, ctx.ctx, u64::from(volatile));
-
-    call_memcpy_generic(ctx, dst.value, src.value, totalsize, is_volatile.value);
-}

nac3core/src/codegen/numpy_new/broadcast.rs

@@ -1,113 +0,0 @@
-use itertools::Itertools;
-
-use crate::{
-    codegen::{
-        irrt::ndarray::broadcast::{
-            call_nac3_ndarray_broadcast_shapes, call_nac3_ndarray_broadcast_to, ShapeEntry,
-        },
-        model::*,
-        numpy_new::util::{create_ndims, extract_ndims},
-        CodeGenContext, CodeGenerator,
-    },
-    typecheck::typedef::Type,
-};
-
-use super::object::NDArrayObject;
-
-#[derive(Debug, Clone)]
-pub struct BroadcastAllResult<'ctx> {
-    /// The statically known `ndims` of the broadcast result.
-    pub ndims: u64,
-    /// The broadcasting shape.
-    pub shape: Ptr<'ctx, IntModel<SizeT>>,
-    /// Broadcasted views on the inputs.
-    ///
-    /// All of them will have `shape` [`BroadcastAllResult::shape`] and
-    /// `ndims` [`BroadcastAllResult::ndims`]. The length of the vector
-    /// is the same as the input.
-    pub ndarrays: Vec<NDArrayObject<'ctx>>,
-}
-
-// TODO: DOCUMENT: Behaves like `np.broadcast()`, except returns results differently.
-pub fn broadcast_all_ndarrays<'ctx, G: CodeGenerator + ?Sized>(
-    generator: &mut G,
-    ctx: &mut CodeGenContext<'ctx, '_>,
-    ndarrays: Vec<NDArrayObject<'ctx>>,
-) -> BroadcastAllResult<'ctx> {
-    assert!(!ndarrays.is_empty());
-
-    let tyctx = generator.type_context(ctx.ctx);
-    let sizet_model = IntModel(SizeT);
-    let shape_model = StructModel(ShapeEntry);
-
-    // We can deduce the final ndims statically and immediately.
-    // It should be `max([ ndarray.ndims for ndarray in ndarrays ])`.
-    let broadcast_ndims =
-        ndarrays.iter().map(|ndarray| extract_ndims(&ctx.unifier, ndarray.ndims)).max().unwrap();
-    let broadcast_ndims_ty = create_ndims(&mut ctx.unifier, broadcast_ndims);
-
-    // NOTE: Now prepare before calling `call_nac3_ndarray_broadcast_shapes`
-
-    // Prepare input shape entries
-    let num_shape_entries =
-        sizet_model.constant(tyctx, ctx.ctx, u64::try_from(ndarrays.len()).unwrap());
-    let shape_entries =
-        shape_model.array_alloca(tyctx, ctx, num_shape_entries.value, "shape_entries");
-    for (i, ndarray) in ndarrays.iter().enumerate() {
-        let i = sizet_model.constant(tyctx, ctx.ctx, i as u64).value;
-
-        let this_shape = ndarray.instance.gep(ctx, |f| f.shape).load(tyctx, ctx, "this_shape");
-        let this_ndims = ndarray.instance.gep(ctx, |f| f.ndims).load(tyctx, ctx, "this_ndims");
-
-        let shape_entry = shape_entries.offset(tyctx, ctx, i, "shape_entry");
-        shape_entry.gep(ctx, |f| f.shape).store(ctx, this_shape);
-        shape_entry.gep(ctx, |f| f.ndims).store(ctx, this_ndims);
-    }
-
-    // Prepare destination
-    let dst_ndims = sizet_model.constant(tyctx, ctx.ctx, broadcast_ndims);
-    let dst_shape = sizet_model.array_alloca(tyctx, ctx, dst_ndims.value, "dst_shape");
-
-    call_nac3_ndarray_broadcast_shapes(
-        generator,
-        ctx,
-        num_shape_entries,
-        shape_entries,
-        dst_ndims,
-        dst_shape,
-    );
-
-    // Now that we know about the broadcasting shape, broadcast all the inputs.
-
-    // Broadcast all the inputs to shape `dst_shape`
-    let broadcasted_ndarrays = ndarrays
-        .into_iter()
-        .map(|ndarray| ndarray.broadcast_to(generator, ctx, broadcast_ndims_ty, dst_shape))
-        .collect_vec();
-
-    BroadcastAllResult { ndims: broadcast_ndims, shape: dst_shape, ndarrays: broadcasted_ndarrays }
-}
-
-impl<'ctx> NDArrayObject<'ctx> {
-    /// Broadcast an ndarray to a target shape.
-    #[must_use]
-    pub fn broadcast_to<G: CodeGenerator + ?Sized>(
-        &self,
-        generator: &mut G,
-        ctx: &mut CodeGenContext<'ctx, '_>,
-        target_ndims_ty: Type,
-        target_shape: Ptr<'ctx, IntModel<SizeT>>,
-    ) -> Self {
-        // Please see comment in IRRT on how the caller should prepare `dst_ndarray`
-        let dst_ndarray = NDArrayObject::alloca(
-            generator,
-            ctx,
-            target_ndims_ty,
-            self.dtype,
-            "broadcast_ndarray_to_dst",
-        );
-        dst_ndarray.copy_shape(generator, ctx, target_shape);
-        call_nac3_ndarray_broadcast_to(generator, ctx, self.instance, dst_ndarray.instance);
-        dst_ndarray
-    }
-}

nac3core/src/codegen/numpy_new/factory.rs

@@ -1,217 +0,0 @@
-use inkwell::{
-    types::BasicType,
-    values::{BasicValue, BasicValueEnum, PointerValue},
-    AddressSpace,
-};
-use nac3parser::ast::StrRef;
-
-use crate::{
-    codegen::{
-        model::*,
-        numpy_new::util::{alloca_ndarray, init_ndarray_data_by_alloca, init_ndarray_shape},
-        structure::ndarray::NpArray,
-        util::shape::make_shape_writer,
-        CodeGenContext, CodeGenerator,
-    },
-    symbol_resolver::ValueEnum,
-    toplevel::DefinitionId,
-    typecheck::typedef::{FunSignature, Type},
-};
-
-use super::util::gen_foreach_ndarray_elements;
-
-/// Helper function to create an ndarray with uninitialized values
-///
-/// * `elem_ty` - The [`Type`] of the ndarray elements
-/// * `shape` - The user input shape argument
-/// * `shape_ty` - The [`Type`] of the shape argument
-/// * `name` - LLVM IR name of the returned ndarray
-fn create_empty_ndarray<'ctx, G>(
-    generator: &mut G,
-    ctx: &mut CodeGenContext<'ctx, '_>,
-    elem_ty: Type,
-    shape: BasicValueEnum<'ctx>,
-    shape_ty: Type,
-    name: &str,
-) -> Result<Ptr<'ctx, StructModel<NpArray>>, String>
-where
-    G: CodeGenerator + ?Sized,
-{
-    let tyctx = generator.type_context(ctx.ctx);
-    let sizet_model = IntModel(SizeT);
-
-    let shape_writer = make_shape_writer(generator, ctx, shape, shape_ty);
-    let ndims = shape_writer.len;
-
-    let ndarray = alloca_ndarray(generator, ctx, ndims, name);
-    init_ndarray_shape(generator, ctx, ndarray, &shape_writer)?;
-
-    let itemsize = ctx.get_llvm_type(generator, elem_ty).size_of().unwrap();
-    let itemsize = sizet_model.check_value(tyctx, ctx.ctx, itemsize).unwrap();
-    ndarray.gep(ctx, |f| f.itemsize).store(ctx, itemsize);
-
-    // Needs `itemsize` and `shape` initialized
-    init_ndarray_data_by_alloca(generator, ctx, ndarray);
-
-    Ok(ndarray)
-}
-
-/// Helper function to create an ndarray full of a value.
-///
-/// * `elem_ty` - The [`Type`] of the ndarray elements and the fill value
-/// * `shape` - The user input shape argument
-/// * `shape_ty` - The [`Type`] of the shape argument
-/// * `fill_value` - The user specified fill value
-/// * `name` - LLVM IR name of the returned ndarray
-fn create_full_ndarray<'ctx, G>(
-    generator: &mut G,
-    ctx: &mut CodeGenContext<'ctx, '_>,
-    elem_ty: Type,
-    shape: BasicValueEnum<'ctx>,
-    shape_ty: Type,
-    fill_value: BasicValueEnum<'ctx>,
-    name: &str,
-) -> Result<Ptr<'ctx, StructModel<NpArray>>, String>
-where
-    G: CodeGenerator + ?Sized,
-{
-    let pndarray = create_empty_ndarray(generator, ctx, elem_ty, shape, shape_ty, name)?;
-    gen_foreach_ndarray_elements(
-        generator,
-        ctx,
-        pndarray,
-        |_generator, ctx, _hooks, _i, pelement| {
-            // Cannot use Model here, fill_value's type is not statically known.
-            let pfill_value_ty = fill_value.get_type().ptr_type(AddressSpace::default());
-            let pelement =
-                ctx.builder.build_pointer_cast(pelement.value, pfill_value_ty, "pelement").unwrap();
-            ctx.builder.build_store(pelement, fill_value).unwrap();
-            Ok(())
-        },
-    )?;
-    Ok(pndarray)
-}
-
-/// Generates LLVM IR for `np.empty`.
-pub fn gen_ndarray_empty<'ctx>(
-    context: &mut CodeGenContext<'ctx, '_>,
-    obj: &Option<(Type, ValueEnum<'ctx>)>,
-    fun: (&FunSignature, DefinitionId),
-    args: &[(Option<StrRef>, ValueEnum<'ctx>)],
-    generator: &mut dyn CodeGenerator,
-) -> Result<PointerValue<'ctx>, String> {
-    assert!(obj.is_none());
-    assert_eq!(args.len(), 1);
-
-    // Parse arguments
-    let shape_ty = fun.0.args[0].ty;
-    let shape = args[0].1.clone().to_basic_value_enum(context, generator, shape_ty)?;
-
-    // Implementation
-    let ndarray_ptr = create_empty_ndarray(
-        generator,
-        context,
-        context.primitives.float,
-        shape,
-        shape_ty,
-        "ndarray",
-    )?;
-    Ok(ndarray_ptr.value)
-}
-
-/// Generates LLVM IR for `np.zeros`.
-pub fn gen_ndarray_zeros<'ctx>(
-    context: &mut CodeGenContext<'ctx, '_>,
-    obj: &Option<(Type, ValueEnum<'ctx>)>,
-    fun: (&FunSignature, DefinitionId),
-    args: &[(Option<StrRef>, ValueEnum<'ctx>)],
-    generator: &mut dyn CodeGenerator,
-) -> Result<PointerValue<'ctx>, String> {
-    assert!(obj.is_none());
-    assert_eq!(args.len(), 1);
-
-    // Parse arguments
-    let shape_ty = fun.0.args[0].ty;
-    let shape = args[0].1.clone().to_basic_value_enum(context, generator, shape_ty)?;
-
-    // Implementation
-    // NOTE: Currently nac3's `np.zeros` is always `float64`.
-    let float64_ty = context.primitives.float;
-    let float64_llvm_type = context.get_llvm_type(generator, float64_ty).into_float_type();
-
-    let ndarray_ptr = create_full_ndarray(
-        generator,
-        context,
-        float64_ty, // `elem_ty` is always `float64`
-        shape,
-        shape_ty,
-        float64_llvm_type.const_zero().as_basic_value_enum(),
-        "ndarray",
-    )?;
-    Ok(ndarray_ptr.value)
-}
-
-/// Generates LLVM IR for `np.ones`.
-pub fn gen_ndarray_ones<'ctx>(
-    context: &mut CodeGenContext<'ctx, '_>,
-    obj: &Option<(Type, ValueEnum<'ctx>)>,
-    fun: (&FunSignature, DefinitionId),
-    args: &[(Option<StrRef>, ValueEnum<'ctx>)],
-    generator: &mut dyn CodeGenerator,
-) -> Result<PointerValue<'ctx>, String> {
-    assert!(obj.is_none());
-    assert_eq!(args.len(), 1);
-
-    // Parse arguments
-    let shape_ty = fun.0.args[0].ty;
-    let shape = args[0].1.clone().to_basic_value_enum(context, generator, shape_ty)?;
-
-    // Implementation
-    // NOTE: Currently nac3's `np.ones` is always `float64`.
-    let float64_ty = context.primitives.float;
-    let float64_llvm_type = context.get_llvm_type(generator, float64_ty).into_float_type();
-
-    let ndarray_ptr = create_full_ndarray(
-        generator,
-        context,
-        float64_ty, // `elem_ty` is always `float64`
-        shape,
-        shape_ty,
-        float64_llvm_type.const_float(1.0).as_basic_value_enum(),
-        "ndarray",
-    )?;
-    Ok(ndarray_ptr.value)
-}
-
-/// Generates LLVM IR for `np.full`.
-pub fn gen_ndarray_full<'ctx>(
-    context: &mut CodeGenContext<'ctx, '_>,
-    obj: &Option<(Type, ValueEnum<'ctx>)>,
-    fun: (&FunSignature, DefinitionId),
-    args: &[(Option<StrRef>, ValueEnum<'ctx>)],
-    generator: &mut dyn CodeGenerator,
-) -> Result<PointerValue<'ctx>, String> {
-    assert!(obj.is_none());
-    assert_eq!(args.len(), 2);
-
-    // Parse argument #1 shape
-    let shape_ty = fun.0.args[0].ty;
-    let shape_arg = args[0].1.clone().to_basic_value_enum(context, generator, shape_ty)?;
-
-    // Parse argument #2 fill_value
-    let fill_value_ty = fun.0.args[1].ty;
-    let fill_value_arg =
-        args[1].1.clone().to_basic_value_enum(context, generator, fill_value_ty)?;
-
-    // Implementation
-    let ndarray_ptr = create_full_ndarray(
-        generator,
-        context,
-        fill_value_ty,
-        shape_arg,
-        shape_ty,
-        fill_value_arg,
-        "ndarray",
-    )?;
-    Ok(ndarray_ptr.value)
-}

nac3core/src/codegen/numpy_new/indexing.rs

@@ -1,76 +0,0 @@
-use crate::{
-    codegen::{
-        irrt::ndarray::indexing::{call_nac3_ndarray_index, RustNDIndex},
-        model::*,
-        CodeGenContext, CodeGenerator,
-    },
-    typecheck::typedef::{Type, Unifier},
-};
-
-use super::{
-    object::{NDArrayObject, ScalarObject, ScalarOrNDArray},
-    util::{create_ndims, extract_ndims},
-};
-
-impl<'ctx> NDArrayObject<'ctx> {
-    pub fn deduce_ndims_after_indexing_with(
-        &self,
-        unifier: &mut Unifier,
-        indexes: &[RustNDIndex<'ctx>],
-    ) -> Type {
-        let ndims = extract_ndims(unifier, self.ndims);
-        let new_ndims = RustNDIndex::deduce_ndims_after_indexing(indexes, ndims);
-        create_ndims(unifier, new_ndims)
-    }
-
-    #[must_use]
-    pub fn index_always_ndarray<G: CodeGenerator + ?Sized>(
-        &self,
-        generator: &mut G,
-        ctx: &mut CodeGenContext<'ctx, '_>,
-        indexes: &[RustNDIndex<'ctx>],
-        name: &str,
-    ) -> Self {
-        let tyctx = generator.type_context(ctx.ctx);
-
-        let dst_ndims = self.deduce_ndims_after_indexing_with(&mut ctx.unifier, indexes);
-        let dst_ndarray = NDArrayObject::alloca(generator, ctx, dst_ndims, self.dtype, name);
-
-        let (num_indexes, indexes) = RustNDIndex::alloca_ndindexes(tyctx, ctx, indexes);
-        call_nac3_ndarray_index(
-            generator,
-            ctx,
-            num_indexes,
-            indexes,
-            self.instance,
-            dst_ndarray.instance,
-        );
-
-        dst_ndarray
-    }
-
-    pub fn index<G: CodeGenerator + ?Sized>(
-        &self,
-        generator: &mut G,
-        ctx: &mut CodeGenContext<'ctx, '_>,
-        indexes: &[RustNDIndex<'ctx>],
-        name: &str,
-    ) -> ScalarOrNDArray<'ctx> {
-        let tyctx = generator.type_context(ctx.ctx);
-        let sizet_model = IntModel(SizeT);
-
-        let subndarray = self.index_always_ndarray(generator, ctx, indexes, name);
-        if subndarray.is_unsized(&ctx.unifier) {
-            // TODO: This actually never fails, don't use the `checked_` version.
-            let value = subndarray.checked_get_nth_element(
-                generator,
-                ctx,
-                sizet_model.const_0(tyctx, ctx.ctx),
-                name,
-            );
-            ScalarOrNDArray::Scalar(ScalarObject { dtype: self.dtype, value })
-        } else {
-            ScalarOrNDArray::NDArray(subndarray)
-        }
-    }
-}

nac3core/src/codegen/numpy_new/mod.rs

@@ -1,6 +0,0 @@
-pub mod broadcast;
-pub mod factory;
-pub mod indexing;
-pub mod object;
-pub mod util;
-pub mod view;

nac3core/src/codegen/numpy_new/object.rs

@@ -1,69 +0,0 @@
-use inkwell::values::{BasicValue, BasicValueEnum};
-
-use crate::{
-    codegen::{model::*, structure::ndarray::NpArray, CodeGenContext},
-    toplevel::numpy::unpack_ndarray_var_tys,
-    typecheck::typedef::{Type, TypeEnum},
-};
-
-/// An LLVM ndarray instance with its typechecker [`Type`]s.
-#[derive(Debug, Clone, Copy)]
-pub struct NDArrayObject<'ctx> {
-    pub dtype: Type,
-    pub ndims: Type,
-    pub instance: Ptr<'ctx, StructModel<NpArray>>,
-}
-
-/// An LLVM numpy scalar with its [`Type`].
-#[derive(Debug, Clone, Copy)]
-pub struct ScalarObject<'ctx> {
-    pub dtype: Type,
-    pub value: BasicValueEnum<'ctx>,
-}
-
-#[derive(Debug, Clone, Copy)]
-pub enum ScalarOrNDArray<'ctx> {
-    Scalar(ScalarObject<'ctx>),
-    NDArray(NDArrayObject<'ctx>),
-}
-
-impl<'ctx> ScalarOrNDArray<'ctx> {
-    /// Get the underlying [`BasicValueEnum<'ctx>`] of this [`ScalarOrNDArray`].
-    #[must_use]
-    pub fn to_basic_value_enum(self) -> BasicValueEnum<'ctx> {
-        match self {
-            ScalarOrNDArray::Scalar(scalar) => scalar.value,
-            ScalarOrNDArray::NDArray(ndarray) => ndarray.instance.value.as_basic_value_enum(),
-        }
-    }
-}
-
-impl<'ctx> From<ScalarOrNDArray<'ctx>> for BasicValueEnum<'ctx> {
-    fn from(input: ScalarOrNDArray<'ctx>) -> BasicValueEnum<'ctx> {
-        input.to_basic_value_enum()
-    }
-}
-
-/// Split an [`BasicValueEnum<'ctx>`] into a [`ScalarOrNDArray`] depending
-/// on its [`Type`].
-pub fn split_scalar_or_ndarray<'ctx>(
-    tyctx: TypeContext<'ctx>,
-    ctx: &mut CodeGenContext<'ctx, '_>,
-    input: BasicValueEnum<'ctx>,
-    input_ty: Type,
-) -> ScalarOrNDArray<'ctx> {
-    let pndarray_model = PtrModel(StructModel(NpArray));
-
-    let input_ty_enum = ctx.unifier.get_ty(input_ty);
-    match &*input_ty_enum {
-        TypeEnum::TObj { obj_id, .. }
-            if *obj_id == ctx.primitives.ndarray.obj_id(&ctx.unifier).unwrap() =>
-        {
-            let value = pndarray_model.check_value(tyctx, ctx.ctx, input).unwrap();
-            let (dtype, ndims) = unpack_ndarray_var_tys(&mut ctx.unifier, input_ty);
-
-            ScalarOrNDArray::NDArray(NDArrayObject { dtype, ndims, instance: value })
-        }
-        _ => ScalarOrNDArray::Scalar(ScalarObject { dtype: input_ty, value: input }),
-    }
-}

nac3core/src/codegen/numpy_new/util.rs

@@ -1,328 +0,0 @@
-use inkwell::{
-    types::BasicType,
-    values::{BasicValueEnum, PointerValue},
-    AddressSpace,
-};
-use util::gen_model_memcpy;
-
-use crate::{
-    codegen::{
-        irrt::ndarray::basic::{
-            call_nac3_ndarray_copy_data, call_nac3_ndarray_get_nth_pelement,
-            call_nac3_ndarray_is_c_contiguous, call_nac3_ndarray_nbytes,
-            call_nac3_ndarray_set_strides_by_shape, call_nac3_ndarray_size,
-            call_nac3_ndarray_util_assert_shape_no_negative,
-        },
-        model::*,
-        stmt::BreakContinueHooks,
-        structure::ndarray::NpArray,
-        util::{array_writer::ArrayWriter, control::gen_model_for},
-        CodeGenContext, CodeGenerator,
-    },
-    symbol_resolver::SymbolValue,
-    typecheck::typedef::{Type, TypeEnum, Unifier},
-};
-
-use super::object::{NDArrayObject, ScalarOrNDArray};
-
-/// Extract an ndarray's `ndims` [type][`Type`] in `u64`. Panic if not possible.
-#[must_use]
-pub fn extract_ndims(unifier: &Unifier, ndims_ty: Type) -> u64 {
-    let ndims_ty_enum = unifier.get_ty_immutable(ndims_ty);
-    let TypeEnum::TLiteral { values, .. } = &*ndims_ty_enum else {
-        panic!("ndims_ty should be a TLiteral");
-    };
-
-    assert_eq!(values.len(), 1, "ndims_ty TLiteral should only contain 1 value");
-
-    let ndims = values[0].clone();
-    u64::try_from(ndims).unwrap()
-}
-
-/// Return an ndarray's `ndims` as a typechecker [`Type`] from its `u64` value.
-pub fn create_ndims(unifier: &mut Unifier, ndims: u64) -> Type {
-    unifier.get_fresh_literal(vec![SymbolValue::U64(ndims)], None)
-}
-
-/// Allocate an ndarray on the stack given its `ndims`.
-///
-/// `shape` and `strides` will be automatically allocated on the stack.
-///
-/// The returned ndarray's content will be:
-/// - `data`: `nullptr`
-/// - `itemsize`: **uninitialized** value
-/// - `ndims`: initialized value, set to the input `ndims`
-/// - `shape`: initialized pointer to an allocated stack with **uninitialized** values
-/// - `strides`: initialized pointer to an allocated stack with **uninitialized** values
-pub fn alloca_ndarray<'ctx, G>(
-    generator: &mut G,
-    ctx: &mut CodeGenContext<'ctx, '_>,
-    ndims: Int<'ctx, SizeT>,
-    name: &str,
-) -> Ptr<'ctx, StructModel<NpArray>>
-where
-    G: CodeGenerator + ?Sized,
-{
-    let tyctx = generator.type_context(ctx.ctx);
-
-    let sizet_model = IntModel(SizeT);
-    let ndarray_model = StructModel(NpArray);
-    let ndarray_data_model = PtrModel(IntModel(Byte));
-
-    // Setup ndarray
-    let ndarray_ptr = ndarray_model.alloca(tyctx, ctx, name);
-    let shape = sizet_model.array_alloca(tyctx, ctx, ndims.value, "shape");
-    let strides = sizet_model.array_alloca(tyctx, ctx, ndims.value, "strides");
-
-    ndarray_ptr.gep(ctx, |f| f.data).store(ctx, ndarray_data_model.nullptr(tyctx, ctx.ctx));
-    ndarray_ptr.gep(ctx, |f| f.ndims).store(ctx, ndims);
-    ndarray_ptr.gep(ctx, |f| f.shape).store(ctx, shape);
-    ndarray_ptr.gep(ctx, |f| f.strides).store(ctx, strides);
-
-    ndarray_ptr
-}
-
-/// Initialize an ndarray's `shape` and asserts on.
-/// `shape`'s values and prohibit illegal inputs like negative dimensions.
-pub fn init_ndarray_shape<'ctx, G: CodeGenerator + ?Sized>(
-    generator: &mut G,
-    ctx: &mut CodeGenContext<'ctx, '_>,
-    pndarray: Ptr<'ctx, StructModel<NpArray>>,
-    shape_writer: &ArrayWriter<'ctx, G, SizeT, IntModel<SizeT>>,
-) -> Result<(), String> {
-    let tyctx = generator.type_context(ctx.ctx);
-    let shape = pndarray.gep(ctx, |f| f.shape).load(tyctx, ctx, "shape");
-    (shape_writer.write)(generator, ctx, shape)?;
-    call_nac3_ndarray_util_assert_shape_no_negative(generator, ctx, shape_writer.len, shape);
-    Ok(())
-}
-
-/// Initialize an ndarray's `data` by allocating a buffer on the stack.
-/// The allocated data buffer is considered to be *owned* by the ndarray.
-///
-/// `strides` of the ndarray will also be updated with `set_strides_by_shape`.
-///
-/// `shape` and `itemsize` of the ndarray ***must*** be initialized first.
-pub fn init_ndarray_data_by_alloca<'ctx, G: CodeGenerator + ?Sized>(
-    generator: &mut G,
-    ctx: &mut CodeGenContext<'ctx, '_>,
-    pndarray: Ptr<'ctx, StructModel<NpArray>>,
-) {
-    let tyctx = generator.type_context(ctx.ctx);
-    let ndarray_data_model = IntModel(Byte);
-
-    let nbytes = call_nac3_ndarray_nbytes(generator, ctx, pndarray);
-    let data = ndarray_data_model.array_alloca(tyctx, ctx, nbytes.value, "data");
-    pndarray.gep(ctx, |f| f.data).store(ctx, data);
-    call_nac3_ndarray_set_strides_by_shape(generator, ctx, pndarray);
-}
-
-/// Iterate through all elements in an ndarray.
-///
-/// `body` is given the index of an element and an opaque pointer (as an `uint8_t*`, you might want to cast it) to the element.
-///
-/// Short-circuiting is possible with the given [`BreakContinueHooks`].
-pub fn gen_foreach_ndarray_elements<'ctx, G, F>(
-    generator: &mut G,
-    ctx: &mut CodeGenContext<'ctx, '_>,
-    pndarray: Ptr<'ctx, StructModel<NpArray>>,
-    body: F,
-) -> Result<(), String>
-where
-    G: CodeGenerator + ?Sized,
-    F: Fn(
-        &mut G,
-        &mut CodeGenContext<'ctx, '_>,
-        BreakContinueHooks<'ctx>,
-        Int<'ctx, SizeT>,
-        Ptr<'ctx, IntModel<Byte>>,
-    ) -> Result<(), String>,
-{
-    // TODO: Make this more efficient - use a special NDArray iterator?
-
-    let tyctx = generator.type_context(ctx.ctx);
-
-    let sizet_model = IntModel(SizeT);
-    let size = call_nac3_ndarray_size(generator, ctx, pndarray);
-
-    gen_model_for(
-        generator,
-        ctx,
-        sizet_model.const_0(tyctx, ctx.ctx),
-        size,
-        sizet_model.const_1(tyctx, ctx.ctx),
-        |generator, ctx, hooks, index| {
-            let pelement = call_nac3_ndarray_get_nth_pelement(generator, ctx, pndarray, index);
-            body(generator, ctx, hooks, index, pelement)
-        },
-    )
-}
-
-impl<'ctx> ScalarOrNDArray<'ctx> {
-    /// Convert `input` to an ndarray - behaves like `np.asarray`.
-    pub fn as_ndarray<G: CodeGenerator + ?Sized>(
-        &self,
-        generator: &mut G,
-        ctx: &mut CodeGenContext<'ctx, '_>,
-    ) -> NDArrayObject<'ctx> {
-        match self {
-            ScalarOrNDArray::NDArray(ndarray) => *ndarray,
-            ScalarOrNDArray::Scalar(scalar) => {
-                let tyctx = generator.type_context(ctx.ctx);
-                let pbyte_model = PtrModel(IntModel(Byte));
-
-                // We have to put the value on the stack to get a data pointer.
-                let data =
-                    ctx.builder.build_alloca(scalar.value.get_type(), "as_ndarray_scalar").unwrap();
-                ctx.builder.build_store(data, scalar.value).unwrap();
-                let data = pbyte_model.transmute(tyctx, ctx, data, "data");
-
-                let ndims_ty = create_ndims(&mut ctx.unifier, 0);
-                let ndarray = NDArrayObject::alloca(
-                    generator,
-                    ctx,
-                    ndims_ty,
-                    scalar.dtype,
-                    "scalar_as_ndarray",
-                );
-                ndarray.instance.gep(ctx, |f| f.data).store(ctx, data);
-
-                // No need to initialize/setup strides or shapes - because `ndims` is 0.
-                // So we only have to set `data`, `itemsize`, and `ndims = 0`.
-
-                ndarray
-            }
-        }
-    }
-}
-
-impl<'ctx> NDArrayObject<'ctx> {
-    pub fn alloca<G: CodeGenerator + ?Sized>(
-        generator: &mut G,
-        ctx: &mut CodeGenContext<'ctx, '_>,
-        ndims: Type,
-        dtype: Type,
-        name: &str,
-    ) -> Self {
-        let tyctx = generator.type_context(ctx.ctx);
-        let sizet_model = IntModel(SizeT);
-
-        let ndims_int = sizet_model.constant(tyctx, ctx.ctx, extract_ndims(&ctx.unifier, ndims));
-        let instance = alloca_ndarray(generator, ctx, ndims_int, name);
-
-        // Set itemsize
-        let dtype_ty = ctx.get_llvm_type(generator, dtype);
-        let itemsize = dtype_ty.size_of().unwrap();
-        let itemsize = sizet_model.s_extend_or_bit_cast(tyctx, ctx, itemsize, "itemsize");
-        instance.gep(ctx, |f| f.itemsize).store(ctx, itemsize);
-
-        NDArrayObject { dtype, ndims, instance }
-    }
-
-    pub fn copy_shape<G: CodeGenerator + ?Sized>(
-        &self,
-        generator: &mut G,
-        ctx: &mut CodeGenContext<'ctx, '_>,
-        src_shape: Ptr<'ctx, IntModel<SizeT>>,
-    ) {
-        let tyctx = generator.type_context(ctx.ctx);
-        let sizet_model = IntModel(SizeT);
-
-        let self_shape = self.instance.gep(ctx, |f| f.shape).load(tyctx, ctx, "self_shape");
-        let ndims_int =
-            sizet_model.constant(tyctx, ctx.ctx, extract_ndims(&ctx.unifier, self.ndims));
-        gen_model_memcpy(tyctx, ctx, self_shape, src_shape, ndims_int.value, false);
-    }
-
-    pub fn copy_shape_from<G: CodeGenerator + ?Sized>(
-        &self,
-        generator: &mut G,
-        ctx: &mut CodeGenContext<'ctx, '_>,
-        src_ndarray: NDArrayObject<'ctx>,
-    ) {
-        let tyctx = generator.type_context(ctx.ctx);
-        let src_shape = src_ndarray.instance.gep(ctx, |f| f.shape).load(tyctx, ctx, "src_shape");
-        self.copy_shape(generator, ctx, src_shape);
-    }
-
-    pub fn update_strides_by_shape<G: CodeGenerator + ?Sized>(
-        &self,
-        generator: &mut G,
-        ctx: &mut CodeGenContext<'ctx, '_>,
-    ) {
-        call_nac3_ndarray_set_strides_by_shape(generator, ctx, self.instance);
-    }
-
-    pub fn checked_get_nth_pelement<G: CodeGenerator + ?Sized>(
-        &self,
-        generator: &mut G,
-        ctx: &mut CodeGenContext<'ctx, '_>,
-        i: Int<'ctx, SizeT>,
-        name: &str,
-    ) -> PointerValue<'ctx> {
-        let elem_ty = ctx.get_llvm_type(generator, self.dtype);
-
-        let p = call_nac3_ndarray_get_nth_pelement(generator, ctx, self.instance, i);
-        ctx.builder
-            .build_pointer_cast(p.value, elem_ty.ptr_type(AddressSpace::default()), name)
-            .unwrap()
-    }
-
-    pub fn checked_get_nth_element<G: CodeGenerator + ?Sized>(
-        &self,
-        generator: &mut G,
-        ctx: &mut CodeGenContext<'ctx, '_>,
-        i: Int<'ctx, SizeT>,
-        name: &str,
-    ) -> BasicValueEnum<'ctx> {
-        let pelement = self.checked_get_nth_pelement(generator, ctx, i, "pelement");
-        ctx.builder.build_load(pelement, name).unwrap()
-    }
-
-    #[must_use]
-    pub fn is_unsized(&self, unifier: &Unifier) -> bool {
-        extract_ndims(unifier, self.ndims) == 0
-    }
-
-    pub fn size<G: CodeGenerator + ?Sized>(
-        &self,
-        generator: &mut G,
-        ctx: &mut CodeGenContext<'ctx, '_>,
-    ) -> Int<'ctx, SizeT> {
-        call_nac3_ndarray_size(generator, ctx, self.instance)
-    }
-
-    pub fn nbytes<G: CodeGenerator + ?Sized>(
-        &self,
-        generator: &mut G,
-        ctx: &mut CodeGenContext<'ctx, '_>,
-    ) -> Int<'ctx, SizeT> {
-        call_nac3_ndarray_nbytes(generator, ctx, self.instance)
-    }
-
-    pub fn is_c_contiguous<G: CodeGenerator + ?Sized>(
-        &self,
-        generator: &mut G,
-        ctx: &mut CodeGenContext<'ctx, '_>,
-    ) -> Int<'ctx, Bool> {
-        call_nac3_ndarray_is_c_contiguous(generator, ctx, self.instance)
-    }
-
-    pub fn alloca_owned_data<G: CodeGenerator + ?Sized>(
-        &self,
-        generator: &mut G,
-        ctx: &mut CodeGenContext<'ctx, '_>,
-    ) {
-        init_ndarray_data_by_alloca(generator, ctx, self.instance);
-    }
-
-    pub fn copy_data_from<G: CodeGenerator + ?Sized>(
-        &self,
-        generator: &mut G,
-        ctx: &mut CodeGenContext<'ctx, '_>,
-        src: NDArrayObject<'ctx>,
-    ) {
-        assert!(ctx.unifier.unioned(self.dtype, src.dtype), "self and src dtype should match");
-        call_nac3_ndarray_copy_data(generator, ctx, src.instance, self.instance);
-    }
-}

nac3core/src/codegen/numpy_new/view.rs

@@ -1,114 +0,0 @@
-use inkwell::values::PointerValue;
-use nac3parser::ast::StrRef;
-
-use crate::{
-    codegen::{
-        irrt::ndarray::reshape::call_nac3_ndarray_resolve_and_check_new_shape,
-        model::*,
-        numpy_new::{object::split_scalar_or_ndarray, util::extract_ndims},
-        util::shape::make_shape_writer,
-        CodeGenContext, CodeGenerator,
-    },
-    symbol_resolver::ValueEnum,
-    toplevel::{numpy::unpack_ndarray_var_tys, DefinitionId},
-    typecheck::typedef::{FunSignature, Type},
-};
-
-use super::object::NDArrayObject;
-
-impl<'ctx> NDArrayObject<'ctx> {
-    #[must_use]
-    pub fn reshape_or_copy<G: CodeGenerator + ?Sized>(
-        &self,
-        generator: &mut G,
-        ctx: &mut CodeGenContext<'ctx, '_>,
-        new_ndims: Type,
-        new_shape: Ptr<'ctx, IntModel<SizeT>>,
-    ) -> Self {
-        let tyctx = generator.type_context(ctx.ctx);
-
-        let current_bb = ctx.builder.get_insert_block().unwrap();
-        let then_bb = ctx.ctx.insert_basic_block_after(current_bb, "then_bb");
-        let else_bb = ctx.ctx.insert_basic_block_after(then_bb, "else_bb");
-        let end_bb = ctx.ctx.insert_basic_block_after(else_bb, "end_bb");
-
-        let dst_ndarray =
-            NDArrayObject::alloca(generator, ctx, new_ndims, self.dtype, "reshaped_ndarray");
-        dst_ndarray.copy_shape(generator, ctx, new_shape);
-        dst_ndarray.update_strides_by_shape(generator, ctx);
-
-        let is_c_contiguous = self.is_c_contiguous(generator, ctx);
-        ctx.builder.build_conditional_branch(is_c_contiguous.value, then_bb, else_bb).unwrap();
-
-        // Inserting into then_bb: reshape is possible without copying
-        ctx.builder.position_at_end(then_bb);
-        dst_ndarray
-            .instance
-            .gep(ctx, |f| f.data)
-            .store(ctx, dst_ndarray.instance.gep(ctx, |f| f.data).load(tyctx, ctx, "data"));
-        ctx.builder.build_unconditional_branch(end_bb).unwrap();
-
-        // Inserting into else_bb: reshape is impossible without copying
-        ctx.builder.position_at_end(else_bb);
-        dst_ndarray.alloca_owned_data(generator, ctx);
-        dst_ndarray.copy_data_from(generator, ctx, *self);
-        ctx.builder.build_unconditional_branch(end_bb).unwrap();
-
-        // Reposition for continuation
-        ctx.builder.position_at_end(end_bb);
-
-        dst_ndarray
-    }
-}
-
-/// Generates LLVM IR for `np.reshape`.
-pub fn gen_ndarray_reshape<'ctx>(
-    ctx: &mut CodeGenContext<'ctx, '_>,
-    obj: &Option<(Type, ValueEnum<'ctx>)>,
-    fun: (&FunSignature, DefinitionId),
-    args: &[(Option<StrRef>, ValueEnum<'ctx>)],
-    generator: &mut dyn CodeGenerator,
-) -> Result<PointerValue<'ctx>, String> {
-    assert!(obj.is_none());
-    assert_eq!(args.len(), 2);
-
-    // Parse argument #1 input
-    let input_ty = fun.0.args[0].ty;
-    let input_arg = args[0].1.clone().to_basic_value_enum(ctx, generator, input_ty)?;
-
-    // Parse argument #2 shape
-    let shape_ty = fun.0.args[1].ty;
-    let shape_arg = args[1].1.clone().to_basic_value_enum(ctx, generator, shape_ty)?;
-
-    // Define models
-    let tyctx = generator.type_context(ctx.ctx);
-    let sizet_model = IntModel(SizeT);
-
-    // Extract reshaped_ndims
-    let (_, reshaped_ndims) = unpack_ndarray_var_tys(&mut ctx.unifier, fun.0.ret);
-    let reshaped_ndims_int = extract_ndims(&ctx.unifier, reshaped_ndims);
-
-    // Process `input`
-    let ndarray =
-        split_scalar_or_ndarray(tyctx, ctx, input_arg, input_ty).as_ndarray(generator, ctx);
-
-    // Process the shape input from user and resolve negative indices
-    let new_shape = make_shape_writer(generator, ctx, shape_arg, shape_ty).alloca_array_and_write(
-        generator,
-        ctx,
-        "new_shape",
-    )?;
-    let size = ndarray.size(generator, ctx);
-    call_nac3_ndarray_resolve_and_check_new_shape(
-        generator,
-        ctx,
-        size,
-        sizet_model.constant(tyctx, ctx.ctx, reshaped_ndims_int),
-        new_shape,
-    );
-
-    // Reshape
-    let reshaped_ndarray = ndarray.reshape_or_copy(generator, ctx, reshaped_ndims, new_shape);
-
-    Ok(reshaped_ndarray.instance.value)
-}

nac3core/src/codegen/stmt.rs

@@ -1,24 +1,3 @@
-use super::model::*;
-use super::structure::cslice::CSlice;
-use super::{
-    super::symbol_resolver::ValueEnum,
-    expr::destructure_range,
-    irrt::{handle_slice_indices, list_slice_assignment},
-    structure::exception::Exception,
-    CodeGenContext, CodeGenerator, Int32, IntModel, Ptr, StructModel,
-};
-use crate::{
-    codegen::{
-        classes::{ArrayLikeIndexer, ArraySliceValue, ListValue, RangeValue},
-        expr::gen_binop_expr,
-        gen_in_range_check,
-    },
-    toplevel::{helper::PrimDef, numpy::unpack_ndarray_var_tys, DefinitionId, TopLevelDef},
-    typecheck::{
-        magic_methods::Binop,
-        typedef::{FunSignature, Type, TypeEnum},
-    },
-};
 use inkwell::{
     attributes::{Attribute, AttributeLoc},
     basic_block::BasicBlock,
@@ -26,10 +5,28 @@ use inkwell::{
     values::{BasicValue, BasicValueEnum, FunctionValue, IntValue, PointerValue},
     IntPredicate,
 };
+use itertools::{izip, Itertools};
+
 use nac3parser::ast::{
     Constant, ExcepthandlerKind, Expr, ExprKind, Location, Stmt, StmtKind, StrRef,
 };
-use std::convert::TryFrom;
+
+use super::{
+    expr::{destructure_range, gen_binop_expr},
+    gen_in_range_check,
+    irrt::{handle_slice_indices, list_slice_assignment},
+    macros::codegen_unreachable,
+    values::{ArrayLikeIndexer, ArraySliceValue, ListValue, RangeValue},
+    CodeGenContext, CodeGenerator,
+};
+use crate::{
+    symbol_resolver::ValueEnum,
+    toplevel::{DefinitionId, TopLevelDef},
+    typecheck::{
+        magic_methods::Binop,
+        typedef::{iter_type_vars, FunSignature, Type, TypeEnum},
+    },
+};
 
 /// See [`CodeGenerator::gen_var_alloc`].
 pub fn gen_var<'ctx>(
@@ -100,8 +97,6 @@ pub fn gen_store_target<'ctx, G: CodeGenerator>(
     pattern: &Expr<Option<Type>>,
     name: Option<&str>,
 ) -> Result<Option<PointerValue<'ctx>>, String> {
-    let llvm_usize = generator.get_size_type(ctx.ctx);
-
     // very similar to gen_expr, but we don't do an extra load at the end
     // and we flatten nested tuples
     Ok(Some(match &pattern.node {
@@ -126,7 +121,7 @@ pub fn gen_store_target<'ctx, G: CodeGenerator>(
                 return Ok(None);
             };
             let BasicValueEnum::PointerValue(ptr) = val else {
-                unreachable!();
+                codegen_unreachable!(ctx);
             };
             unsafe {
                 ctx.builder.build_in_bounds_gep(
@@ -140,66 +135,7 @@ pub fn gen_store_target<'ctx, G: CodeGenerator>(
             }
             .unwrap()
         }
-        ExprKind::Subscript { value, slice, .. } => {
+        _ => codegen_unreachable!(ctx),
-            match ctx.unifier.get_ty_immutable(value.custom.unwrap()).as_ref() {
-                TypeEnum::TObj { obj_id, .. } if *obj_id == PrimDef::List.id() => {
-                    let v = generator
-                        .gen_expr(ctx, value)?
-                        .unwrap()
-                        .to_basic_value_enum(ctx, generator, value.custom.unwrap())?
-                        .into_pointer_value();
-                    let v = ListValue::from_ptr_val(v, llvm_usize, None);
-                    let len = v.load_size(ctx, Some("len"));
-                    let raw_index = generator
-                        .gen_expr(ctx, slice)?
-                        .unwrap()
-                        .to_basic_value_enum(ctx, generator, slice.custom.unwrap())?
-                        .into_int_value();
-                    let raw_index = ctx
-                        .builder
-                        .build_int_s_extend(raw_index, generator.get_size_type(ctx.ctx), "sext")
-                        .unwrap();
-                    // handle negative index
-                    let is_negative = ctx
-                        .builder
-                        .build_int_compare(
-                            IntPredicate::SLT,
-                            raw_index,
-                            generator.get_size_type(ctx.ctx).const_zero(),
-                            "is_neg",
-                        )
-                        .unwrap();
-                    let adjusted = ctx.builder.build_int_add(raw_index, len, "adjusted").unwrap();
-                    let index = ctx
-                        .builder
-                        .build_select(is_negative, adjusted, raw_index, "index")
-                        .map(BasicValueEnum::into_int_value)
-                        .unwrap();
-                    // unsigned less than is enough, because negative index after adjustment is
-                    // bigger than the length (for unsigned cmp)
-                    let bound_check = ctx
-                        .builder
-                        .build_int_compare(IntPredicate::ULT, index, len, "inbound")
-                        .unwrap();
-                    ctx.make_assert(
-                        generator,
-                        bound_check,
-                        "0:IndexError",
-                        "index {0} out of bounds 0:{1}",
-                        [Some(raw_index), Some(len), None],
-                        slice.location,
-                    );
-                    v.data().ptr_offset(ctx, generator, &index, name)
-                }
-
-                TypeEnum::TObj { obj_id, .. } if *obj_id == PrimDef::NDArray.id() => {
-                    todo!()
-                }
-
-                _ => unreachable!(),
-            }
-        }
-        _ => unreachable!(),
     }))
 }
 
@@ -211,69 +147,18 @@ pub fn gen_assign<'ctx, G: CodeGenerator>(
     value: ValueEnum<'ctx>,
     value_ty: Type,
 ) -> Result<(), String> {
-    let llvm_usize = generator.get_size_type(ctx.ctx);
+    // See https://docs.python.org/3/reference/simple_stmts.html#assignment-statements.
-
     match &target.node {
-        ExprKind::Tuple { elts, .. } => {
+        ExprKind::Subscript { value: target, slice: key, .. } => {
-            let BasicValueEnum::StructValue(v) =
+            // Handle "slicing" or "subscription"
-                value.to_basic_value_enum(ctx, generator, target.custom.unwrap())?
+            generator.gen_setitem(ctx, target, key, value, value_ty)?;
-            else {
-                unreachable!()
-            };
-
-            for (i, elt) in elts.iter().enumerate() {
-                let v = ctx
-                    .builder
-                    .build_extract_value(v, u32::try_from(i).unwrap(), "struct_elem")
-                    .unwrap();
-                generator.gen_assign(ctx, elt, v.into(), value_ty)?;
         }
-        }
+        ExprKind::Tuple { elts, .. } | ExprKind::List { elts, .. } => {
-        ExprKind::Subscript { value: ls, slice, .. }
+            // Fold on `"[" [target_list] "]"` and `"(" [target_list] ")"`
-            if matches!(&slice.node, ExprKind::Slice { .. }) =>
+            generator.gen_assign_target_list(ctx, elts, value, value_ty)?;
-        {
-            let ExprKind::Slice { lower, upper, step } = &slice.node else { unreachable!() };
-
-            let ls = generator
-                .gen_expr(ctx, ls)?
-                .unwrap()
-                .to_basic_value_enum(ctx, generator, ls.custom.unwrap())?
-                .into_pointer_value();
-            let ls = ListValue::from_ptr_val(ls, llvm_usize, None);
-            let Some((start, end, step)) =
-                handle_slice_indices(lower, upper, step, ctx, generator, ls.load_size(ctx, None))?
-            else {
-                return Ok(());
-            };
-            let value = value
-                .to_basic_value_enum(ctx, generator, target.custom.unwrap())?
-                .into_pointer_value();
-            let value = ListValue::from_ptr_val(value, llvm_usize, None);
-            let ty = match &*ctx.unifier.get_ty_immutable(target.custom.unwrap()) {
-                TypeEnum::TObj { obj_id, params, .. } if *obj_id == PrimDef::List.id() => {
-                    *params.iter().next().unwrap().1
-                }
-                TypeEnum::TObj { obj_id, .. } if *obj_id == PrimDef::NDArray.id() => {
-                    unpack_ndarray_var_tys(&mut ctx.unifier, target.custom.unwrap()).0
-                }
-                _ => unreachable!(),
-            };
-
-            let ty = ctx.get_llvm_type(generator, ty);
-            let Some(src_ind) = handle_slice_indices(
-                &None,
-                &None,
-                &None,
-                ctx,
-                generator,
-                value.load_size(ctx, None),
-            )?
-            else {
-                return Ok(());
-            };
-            list_slice_assignment(generator, ctx, ty, ls, (start, end, step), value, src_ind);
         }
         _ => {
+            // Handle attribute and direct variable assignments.
             let name = if let ExprKind::Name { id, .. } = &target.node {
                 format!("{id}.addr")
             } else {
@@ -291,19 +176,259 @@ pub fn gen_assign<'ctx, G: CodeGenerator>(
                 }
             }
             let val = value.to_basic_value_enum(ctx, generator, target.custom.unwrap())?;
+
+            // Perform i1 <-> i8 conversion as needed
+            let val = if ctx.unifier.unioned(target.custom.unwrap(), ctx.primitives.bool) {
+                generator.bool_to_i8(ctx, val.into_int_value()).into()
+            } else {
+                val
+            };
+
             ctx.builder.build_store(ptr, val).unwrap();
         }
     };
     Ok(())
 }
 
+/// See [`CodeGenerator::gen_assign_target_list`].
+pub fn gen_assign_target_list<'ctx, G: CodeGenerator>(
+    generator: &mut G,
+    ctx: &mut CodeGenContext<'ctx, '_>,
+    targets: &Vec<Expr<Option<Type>>>,
+    value: ValueEnum<'ctx>,
+    value_ty: Type,
+) -> Result<(), String> {
+    // Deconstruct the tuple `value`
+    let BasicValueEnum::StructValue(tuple) = value.to_basic_value_enum(ctx, generator, value_ty)?
+    else {
+        codegen_unreachable!(ctx)
+    };
+
+    // NOTE: Currently, RHS's type is forced to be a Tuple by the type inferencer.
+    let TypeEnum::TTuple { ty: tuple_tys, .. } = &*ctx.unifier.get_ty(value_ty) else {
+        codegen_unreachable!(ctx);
+    };
+
+    assert_eq!(tuple.get_type().count_fields() as usize, tuple_tys.len());
+
+    let tuple = (0..tuple.get_type().count_fields())
+        .map(|i| ctx.builder.build_extract_value(tuple, i, "item").unwrap())
+        .collect_vec();
+
+    // Find the starred target if it exists.
+    let mut starred_target_index: Option<usize> = None; // Index of the "starred" target. If it exists, there may only be one.
+    for (i, target) in targets.iter().enumerate() {
+        if matches!(target.node, ExprKind::Starred { .. }) {
+            assert!(starred_target_index.is_none()); // The typechecker ensures this
+            starred_target_index = Some(i);
+        }
+    }
+
+    if let Some(starred_target_index) = starred_target_index {
+        assert!(tuple_tys.len() >= targets.len() - 1); // The typechecker ensures this
+
+        let a = starred_target_index; // Number of RHS values before the starred target
+        let b = tuple_tys.len() - (targets.len() - 1 - starred_target_index); // Number of RHS values after the starred target
+                                                                              // Thus `tuple[a..b]` is assigned to the starred target.
+
+        // Handle assignment before the starred target
+        for (target, val, val_ty) in
+            izip!(&targets[..starred_target_index], &tuple[..a], &tuple_tys[..a])
+        {
+            generator.gen_assign(ctx, target, ValueEnum::Dynamic(*val), *val_ty)?;
+        }
+
+        // Handle assignment to the starred target
+        if let ExprKind::Starred { value: target, .. } = &targets[starred_target_index].node {
+            let vals = &tuple[a..b];
+            let val_tys = &tuple_tys[a..b];
+
+            // Create a sub-tuple from `value` for the starred target.
+            let sub_tuple_ty = ctx
+                .ctx
+                .struct_type(&vals.iter().map(BasicValueEnum::get_type).collect_vec(), false);
+            let psub_tuple_val =
+                ctx.builder.build_alloca(sub_tuple_ty, "starred_target_value_ptr").unwrap();
+            for (i, val) in vals.iter().enumerate() {
+                let pitem = ctx
+                    .builder
+                    .build_struct_gep(psub_tuple_val, i as u32, "starred_target_value_item")
+                    .unwrap();
+                ctx.builder.build_store(pitem, *val).unwrap();
+            }
+            let sub_tuple_val =
+                ctx.builder.build_load(psub_tuple_val, "starred_target_value").unwrap();
+
+            // Create the typechecker type of the sub-tuple
+            let sub_tuple_ty =
+                ctx.unifier.add_ty(TypeEnum::TTuple { ty: val_tys.to_vec(), is_vararg_ctx: false });
+
+            // Now assign with that sub-tuple to the starred target.
+            generator.gen_assign(ctx, target, ValueEnum::Dynamic(sub_tuple_val), sub_tuple_ty)?;
+        } else {
+            codegen_unreachable!(ctx) // The typechecker ensures this
+        }
+
+        // Handle assignment after the starred target
+        for (target, val, val_ty) in
+            izip!(&targets[starred_target_index + 1..], &tuple[b..], &tuple_tys[b..])
+        {
+            generator.gen_assign(ctx, target, ValueEnum::Dynamic(*val), *val_ty)?;
+        }
+    } else {
+        assert_eq!(tuple_tys.len(), targets.len()); // The typechecker ensures this
+
+        for (target, val, val_ty) in izip!(targets, tuple, tuple_tys) {
+            generator.gen_assign(ctx, target, ValueEnum::Dynamic(val), *val_ty)?;
+        }
+    }
+    Ok(())
+}
+
+/// See [`CodeGenerator::gen_setitem`].
+pub fn gen_setitem<'ctx, G: CodeGenerator>(
+    generator: &mut G,
+    ctx: &mut CodeGenContext<'ctx, '_>,
+    target: &Expr<Option<Type>>,
+    key: &Expr<Option<Type>>,
+    value: ValueEnum<'ctx>,
+    value_ty: Type,
+) -> Result<(), String> {
+    let target_ty = target.custom.unwrap();
+    let key_ty = key.custom.unwrap();
+
+    match &*ctx.unifier.get_ty(target_ty) {
+        TypeEnum::TObj { obj_id, params: list_params, .. }
+            if *obj_id == ctx.primitives.list.obj_id(&ctx.unifier).unwrap() =>
+        {
+            // Handle list item assignment
+            let llvm_usize = generator.get_size_type(ctx.ctx);
+            let target_item_ty = iter_type_vars(list_params).next().unwrap().ty;
+
+            let target = generator
+                .gen_expr(ctx, target)?
+                .unwrap()
+                .to_basic_value_enum(ctx, generator, target_ty)?
+                .into_pointer_value();
+            let target = ListValue::from_pointer_value(target, llvm_usize, None);
+
+            if let ExprKind::Slice { .. } = &key.node {
+                // Handle assigning to a slice
+                let ExprKind::Slice { lower, upper, step } = &key.node else {
+                    codegen_unreachable!(ctx)
+                };
+                let Some((start, end, step)) = handle_slice_indices(
+                    lower,
+                    upper,
+                    step,
+                    ctx,
+                    generator,
+                    target.load_size(ctx, None),
+                )?
+                else {
+                    return Ok(());
+                };
+
+                let value =
+                    value.to_basic_value_enum(ctx, generator, value_ty)?.into_pointer_value();
+                let value = ListValue::from_pointer_value(value, llvm_usize, None);
+
+                let target_item_ty = ctx.get_llvm_type(generator, target_item_ty);
+                let Some(src_ind) = handle_slice_indices(
+                    &None,
+                    &None,
+                    &None,
+                    ctx,
+                    generator,
+                    value.load_size(ctx, None),
+                )?
+                else {
+                    return Ok(());
+                };
+                list_slice_assignment(
+                    generator,
+                    ctx,
+                    target_item_ty,
+                    target,
+                    (start, end, step),
+                    value,
+                    src_ind,
+                );
+            } else {
+                // Handle assigning to an index
+                let len = target.load_size(ctx, Some("len"));
+
+                let index = generator
+                    .gen_expr(ctx, key)?
+                    .unwrap()
+                    .to_basic_value_enum(ctx, generator, key_ty)?
+                    .into_int_value();
+                let index = ctx
+                    .builder
+                    .build_int_s_extend(index, generator.get_size_type(ctx.ctx), "sext")
+                    .unwrap();
+
+                // handle negative index
+                let is_negative = ctx
+                    .builder
+                    .build_int_compare(
+                        IntPredicate::SLT,
+                        index,
+                        generator.get_size_type(ctx.ctx).const_zero(),
+                        "is_neg",
+                    )
+                    .unwrap();
+                let adjusted = ctx.builder.build_int_add(index, len, "adjusted").unwrap();
+                let index = ctx
+                    .builder
+                    .build_select(is_negative, adjusted, index, "index")
+                    .map(BasicValueEnum::into_int_value)
+                    .unwrap();
+
+                // unsigned less than is enough, because negative index after adjustment is
+                // bigger than the length (for unsigned cmp)
+                let bound_check = ctx
+                    .builder
+                    .build_int_compare(IntPredicate::ULT, index, len, "inbound")
+                    .unwrap();
+                ctx.make_assert(
+                    generator,
+                    bound_check,
+                    "0:IndexError",
+                    "index {0} out of bounds 0:{1}",
+                    [Some(index), Some(len), None],
+                    key.location,
+                );
+
+                // Write value to index on list
+                let item_ptr =
+                    target.data().ptr_offset(ctx, generator, &index, Some("list_item_ptr"));
+                let value = value.to_basic_value_enum(ctx, generator, value_ty)?;
+                ctx.builder.build_store(item_ptr, value).unwrap();
+            }
+        }
+        TypeEnum::TObj { obj_id, .. }
+            if *obj_id == ctx.primitives.ndarray.obj_id(&ctx.unifier).unwrap() =>
+        {
+            // Handle NDArray item assignment
+            todo!("ndarray subscript assignment is not yet implemented");
+        }
+        _ => {
+            panic!("encountered unknown target type: {}", ctx.unifier.stringify(target_ty));
+        }
+    }
+    Ok(())
+}
+
 /// See [`CodeGenerator::gen_for`].
 pub fn gen_for<G: CodeGenerator>(
     generator: &mut G,
     ctx: &mut CodeGenContext<'_, '_>,
     stmt: &Stmt<Option<Type>>,
 ) -> Result<(), String> {
-    let StmtKind::For { iter, target, body, orelse, .. } = &stmt.node else { unreachable!() };
+    let StmtKind::For { iter, target, body, orelse, .. } = &stmt.node else {
+        codegen_unreachable!(ctx)
+    };
 
     // var_assignment static values may be changed in another branch
     // if so, remove the static value as it may not be correct in this branch
@@ -319,9 +444,6 @@ pub fn gen_for<G: CodeGenerator>(
     let orelse_bb =
         if orelse.is_empty() { cont_bb } else { ctx.ctx.append_basic_block(current, "for.orelse") };
 
-    // Whether the iterable is a range() expression
-    let is_iterable_range_expr = ctx.unifier.unioned(iter.custom.unwrap(), ctx.primitives.range);
-
     // The BB containing the increment expression
     let incr_bb = ctx.ctx.append_basic_block(current, "for.incr");
     // The BB containing the loop condition check
@@ -330,27 +452,36 @@ pub fn gen_for<G: CodeGenerator>(
     // store loop bb information and restore it later
     let loop_bb = ctx.loop_target.replace((incr_bb, cont_bb));
 
+    let iter_ty = iter.custom.unwrap();
     let iter_val = if let Some(v) = generator.gen_expr(ctx, iter)? {
-        v.to_basic_value_enum(ctx, generator, iter.custom.unwrap())?
+        v.to_basic_value_enum(ctx, generator, iter_ty)?
     } else {
         return Ok(());
     };
-    if is_iterable_range_expr {
+
-        let iter_val = RangeValue::from_ptr_val(iter_val.into_pointer_value(), Some("range"));
+    match &*ctx.unifier.get_ty(iter_ty) {
+        TypeEnum::TObj { obj_id, .. }
+            if *obj_id == ctx.primitives.range.obj_id(&ctx.unifier).unwrap() =>
+        {
+            let iter_val =
+                RangeValue::from_pointer_value(iter_val.into_pointer_value(), Some("range"));
             // Internal variable for loop; Cannot be assigned
             let i = generator.gen_var_alloc(ctx, int32.into(), Some("for.i.addr"))?;
             // Variable declared in "target" expression of the loop; Can be reassigned *or* shadowed
-        let Some(target_i) = generator.gen_store_target(ctx, target, Some("for.target.addr"))?
+            let Some(target_i) =
+                generator.gen_store_target(ctx, target, Some("for.target.addr"))?
             else {
-            unreachable!()
+                codegen_unreachable!(ctx)
             };
             let (start, stop, step) = destructure_range(ctx, iter_val);
 
             ctx.builder.build_store(i, start).unwrap();
 
             // Check "If step is zero, ValueError is raised."
-        let rangenez =
+            let rangenez = ctx
-            ctx.builder.build_int_compare(IntPredicate::NE, step, int32.const_zero(), "").unwrap();
+                .builder
+                .build_int_compare(IntPredicate::NE, step, int32.const_zero(), "")
+                .unwrap();
             ctx.make_assert(
                 generator,
                 rangenez,
@@ -367,7 +498,10 @@ pub fn gen_for<G: CodeGenerator>(
                     .build_conditional_branch(
                         gen_in_range_check(
                             ctx,
-                        ctx.builder.build_load(i, "").map(BasicValueEnum::into_int_value).unwrap(),
+                            ctx.builder
+                                .build_load(i, "")
+                                .map(BasicValueEnum::into_int_value)
+                                .unwrap(),
                             stop,
                             step,
                         ),
@@ -397,7 +531,10 @@ pub fn gen_for<G: CodeGenerator>(
                 )
                 .unwrap();
             generator.gen_block(ctx, body.iter())?;
-    } else {
+        }
+        TypeEnum::TObj { obj_id, params: list_params, .. }
+            if *obj_id == ctx.primitives.list.obj_id(&ctx.unifier).unwrap() =>
+        {
             let index_addr = generator.gen_var_alloc(ctx, size_t.into(), Some("for.index.addr"))?;
             ctx.builder.build_store(index_addr, size_t.const_zero()).unwrap();
             let len = ctx
@@ -435,9 +572,14 @@ pub fn gen_for<G: CodeGenerator>(
                 .map(BasicValueEnum::into_int_value)
                 .unwrap();
             let val = ctx.build_gep_and_load(arr_ptr, &[index], Some("val"));
-        generator.gen_assign(ctx, target, val.into(), ctx.primitives.int32)?;
+            let val_ty = iter_type_vars(list_params).next().unwrap().ty;
+            generator.gen_assign(ctx, target, val.into(), val_ty)?;
             generator.gen_block(ctx, body.iter())?;
         }
+        _ => {
+            panic!("unsupported for loop iterator type: {}", ctx.unifier.stringify(iter_ty));
+        }
+    }
 
     for (k, (_, _, counter)) in &var_assignment {
         let (_, static_val, counter2) = ctx.var_assignment.get_mut(k).unwrap();
@@ -674,7 +816,7 @@ where
     BodyFn: FnOnce(
         &mut G,
         &mut CodeGenContext<'ctx, 'a>,
-        BreakContinueHooks,
+        BreakContinueHooks<'ctx>,
         IntValue<'ctx>,
     ) -> Result<(), String>,
 {
@@ -772,7 +914,7 @@ pub fn gen_while<G: CodeGenerator>(
     ctx: &mut CodeGenContext<'_, '_>,
     stmt: &Stmt<Option<Type>>,
 ) -> Result<(), String> {
-    let StmtKind::While { test, body, orelse, .. } = &stmt.node else { unreachable!() };
+    let StmtKind::While { test, body, orelse, .. } = &stmt.node else { codegen_unreachable!(ctx) };
 
     // var_assignment static values may be changed in another branch
     // if so, remove the static value as it may not be correct in this branch
@@ -802,7 +944,7 @@ pub fn gen_while<G: CodeGenerator>(
 
         return Ok(());
     };
-    let BasicValueEnum::IntValue(test) = test else { unreachable!() };
+    let BasicValueEnum::IntValue(test) = test else { codegen_unreachable!(ctx) };
 
     ctx.builder
         .build_conditional_branch(generator.bool_to_i1(ctx, test), body_bb, orelse_bb)
@@ -950,7 +1092,7 @@ pub fn gen_if<G: CodeGenerator>(
     ctx: &mut CodeGenContext<'_, '_>,
     stmt: &Stmt<Option<Type>>,
 ) -> Result<(), String> {
-    let StmtKind::If { test, body, orelse, .. } = &stmt.node else { unreachable!() };
+    let StmtKind::If { test, body, orelse, .. } = &stmt.node else { codegen_unreachable!(ctx) };
 
     // var_assignment static values may be changed in another branch
     // if so, remove the static value as it may not be correct in this branch
@@ -1073,11 +1215,11 @@ pub fn exn_constructor<'ctx>(
     let zelf_id = if let TypeEnum::TObj { obj_id, .. } = &*ctx.unifier.get_ty(zelf_ty) {
         obj_id.0
     } else {
-        unreachable!()
+        codegen_unreachable!(ctx)
     };
     let defs = ctx.top_level.definitions.read();
     let def = defs[zelf_id].read();
-    let TopLevelDef::Class { name: zelf_name, .. } = &*def else { unreachable!() };
+    let TopLevelDef::Class { name: zelf_name, .. } = &*def else { codegen_unreachable!(ctx) };
     let exception_name = format!("{}:{}", ctx.resolver.get_exception_id(zelf_id), zelf_name);
     unsafe {
         let id_ptr = ctx.builder.build_in_bounds_gep(zelf, &[zero, zero], "exn.id").unwrap();
@@ -1134,37 +1276,47 @@ pub fn exn_constructor<'ctx>(
 pub fn gen_raise<'ctx, G: CodeGenerator + ?Sized>(
     generator: &mut G,
     ctx: &mut CodeGenContext<'ctx, '_>,
-    exception: Option<Ptr<'ctx, StructModel<Exception>>>,
+    exception: Option<&BasicValueEnum<'ctx>>,
     loc: Location,
 ) {
-    if let Some(pexn) = exception {
+    if let Some(exception) = exception {
-        let type_context = generator.type_context(ctx.ctx);
+        unsafe {
-        let i32_model = IntModel(Int32);
+            let int32 = ctx.ctx.i32_type();
-        let cslice_model = StructModel(CSlice);
+            let zero = int32.const_zero();
+            let exception = exception.into_pointer_value();
+            let file_ptr = ctx
+                .builder
+                .build_in_bounds_gep(exception, &[zero, int32.const_int(1, false)], "file_ptr")
+                .unwrap();
+            let filename = ctx.gen_string(generator, loc.file.0);
+            ctx.builder.build_store(file_ptr, filename).unwrap();
+            let row_ptr = ctx
+                .builder
+                .build_in_bounds_gep(exception, &[zero, int32.const_int(2, false)], "row_ptr")
+                .unwrap();
+            ctx.builder.build_store(row_ptr, int32.const_int(loc.row as u64, false)).unwrap();
+            let col_ptr = ctx
+                .builder
+                .build_in_bounds_gep(exception, &[zero, int32.const_int(3, false)], "col_ptr")
+                .unwrap();
+            ctx.builder.build_store(col_ptr, int32.const_int(loc.column as u64, false)).unwrap();
 
-        // Get and store filename
+            let current_fun = ctx.builder.get_insert_block().unwrap().get_parent().unwrap();
-        let filename = loc.file.0;
+            let fun_name = ctx.gen_string(generator, current_fun.get_name().to_str().unwrap());
-        let filename = ctx.gen_string(generator, &String::from(filename)).value;
+            let name_ptr = ctx
-        let filename = cslice_model.check_value(type_context, ctx.ctx, filename).unwrap();
+                .builder
-        pexn.gep(ctx, |f| f.filename).store(ctx, filename);
+                .build_in_bounds_gep(exception, &[zero, int32.const_int(4, false)], "name_ptr")
-
+                .unwrap();
-        let row = i32_model.constant(type_context, ctx.ctx, loc.row as u64);
+            ctx.builder.build_store(name_ptr, fun_name).unwrap();
-        pexn.gep(ctx, |f| f.line).store(ctx, row);
+        }
-
-        let column = i32_model.constant(type_context, ctx.ctx, loc.column as u64);
-        pexn.gep(ctx, |f| f.column).store(ctx, column);
-
-        let current_fn = ctx.builder.get_insert_block().unwrap().get_parent().unwrap();
-        let fn_name = ctx.gen_string(generator, current_fn.get_name().to_str().unwrap());
-        pexn.gep(ctx, |f| f.function).store(ctx, fn_name);
 
         let raise = get_builtins(generator, ctx, "__nac3_raise");
-        ctx.build_call_or_invoke(raise, &[pexn.value.into()], "raise");
+        let exception = *exception;
+        ctx.build_call_or_invoke(raise, &[exception], "raise");
     } else {
         let resume = get_builtins(generator, ctx, "__nac3_resume");
         ctx.build_call_or_invoke(resume, &[], "resume");
     }
-
     ctx.builder.build_unreachable().unwrap();
 }
 
@@ -1175,7 +1327,7 @@ pub fn gen_try<'ctx, 'a, G: CodeGenerator>(
     target: &Stmt<Option<Type>>,
 ) -> Result<(), String> {
     let StmtKind::Try { body, handlers, orelse, finalbody, .. } = &target.node else {
-        unreachable!()
+        codegen_unreachable!(ctx)
     };
 
     // if we need to generate anything related to exception, we must have personality defined
@@ -1252,7 +1404,7 @@ pub fn gen_try<'ctx, 'a, G: CodeGenerator>(
             if let TypeEnum::TObj { obj_id, .. } = &*ctx.unifier.get_ty(type_.custom.unwrap()) {
                 *obj_id
             } else {
-                unreachable!()
+                codegen_unreachable!(ctx)
             };
         let exception_name = format!("{}:{}", ctx.resolver.get_exception_id(obj_id.0), exn_name);
         let exn_id = ctx.resolver.get_string_id(&exception_name);
@@ -1524,6 +1676,23 @@ pub fn gen_return<G: CodeGenerator>(
     } else {
         None
     };
+
+    // Remap boolean return type into i1
+    let value = value.map(|ret_val| {
+        // The "return type" of a sret function is in the first parameter
+        let expected_ty = if ctx.need_sret {
+            func.get_type().get_param_types()[0]
+        } else {
+            func.get_type().get_return_type().unwrap()
+        };
+
+        if matches!(expected_ty, BasicTypeEnum::IntType(ty) if ty.get_bit_width() == 1) {
+            generator.bool_to_i1(ctx, ret_val.into_int_value()).into()
+        } else {
+            ret_val
+        }
+    });
+
     if let Some(return_target) = ctx.return_target {
         if let Some(value) = value {
             ctx.builder.build_store(ctx.return_buffer.unwrap(), value).unwrap();
@@ -1534,25 +1703,6 @@ pub fn gen_return<G: CodeGenerator>(
         ctx.builder.build_store(ctx.return_buffer.unwrap(), value.unwrap()).unwrap();
         ctx.builder.build_return(None).unwrap();
     } else {
-        // Remap boolean return type into i1
-        let value = value.map(|v| {
-            let expected_ty = func.get_type().get_return_type().unwrap();
-            let ret_val = v.as_basic_value_enum();
-
-            if expected_ty.is_int_type() && ret_val.is_int_value() {
-                let ret_type = expected_ty.into_int_type();
-                let ret_val = ret_val.into_int_value();
-
-                if ret_type.get_bit_width() == 1 && ret_val.get_type().get_bit_width() != 1 {
-                    generator.bool_to_i1(ctx, ret_val)
-                } else {
-                    ret_val
-                }
-                .into()
-            } else {
-                ret_val
-            }
-        });
         let value = value.as_ref().map(|v| v as &dyn BasicValue);
         ctx.builder.build_return(value).unwrap();
     }
@@ -1586,16 +1736,14 @@ pub fn gen_stmt<G: CodeGenerator>(
         }
         StmtKind::AnnAssign { target, value, .. } => {
             if let Some(value) = value {
-                let value_ty = value.custom.unwrap();
+                let Some(value_enum) = generator.gen_expr(ctx, value)? else { return Ok(()) };
-                let Some(value) = generator.gen_expr(ctx, value)? else { return Ok(()) };
+                generator.gen_assign(ctx, target, value_enum, value.custom.unwrap())?;
-                generator.gen_assign(ctx, target, value, value_ty)?;
             }
         }
         StmtKind::Assign { targets, value, .. } => {
-            let value_ty = value.custom.unwrap();
+            let Some(value_enum) = generator.gen_expr(ctx, value)? else { return Ok(()) };
-            let Some(value) = generator.gen_expr(ctx, value)? else { return Ok(()) };
             for target in targets {
-                generator.gen_assign(ctx, target, value.clone(), value_ty)?;
+                generator.gen_assign(ctx, target, value_enum.clone(), value.custom.unwrap())?;
             }
         }
         StmtKind::Continue { .. } => {
@@ -1609,68 +1757,109 @@ pub fn gen_stmt<G: CodeGenerator>(
         StmtKind::For { .. } => generator.gen_for(ctx, stmt)?,
         StmtKind::With { .. } => generator.gen_with(ctx, stmt)?,
         StmtKind::AugAssign { target, op, value, .. } => {
-            let value_ty = value.custom.unwrap();
+            let value_enum = gen_binop_expr(
-            let value = gen_binop_expr(
                 generator,
                 ctx,
                 target,
                 Binop::aug_assign(*op),
                 value,
                 stmt.location,
-            )?;
+            )?
-            generator.gen_assign(ctx, target, value.unwrap(), value_ty)?;
+            .unwrap();
+            generator.gen_assign(ctx, target, value_enum, value.custom.unwrap())?;
         }
         StmtKind::Try { .. } => gen_try(generator, ctx, stmt)?,
         StmtKind::Raise { exc, .. } => {
             if let Some(exc) = exc {
-                let exc = if let Some(v) = generator.gen_expr(ctx, exc)? {
+                let exn = if let ExprKind::Name { id, .. } = &exc.node {
+                    // Handle "raise Exception" short form
+                    let def_id = ctx.resolver.get_identifier_def(*id).map_err(|e| {
+                        format!("{} (at {})", e.iter().next().unwrap(), exc.location)
+                    })?;
+                    let def = ctx.top_level.definitions.read();
+                    let TopLevelDef::Class { constructor, .. } = *def[def_id.0].read() else {
+                        return Err(format!("Failed to resolve symbol {id} (at {})", exc.location));
+                    };
+
+                    let TypeEnum::TFunc(signature) =
+                        ctx.unifier.get_ty(constructor.unwrap()).as_ref().clone()
+                    else {
+                        return Err(format!("Failed to resolve symbol {id} (at {})", exc.location));
+                    };
+
+                    generator
+                        .gen_call(ctx, None, (&signature, def_id), Vec::default())?
+                        .map(Into::into)
+                } else {
+                    generator.gen_expr(ctx, exc)?
+                };
+
+                let exc = if let Some(v) = exn {
                     v.to_basic_value_enum(ctx, generator, exc.custom.unwrap())?
                 } else {
                     return Ok(());
                 };
-
+                gen_raise(generator, ctx, Some(&exc), stmt.location);
-                let type_context = generator.type_context(ctx.ctx);
-                let pexn_model = PtrModel(StructModel(Exception));
-                let exn = pexn_model.check_value(type_context, ctx.ctx, exc).unwrap();
-
-                gen_raise(generator, ctx, Some(exn), stmt.location);
             } else {
                 gen_raise(generator, ctx, None, stmt.location);
             }
         }
         StmtKind::Assert { test, msg, .. } => {
-            let type_context = generator.type_context(ctx.ctx);
+            let test = if let Some(v) = generator.gen_expr(ctx, test)? {
-            let byte_model = IntModel(Byte);
+                v.to_basic_value_enum(ctx, generator, test.custom.unwrap())?
-            let cslice_model = StructModel(CSlice);
+            } else {
-
-            let Some(test) = generator.gen_expr(ctx, test)? else {
                 return Ok(());
             };
-            let test = test.to_basic_value_enum(ctx, generator, ctx.primitives.bool)?;
-            let test = byte_model.check_value(type_context, ctx.ctx, test).unwrap(); // Python `bool` is represented as `i8` in nac3core
-
-            // Check `msg`
             let err_msg = match msg {
                 Some(msg) => {
-                    let Some(msg) = generator.gen_expr(ctx, msg)? else {
+                    if let Some(v) = generator.gen_expr(ctx, msg)? {
+                        v.to_basic_value_enum(ctx, generator, msg.custom.unwrap())?
+                    } else {
                         return Ok(());
-                    };
-
-                    let msg = msg.to_basic_value_enum(ctx, generator, ctx.primitives.str)?;
-                    cslice_model.check_value(type_context, ctx.ctx, msg).unwrap()
                     }
-                None => ctx.gen_string(generator, ""),
+                }
+                None => ctx.gen_string(generator, "").into(),
             };
-
             ctx.make_assert_impl(
                 generator,
-                test.value,
+                generator.bool_to_i1(ctx, test.into_int_value()),
                 "0:AssertionError",
                 err_msg,
                 [None, None, None],
                 stmt.location,
             );
         }
+        StmtKind::Global { names, .. } => {
+            let registered_globals = ctx
+                .top_level
+                .definitions
+                .read()
+                .iter()
+                .filter_map(|def| {
+                    if let TopLevelDef::Variable { simple_name, ty, .. } = &*def.read() {
+                        Some((*simple_name, *ty))
+                    } else {
+                        None
+                    }
+                })
+                .collect_vec();
+
+            for id in names {
+                let Some((_, ty)) = registered_globals.iter().find(|(name, _)| name == id) else {
+                    return Err(format!("{id} is not a global at {}", stmt.location));
+                };
+
+                let resolver = ctx.resolver.clone();
+                let ptr = resolver
+                    .get_symbol_value(*id, ctx, generator)
+                    .map(|val| val.to_basic_value_enum(ctx, generator, *ty))
+                    .transpose()?
+                    .map(BasicValueEnum::into_pointer_value)
+                    .unwrap();
+
+                ctx.var_assignment.insert(*id, (ptr, None, 0));
+            }
+        }
         _ => unimplemented!(),
     };
     Ok(())

nac3core/src/codegen/structure/cslice.rs

@@ -1,43 +0,0 @@
-use crate::codegen::{model::*, CodeGenContext};
-
-/// Fields of [`CSlice<'ctx>`].
-pub struct CSliceFields<F: FieldVisitor> {
-    /// Pointer to the data.
-    pub base: F::Field<PtrModel<IntModel<Byte>>>,
-    /// Number of bytes of the data.
-    pub len: F::Field<IntModel<SizeT>>,
-}
-
-/// See <https://crates.io/crates/cslice>.
-///
-/// Additionally, see <https://github.com/m-labs/artiq/blob/b0d2705c385f64b6e6711c1726cd9178f40b598e/artiq/firmware/libeh/eh_artiq.rs>)
-/// for ARTIQ-specific notes.
-#[derive(Debug, Clone, Copy, Default)]
-pub struct CSlice;
-
-impl StructKind for CSlice {
-    type Fields<F: FieldVisitor> = CSliceFields<F>;
-
-    fn visit_fields<F: FieldVisitor>(&self, visitor: &mut F) -> Self::Fields<F> {
-        Self::Fields { base: visitor.add("base"), len: visitor.add("len") }
-    }
-}
-
-impl StructModel<CSlice> {
-    /// Create a [`CSlice`].
-    ///
-    /// `base` and `len` must be LLVM global constants.
-    pub fn create_const<'ctx>(
-        &self,
-        type_context: TypeContext<'ctx>,
-        ctx: &CodeGenContext<'ctx, '_>,
-        base: Ptr<'ctx, IntModel<Byte>>,
-        len: Int<'ctx, SizeT>,
-    ) -> Struct<'ctx, CSlice> {
-        let value = self
-            .0
-            .get_struct_type(type_context, ctx.ctx)
-            .const_named_struct(&[base.value.into(), len.value.into()]);
-        self.believe_value(value)
-    }
-}

nac3core/src/codegen/structure/exception.rs

@@ -1,57 +0,0 @@
-use crate::codegen::model::*;
-
-use super::cslice::CSlice;
-
-/// The LLVM int type of an Exception ID.
-pub type ExceptionId = Int32;
-
-/// Fields of [`Exception<'ctx>`]
-///
-/// The definition came from `pub struct Exception<'a>` in
-/// <https://github.com/m-labs/artiq/blob/master/artiq/firmware/libeh/eh_artiq.rs>.
-pub struct ExceptionFields<F: FieldVisitor> {
-    /// nac3core's ID of the exception
-    pub id: F::Field<IntModel<ExceptionId>>,
-    /// The name of the file this `Exception` was raised in.
-    pub filename: F::Field<StructModel<CSlice>>,
-    /// The line number in the file this `Exception` was raised in.
-    pub line: F::Field<IntModel<Int32>>,
-    /// The column number in the file this `Exception` was raised in.
-    pub column: F::Field<IntModel<Int32>>,
-    /// The name of the Python function this `Exception` was raised in.
-    pub function: F::Field<StructModel<CSlice>>,
-    /// The message of this Exception.
-    ///
-    /// The message can optionally contain integer parameters `{0}`, `{1}`, and `{2}` in its string,
-    /// where they will be substituted by `params[0]`, `params[1]`, and `params[2]` respectively (as `int64_t`s).
-    /// Here is an example:
-    ///
-    /// ```ignore
-    /// "Index {0} is out of bounds! List only has {1} element(s)."
-    /// ```
-    ///
-    /// In this case, `params[0]` and `params[1]` must be specified, and `params[2]` is ***unused***.
-    /// Having only 3 parameters is a constraint in ARTIQ.
-    pub msg: F::Field<StructModel<CSlice>>,
-    pub params: [F::Field<IntModel<Int64>>; 3],
-}
-
-/// nac3core & ARTIQ's Exception
-#[derive(Debug, Clone, Copy, Default)]
-pub struct Exception;
-
-impl StructKind for Exception {
-    type Fields<F: FieldVisitor> = ExceptionFields<F>;
-
-    fn visit_fields<F: FieldVisitor>(&self, visitor: &mut F) -> Self::Fields<F> {
-        Self::Fields {
-            id: visitor.add("id"),
-            filename: visitor.add("filename"),
-            line: visitor.add("line"),
-            column: visitor.add("column"),
-            function: visitor.add("function"),
-            msg: visitor.add("msg"),
-            params: [visitor.add("params[0]"), visitor.add("params[1]"), visitor.add("params[2]")],
-        }
-    }
-}