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": 1720418205,
-        "narHash": "sha256-cPJoFPXU44GlhWg4pUk9oUPqurPlCFZ11ZQPk21GTPU=",
+        "lastModified": 1733940404,
+        "narHash": "sha256-Pj39hSoUA86ZePPF/UXiYHHM7hMIkios8TYG29kQT4g=",
         "owner": "NixOS",
         "repo": "nixpkgs",
-        "rev": "655a58a72a6601292512670343087c2d75d859c1",
+        "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 $out/bin/llvm-as-irrt
           '';
+        demo-linalg-stub = pkgs.rustPlatform.buildRustPackage {
+          name = "demo-linalg-stub";
+          src = ./nac3standalone/demo/linalg;
+          cargoLock = {
+            lockFile = ./nac3standalone/demo/linalg/Cargo.lock;
+          };
+          doCheck = false;
+        };
+        demo-linalg-stub32 = pkgs32.rustPlatform.buildRustPackage {
+          name = "demo-linalg-stub32";
+          src = ./nac3standalone/demo/linalg;
+          cargoLock = {
+            lockFile = ./nac3standalone/demo/linalg/Cargo.lock;
+          };
+          doCheck = false;
+        };
         nac3artiq = pkgs.python3Packages.toPythonModule (
           pkgs.rustPlatform.buildRustPackage rec {
             name = "nac3artiq";
@@ -24,9 +40,8 @@
             cargoLock = {
               lockFile = ./Cargo.lock;
             };
-            cargoTestFlags = [ "--features" "test" ];
             passthru.cargoLock = cargoLock;
-            nativeBuildInputs = [ pkgs.python3 pkgs.llvmPackages_14.clang llvm-tools-irrt pkgs.llvmPackages_14.llvm.out llvm-nac3 ];
+            nativeBuildInputs = [ pkgs.python3 (pkgs.wrapClangMulti pkgs.llvmPackages_14.clang) llvm-tools-irrt pkgs.llvmPackages_14.llvm.out llvm-nac3 ];
             buildInputs = [ pkgs.python3 llvm-nac3 ];
             checkInputs = [ (pkgs.python3.withPackages(ps: [ ps.numpy ps.scipy ])) ];
             checkPhase =
@@ -34,7 +49,9 @@
               echo "Checking nac3standalone demos..."
               pushd nac3standalone/demo
               patchShebangs .
-              ./check_demos.sh
+              export DEMO_LINALG_STUB=${demo-linalg-stub}/lib/liblinalg.a
+              export DEMO_LINALG_STUB32=${demo-linalg-stub32}/lib/liblinalg.a
+              ./check_demos.sh -i686
               popd
               echo "Running Cargo tests..."
               cargoCheckHook
@@ -90,18 +107,18 @@
             (pkgs.fetchFromGitHub {
               owner = "m-labs";
               repo = "sipyco";
-              rev = "939f84f9b5eef7efbf7423c735d1834783b6140e";
-              sha256 = "sha256-15Nun4EY35j+6SPZkjzZtyH/ncxLS60KuGJjFh5kSTc=";
+              rev = "094a6cd63ffa980ef63698920170e50dc9ba77fd";
+              sha256 = "sha256-PPnAyDedUQ7Og/Cby9x5OT9wMkNGTP8GS53V6N/dk4w=";
             })
             (pkgs.fetchFromGitHub {
               owner = "m-labs";
               repo = "artiq";
-              rev = "923ca3377d42c815f979983134ec549dc39d3ca0";
-              sha256 = "sha256-oJoEeNEeNFSUyh6jXG8Tzp6qHVikeHS0CzfE+mODPgw=";
+              rev = "28c9de3e251daa89a8c9fd79d5ab64a3ec03bac6";
+              sha256 = "sha256-vAvpbHc5B+1wtG8zqN7j9dQE1ON+i22v+uqA+tw6Gak=";
             })
           ];
           buildInputs = [
-            (python3-mimalloc.withPackages(ps: [ ps.numpy ps.scipy ps.jsonschema ps.lmdb nac3artiq-instrumented ]))
+            (python3-mimalloc.withPackages(ps: [ ps.numpy ps.scipy ps.jsonschema ps.lmdb ps.platformdirs nac3artiq-instrumented ]))
             pkgs.llvmPackages_14.llvm.out
           ];
           phases = [ "buildPhase" "installPhase" ];
@@ -151,7 +168,7 @@
         buildInputs = with pkgs; [
           # build dependencies
           packages.x86_64-linux.llvm-nac3
-          llvmPackages_14.clang llvmPackages_14.llvm.out llvmPackages_14.lldb.out # for running nac3standalone demos
+          (pkgs.wrapClangMulti llvmPackages_14.clang) llvmPackages_14.llvm.out  # for running nac3standalone demos
           packages.x86_64-linux.llvm-tools-irrt
           cargo
           rustc
@@ -163,9 +180,12 @@
           clippy
           pre-commit
           rustfmt
-          rust-analyzer
         ];
-        RUST_SRC_PATH = "${pkgs.rust.packages.stable.rustPlatform.rustLibSrc}";
+        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"
-nac3parser = { path = "../nac3parser" }
+tempfile = "3.13"
 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."""
-    register_function(function)
-    return function
+
+def rpc(arg=None, flags={}):
+    """Decorates a function or method to be executed on the host interpreter."""
+    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(
-    future_incompatible,
-    let_underscore,
-    nonstandard_style,
-    rust_2024_compatibility,
-    clippy::all
-)]
+#![deny(future_incompatible, let_underscore, nonstandard_style, clippy::all)]
 #![warn(clippy::pedantic)]
 #![allow(
     unsafe_op_in_unsafe_fn,
@@ -16,63 +10,65 @@
     clippy::wildcard_imports
 )]
 
-use std::collections::{HashMap, HashSet};
-use std::fs;
-use std::io::Write;
-use std::process::Command;
-use std::rc::Rc;
-use std::sync::Arc;
-
-use inkwell::{
-    memory_buffer::MemoryBuffer,
-    module::{Linkage, Module},
-    passes::PassBuilderOptions,
-    support::is_multithreaded,
-    targets::*,
-    OptimizationLevel,
+use std::{
+    collections::{HashMap, HashSet},
+    fs,
+    io::Write,
+    process::Command,
+    rc::Rc,
+    sync::Arc,
 };
+
 use itertools::Itertools;
-use nac3core::codegen::{gen_func_impl, CodeGenLLVMOptions, CodeGenTargetMachineOptions};
-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},
-        DefinitionId, GenCall, TopLevelDef,
-    },
-    typecheck::typedef::{FunSignature, FuncArg},
-    typecheck::{type_inferencer::PrimitiveStore, typedef::Type},
+use pyo3::{
+    create_exception, exceptions,
+    prelude::*,
+    types::{PyBytes, PyDict, PyNone, PySet},
 };
-
-use nac3ld::Linker;
-
 use tempfile::{self, TempDir};
 
-use crate::codegen::attributes_writeback;
-use crate::{
-    codegen::{rpc_codegen_callback, ArtiqCodeGenerator},
-    symbol_resolver::{DeferredEvaluationStore, InnerResolver, PythonHelper, Resolver},
+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::{FlagBehavior, Linkage, Module},
+        passes::PassBuilderOptions,
+        support::is_multithreaded,
+        targets::*,
+        OptimizationLevel,
+    },
+    nac3parser::{
+        ast::{Constant, ExprKind, Located, Stmt, StmtKind, StrRef},
+        parser::parse_program,
+    },
+    symbol_resolver::SymbolResolver,
+    toplevel::{
+        builtins::get_exn_constructor,
+        composer::{BuiltinFuncCreator, BuiltinFuncSpec, ComposerConfig, TopLevelComposer},
+        DefinitionId, GenCall, TopLevelDef,
+    },
+    typecheck::{
+        type_inferencer::PrimitiveStore,
+        typedef::{into_var_map, FunSignature, FuncArg, Type, TypeEnum, Unifier, VarMap},
+    },
 };
+use nac3ld::Linker;
+
+use codegen::{
+    attributes_writeback, gen_core_log, gen_rtio_log, rpc_codegen_callback, ArtiqCodeGenerator,
+};
+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,
@@ -126,7 +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,
@@ -146,14 +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: &PyAny = module.extract(py)?;
-            Ok((module.getattr("__name__")?.extract()?, module.getattr("__file__")?.extract()?))
-        })?;
+        let (module_name, source_file, source) =
+            Python::with_gil(|py| -> PyResult<(String, String, String)> {
+                let module: &PyAny = module.extract(py)?;
+                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}")))?;
 
@@ -193,10 +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 {
-                                    id.to_string() == "kernel"
-                                        || id.to_string() == "portable"
-                                        || id.to_string() == "rpc"
+                                if let Some(id) = decorator_id_string(decorator) {
+                                    id == "kernel" || id == "portable" || id == "rpc"
                                 } else {
                                     false
                                 }
@@ -209,9 +221,8 @@ impl Nac3 {
                 }
                 StmtKind::FunctionDef { ref decorator_list, .. } => {
                     decorator_list.iter().any(|decorator| {
-                        if let ExprKind::Name { id, .. } = decorator.node {
-                            let id = id.to_string();
-                            id == "extern" || id == "portable" || id == "kernel" || id == "rpc"
+                        if let Some(id) = decorator_id_string(decorator) {
+                            id == "extern" || id == "kernel" || id == "portable" || id == "rpc"
                         } else {
                             false
                         }
@@ -264,7 +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() => {
@@ -300,6 +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,
@@ -312,6 +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,
         );
@@ -388,7 +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(),
@@ -419,9 +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())) {
-                        store_fun.call1(py, (def_id.0.into_py(py), module.getattr(py, name.to_string().as_str()).unwrap())).unwrap();
-                        rpc_ids.push((None, def_id));
+                    if decorator_list
+                        .iter()
+                        .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, .. } => {
@@ -429,19 +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();
@@ -480,13 +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(),
@@ -497,6 +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();
@@ -534,13 +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();
@@ -551,7 +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,
@@ -566,6 +660,11 @@ impl Nac3 {
                             }
                         }
                     }
+                    TopLevelDef::Variable { .. } => {
+                        return Err(CompileError::new_err(String::from(
+                            "Unsupported @rpc annotation on global variable",
+                        )))
+                    }
                 }
             }
         }
@@ -586,33 +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,
         };
 
@@ -625,7 +703,9 @@ impl Nac3 {
             let buffer = buffer.as_slice().into();
             membuffer.lock().push(buffer);
         })));
-        let size_t = if self.isa == Isa::Host { 64 } else { 32 };
+        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 };
         let thread_names: Vec<String> = (0..num_threads).map(|_| "main".to_string()).collect();
         let threads: Vec<_> = thread_names
@@ -634,16 +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 =
-                ArtiqCodeGenerator::new("attributes_writeback".to_string(), size_t, self.time_fns);
-            let context = inkwell::context::Context::create();
-            let module = context.create_module("attributes_writeback");
+            let mut generator = ArtiqCodeGenerator::new("main".to_string(), size_t, self.time_fns);
+            let context = Context::create();
+            let module = context.create_module("main");
+            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,
@@ -651,9 +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();
@@ -662,37 +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();
-        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()))?;
+        main.link_in_module(irrt).map_err(|err| CompileError::new_err(err.to_string()))?;
 
         let mut function_iter = main.get_first_function();
         while let Some(func) = function_iter {
@@ -726,6 +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)
     }
 
@@ -778,6 +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(),
@@ -847,7 +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(),
@@ -863,6 +1008,7 @@ impl Nac3 {
                         name: "t".into(),
                         ty: primitive.int64,
                         default_value: None,
+                        is_vararg: false,
                     }],
                     ret: primitive.none,
                     vars: VarMap::new(),
@@ -882,6 +1028,7 @@ impl Nac3 {
                         name: "dt".into(),
                         ty: primitive.int64,
                         default_value: None,
+                        is_vararg: false,
                     }],
                     ret: primitive.none,
                     vars: VarMap::new(),
@@ -938,6 +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,
@@ -947,7 +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 {
@@ -957,7 +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();
@@ -967,14 +1161,22 @@ impl Nac3 {
                 let getmodule_fn = PyModule::import(py, "inspect")?.getattr("getmodule")?;
 
                 for function in functions {
-                    let module = getmodule_fn.call1((function,))?.extract()?;
-                    modules.insert(id_fn.call1((&module,))?.extract()?, module);
+                    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()?;
-                    modules.insert(id_fn.call1((&module,))?.extract()?, module);
+                    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::{
-    types::{BasicType, BasicTypeEnum},
-    values::BasicValueEnum,
-    AddressSpace,
+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::{
-        classes::{NDArrayType, ProxyType},
+        types::{ndarray::NDArrayType, ProxyType},
+        values::ndarray::make_contiguous_strides,
         CodeGenContext, CodeGenerator,
     },
+    inkwell::{
+        module::Linkage,
+        types::{BasicType, BasicTypeEnum},
+        values::BasicValueEnum,
+        AddressSpace,
+    },
+    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) =
-                unpack_ndarray_var_tys(&mut ctx.unifier, ndarray_ty);
+            let (ndarray_dtype, _) = 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 ndarray_llvm_ty = NDArrayType::new(generator, ctx.ctx, ndarray_dtype_llvm_ty);
+            let llvm_ndarray = NDArrayType::from_unifier_type(generator, ctx, ndarray_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)
-            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")
-            };
+            let ndims = llvm_ndarray.ndims().unwrap();
 
             // Obtain the shape of the ndarray
             let shape_tuple: &PyTuple = obj.getattr("shape")?.downcast()?;
-            assert_eq!(shape_tuple.len(), ndarray_ndims as usize);
-            let shape_values: Result<Option<Vec<_>>, _> = shape_tuple
+            assert_eq!(shape_tuple.len(), ndims as usize);
+
+            // 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(
-                        |e| super::CompileError::new_err(format!("Error getting element {i}: {e}")),
-                    )
+                    let value = self
+                        .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();
-            let shape_values = shape_values?.unwrap();
-            let shape_values = llvm_usize.const_array(
-                &shape_values.into_iter().map(BasicValueEnum::into_int_value).collect_vec(),
-            );
+                .collect::<Result<Vec<_>, PyErr>>()?;
+
+            // Also use this opportunity to get the constant values of `shape_values` for calculating strides.
+            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| {
-                            super::CompileError::new_err(format!("Error getting element {i}: {e}"))
-                        })
+                        let value = self
+                            .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)
                     })
                 })
-                .collect();
-            let data = data?.unwrap().into_iter();
-            let data = match ndarray_dtype_llvm_ty {
+                .try_collect()?;
+            let data = data.into_iter();
+            let data = match dtype {
                 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);
 
-            // 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(),
-                shape_global
-                    .as_pointer_value()
-                    .const_cast(llvm_usize.ptr_type(AddressSpace::default()))
-                    .into(),
-                data_global
-                    .as_pointer_value()
-                    .const_cast(ndarray_dtype_llvm_ty.ptr_type(AddressSpace::default()))
-                    .into(),
-            ]);
+            // Get the constant itemsize.
+            let itemsize = dtype.size_of().unwrap();
+            let itemsize = itemsize.get_zero_extended_constant().unwrap();
 
-            let ndarray = ctx.module.add_global(
-                ndarray_llvm_ty.as_underlying_type(),
+            // 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
+
+            // NOTE: data_global is an array of dtype, we want a `u8*`.
+            let ndarray_data = data_global.as_pointer_value();
+            let ndarray_data = ctx.builder.build_pointer_cast(ndarray_data, llvm_pi8, "").unwrap();
+
+            let ndarray_itemsize = llvm_usize.const_int(itemsize, false);
+
+            let ndarray_ndims = llvm_usize.const_int(ndims, false);
+
+            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_global = ctx.module.add_global(
+                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> {
-                self.0.helper.store_str.call1(py, (s,))?.extract(py)
-            })
-            .unwrap();
+            let id = i32::try_from(string_store.len()).unwrap();
             string_store.insert(s.into(), id);
             id
         }

nac3artiq/src/timeline.rs

@@ -1,9 +1,12 @@
-use inkwell::{
-    values::{BasicValueEnum, CallSiteValue},
-    AddressSpace, AtomicOrdering,
-};
 use itertools::Either;
-use nac3core::codegen::CodeGenContext;
+
+use nac3core::{
+    codegen::CodeGenContext,
+    inkwell::{
+        values::{BasicValueEnum, CallSiteValue},
+        AddressSpace, AtomicOrdering,
+    },
+};
 
 /// 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 ref INTERNER: Mutex<Interner> =
-        Mutex::new(StringInterner::with_hasher(FxBuildHasher::default()));
-}
+static INTERNER: LazyLock<Mutex<Interner>> =
+    LazyLock::new(|| 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(
-    future_incompatible,
-    let_underscore,
-    nonstandard_style,
-    rust_2024_compatibility,
-    clippy::all
-)]
+#![deny(future_incompatible, let_underscore, nonstandard_style, 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_macros = "0.26.4"
+strum = "0.26"
+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";
-const CMD_IRRT_CLANG_TEST: &str = "clang-irrt-test";
-const CMD_IRRT_LLVM_AS: &str = "llvm-as-irrt";
+use regex::Regex;
 
-fn get_out_dir() -> PathBuf {
-    PathBuf::from(env::var("OUT_DIR").unwrap())
-}
+fn main() {
+    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 {
-    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();
+    let irrt_cpp_path = irrt_dir.join("irrt.cpp");
 
     /*
      * 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 flags: &[&str] = &[
+    let mut flags: Vec<&str> = vec![
         "--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
-    // That .bc will be integrated into nac3core's codegen
-    let mut llvm_as = Command::new(CMD_IRRT_LLVM_AS)
+    let mut llvm_as = Command::new("llvm-as-irrt")
         .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_everything.hpp>
-
-/*
- * All IRRT implementations.
- *
- * We don't have pre-compiled objects, so we are writing all implementations in
- * headers and concatenate them with `#include` into one massive source file that
- * contains all the IRRT stuff.
- */
+#include "irrt/exception.hpp"
+#include "irrt/list.hpp"
+#include "irrt/math.hpp"
+#include "irrt/ndarray.hpp"
+#include "irrt/range.hpp"
+#include "irrt/slice.hpp"
+#include "irrt/ndarray/basic.hpp"
+#include "irrt/ndarray/def.hpp"
+#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

@@ -1,94 +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 Error IDs
- */
-struct ErrorIds {
-    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 {
-    /**
-     * @brief The set of all
-     */
-    const ErrorIds *error_ids;
-
-    // Error thrown by IRRT
-    ExceptionId error_id;
-    const char *message_template;
-    uint64_t param1;
-    uint64_t param2;
-    uint64_t param3;
-
-    void initialize(const ErrorIds *error_ids) {
-        this->error_ids = error_ids;
-        clear_error();
-    }
-
-    void clear_error() {
-        // Point the message_template to an empty str. Don't set it to nullptr
-        // as a sentinel
-        this->message_template = "";
-    }
-
-    void set_error(ExceptionId error_id, const char *message,
-                   uint64_t param1 = 0, uint64_t param2 = 0,
-                   uint64_t param3 = 0) {
-        this->error_id = error_id;
-        this->message_template = message;
-        this->param1 = param1;
-        this->param2 = param2;
-        this->param3 = param3;
-    }
-
-    bool has_error() { return !cstr_utils::is_empty(message_template); }
-
-    template <typename SizeT>
-    void get_error_str(CSlice<SizeT> *dst_str) {
-        dst_str->base = message_template;
-        dst_str->len = (SizeT)cstr_utils::length(message_template);
-    }
-};
-}  // namespace
-
-extern "C" {
-void __nac3_error_context_initialize(ErrorContext *errctx,
-                                     ErrorIds *error_ids) {
-    errctx->initialize(error_ids);
-}
-
-bool __nac3_error_context_has_error(ErrorContext *errctx) {
-    return errctx->has_error();
-}
-
-void __nac3_error_context_get_error_str(ErrorContext *errctx,
-                                        CSlice<int32_t> *dst_str) {
-    errctx->get_error_str<int32_t>(dst_str);
-}
-
-void __nac3_error_context_get_error_str64(ErrorContext *errctx,
-                                          CSlice<int64_t> *dst_str) {
-    errctx->get_error_str<int64_t>(dst_str);
-}
-
-// Used for testing
-void __nac3_error_dummy_raise(ErrorContext *errctx) {
-    errctx->set_error(errctx->error_ids->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

@@ -1,43 +1,67 @@
 #pragma once
 
-#include <irrt/error_context.hpp>
-#include <irrt/int_defs.hpp>
-#include <irrt/ndarray/def.hpp>
+#include "irrt/debug.hpp"
+#include "irrt/exception.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,
-                              const SizeT* shape) {
+template<typename SizeT>
+void assert_shape_no_negative(SizeT ndims, const SizeT* shape) {
     for (SizeT axis = 0; axis < ndims; axis++) {
         if (shape[axis] < 0) {
-            errctx->set_error(errctx->error_ids->value_error,
-                              "negative dimensions are not allowed; axis {0} "
-                              "has dimension {1}",
-                              axis, shape[axis]);
-            return;
+            raise_exception(SizeT, EXN_VALUE_ERROR,
+                            "negative dimensions are not allowed; axis {0} "
+                            "has dimension {1}",
+                            axis, shape[axis], NO_PARAM);
         }
     }
 }
 
 /**
- * @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
  */
-template <typename SizeT>
+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;
 }
 
@@ -49,27 +73,25 @@ SizeT calc_size_from_shape(SizeT ndims, const SizeT* shape) {
  * @param indices The returned indices indexing the ndarray with shape `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,
-                        SizeT nth) {
-    for (int32_t i = 0; i < ndims; i++) {
-        int32_t axis = ndims - i - 1;
-        int32_t dim = shape[axis];
+template<typename SizeT>
+void set_indices_by_nth(SizeT ndims, const SizeT* shape, SizeT* indices, SizeT nth) {
+    for (SizeT i = 0; i < ndims; i++) {
+        SizeT axis = ndims - i - 1;
+        SizeT dim = shape[axis];
 
         indices[axis] = nth % dim;
         nth /= dim;
     }
 }
-}  // namespace util
 
 /**
  * @brief Return the number of elements of an `ndarray`
  *
  * This function corresponds to `<an_ndarray>.size`
  */
-template <typename SizeT>
+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);
 }
 
 /**
@@ -77,128 +99,47 @@ SizeT size(const NDArray<SizeT>* ndarray) {
  *
  * This function corresponds to `<an_ndarray>.nbytes`.
  */
-template <typename SizeT>
+template<typename SizeT>
 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_error(
-            errctx->error_ids->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,
-         SliceIndex* dst_length) {
+template<typename SizeT>
+SizeT len(const NDArray<SizeT>* ndarray) {
+    if (ndarray->ndims != 0) {
+        return ndarray->shape[0];
+    }
+
     // numpy prohibits `__len__` on unsized objects
-    if (ndarray->ndims == 0) {
-        errctx->set_error(errctx->error_ids->type_error,
-                          "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);
-    }
+    raise_exception(SizeT, EXN_TYPE_ERROR, "len() of unsized object", NO_PARAM, NO_PARAM, NO_PARAM);
+    __builtin_unreachable();
 }
 
 /**
  * @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>
+template<typename SizeT>
 bool is_c_contiguous(const NDArray<SizeT>* ndarray) {
-    // Other references:
-    // - tinynumpy's implementation: https://github.com/wadetb/tinynumpy/blob/0d23d22e07062ffab2afa287374c7b366eebdda1/tinynumpy/tinynumpy.py#L102
-    // - 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
+    // References:
+    // - tinynumpy's implementation:
+    // https://github.com/wadetb/tinynumpy/blob/0d23d22e07062ffab2afa287374c7b366eebdda1/tinynumpy/tinynumpy.py#L102
+    // - 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:
@@ -224,14 +165,88 @@ bool is_c_contiguous(const NDArray<SizeT>* ndarray) {
 
     for (SizeT i = 1; i < ndarray->ndims; i++) {
         SizeT axis_i = ndarray->ndims - i - 1;
-        if (ndarray->strides[axis_i] !=
-            ndarray->shape[axis_i + 1] + ndarray->strides[axis_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,
-                        SliceIndex* dst_len) {
-    return len(errctx, ndarray, dst_len);
+int32_t __nac3_ndarray_len(NDArray<int32_t>* ndarray) {
+    return len(ndarray);
 }
 
-void __nac3_ndarray_len64(ErrorContext* errctx, NDArray<int64_t>* ndarray,
-                          SliceIndex* dst_len) {
-    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);
+int64_t __nac3_ndarray_len64(NDArray<int64_t>* ndarray) {
+    return len(ndarray);
 }
 
 bool __nac3_ndarray_is_c_contiguous(NDArray<int32_t>* ndarray) {
@@ -293,13 +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,
-                              NDArray<int32_t>* dst_ndarray) {
+void* __nac3_ndarray_get_nth_pelement(const NDArray<int32_t>* ndarray, int32_t nth) {
+    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,
-                                NDArray<int64_t>* dst_ndarray) {
+void __nac3_ndarray_copy_data64(NDArray<int64_t>* src_ndarray, NDArray<int64_t>* dst_ndarray) {
     copy_data(src_ndarray, dst_ndarray);
 }
 }

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>
+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/fill.hpp

@@ -1,38 +0,0 @@
-#pragma once
-
-#include <irrt/ndarray/basic.hpp>
-#include <irrt/ndarray/def.hpp>
-
-namespace {
-namespace ndarray {
-namespace fill {
-
-/**
- * Fill an ndarray with a value.
- *
- * @param pvalue Pointer to the fill value, and the fill value should be of `ndarray->itemsize` bytes.
- */
-template <typename SizeT>
-void fill_generic(NDArray<SizeT>* ndarray, const uint8_t* pvalue) {
-    const SizeT size = ndarray::basic::size(ndarray);
-    for (SizeT i = 0; i < size; i++) {
-        uint8_t* pelement = ndarray::basic::get_nth_pelement(
-            ndarray, i);  // No need for checked_get_nth_pelement
-        ndarray::basic::set_pelement_value(ndarray, pelement, pvalue);
-    }
-}
-}  // namespace fill
-}  // namespace ndarray
-}  // namespace
-
-extern "C" {
-using namespace ndarray::fill;
-
-void __nac3_ndarray_fill_generic(NDArray<int32_t>* ndarray, uint8_t* pvalue) {
-    fill_generic(ndarray, pvalue);
-}
-
-void __nac3_ndarray_fill_generic64(NDArray<int64_t>* ndarray, uint8_t* pvalue) {
-    fill_generic(ndarray, pvalue);
-}
-}

nac3core/irrt/irrt/ndarray/indexing.hpp

@@ -1,9 +1,11 @@
 #pragma once
 
-#include <irrt/error_context.hpp>
-#include <irrt/ndarray/basic.hpp>
-#include <irrt/ndarray/def.hpp>
-#include <irrt/slice.hpp>
+#include "irrt/exception.hpp"
+#include "irrt/int_types.hpp"
+#include "irrt/ndarray/basic.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 `SliceIndex`.
+ * `data` points to a `int32_t`.
  */
 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 `UserRange`.
+ * `data` points to a `Slice<int32_t>`.
  */
 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_error(errctx->error_ids->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
- * can all be found in the parameter of this function).
+ * This function is very similar to performing `dst_ndarray = src_ndarray[indices]` in Python.
  *
- * In other words, this function takes in an ndarray (`src_ndarray`), index it with `indexes`, and return the
- * indexed array (by writing the result to `dst_ndarray`).
- *
- * This function also does proper assertions on `indexes`.
+ * This function also does proper assertions on `indices` to check for out of bounds access and more.
  *
  * # 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->itemsize` is set to `src_ndarray->itemsize`
+ *   - `dst_ndarray->data` is set to `src_ndarray->data`.
+ *   - `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,
-           const NDArray<SizeT>* src_ndarray, NDArray<SizeT>* dst_ndarray) {
-    // Reference code: https://github.com/wadetb/tinynumpy/blob/0d23d22e07062ffab2afa287374c7b366eebdda1/tinynumpy/tinynumpy.py#L652
+template<typename SizeT>
+void index(SizeT num_indices, const NDIndex* indices, const NDArray<SizeT>* src_ndarray, NDArray<SizeT>* dst_ndarray) {
+    // Validate `indices`.
+
+    // 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++) {
-        const NDIndex* index = &indexes[i];
+    for (int32_t i = 0; i < num_indices; i++) {
+        const NDIndex* index = &indices[i];
         if (index->type == ND_INDEX_TYPE_SINGLE_ELEMENT) {
-            SliceIndex input = *((SliceIndex*)index->data);
-            SliceIndex k = slice::resolve_index_in_length(
-                src_ndarray->shape[src_axis], input);
+            SizeT input = (SizeT) * ((int32_t*)index->data);
 
-            if (k == slice::OUT_OF_BOUNDS) {
-                errctx->set_error(errctx->error_ids->index_error,
-                                  "index {0} is out of bounds for axis {1} "
-                                  "with size {2}",
-                                  input, src_axis,
-                                  src_ndarray->shape[src_axis]);
-                return;
+            SizeT k = slice::resolve_index_in_length(src_ndarray->shape[src_axis], input);
+            if (k == -1) {
+                raise_exception(SizeT, EXN_INDEX_ERROR,
+                                "index {0} is out of bounds for axis {1} "
+                                "with size {2}",
+                                input, src_axis, src_ndarray->shape[src_axis]);
             }
 
-            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;
-            input->indices_checked(errctx, src_ndarray->shape[src_axis],
-                                   &slice);
-            if (errctx->has_error()) {
-                return;
-            }
+            Range<int32_t> range = slice->indices_checked<SizeT>(src_ndarray->shape[src_axis]);
 
-            dst_ndarray->data +=
-                (SizeT)slice.start * src_ndarray->strides[src_axis];
-            dst_ndarray->strides[dst_axis] =
-                ((SizeT)slice.step) * src_ndarray->strides[src_axis];
-            dst_ndarray->shape[dst_axis] = (SizeT)slice.len();
+            dst_ndarray->data = static_cast<uint8_t*>(dst_ndarray->data) + (SizeT)range.start * src_ndarray->strides[src_axis];
+            dst_ndarray->strides[dst_axis] = ((SizeT)range.step) * src_ndarray->strides[src_axis];
+            dst_ndarray->shape[dst_axis] = (SizeT)range.len<SizeT>();
 
             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(
-    ErrorContext* errctx, int32_t* result, int32_t ndims, int32_t num_indexes,
-    const NDIndex* indexes) {
-    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,
+void __nac3_ndarray_index(int32_t num_indices,
+                          NDIndex* indices,
+                          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,
-                            NDIndex* indexes, NDArray<int64_t>* src_ndarray,
+void __nac3_ndarray_index64(int64_t num_indices,
+                            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

@@ -1,116 +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_error(errctx->error_ids->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_error(errctx->error_ids->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_error(errctx->error_ids->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/ndarray/transpose.hpp

@@ -1,162 +0,0 @@
-#pragma once
-
-#include <irrt/int_defs.hpp>
-#include <irrt/ndarray/def.hpp>
-#include <irrt/slice.hpp>
-
-/*
- * Notes on `np.transpose(<array>, <axes>)`
- *
- * TODO: `axes`, if specified, can actually contain negative indices,
- * but it is not documented in numpy.
- *
- * Supporting it for now.
- */
-
-namespace {
-namespace ndarray {
-namespace transpose {
-namespace util {
-
-/**
- * @brief Do assertions on `<axes>` in `np.transpose(<array>, <axes>)`.
- *
- * Note that `np.transpose`'s `<axe>` argument is optional. If the argument
- * is specified but the user, use this function to do assertions on it.
- *
- * @param ndims The number of dimensions of `<array>`
- * @param num_axes Number of elements in `<axes>` as specified by the user.
- *   This should be equal to `ndims`. If not, a "ValueError: axes don't match array" is thrown.
- * @param axes The user specified `<axes>`.
- */
-template <typename SizeT>
-void assert_transpose_axes(ErrorContext* errctx, SizeT ndims, SizeT num_axes,
-                           const SizeT* axes) {
-    /*
-     * TODO: `axes` can actually contain negative indices, but it is not documented in numpy.
-     *
-     * Supporting it for now.
-     */
-
-    if (ndims != num_axes) {
-        errctx->set_error(errctx->error_ids->value_error,
-                          "axes don't match array");
-        return;
-    }
-
-    // TODO: Optimize this
-    bool* axe_specified = (bool*)__builtin_alloca(sizeof(bool) * ndims);
-    for (SizeT i = 0; i < ndims; i++) axe_specified[i] = false;
-
-    for (SizeT i = 0; i < ndims; i++) {
-        SizeT axis = slice::resolve_index_in_length(ndims, axes[i]);
-        if (axis == slice::OUT_OF_BOUNDS) {
-            // TODO: numpy actually throws a `numpy.exceptions.AxisError`
-            errctx->set_error(
-                errctx->error_ids->value_error,
-                "axis {0} is out of bounds for array of dimension {1}", axis,
-                ndims);
-            return;
-        }
-
-        if (axe_specified[axis]) {
-            errctx->set_error(errctx->error_ids->value_error,
-                              "repeated axis in transpose");
-            return;
-        }
-
-        axe_specified[axis] = true;
-    }
-}
-}  // namespace util
-
-/**
- * @brief Create a transpose view of `src_ndarray` and perform proper assertions.
- *
- * This function is very similar to doing `dst_ndarray = np.transpose(src_ndarray, <axes>)`.
- * If `<axes>` is supposed to be `None`, caller can pass in a `nullptr` to `<axes>`.
- *
- * The transpose view created is returned by modifying `dst_ndarray`.
- *
- * The caller is responsible for setting up `dst_ndarray` before calling this function.
- * 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, must be equal to `src_ndarray->ndims`.
- *   - `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->itemsize` is set to `src_ndarray->itemsize`
- *   - `dst_ndarray->ndims` is unchanged
- *   - `dst_ndarray->shape` is updated according to how `np.transpose` works
- *   - `dst_ndarray->strides` is updated according to how `np.transpose` works
- *
- * @param src_ndarray The NDArray to build a transpose view on
- * @param dst_ndarray The resulting NDArray after transpose. Further details in the comments above,
- * @param num_axes Number of elements in axes, can be undefined if `axes` is nullptr.
- * @param axes Axes permutation. Set it to `nullptr` if `<axes>` is supposed to be `None`.
- */
-template <typename SizeT>
-void transpose(ErrorContext* errctx, const NDArray<SizeT>* src_ndarray,
-               NDArray<SizeT>* dst_ndarray, SizeT num_axes, const SizeT* axes) {
-    __builtin_assume(src_ndarray->ndims == dst_ndarray->ndims);
-    const auto ndims = src_ndarray->ndims;
-
-    if (axes != nullptr) {
-        util::assert_transpose_axes(errctx, ndims, num_axes, axes);
-        if (errctx->has_error()) return;
-    }
-
-    dst_ndarray->data = src_ndarray->data;
-    dst_ndarray->itemsize = src_ndarray->itemsize;
-
-    // Check out https://ajcr.net/stride-guide-part-2/ to see how `np.transpose` works behind the scenes.
-    if (axes == nullptr) {
-        // `np.transpose(<array>, axes=None)`
-
-        /*
-         * Minor note: `np.transpose(<array>, axes=None)` is equivalent to
-         * `np.transpose(<array>, axes=[N-1, N-2, ..., 0])` - basically it
-         * is reversing the order of strides and shape.
-         *
-         * This is a fast implementation to handle this special (but very common) case.
-         */
-
-        for (SizeT axis = 0; axis < ndims; axis++) {
-            dst_ndarray->shape[axis] = src_ndarray->shape[ndims - axis - 1];
-            dst_ndarray->strides[axis] = src_ndarray->strides[ndims - axis - 1];
-        }
-    } else {
-        // `np.transpose(<array>, <axes>)`
-
-        // Permute strides and shape according to `axes`, while resolving negative indices in `axes`
-        for (SizeT axis = 0; axis < ndims; axis++) {
-            // `i` cannot be OUT_OF_BOUNDS because of assertions
-            SizeT i = slice::resolve_index_in_length(ndims, axes[axis]);
-
-            dst_ndarray->shape[axis] = src_ndarray->shape[i];
-            dst_ndarray->strides[axis] = src_ndarray->strides[i];
-        }
-    }
-}
-}  // namespace transpose
-}  // namespace ndarray
-}  // namespace
-
-extern "C" {
-using namespace ndarray::transpose;
-void __nac3_ndarray_transpose(ErrorContext* errctx,
-                              const NDArray<int32_t>* src_ndarray,
-                              NDArray<int32_t>* dst_ndarray, int32_t num_axes,
-                              const int32_t* axes) {
-    transpose(errctx, src_ndarray, dst_ndarray, num_axes, axes);
-}
-
-void __nac3_ndarray_transpose64(ErrorContext* errctx,
-                                const NDArray<int64_t>* src_ndarray,
-                                NDArray<int64_t>* dst_ndarray, int64_t num_axes,
-                                const int64_t* axes) {
-    transpose(errctx, src_ndarray, dst_ndarray, num_axes, axes);
-}
-}

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/int_defs.hpp>
-#include <irrt/slice.hpp>
-#include <irrt/utils.hpp>
-
-// The type of an index or a value describing the length of a
-// range/slice is always `int32_t`.
-using SliceIndex = int32_t;
+#include "irrt/debug.hpp"
+#include "irrt/exception.hpp"
+#include "irrt/int_types.hpp"
+#include "irrt/math_util.hpp"
+#include "irrt/range.hpp"
 
 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.
- *
- * 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).
+ * @brief Resolve a possibly negative index in a list of a known length.
  *
+ * Returns -1 if the resolved index is out of the list's bounds.
  */
-SliceIndex resolve_index_in_length_clamped(SliceIndex length,
-                                           SliceIndex index) {
-    if (index < 0) {
-        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;
+template<typename T>
+T resolve_index_in_length(T length, T index) {
+    T 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;
@@ -98,68 +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)`.
-     *
-     * @return A `Slice` with the resolved indices.
+     * In Python, this would be `range(*slice(start, stop, step).indices(length))`.
      */
-    Slice indices(SliceIndex length) {
-        Slice result;
-
-        result.step = step_defined ? step : 1;
-        bool step_is_negative = result.step < 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;
-        }
+    template<typename SizeT>
+    Range<T> indices(T length) {
+        // Reference:
+        // https://github.com/python/cpython/blob/main/Objects/sliceobject.c#L388
+        debug_assert(SizeT, length >= 0);
 
+        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,
-                         Slice* result) {
+    template<typename SizeT>
+    Range<T> indices_checked(T length) {
+        // TODO: Switch to `SizeT length`
+
         if (length < 0) {
-            errctx->set_error(errctx->error_ids->value_error,
-                              "length should not be negative, got {0}", length);
-            return;
+            raise_exception(SizeT, EXN_VALUE_ERROR, "length should not be negative, got {0}", length, NO_PARAM,
+                            NO_PARAM);
         }
 
         if (this->step_defined && this->step == 0) {
-            errctx->set_error(errctx->error_ids->value_error,
-                              "slice step cannot be zero");
-            return;
+            raise_exception(SizeT, EXN_VALUE_ERROR, "slice step cannot be zero", NO_PARAM, NO_PARAM, NO_PARAM);
         }
 
-        *result = this->indices(length);
+        return this->indices<SizeT>(length);
     }
 };
-}  // namespace
+}  // 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

@@ -1,14 +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/def.hpp>
-#include <irrt/ndarray/fill.hpp>
-#include <irrt/ndarray/indexing.hpp>
-#include <irrt/ndarray/reshape.hpp>
-#include <irrt/ndarray/transpose.hpp>
-#include <irrt/slice.hpp>
-#include <irrt/utils.hpp>

nac3core/irrt/irrt_test.cpp

@@ -1,18 +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_indexing.hpp>
-#include <test/test_slice.hpp>
-
-int main() {
-    test::core::run();
-    test::slice::run();
-    test::ndarray_basic::run();
-    test::ndarray_indexing::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_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_error(&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_error(&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_error(&errctx, errctx.error_ids->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_error(&errctx, errctx.error_ids->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

@@ -1,179 +0,0 @@
-#pragma once
-
-#include <cstdio>
-#include <cstdlib>
-
-template <class T>
-void print_value(const T& value);
-
-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 ErrorIds for testing only
-const ErrorIds TEST_ERROR_IDS = {
-    .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_IDS);
-    return errctx;
-}
-
-void print_errctx_content(ErrorContext* errctx) {
-    if (errctx->has_error()) {
-        printf(
-            "(Error ID %d): %s ... where param1 = %ld, param2 = %ld, param3 = "
-            "%ld\n",
-            errctx->error_id, errctx->message_template, errctx->param1,
-            errctx->param2, errctx->param3);
-    } else {
-        printf("<no error>\n");
-    }
-}
-
-void __assert_errctx_no_error(const char* file, int line,
-                              ErrorContext* errctx) {
-    if (errctx->has_error()) {
-        print_assertion_failed(file, line);
-        printf("Expecting no error but caught the following:\n\n");
-        print_errctx_content(errctx);
-        test_fail();
-    }
-}
-
-#define assert_errctx_no_error(errctx) \
-    __assert_errctx_no_error(__FILE__, __LINE__, errctx)
-
-void __assert_errctx_has_error(const char* file, int line, ErrorContext* errctx,
-                               ExceptionId expected_error_id) {
-    if (errctx->has_error()) {
-        if (errctx->error_id != expected_error_id) {
-            print_assertion_failed(file, line);
-            printf(
-                "Expecting error id %d but got error id %d. Error caught:\n\n",
-                expected_error_id, errctx->error_id);
-            print_errctx_content(errctx);
-            test_fail();
-        }
-    } else {
-        print_assertion_failed(file, line);
-        printf("Expecting an error, but there is none.");
-        test_fail();
-    }
-}
-
-#define assert_errctx_has_error(errctx, expected_error_id) \
-    __assert_errctx_has_error(__FILE__, __LINE__, errctx, expected_error_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::values::{BasicValueEnum, CallSiteValue, FloatValue, IntValue};
+use inkwell::{
+    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`
@@ -13,11 +15,11 @@ use crate::codegen::CodeGenContext;
 /// * `$extern_fn:literal`: Name of underlying extern function
 ///
 /// Optional Arguments:
-/// * `$(,$attributes:literal)*)`: Attributes linked with the extern function
-/// The default attributes are "mustprogress", "nofree", "nounwind", "willreturn", and "writeonly"
-/// These will be used unless other attributes are specified
+/// * `$(,$attributes:literal)*)`: Attributes linked with the extern function.
+///   The default attributes are "mustprogress", "nofree", "nounwind", "willreturn", and "writeonly".
+///   These will be used unless other attributes are specified
 /// * `$(,$args:ident)*`: Operands of the extern function
-/// The data type of these operands will be set to `FloatValue`
+///   The data type of these operands will be set to `FloatValue`
 ///  
 macro_rules! generate_extern_fn {
     ("unary", $fn_name:ident, $extern_fn:literal) => {
@@ -130,3 +132,62 @@ pub fn call_ldexp<'ctx>(
         .map(Either::unwrap_left)
         .unwrap()
 }
+
+/// Macro to generate `np_linalg` and `sp_linalg` functions
+/// The function takes as input `NDArray` and returns ()
+///
+/// Arguments:
+/// * `$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

@@ -1,17 +1,17 @@
-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::model::SizeTModel;
+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.
@@ -19,10 +19,6 @@ pub trait CodeGenerator {
 
     fn get_size_type<'ctx>(&self, ctx: &'ctx Context) -> IntType<'ctx>;
 
-    fn get_sizet<'ctx>(&self, ctx: &'ctx Context) -> SizeTModel<'ctx> {
-        SizeTModel(self.get_size_type(ctx))
-    }
-
     /// Generate function call and returns the function return value.
     /// - obj: Optional object for method call.
     /// - fun: Function signature and definition ID.
@@ -63,6 +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>(
@@ -129,11 +126,45 @@ pub trait CodeGenerator {
         ctx: &mut CodeGenContext<'ctx, '_>,
         target: &Expr<Option<Type>>,
         value: ValueEnum<'ctx>,
+        value_ty: Type,
     ) -> Result<(), String>
     where
         Self: Sized,
     {
-        gen_assign(self, ctx, target, value)
+        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.

nac3core/src/codegen/irrt/error_context.rs

@@ -1,195 +0,0 @@
-use crate::codegen::{model::*, structs::cslice::CSlice, CodeGenContext, CodeGenerator};
-
-use super::util::get_sized_dependent_function_name;
-
-/// The [`IntModel`] of nac3core's error ID.
-///
-/// It is always [`Int32`].
-type ErrorId = Int32;
-
-#[allow(clippy::struct_field_names)]
-pub struct ErrorIdsFields {
-    pub index_error: Field<NIntModel<ErrorId>>,
-    pub value_error: Field<NIntModel<ErrorId>>,
-    pub assertion_error: Field<NIntModel<ErrorId>>,
-    pub runtime_error: Field<NIntModel<ErrorId>>,
-    pub type_error: Field<NIntModel<ErrorId>>,
-}
-
-/// Corresponds to IRRT's `struct ErrorIds`
-#[derive(Debug, Clone, Copy, Default, PartialEq, Eq)]
-pub struct ErrorIds;
-
-impl<'ctx> StructKind<'ctx> for ErrorIds {
-    type Fields = ErrorIdsFields;
-
-    fn struct_name(&self) -> &'static str {
-        "ErrorIds"
-    }
-
-    fn build_fields(&self, builder: &mut FieldBuilder) -> Self::Fields {
-        Self::Fields {
-            index_error: builder.add_field_auto("index_error"),
-            value_error: builder.add_field_auto("value_error"),
-            assertion_error: builder.add_field_auto("assertion_error"),
-            runtime_error: builder.add_field_auto("runtime_error"),
-            type_error: builder.add_field_auto("type_error"),
-        }
-    }
-}
-
-pub struct ErrorContextFields {
-    pub error_ids: Field<PointerModel<StructModel<ErrorIds>>>,
-    pub error_id: Field<NIntModel<ErrorId>>,
-    pub message_template: Field<PointerModel<NIntModel<Byte>>>,
-    pub param1: Field<NIntModel<Int64>>,
-    pub param2: Field<NIntModel<Int64>>,
-    pub param3: Field<NIntModel<Int64>>,
-}
-
-/// Corresponds to IRRT's `struct ErrorContext`
-#[derive(Debug, Clone, Copy, Default, PartialEq, Eq)]
-pub struct ErrorContext;
-
-impl<'ctx> StructKind<'ctx> for ErrorContext {
-    type Fields = ErrorContextFields;
-
-    fn struct_name(&self) -> &'static str {
-        "ErrorIds"
-    }
-
-    fn build_fields(&self, builder: &mut FieldBuilder) -> Self::Fields {
-        Self::Fields {
-            error_ids: builder.add_field_auto("error_ids"),
-            error_id: builder.add_field_auto("error_id"),
-            message_template: builder.add_field_auto("message_template"),
-            param1: builder.add_field_auto("param1"),
-            param2: builder.add_field_auto("param2"),
-            param3: builder.add_field_auto("param3"),
-        }
-    }
-}
-
-// Prepare ErrorIds
-fn build_error_ids<'ctx>(ctx: &CodeGenContext<'ctx, '_>) -> Pointer<'ctx, StructModel<ErrorIds>> {
-    // ErrorIdsLens.get_fields(ctx.ctx).assertion_error.
-    let error_ids = StructModel(ErrorIds).alloca(ctx, "error_ids");
-    let i32_model = NIntModel(Int32);
-    // i32_model.make_constant()
-
-    let get_string_id =
-        |string_id| i32_model.constant(ctx.ctx, ctx.resolver.get_string_id(string_id) as u64);
-
-    error_ids.gep(ctx, |f| f.index_error).store(ctx, get_string_id("0:IndexError"));
-    error_ids.gep(ctx, |f| f.value_error).store(ctx, get_string_id("0:ValueError"));
-    error_ids.gep(ctx, |f| f.assertion_error).store(ctx, get_string_id("0:AssertionError"));
-    error_ids.gep(ctx, |f| f.runtime_error).store(ctx, get_string_id("0:RuntimeError"));
-    error_ids.gep(ctx, |f| f.type_error).store(ctx, get_string_id("0:TypeError"));
-
-    error_ids
-}
-
-pub fn call_nac3_error_context_initialize<'ctx>(
-    ctx: &CodeGenContext<'ctx, '_>,
-    perrctx: Pointer<'ctx, StructModel<ErrorContext>>,
-    perror_ids: Pointer<'ctx, StructModel<ErrorIds>>,
-) {
-    FunctionBuilder::begin(ctx, "__nac3_error_context_initialize")
-        .arg("errctx", perrctx)
-        .arg("error_ids", perror_ids)
-        .returning_void();
-}
-
-pub fn call_nac3_error_context_has_error<'ctx>(
-    ctx: &CodeGenContext<'ctx, '_>,
-    errctx: Pointer<'ctx, StructModel<ErrorContext>>,
-) -> NInt<'ctx, Bool> {
-    FunctionBuilder::begin(ctx, "__nac3_error_context_has_error")
-        .arg("errctx", errctx)
-        .returning("has_error", NIntModel(Bool))
-}
-
-pub fn call_nac3_error_context_get_error_str<'ctx, G: CodeGenerator + ?Sized>(
-    generator: &mut G,
-    ctx: &CodeGenContext<'ctx, '_>,
-    errctx: Pointer<'ctx, StructModel<ErrorContext>>,
-    dst_str: Pointer<'ctx, StructModel<CSlice<'ctx>>>,
-) {
-    let sizet = generator.get_sizet(ctx.ctx);
-
-    FunctionBuilder::begin(
-        ctx,
-        &get_sized_dependent_function_name(sizet, "__nac3_error_context_get_error_str"),
-    )
-    .arg("errctx", errctx)
-    .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>(
-    ctx: &CodeGenContext<'ctx, '_>,
-) -> Pointer<'ctx, StructModel<ErrorContext>> {
-    let error_ids = build_error_ids(ctx);
-    let errctx_ptr = StructModel(ErrorContext).alloca(ctx, "errctx");
-    call_nac3_error_context_initialize(ctx, errctx_ptr, error_ids);
-    errctx_ptr
-}
-
-/// Check a [`ErrorContext`] to see
-/// if it contains error.
-///
-/// If there is an error, an LLVM exception will be raised at runtime.
-pub fn check_error_context<'ctx, G: CodeGenerator + ?Sized>(
-    generator: &mut G,
-    ctx: &mut CodeGenContext<'ctx, '_>,
-    errctx_ptr: Pointer<'ctx, StructModel<ErrorContext>>,
-) {
-    let sizet = generator.get_sizet(ctx.ctx);
-    let cslice_model = StructModel(CSlice { sizet });
-
-    let current_bb = ctx.builder.get_insert_block().unwrap();
-    let irrt_has_error_bb = ctx.ctx.insert_basic_block_after(current_bb, "irrt_has_error");
-    let end_bb = ctx.ctx.insert_basic_block_after(irrt_has_error_bb, "end");
-
-    // Inserting into `current_bb`
-    let has_error = call_nac3_error_context_has_error(ctx, errctx_ptr);
-    ctx.builder.build_conditional_branch(has_error.value, irrt_has_error_bb, end_bb).unwrap();
-
-    // Inserting into `irrt_has_error_bb`
-    ctx.builder.position_at_end(irrt_has_error_bb);
-
-    // Load all the values for `ctx.make_assert_impl_by_id`
-    let pstr = cslice_model.alloca(ctx, "error_str");
-    call_nac3_error_context_get_error_str(generator, ctx, errctx_ptr, pstr);
-
-    let error_id = errctx_ptr.gep(ctx, |f| f.error_id).load(ctx, "error_id");
-    let msg = pstr.load(ctx, "msg");
-    let param1 = errctx_ptr.gep(ctx, |f| f.param1).load(ctx, "param1");
-    let param2 = errctx_ptr.gep(ctx, |f| f.param2).load(ctx, "param2");
-    let param3 = errctx_ptr.gep(ctx, |f| f.param3).load(ctx, "param3");
-
-    ctx.raise_exn_impl(
-        generator,
-        error_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 errctx = setup_error_context(ctx);
-    FunctionBuilder::begin(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

@@ -1,34 +1,29 @@
-use crate::typecheck::typedef::Type;
-
-mod error_context;
-pub mod ndarray;
-pub mod slice;
-mod test;
-mod util;
-
-use super::{
-    classes::{
-        ArrayLikeIndexer, ArrayLikeValue, ArraySliceValue, ListValue, NDArrayValue,
-        TypedArrayLikeAdapter, UntypedArrayLikeAccessor,
-    },
-    llvm_intrinsics, CodeGenContext, CodeGenerator, Int, Int64, NIntModel,
-};
-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::{BasicValueEnum, CallSiteValue, FloatValue, IntValue},
-    AddressSpace, IntPredicate,
+    values::{BasicValue, BasicValueEnum, IntValue},
+    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",
@@ -44,89 +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:
-// 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",
-        _ => unreachable!(),
-    };
-    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>(
-    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()
+/// Returns the name of a function which contains variants for 32-bit and 64-bit `size_t`.
+///
+/// - 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_usize_dependent_function_name<G: CodeGenerator + ?Sized>(
+    generator: &G,
+    ctx: &CodeGenContext<'_, '_>,
+    name: &str,
+) -> String {
+    let mut name = name.to_owned();
+    match generator.get_size_type(ctx.ctx).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
 }
 
 /// NOTE: the output value of the end index of this function should be compared ***inclusively***,
@@ -294,655 +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 param_model = NIntModel(Int64);
-
-        let src_slice_len =
-            Int::from(src_slice_len).s_extend_or_bit_cast(ctx, param_model, "src_slice_len");
-        let dest_slice_len =
-            Int::from(dest_slice_len).s_extend_or_bit_cast(ctx, param_model, "dest_slice_len");
-        let dest_idx_2 = Int::from(dest_idx.2).s_extend_or_bit_cast(ctx, param_model, "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,
-        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/allocation.rs

@@ -1,93 +0,0 @@
-use crate::codegen::model::*;
-use crate::codegen::util::array_writer::ArrayWriter;
-use crate::codegen::{structs::ndarray::NpArray, CodeGenContext, CodeGenerator};
-
-use super::basic::{
-    call_nac3_ndarray_nbytes, call_nac3_ndarray_set_strides_by_shape,
-    call_nac3_ndarray_util_assert_shape_no_negative,
-};
-
-/**
-    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: SizeT<'ctx>,
-    name: &str,
-) -> Result<Pointer<'ctx, StructModel<NpArray<'ctx>>>, String>
-where
-    G: CodeGenerator + ?Sized,
-{
-    let sizet = generator.get_sizet(ctx.ctx);
-
-    let ndarray_model = StructModel(NpArray { sizet });
-    let ndarray_data_model = PointerModel(NIntModel(Byte));
-
-    // Allocate ndarray
-    let ndarray_ptr = ndarray_model.alloca(ctx, name);
-
-    // Set data to nullptr
-    ndarray_ptr.gep(ctx, |f| f.data).store(ctx, ndarray_data_model.nullptr(ctx.ctx));
-
-    // Set ndims
-    ndarray_ptr.gep(ctx, |f| f.ndims).store(ctx, ndims);
-
-    // Allocate and set shape
-    let shape_array = sizet.array_alloca(ctx, ndims, "shape");
-    ndarray_ptr.gep(ctx, |f| f.shape).store(ctx, shape_array.pointer);
-
-    // Allocate and set strides
-    let strides_array = sizet.array_alloca(ctx, ndims, "strides");
-    ndarray_ptr.gep(ctx, |f| f.strides).store(ctx, strides_array.pointer);
-
-    Ok(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, '_>,
-    ndarray_ptr: Pointer<'ctx, StructModel<NpArray<'ctx>>>,
-    shape_writer: &ArrayWriter<'ctx, G, SizeTModel<'ctx>, SizeTModel<'ctx>>,
-) -> Result<(), String> {
-    (shape_writer.write)(generator, ctx, &ndarray_ptr.shape_slice(ctx))?;
-
-    call_nac3_ndarray_util_assert_shape_no_negative(
-        generator,
-        ctx,
-        shape_writer.count,
-        ndarray_ptr.gep(ctx, |f| f.shape).load(ctx, "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, '_>,
-    ndarray_ptr: Pointer<'ctx, StructModel<NpArray<'ctx>>>,
-) {
-    let ndarray_nbytes = call_nac3_ndarray_nbytes(generator, ctx, ndarray_ptr); // Needs `itemsize` initialized
-
-    let data_array = NIntModel(Byte).array_alloca(ctx, ndarray_nbytes, "data");
-    ndarray_ptr.gep(ctx, |f| f.data).store(ctx, data_array.pointer);
-
-    call_nac3_ndarray_set_strides_by_shape(generator, ctx, ndarray_ptr);
-}

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

@@ -1,117 +1,250 @@
-use crate::codegen::irrt::error_context::{check_error_context, setup_error_context};
-use crate::codegen::irrt::slice::SliceIndex;
-use crate::codegen::irrt::util::get_sized_dependent_function_name;
-use crate::codegen::model::*;
-use crate::codegen::{structs::ndarray::NpArray, CodeGenContext, CodeGenerator};
+use inkwell::{
+    values::{BasicValueEnum, IntValue, PointerValue},
+    AddressSpace,
+};
+
+use crate::codegen::{
+    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,
-    ctx: &mut CodeGenContext<'ctx, '_>,
-    ndarray_ptr: Pointer<'ctx, StructModel<NpArray<'ctx>>>,
-) -> SizeT<'ctx> {
-    let sizet = generator.get_sizet(ctx.ctx);
+    generator: &G,
+    ctx: &CodeGenContext<'ctx, '_>,
+    ndarray: NDArrayValue<'ctx>,
+) -> IntValue<'ctx> {
+    let llvm_usize = generator.get_size_type(ctx.ctx);
+    let llvm_ndarray = ndarray.get_type().as_base_type();
 
-    FunctionBuilder::begin(ctx, &get_sized_dependent_function_name(sizet, "__nac3_ndarray_size"))
-        .arg("ndarray", ndarray_ptr)
-        .returning("size", sizet)
+    let name = get_usize_dependent_function_name(generator, ctx, "__nac3_ndarray_size");
+
+    create_and_call_function(
+        ctx,
+        &name,
+        Some(llvm_usize.into()),
+        &[(llvm_ndarray.into(), ndarray.as_base_value().into())],
+        Some("size"),
+        None,
+    )
+    .map(BasicValueEnum::into_int_value)
+    .unwrap()
 }
 
 pub fn call_nac3_ndarray_nbytes<'ctx, G: CodeGenerator + ?Sized>(
-    generator: &mut G,
-    ctx: &mut CodeGenContext<'ctx, '_>,
-    ndarray_ptr: Pointer<'ctx, StructModel<NpArray<'ctx>>>,
-) -> SizeT<'ctx> {
-    let sizet = generator.get_sizet(ctx.ctx);
+    generator: &G,
+    ctx: &CodeGenContext<'ctx, '_>,
+    ndarray: NDArrayValue<'ctx>,
+) -> IntValue<'ctx> {
+    let llvm_usize = generator.get_size_type(ctx.ctx);
+    let llvm_ndarray = ndarray.get_type().as_base_type();
 
-    FunctionBuilder::begin(ctx, &get_sized_dependent_function_name(sizet, "__nac3_ndarray_nbytes"))
-        .arg("ndarray", ndarray_ptr)
-        .returning("nbytes", sizet)
+    let name = get_usize_dependent_function_name(generator, ctx, "__nac3_ndarray_nbytes");
+
+    create_and_call_function(
+        ctx,
+        &name,
+        Some(llvm_usize.into()),
+        &[(llvm_ndarray.into(), ndarray.as_base_value().into())],
+        Some("nbytes"),
+        None,
+    )
+    .map(BasicValueEnum::into_int_value)
+    .unwrap()
 }
 
 pub fn call_nac3_ndarray_len<'ctx, G: CodeGenerator + ?Sized>(
-    generator: &mut G,
-    ctx: &mut CodeGenContext<'ctx, '_>,
-    ndarray_ptr: Pointer<'ctx, StructModel<NpArray<'ctx>>>,
-) -> NInt<'ctx, SliceIndex> {
-    let sizet = generator.get_sizet(ctx.ctx);
-    let slice_index_model = NIntModel(SliceIndex::default());
+    generator: &G,
+    ctx: &CodeGenContext<'ctx, '_>,
+    ndarray: NDArrayValue<'ctx>,
+) -> IntValue<'ctx> {
+    let llvm_usize = generator.get_size_type(ctx.ctx);
+    let llvm_ndarray = ndarray.get_type().as_base_type();
 
-    let dst_len = slice_index_model.alloca(ctx, "dst_len");
+    let name = get_usize_dependent_function_name(generator, ctx, "__nac3_ndarray_len");
 
-    let errctx = setup_error_context(ctx);
-    FunctionBuilder::begin(ctx, &get_sized_dependent_function_name(sizet, "__nac3_ndarray_len"))
-        .arg("errctx", errctx)
-        .arg("ndarray", ndarray_ptr)
-        .arg("dst_len", dst_len)
-        .returning_void();
-    check_error_context(generator, ctx, errctx);
-
-    dst_len.load(ctx, "len")
-}
-
-pub fn call_nac3_ndarray_util_assert_shape_no_negative<'ctx, G: CodeGenerator + ?Sized>(
-    generator: &mut G,
-    ctx: &mut CodeGenContext<'ctx, '_>,
-    ndims: SizeT<'ctx>,
-    shape_ptr: Pointer<'ctx, SizeTModel<'ctx>>,
-) {
-    let sizet = generator.get_sizet(ctx.ctx);
-
-    let errctx = setup_error_context(ctx);
-    FunctionBuilder::begin(
+    create_and_call_function(
         ctx,
-        &get_sized_dependent_function_name(sizet, "__nac3_ndarray_util_assert_shape_no_negative"),
+        &name,
+        Some(llvm_usize.into()),
+        &[(llvm_ndarray.into(), ndarray.as_base_value().into())],
+        Some("len"),
+        None,
     )
-    .arg("errctx", errctx)
-    .arg("ndims", ndims)
-    .arg("shape", shape_ptr)
-    .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: Pointer<'ctx, StructModel<NpArray<'ctx>>>,
-) {
-    let sizet = generator.get_sizet(ctx.ctx);
-
-    FunctionBuilder::begin(
-        ctx,
-        &get_sized_dependent_function_name(sizet, "__nac3_ndarray_set_strides_by_shape"),
-    )
-    .arg("ndarray", ndarray_ptr)
-    .returning_void();
+    .map(BasicValueEnum::into_int_value)
+    .unwrap()
 }
 
 pub fn call_nac3_ndarray_is_c_contiguous<'ctx, G: CodeGenerator + ?Sized>(
-    generator: &mut G,
-    ctx: &mut CodeGenContext<'ctx, '_>,
-    ndarray_ptr: Pointer<'ctx, StructModel<NpArray<'ctx>>>,
-) -> NInt<'ctx, Bool> {
-    let sizet = generator.get_sizet(ctx.ctx);
+    generator: &G,
+    ctx: &CodeGenContext<'ctx, '_>,
+    ndarray: NDArrayValue<'ctx>,
+) -> IntValue<'ctx> {
+    let llvm_i1 = ctx.ctx.bool_type();
+    let llvm_ndarray = ndarray.get_type().as_base_type();
 
-    FunctionBuilder::begin(
+    let name = get_usize_dependent_function_name(generator, ctx, "__nac3_ndarray_is_c_contiguous");
+
+    create_and_call_function(
         ctx,
-        &get_sized_dependent_function_name(sizet, "__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)
-    .returning("is_c_contiguous", NIntModel(Bool))
+    .map(BasicValueEnum::into_int_value)
+    .unwrap()
+}
+
+pub fn call_nac3_ndarray_get_nth_pelement<'ctx, G: CodeGenerator + ?Sized>(
+    generator: &G,
+    ctx: &CodeGenContext<'ctx, '_>,
+    ndarray: NDArrayValue<'ctx>,
+    index: IntValue<'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_ndarray = ndarray.get_type().as_base_type();
+
+    let name = get_usize_dependent_function_name(generator, ctx, "__nac3_ndarray_get_nth_pelement");
+
+    create_and_call_function(
+        ctx,
+        &name,
+        Some(llvm_pi8.into()),
+        &[(llvm_ndarray.into(), ndarray.as_base_value().into()), (llvm_usize.into(), index.into())],
+        Some("pelement"),
+        None,
+    )
+    .map(BasicValueEnum::into_pointer_value)
+    .unwrap()
+}
+
+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: &mut G,
-    ctx: &mut CodeGenContext<'ctx, '_>,
-    src_ndarray: Pointer<'ctx, StructModel<NpArray<'ctx>>>,
-    dst_ndarray: Pointer<'ctx, StructModel<NpArray<'ctx>>>,
-) -> NInt<'ctx, Bool> {
-    let sizet = generator.get_sizet(ctx.ctx);
+    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");
 
-    FunctionBuilder::begin(
+    infer_and_call_function(
         ctx,
-        &get_sized_dependent_function_name(sizet, "__nac3_ndarray_copy_data"),
-    )
-    .arg("src_ndarray", src_ndarray)
-    .arg("dst_ndarray", dst_ndarray)
-    .returning("is_c_contiguous", NIntModel(Bool))
+        &name,
+        None,
+        &[src_ndarray.as_base_value().into(), dst_ndarray.as_base_value().into()],
+        None,
+        None,
+    );
 }

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

@@ -1,21 +0,0 @@
-use crate::codegen::{
-    irrt::util::get_sized_dependent_function_name, model::*, structs::ndarray::NpArray,
-    CodeGenContext, CodeGenerator,
-};
-
-pub fn call_nac3_ndarray_fill_generic<'ctx, G: CodeGenerator + ?Sized>(
-    generator: &mut G,
-    ctx: &mut CodeGenContext<'ctx, '_>,
-    ndarray_ptr: Pointer<'ctx, StructModel<NpArray<'ctx>>>,
-    fill_value_ptr: Pointer<'ctx, ByteModel>,
-) {
-    let sizet = generator.get_sizet(ctx.ctx);
-
-    FunctionBuilder::begin(
-        ctx,
-        &get_sized_dependent_function_name(sizet, "__nac3_ndarray_fill_generic"),
-    )
-    .arg("ndarray", ndarray_ptr)
-    .arg("pvalue", fill_value_ptr)
-    .returning_void();
-}

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

@@ -1,169 +1,29 @@
 use crate::codegen::{
-    irrt::{
-        error_context::{check_error_context, setup_error_context},
-        slice::{RustUserSlice, SliceIndex, UserSlice},
-        util::get_sized_dependent_function_name,
-    },
-    model::*,
-    structs::ndarray::NpArray,
+    expr::infer_and_call_function,
+    irrt::get_usize_dependent_function_name,
+    values::{ndarray::NDArrayValue, ArrayLikeValue, ArraySliceValue, ProxyValue},
     CodeGenContext, CodeGenerator,
 };
 
-#[derive(Debug, Clone, Copy)]
-pub struct NDIndexFields {
-    pub type_: Field<ByteModel>, // Defined to be uint8_t in IRRT
-    pub data: Field<PointerModel<ByteModel>>,
-}
-
-#[derive(Debug, Clone, Copy, Default, PartialEq, Eq)]
-pub struct NDIndex;
-
-impl<'ctx> StructKind<'ctx> for NDIndex {
-    type Fields = NDIndexFields;
-
-    fn struct_name(&self) -> &'static str {
-        "NDIndex"
-    }
-
-    fn build_fields(&self, builder: &mut FieldBuilder<'ctx>) -> Self::Fields {
-        Self::Fields { type_: builder.add_field_auto("type"), data: builder.add_field_auto("data") }
-    }
-}
-
-// An enum variant to store the content
-// and type of an NDIndex in high level.
-#[derive(Debug, Clone)]
-pub enum RustNDIndex<'ctx> {
-    SingleElement(NInt<'ctx, SliceIndex>),
-    Slice(RustUserSlice<'ctx>),
-}
-
-impl<'ctx> RustNDIndex<'ctx> {
-    fn irrt_ndindex_id(&self) -> u64 {
-        // Defined in IRRT, must be in sync
-        match self {
-            RustNDIndex::SingleElement(_) => 0,
-            RustNDIndex::Slice(_) => 1,
-        }
-    }
-
-    fn write_to_ndindex(
-        &self,
-        ctx: &CodeGenContext<'ctx, '_>,
-        dst_ndindex_ptr: Pointer<'ctx, StructModel<NDIndex>>,
-    ) {
-        let byte_model = ByteModel::default();
-        let slice_index_model = NIntModel(SliceIndex::default());
-        let user_slice_model = StructModel(UserSlice);
-
-        // Set `dst_ndindex_ptr->type`
-        dst_ndindex_ptr
-            .gep(ctx, |f| f.type_)
-            .store(ctx, byte_model.constant(ctx.ctx, self.irrt_ndindex_id()));
-
-        // Set `dst_ndindex_ptr->data`
-        let data = match self {
-            RustNDIndex::SingleElement(in_index) => {
-                let index_ptr = slice_index_model.alloca(ctx, "index");
-                index_ptr.store(ctx, *in_index);
-                index_ptr.cast_to(ctx, NIntModel(Byte), "")
-            }
-            RustNDIndex::Slice(in_rust_slice) => {
-                let user_slice_ptr = user_slice_model.alloca(ctx, "user_slice");
-                in_rust_slice.write_to_user_slice(ctx, user_slice_ptr);
-                user_slice_ptr.cast_to(ctx, NIntModel(Byte), "")
-            }
-        };
-        dst_ndindex_ptr.gep(ctx, |f| f.data).store(ctx, data);
-    }
-
-    // Allocate an array of `NDIndex`es onto the stack and return its stack pointer
-    pub fn alloca_ndindexes<G: CodeGenerator + ?Sized>(
-        generator: &mut G,
-        ctx: &CodeGenContext<'ctx, '_>,
-        ndindexes: &[RustNDIndex<'ctx>],
-    ) -> ArraySlice<'ctx, SizeTModel<'ctx>, StructModel<NDIndex>> {
-        let sizet = generator.get_sizet(ctx.ctx);
-
-        let ndindex_model = StructModel(NDIndex);
-        let ndindex_array = ndindex_model.array_alloca(
-            ctx,
-            sizet.constant(ctx.ctx, ndindexes.len() as u64),
-            "ndindexs",
-        );
-
-        for (i, rust_ndindex) in ndindexes.iter().enumerate() {
-            let ndindex_ptr =
-                ndindex_array.ix_unchecked(ctx, sizet.constant(ctx.ctx, i as u64), "");
-            rust_ndindex.write_to_ndindex(ctx, ndindex_ptr);
-        }
-
-        ndindex_array
-    }
-
-    #[must_use]
-    pub fn deduce_ndims_after_slicing(slices: &[RustNDIndex], original_ndims: i32) -> i32 {
-        let mut final_ndims: i32 = original_ndims;
-        for slice in slices {
-            match slice {
-                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>,
-    num_ndindexs: SizeT<'ctx>,
-    ndindexs: Pointer<'ctx, StructModel<NDIndex>>,
-) -> SizeT<'ctx> {
-    let sizet = generator.get_sizet(ctx.ctx);
-
-    let final_ndims = sizet.alloca(ctx, "result");
-
-    let errctx_ptr = setup_error_context(ctx);
-    FunctionBuilder::begin(
-        ctx,
-        &get_sized_dependent_function_name(
-            sizet,
-            "__nac3_ndarray_indexing_deduce_ndims_after_indexing",
-        ),
-    )
-    .arg("errctx", errctx_ptr)
-    .arg("result", final_ndims)
-    .arg("ndims", ndims)
-    .arg("num_ndindexs", num_ndindexs)
-    .arg("ndindexs", ndindexs)
-    .returning_void();
-    check_error_context(generator, ctx, errctx_ptr);
-
-    final_ndims.load(ctx, "final_ndims")
-}
-
 pub fn call_nac3_ndarray_index<'ctx, G: CodeGenerator + ?Sized>(
-    generator: &mut G,
-    ctx: &mut CodeGenContext<'ctx, '_>,
-    num_indexes: SizeT<'ctx>,
-    indexes: Pointer<'ctx, StructModel<NDIndex>>,
-    src_ndarray: Pointer<'ctx, StructModel<NpArray<'ctx>>>,
-    dst_ndarray: Pointer<'ctx, StructModel<NpArray<'ctx>>>,
+    generator: &G,
+    ctx: &CodeGenContext<'ctx, '_>,
+    indices: ArraySliceValue<'ctx>,
+    src_ndarray: NDArrayValue<'ctx>,
+    dst_ndarray: NDArrayValue<'ctx>,
 ) {
-    let sizet = generator.get_sizet(ctx.ctx);
-    let errctx_ptr = setup_error_context(ctx);
-
-    FunctionBuilder::begin(ctx, &get_sized_dependent_function_name(sizet, "__nac3_ndarray_index"))
-        .arg("errctx", errctx_ptr)
-        .arg("num_indexes", num_indexes)
-        .arg("indexes", indexes)
-        .arg("src_ndarray", src_ndarray)
-        .arg("dst_ndarray", dst_ndarray)
-        .returning_void();
-
-    check_error_context(generator, ctx, errctx_ptr);
+    let name = get_usize_dependent_function_name(generator, ctx, "__nac3_ndarray_index");
+    infer_and_call_function(
+        ctx,
+        &name,
+        None,
+        &[
+            indices.size(ctx, generator).into(),
+            indices.base_ptr(ctx, generator).into(),
+            src_ndarray.as_base_value().into(),
+            dst_ndarray.as_base_value().into(),
+        ],
+        None,
+        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

@@ -1,6 +1,391 @@
-pub mod allocation;
-pub mod basic;
-pub mod fill;
-pub mod indexing;
-pub mod reshape;
-pub mod transpose;
+use inkwell::{
+    types::IntType,
+    values::{BasicValueEnum, CallSiteValue, IntValue},
+    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

@@ -1,30 +0,0 @@
-use crate::codegen::{
-    irrt::{
-        error_context::{check_error_context, setup_error_context},
-        util::get_sized_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: SizeT<'ctx>,
-    new_ndims: SizeT<'ctx>,
-    new_shape: Pointer<'ctx, SizeTModel<'ctx>>,
-) {
-    let sizet = generator.get_sizet(ctx.ctx);
-
-    let perrctx = setup_error_context(ctx);
-    FunctionBuilder::begin(
-        ctx,
-        &get_sized_dependent_function_name(sizet, "__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/ndarray/transpose.rs

@@ -1,43 +0,0 @@
-use crate::codegen::{
-    irrt::{
-        error_context::{check_error_context, setup_error_context},
-        util::get_sized_dependent_function_name,
-    },
-    model::*,
-    structs::ndarray::NpArray,
-    CodeGenContext, CodeGenerator,
-};
-
-pub fn call_nac3_ndarray_transpose<'ctx, G: CodeGenerator + ?Sized>(
-    generator: &mut G,
-    ctx: &mut CodeGenContext<'ctx, '_>,
-    src_ndarray: Pointer<'ctx, StructModel<NpArray<'ctx>>>,
-    dst_ndarray: Pointer<'ctx, StructModel<NpArray<'ctx>>>,
-    axes_or_none: Option<ArraySlice<'ctx, SizeTModel<'ctx>, SizeTModel<'ctx>>>,
-) -> Pointer<'ctx, StructModel<NpArray<'ctx>>> {
-    let sizet = generator.get_sizet(ctx.ctx);
-    let axes_model = PointerModel(sizet);
-
-    let (num_axes, axes) = match axes_or_none {
-        Some(axes) => (axes.num_elements, axes.pointer),
-        None => {
-            // Please refer to the comment in the IRRT implementation
-            (sizet.constant(ctx.ctx, 0), axes_model.nullptr(ctx.ctx))
-        }
-    };
-
-    let perrctx = setup_error_context(ctx);
-    FunctionBuilder::begin(
-        ctx,
-        &get_sized_dependent_function_name(sizet, "__nac3_ndarray_transpose"),
-    )
-    .arg("errctx", perrctx)
-    .arg("src_ndarray", src_ndarray)
-    .arg("dst_ndarray", dst_ndarray)
-    .arg("num_axes", num_axes)
-    .arg("axes", axes)
-    .returning_void();
-    check_error_context(generator, ctx, perrctx);
-
-    dst_ndarray
-}

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

@@ -1,84 +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
-pub type SliceIndex = Int32;
+use nac3parser::ast::Expr;
 
-#[derive(Debug, Clone)]
-pub struct UserSliceFields {
-    pub start_defined: Field<BoolModel>,
-    pub start: Field<NIntModel<SliceIndex>>,
-    pub stop_defined: Field<BoolModel>,
-    pub stop: Field<NIntModel<SliceIndex>>,
-    pub step_defined: Field<BoolModel>,
-    pub step: Field<NIntModel<SliceIndex>>,
-}
-
-#[derive(Debug, Clone, Copy, Default, PartialEq, Eq)]
-pub struct UserSlice;
-
-impl<'ctx> StructKind<'ctx> for UserSlice {
-    type Fields = UserSliceFields;
-
-    fn struct_name(&self) -> &'static str {
-        "UserSlice"
-    }
-
-    fn build_fields(&self, builder: &mut FieldBuilder<'ctx>) -> Self::Fields {
-        Self::Fields {
-            start_defined: builder.add_field_auto("start_defined"),
-            start: builder.add_field_auto("start"),
-            stop_defined: builder.add_field_auto("stop_defined"),
-            stop: builder.add_field_auto("stop"),
-            step_defined: builder.add_field_auto("step_defined"),
-            step: builder.add_field_auto("step"),
-        }
-    }
-}
-
-#[derive(Debug, Clone)]
-pub struct RustUserSlice<'ctx> {
-    pub start: Option<NInt<'ctx, SliceIndex>>,
-    pub stop: Option<NInt<'ctx, SliceIndex>>,
-    pub step: Option<NInt<'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,
-        ctx: &CodeGenContext<'ctx, '_>,
-        dst_slice_ptr: Pointer<'ctx, StructModel<UserSlice>>,
-    ) {
-        // TODO: make this neater, with a helper lambda?
-
-        let bool_model = BoolModel::default();
-
-        let false_ = bool_model.constant(ctx.ctx, 0);
-        let true_ = bool_model.constant(ctx.ctx, 1);
-
-        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_),
-        }
-    }
+use crate::{
+    codegen::{CodeGenContext, CodeGenerator},
+    typecheck::typedef::Type,
+};
+
+/// 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(),
+    ))
 }

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

@@ -1,16 +0,0 @@
-use crate::codegen::model::*;
-
-#[must_use]
-pub fn get_sized_dependent_function_name(sizet: SizeTModel<'_>, fn_name: &str) -> String {
-    // When its 32-bits, the function name is "{fn_name}"
-    // When its 64-bits, the function name is "{fn_name}64"
-    let mut fn_name = fn_name.to_owned();
-    match sizet.0.get_bit_width() {
-        32 => {}
-        64 => fn_name.push_str("64"),
-        bit_width => {
-            panic!("Unsupported int type bit width {bit_width}, must be either 32-bits or 64-bits")
-        }
-    }
-    fn_name
-}

nac3core/src/codegen/llvm_intrinsics.rs

@@ -1,12 +1,14 @@
-use crate::codegen::CodeGenContext;
-use inkwell::context::Context;
-use inkwell::intrinsics::Intrinsic;
-use inkwell::types::AnyTypeEnum::IntType;
-use inkwell::types::FloatType;
-use inkwell::values::{BasicValueEnum, CallSiteValue, FloatValue, IntValue, PointerValue};
-use inkwell::AddressSpace;
+use inkwell::{
+    context::Context,
+    intrinsics::Intrinsic,
+    types::{AnyTypeEnum::IntType, FloatType},
+    values::{BasicValueEnum, CallSiteValue, FloatValue, IntValue, PointerValue},
+    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)
-/// Use `BasicValueEnum::into_int_value` for Integer return type and `BasicValueEnum::into_float_value` for Float return type
+/// * `$map_fn:ident`: Mapping function to be applied on `BasicValue` (`BasicValue` -> Function Return Type).
+///   Use `BasicValueEnum::into_int_value` for Integer return type and
+///   `BasicValueEnum::into_float_value` for Float return type
 /// * `$llvm_ty:ident`: Type of first operand
 /// * `,($val:ident)*`: Comma separated list of operands
 macro_rules! generate_llvm_intrinsic_fn_body {
@@ -188,8 +268,8 @@ macro_rules! generate_llvm_intrinsic_fn_body {
 /// Arguments:
 /// * `float/int`: Indicates the return and argument type of the function
 /// * `$fn_name:ident`: The identifier of the rust function to be generated
-/// * `$llvm_name:literal`: Name of underlying llvm intrinsic function
-/// Omit "llvm." prefix from the function name i.e. use "ceil" instead of "llvm.ceil"
+/// * `$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
 macro_rules! generate_llvm_intrinsic_fn {
@@ -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::{
-    codegen::classes::{ListType, ProxyType, RangeType},
-    symbol_resolver::{StaticValue, SymbolResolver},
-    toplevel::{helper::PrimDef, TopLevelContext, TopLevelDef},
-    typecheck::{
-        type_inferencer::{CodeLocation, PrimitiveStore},
-        typedef::{CallId, FuncArg, Type, TypeEnum, Unifier},
+use std::{
+    collections::{HashMap, HashSet},
+    sync::{
+        atomic::{AtomicBool, Ordering},
+        Arc,
     },
+    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::{
-    atomic::{AtomicBool, Ordering},
-    Arc,
+
+use nac3parser::ast::{Location, Stmt, StrRef};
+
+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 structs::{cslice::CSlice, exception::Exception, ndarray::NpArray};
+use concrete_type::{ConcreteType, ConcreteTypeEnum, ConcreteTypeStore};
+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 structs;
+pub mod types;
+pub mod values;
 
 #[cfg(test)]
 mod test;
-pub mod util;
 
-use concrete_type::{ConcreteType, ConcreteTypeEnum, ConcreteTypeStore};
-pub use generator::{CodeGenerator, DefaultCodeGenerator};
+mod macros {
+    /// 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 {
@@ -74,6 +93,16 @@ pub struct CodeGenLLVMOptions {
     pub target: CodeGenTargetMachineOptions,
 }
 
+impl CodeGenLLVMOptions {
+    /// Creates a [`TargetMachine`] using the target options specified by this struct.
+    ///
+    /// See [`Target::create_target_machine`].
+    #[must_use]
+    pub fn create_target_machine(&self) -> Option<TargetMachine> {
+        self.target.create_target_machine(self.opt_level)
+    }
+}
+
 /// Additional options for code generation for the target machine.
 #[derive(Clone, Debug, Eq, PartialEq)]
 pub struct CodeGenTargetMachineOptions {
@@ -164,11 +193,11 @@ pub struct CodeGenContext<'ctx, 'a> {
     pub registry: &'a WorkerRegistry,
 
     /// Cache for constant strings.
-    pub const_strings: HashMap<String, Struct<'ctx, CSlice<'ctx>>>,
+    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<Pointer<'ctx, StructModel<Exception<'ctx>>>>,
+    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.
@@ -344,6 +373,10 @@ impl WorkerRegistry {
         let mut builder = context.create_builder();
         let mut module = context.create_module(generator.get_name());
 
+        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",
             inkwell::module::FlagBehavior::Warning,
@@ -367,6 +400,10 @@ impl WorkerRegistry {
                     errors.insert(e);
                     // create a new empty module just to continue codegen and collect errors
                     module = context.create_module(&format!("{}_recover", generator.get_name()));
+
+                    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());
                 }
             }
             *self.task_count.lock() -= 1;
@@ -432,7 +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>>,
@@ -477,9 +514,13 @@ fn get_llvm_type<'ctx, G: CodeGenerator + ?Sized>(
                         }
 
                         TObj { obj_id, .. } if *obj_id == PrimDef::NDArray.id() => {
-                            let sizet = generator.get_sizet(ctx);
-                            let pndarray_model = PointerModel(StructModel(NpArray { sizet }));
-                            pndarray_model.get_type(ctx).into()
+                            let (dtype, ndims) = unpack_ndarray_var_tys(unifier, ty);
+                            let ndims = extract_ndims(unifier, ndims);
+                            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!(
@@ -523,8 +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| {
@@ -554,7 +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>>,
@@ -563,11 +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`.
@@ -592,6 +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,
@@ -649,24 +726,47 @@ pub fn gen_func_impl<
         ..primitives
     };
 
-    let sizet = generator.get_sizet(context);
-    let cslice_type = StructModel(CSlice { sizet });
-    let pexception_type = PointerModel(StructModel(Exception { sizet }));
-
-    let mut type_cache: HashMap<_, BasicTypeEnum<'ctx>> = [
+    let mut type_cache: HashMap<_, _> = [
         (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_type.get_type(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, pexception_type.get_type(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()
+            }
+        }),
     ]
-    .into_iter()
+    .iter()
+    .copied()
     .collect();
-
     // NOTE: special handling of option cannot use this type cache since it contains type var,
     // handled inside get_llvm_type instead
 
@@ -680,6 +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),
@@ -702,7 +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,
@@ -721,9 +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),
-        _ => context.void_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, vararg_arg.is_some()),
     };
 
     let symbol = &task.symbol_name;
@@ -751,9 +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,
@@ -786,6 +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 {
@@ -1008,3 +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

@@ -1,204 +0,0 @@
-use core::fmt;
-use std::marker::PhantomData;
-
-use inkwell::{
-    context::Context,
-    types::{BasicType, BasicTypeEnum, IntType},
-    values::{BasicValue, IntValue, PointerValue},
-};
-
-use crate::codegen::{CodeGenContext, CodeGenerator};
-
-use super::{ArraySlice, Pointer, PointerModel};
-
-/*
-TODO: UPDATE when the Model finally stablizes
-Explanation on the abstraction:
-
-    In LLVM, there are TYPES and VALUES.
-
-    Inkwell gives us TYPES [`BasicTypeEnum<'ctx>`] and VALUES [`BasicValueEnum<'ctx>`],
-        but by themselves, they lack a lot of Rust compile-time known info.
-
-        e.g., You did `let ptr = builder.build_alloca(my_llvm_ndarray_struct_ty)`,
-        but `ptr` is just a `PointerValue<'ctx>`, almost everything about the
-        underlying `my_llvm_ndarray_struct_ty` is gone.
-
-    The `Model` abstraction is a wrapper around inkwell TYPES and VALUES but with
-        a richer interface.
-
-    `Model<'ctx>` is a wrapper around for an inkwell TYPE:
-        - `NIntModel<Byte>` is a i8.
-        - `NIntModel<Int32>` is a i32.
-        - `NIntModel<Int64>` is a i64.
-        - `IntModel` is a carrier for an inkwell `IntType<'ctx>`,
-              used when the type is dynamic/cannot be specified in Rust compile-time.
-        - `PointerModel<'ctx, E>` is a wrapper for `PointerType<'ctx>`,
-              where `E` is another `Model<'ctx>` that describes the element type of the pointer.
-        - `StructModel<'ctx, NDArray>` is a wrapper for `StructType<'ctx>`,
-              with additional information encoded within `NDArray`. (See `IsStruct<'ctx>`)
-
-    `Model<'ctx>::Value`/`ModelValue<'ctx>` is a wrapper around for an inkwell VALUE:
-        - `NInt<'ctx, T>` is a value of `NIntModel<'ctx, T>`,
-              where `T` could be `Byte`, `Int32`, or `Int64`.
-        - `Pointer<'ctx, E>` is a value of `PointerModel<'ctx, E>`.
-
-    Other interesting utilities:
-        - Given a `Model<'ctx>`, say, `let ndarray_model = StructModel<'ctx, NDArray>`,
-              you are do `ndarray_model.alloca(ctx, "my_ndarray")` to get a `Pointer<'ctx, Struct<'ctx, NDArray>>`,
-              notice that all LLVM type information are preserved.
-        - For a `let my_ndarray = Pointer<'ctx, StructModel<NDArray>>`, you can access a field by doing
-              `my_ndarray.gep(ctx, |f| f.itemsize).load() // or .store()`, and you can chain them
-              together for nested structures.
-
-    A brief summary on the `Model<'ctx>` and `ModelValue<'ctx>` traits:
-        - Model<'ctx>
-            // The associated ModelValue of this Model
-            - type Value: ModelValue<'ctx>
-
-            // Get the LLVM type of this Model
-            - fn get_llvm_type(&self)
-
-            // Check if the input type is equal to the LLVM type of this Model
-            // NOTE: this function is provideed through `CanCheckLLVMType<'ctx>`
-            - fn check_llvm_type(&self, ty) -> Result<(), String>
-
-            // Check if the input value's type is equal to the LLVM type of this Model.
-            //
-            // If so, wrap it with `Self::Value`.
-            - fn review_value<V: BasicType<'ctx>>(&self, val: V) -> Result<Self::Value, String>
-
-        - ModelValue<'ctx>
-            // get the LLVM value of this ModelValue
-            - fn get_llvm_value(&self) -> BasicValueEnum<'ctx>
-*/
-
-#[derive(Debug, Clone)]
-pub struct ModelError(pub String);
-
-// NOTE: Should have been within [`Model<'ctx>`],
-// but rust object safety requirements made it necessary to
-// split the trait.
-pub trait CanCheckLLVMType<'ctx> {
-    /// See [`Model::check_llvm_type`]
-    fn check_llvm_type_impl(
-        &self,
-        ctx: &'ctx Context,
-        ty: BasicTypeEnum<'ctx>,
-    ) -> Result<(), ModelError>;
-}
-
-pub trait Model<'ctx>: fmt::Debug + Clone + Copy + CanCheckLLVMType<'ctx> + Sized + Eq {
-    /// The corresponding LLVM [`BasicValue<'ctx>`] of this Model.
-    type Value: BasicValue<'ctx>;
-    /// The corresponding LLVM [`BasicType<'ctx>`] of this Model.
-    type Type: BasicType<'ctx>;
-
-    /// Get the LLVM type of this [`Model<'ctx>`]
-    fn get_type(&self, ctx: &'ctx Context) -> Self::Type;
-
-    /// Check if the input type is equal to the LLVM type of this Model.
-    ///
-    /// If it doesn't match, an [`Err`] with a human-readable message is
-    /// thrown explaining *how* it was different. Meant for debugging.
-    fn check_type<T: BasicType<'ctx>>(&self, ctx: &'ctx Context, ty: T) -> Result<(), ModelError> {
-        self.check_llvm_type_impl(ctx, ty.as_basic_type_enum())
-    }
-
-    /// Check if an LLVM value's type is equal to the LLVM type of this [`Model`].
-    /// If so, wrap it with [`Instance`].
-    fn review_value<V: BasicValue<'ctx>>(
-        &self,
-        ctx: &'ctx Context,
-        value: V,
-    ) -> Result<Instance<'ctx, Self>, ModelError>;
-
-    /// Directly create an [`Instance`] of this [`Model`].
-    ///
-    /// It is assumed that the LLVM type of `value` has been checked.
-    ///
-    /// It is recommended that you use [`Model::review_value`] instead in order to
-    /// catch bugs.
-    fn believe_value(&self, value: Self::Value) -> Instance<'ctx, Self> {
-        Instance { model: *self, value, _phantom: PhantomData }
-    }
-
-    /// Build an instruction to allocate a value with the LLVM type of this [`Model<'ctx>`].
-    fn alloca(&self, ctx: &CodeGenContext<'ctx, '_>, name: &str) -> Pointer<'ctx, Self> {
-        let ptr_model = PointerModel(*self);
-        let ptr = ctx.builder.build_alloca(self.get_type(ctx.ctx), name).unwrap();
-        ptr_model.believe_value(ptr)
-    }
-
-    /// Build an instruction to allocate an array of the LLVM type of this [`Model<'ctx>`].
-    fn array_alloca<N>(
-        &self,
-        ctx: &CodeGenContext<'ctx, '_>,
-        num_elements: Instance<'ctx, N>,
-        name: &str,
-    ) -> ArraySlice<'ctx, N, Self>
-    where
-        N: Model<'ctx, Value = IntValue<'ctx>, Type = IntType<'ctx>>,
-    {
-        let ptr_model = PointerModel(*self);
-        let ptr = ctx
-            .builder
-            .build_array_alloca(
-                self.get_type(ctx.ctx).as_basic_type_enum(),
-                num_elements.value,
-                name,
-            )
-            .unwrap();
-        let pointer = ptr_model.believe_value(ptr);
-
-        ArraySlice { pointer, num_elements }
-    }
-
-    /// Do [`CodeGenerator::gen_var_alloc`] with the LLVM type of this [`Model<'ctx>`].
-    fn var_alloc<G: CodeGenerator + ?Sized>(
-        &self,
-        generator: &mut G,
-        ctx: &mut CodeGenContext<'ctx, '_>,
-        name: Option<&str>,
-    ) -> Result<Pointer<'ctx, Self>, String> {
-        let ptr_model = PointerModel(*self);
-        let ptr =
-            generator.gen_var_alloc(ctx, self.get_type(ctx.ctx).as_basic_type_enum(), name)?;
-        Ok(ptr_model.believe_value(ptr))
-    }
-
-    /// Do [`CodeGenerator::gen_array_var_alloc`] with the LLVM type of this [`Model<'ctx>`].
-    fn array_var_alloc<G: CodeGenerator + ?Sized, N>(
-        &self,
-        generator: &mut G,
-        ctx: &mut CodeGenContext<'ctx, '_>,
-        num_elements: Instance<'ctx, N>,
-        name: Option<&'ctx str>,
-    ) -> Result<ArraySlice<'ctx, N, Self>, String>
-    where
-        N: Model<'ctx, Value = IntValue<'ctx>, Type = IntType<'ctx>>,
-    {
-        let ptr_model = PointerModel(*self);
-
-        // TODO: Remove ProxyType ArraySlice
-        let ptr = ptr_model.believe_value(PointerValue::from(generator.gen_array_var_alloc(
-            ctx,
-            self.get_type(ctx.ctx).as_basic_type_enum(),
-            num_elements.value,
-            name,
-        )?));
-
-        Ok(ArraySlice { num_elements, pointer: ptr })
-    }
-}
-
-/// An LLVM value of a type of a [`Model<'ctx>`].
-///
-/// It is guaranteed that [`Instance::value`]'s LLVM type
-/// has been *checked* to match [`Instance::model`].
-#[derive(Debug, Clone, Copy)]
-pub struct Instance<'ctx, M: Model<'ctx>> {
-    pub model: M,
-    pub value: M::Value,
-    _phantom: PhantomData<&'ctx ()>,
-}

nac3core/src/codegen/model/fixed_int.rs

@@ -1,161 +0,0 @@
-use core::fmt;
-
-use inkwell::{
-    context::Context,
-    types::{BasicTypeEnum, IntType},
-    values::{BasicValue, IntValue},
-};
-
-use super::{
-    core::*,
-    int_util::{check_int_llvm_type, int_constant, review_int_llvm_value},
-    Int, IntModel,
-};
-
-/// A marker trait to mark a singleton struct that describes a particular fixed integer type.
-/// See [`Bool`], [`Byte`], [`Int32`], etc.
-///
-/// The [`Default`] trait is to enable auto-instantiations.
-pub trait NIntKind: fmt::Debug + Clone + Copy + Default + PartialEq + Eq {
-    /// Get the [`IntType<'ctx>`] of this [`NIntKind`].
-    fn get_int_type(ctx: &Context) -> IntType<'_>;
-
-    /// Get the [`IntType<'ctx>`] of this [`NIntKind`].
-    ///
-    /// Compared to using [`NIntKind::get_int_type`], this
-    /// function does not require [`Context`].
-    fn get_bit_width() -> u32;
-}
-
-/// A [`Model`] representing an [`IntType<'ctx>`] of a specified bit width.
-///
-/// Also see [`IntModel`], which is less constrained than [`NIntModel`],
-/// but enables one to handle dynamic [`IntType<'ctx>`] at runtime.
-#[derive(Debug, Clone, Copy, Default, PartialEq, Eq)]
-pub struct NIntModel<T: NIntKind>(pub T);
-pub type NInt<'ctx, T> = Instance<'ctx, NIntModel<T>>;
-
-impl<'ctx, T: NIntKind> CanCheckLLVMType<'ctx> for NIntModel<T> {
-    fn check_llvm_type_impl(
-        &self,
-        ctx: &'ctx Context,
-        ty: BasicTypeEnum<'ctx>,
-    ) -> Result<(), ModelError> {
-        check_int_llvm_type(ty, T::get_int_type(ctx))
-    }
-}
-
-impl<'ctx, T: NIntKind> Model<'ctx> for NIntModel<T> {
-    type Type = IntType<'ctx>;
-    type Value = IntValue<'ctx>;
-
-    fn get_type(&self, ctx: &'ctx Context) -> Self::Type {
-        T::get_int_type(ctx)
-    }
-
-    fn review_value<V: BasicValue<'ctx>>(
-        &self,
-        ctx: &'ctx Context,
-        value: V,
-    ) -> Result<NInt<'ctx, T>, ModelError> {
-        let value = review_int_llvm_value(value.as_basic_value_enum(), T::get_int_type(ctx))?;
-        Ok(self.believe_value(value))
-    }
-}
-
-impl<T: NIntKind> NIntModel<T> {
-    /// "Demote" this [`NIntModel<T>`] to an [`IntModel`].
-    ///
-    /// Information about the [`NIntKind`] will be lost.
-    pub fn to_int_model(self, ctx: &Context) -> IntModel<'_> {
-        IntModel(T::get_int_type(ctx))
-    }
-
-    /// Create an unsigned constant of this [`NIntModel`].
-    pub fn constant<'ctx>(&self, ctx: &'ctx Context, value: u64) -> NInt<'ctx, T> {
-        int_constant(ctx, *self, value)
-    }
-}
-
-impl<'ctx, T: NIntKind> NInt<'ctx, T> {
-    /// "Demote" this [`NInt<T>`] to an [`Int`].
-    ///
-    /// Information about the [`NIntKind`] will be lost.
-    pub fn to_int(self, ctx: &'ctx Context) -> Int<'ctx> {
-        let int_model = self.model.to_int_model(ctx);
-        int_model.believe_value(self.value)
-    }
-}
-
-// Some pre-defined fixed integer types
-
-#[derive(Debug, Clone, Copy, Default, PartialEq, Eq)]
-pub struct Bool;
-pub type BoolModel = NIntModel<Bool>;
-
-impl NIntKind for Bool {
-    fn get_int_type(ctx: &Context) -> IntType<'_> {
-        ctx.bool_type()
-    }
-
-    fn get_bit_width() -> u32 {
-        1
-    }
-}
-
-// Extra utilities for [`Bool`]
-impl NIntModel<Bool> {
-    /// Create a constant `false`
-    #[must_use]
-    pub fn const_false<'ctx>(&self, ctx: &'ctx Context) -> NInt<'ctx, Bool> {
-        self.constant(ctx, 0)
-    }
-
-    /// Create a constant `true`
-    #[must_use]
-    pub fn const_true<'ctx>(&self, ctx: &'ctx Context) -> NInt<'ctx, Bool> {
-        self.constant(ctx, 1)
-    }
-}
-
-#[derive(Debug, Clone, Copy, Default, PartialEq, Eq)]
-pub struct Byte;
-pub type ByteModel = NIntModel<Byte>;
-
-impl NIntKind for Byte {
-    fn get_int_type(ctx: &Context) -> IntType<'_> {
-        ctx.i8_type()
-    }
-
-    fn get_bit_width() -> u32 {
-        8
-    }
-}
-
-#[derive(Debug, Clone, Copy, Default, PartialEq, Eq)]
-pub struct Int32;
-pub type Int32Model = NIntModel<Int32>;
-
-impl NIntKind for Int32 {
-    fn get_int_type(ctx: &Context) -> IntType<'_> {
-        ctx.i32_type()
-    }
-
-    fn get_bit_width() -> u32 {
-        32
-    }
-}
-
-#[derive(Debug, Clone, Copy, Default, PartialEq, Eq)]
-pub struct Int64;
-pub type Int64Model = NIntModel<Int64>;
-
-impl NIntKind for Int64 {
-    fn get_int_type(ctx: &Context) -> IntType<'_> {
-        ctx.i64_type()
-    }
-
-    fn get_bit_width() -> u32 {
-        64
-    }
-}

nac3core/src/codegen/model/function_builder.rs

@@ -1,66 +0,0 @@
-use inkwell::{
-    types::{BasicMetadataTypeEnum, BasicType},
-    values::{AnyValue, BasicMetadataValueEnum, BasicValue, BasicValueEnum},
-};
-
-use crate::codegen::{model::*, CodeGenContext};
-
-// TODO: Variadic argument?
-pub struct FunctionBuilder<'ctx, 'a> {
-    ctx: &'a CodeGenContext<'ctx, 'a>,
-    fn_name: &'a str,
-    arguments: Vec<(BasicMetadataTypeEnum<'ctx>, BasicMetadataValueEnum<'ctx>)>,
-}
-
-impl<'ctx, 'a> FunctionBuilder<'ctx, 'a> {
-    pub fn begin(ctx: &'a CodeGenContext<'ctx, 'a>, fn_name: &'a str) -> Self {
-        FunctionBuilder { ctx, fn_name, arguments: Vec::new() }
-    }
-
-    // NOTE: `_name` is for self-documentation
-    #[must_use]
-    #[allow(clippy::needless_pass_by_value)]
-    pub fn arg<M: Model<'ctx>>(mut self, _name: &'static str, arg: Instance<'ctx, M>) -> Self {
-        self.arguments.push((
-            arg.model.get_type(self.ctx.ctx).as_basic_type_enum().into(),
-            arg.value.as_basic_value_enum().into(),
-        ));
-        self
-    }
-
-    pub fn returning<M: Model<'ctx>>(
-        self,
-        name: &'static str,
-        return_model: M,
-    ) -> Instance<'ctx, M> {
-        let (param_tys, param_vals): (Vec<_>, Vec<_>) = self.arguments.into_iter().unzip();
-
-        // Get the LLVM function, create (by declaring) the function if it doesn't exist in `ctx.module`.
-        let function = self.ctx.module.get_function(self.fn_name).unwrap_or_else(|| {
-            let fn_type = return_model.get_type(self.ctx.ctx).fn_type(&param_tys, false);
-            self.ctx.module.add_function(self.fn_name, fn_type, None)
-        });
-
-        // Build call
-        let ret = self.ctx.builder.build_call(function, &param_vals, name).unwrap();
-
-        // Check the return value/type
-        let Ok(ret) = BasicValueEnum::try_from(ret.as_any_value_enum()) else {
-            panic!("Return type is not a BasicValue");
-        };
-        return_model.review_value(self.ctx.ctx, ret).unwrap()
-    }
-
-    // TODO: Code duplication, but otherwise returning<S: Optic<'ctx>> cannot resolve S if return_optic = None
-    pub fn returning_void(self) {
-        let (param_tys, param_vals): (Vec<_>, Vec<_>) = self.arguments.into_iter().unzip();
-
-        let function = self.ctx.module.get_function(self.fn_name).unwrap_or_else(|| {
-            let return_type = self.ctx.ctx.void_type();
-            let fn_type = return_type.fn_type(&param_tys, false);
-            self.ctx.module.add_function(self.fn_name, fn_type, None)
-        });
-
-        self.ctx.builder.build_call(function, &param_vals, "").unwrap();
-    }
-}

nac3core/src/codegen/model/int.rs

@@ -1,107 +0,0 @@
-use inkwell::{
-    context::Context,
-    types::{BasicTypeEnum, IntType},
-    values::{BasicValue, IntValue},
-};
-
-use super::{
-    core::*,
-    int_util::{check_int_llvm_type, int_constant, review_int_llvm_value},
-};
-
-/// A model representing an [`IntType<'ctx>`].
-///
-/// Also see [`NIntModel`][`super::NIntModel`], which is more constrained than [`IntModel`]
-/// but provides more type-safe mechanisms and even auto-derivation of [`BasicTypeEnum<'ctx>`]
-/// for creating LLVM structures.
-#[derive(Debug, Clone, Copy, PartialEq, Eq)]
-pub struct IntModel<'ctx>(pub IntType<'ctx>);
-
-pub type Int<'ctx> = Instance<'ctx, IntModel<'ctx>>;
-
-impl<'ctx> CanCheckLLVMType<'ctx> for IntModel<'ctx> {
-    fn check_llvm_type_impl(
-        &self,
-        _ctx: &'ctx Context,
-        ty: BasicTypeEnum<'ctx>,
-    ) -> Result<(), ModelError> {
-        check_int_llvm_type(ty, self.0)
-    }
-}
-
-impl<'ctx> Model<'ctx> for IntModel<'ctx> {
-    type Value = IntValue<'ctx>;
-    type Type = IntType<'ctx>;
-
-    fn get_type(&self, _ctx: &'ctx Context) -> Self::Type {
-        self.0
-    }
-
-    fn review_value<V: BasicValue<'ctx>>(
-        &self,
-        _ctx: &'ctx Context,
-        value: V,
-    ) -> Result<Int<'ctx>, ModelError> {
-        let value = review_int_llvm_value(value.as_basic_value_enum(), self.0)?;
-        Ok(self.believe_value(value))
-    }
-}
-
-impl<'ctx> IntModel<'ctx> {
-    /// Create a constant value that inhabits this [`IntModel<'ctx>`].
-    #[must_use]
-    pub fn constant(&self, ctx: &'ctx Context, value: u64) -> Int<'ctx> {
-        int_constant(ctx, *self, value)
-    }
-}
-
-impl<'ctx> From<IntValue<'ctx>> for Int<'ctx> {
-    fn from(value: IntValue<'ctx>) -> Self {
-        let model = IntModel(value.get_type());
-        model.believe_value(value)
-    }
-}
-
-/// A model representing an [`IntType<'ctx>`] that happens to be defined as `size_t`.
-///
-/// This is specifically created to guide developers to write `size_t`-dependent code.
-#[derive(Debug, Clone, Copy, PartialEq, Eq)]
-pub struct SizeTModel<'ctx>(pub IntType<'ctx>);
-
-pub type SizeT<'ctx> = Instance<'ctx, SizeTModel<'ctx>>;
-
-impl<'ctx> CanCheckLLVMType<'ctx> for SizeTModel<'ctx> {
-    fn check_llvm_type_impl(
-        &self,
-        _ctx: &'ctx Context,
-        ty: BasicTypeEnum<'ctx>,
-    ) -> Result<(), ModelError> {
-        check_int_llvm_type(ty, self.0)
-    }
-}
-
-impl<'ctx> Model<'ctx> for SizeTModel<'ctx> {
-    type Value = IntValue<'ctx>;
-    type Type = IntType<'ctx>;
-
-    fn get_type(&self, _ctx: &'ctx Context) -> Self::Type {
-        self.0
-    }
-
-    fn review_value<V: BasicValue<'ctx>>(
-        &self,
-        _ctx: &'ctx Context,
-        value: V,
-    ) -> Result<SizeT<'ctx>, ModelError> {
-        let value = review_int_llvm_value(value.as_basic_value_enum(), self.0)?;
-        Ok(self.believe_value(value))
-    }
-}
-
-impl<'ctx> SizeTModel<'ctx> {
-    /// Create a constant value that inhabits this [`SizeTModel<'ctx>`].
-    #[must_use]
-    pub fn constant(&self, ctx: &'ctx Context, value: u64) -> SizeT<'ctx> {
-        int_constant(ctx, *self, value)
-    }
-}

nac3core/src/codegen/model/int_util.rs

@@ -1,87 +0,0 @@
-use inkwell::{
-    context::Context,
-    types::{BasicType, BasicTypeEnum, IntType},
-    values::{BasicValueEnum, IntValue},
-};
-
-use crate::codegen::CodeGenContext;
-
-use super::{Instance, Model, ModelError};
-
-/// Helper function to check if `scrutinee` is the same as `expected_int_type`
-pub fn check_int_llvm_type<'ctx>(
-    ty: BasicTypeEnum<'ctx>,
-    expected_int_type: IntType<'ctx>,
-) -> Result<(), ModelError> {
-    // Check if llvm_type is int type
-    let BasicTypeEnum::IntType(ty) = ty else {
-        return Err(ModelError(format!("Expecting an int type but got {ty:?}")));
-    };
-
-    // Check bit width
-    if ty.get_bit_width() != expected_int_type.get_bit_width() {
-        return Err(ModelError(format!(
-            "Expecting an int type of {}-bit(s) but got int type {}-bit(s)",
-            expected_int_type.get_bit_width(),
-            ty.get_bit_width()
-        )));
-    }
-
-    Ok(())
-}
-
-/// Helper function to cast `scrutinee` is into an [`IntValue<'ctx>`].
-/// The LLVM type of `scrutinee` will be checked with [`check_int_llvm_type`].
-pub fn review_int_llvm_value<'ctx>(
-    value: BasicValueEnum<'ctx>,
-    expected_int_type: IntType<'ctx>,
-) -> Result<IntValue<'ctx>, ModelError> {
-    // Check if value is of int type, error if that is anything else
-    check_int_llvm_type(value.get_type().as_basic_type_enum(), expected_int_type)?;
-
-    // Ok, it is must be an int
-    Ok(value.into_int_value())
-}
-
-pub fn int_constant<'ctx, M>(ctx: &'ctx Context, model: M, value: u64) -> Instance<'ctx, M>
-where
-    M: Model<'ctx, Value = IntValue<'ctx>, Type = IntType<'ctx>>,
-{
-    let value = model.get_type(ctx).const_int(value, false);
-    model.believe_value(value)
-}
-
-impl<'ctx, M> Instance<'ctx, M>
-where
-    M: Model<'ctx, Value = IntValue<'ctx>, Type = IntType<'ctx>>,
-{
-    pub fn s_extend_or_bit_cast<N>(
-        &self,
-        ctx: &CodeGenContext<'ctx, '_>,
-        to_model: N,
-        name: &str,
-    ) -> Instance<'ctx, N>
-    where
-        N: Model<'ctx, Value = IntValue<'ctx>, Type = IntType<'ctx>>,
-    {
-        let value = ctx
-            .builder
-            .build_int_s_extend_or_bit_cast(self.value, to_model.get_type(ctx.ctx), name)
-            .unwrap();
-        to_model.believe_value(value)
-    }
-
-    pub fn truncate<N>(
-        &self,
-        ctx: &CodeGenContext<'ctx, '_>,
-        to_model: N,
-        name: &str,
-    ) -> Instance<'ctx, N>
-    where
-        N: Model<'ctx, Value = IntValue<'ctx>, Type = IntType<'ctx>>,
-    {
-        let value =
-            ctx.builder.build_int_truncate(self.value, to_model.get_type(ctx.ctx), name).unwrap();
-        to_model.believe_value(value)
-    }
-}

nac3core/src/codegen/model/mod.rs

@@ -1,18 +0,0 @@
-pub mod core;
-pub mod fixed_int;
-pub mod function_builder;
-pub mod int;
-mod int_util;
-pub mod opaque;
-pub mod pointer;
-pub mod slice;
-pub mod structure;
-
-pub use core::*;
-pub use fixed_int::*;
-pub use function_builder::*;
-pub use int::*;
-pub use opaque::*;
-pub use pointer::*;
-pub use slice::*;
-pub use structure::*;

nac3core/src/codegen/model/opaque.rs

@@ -1,57 +0,0 @@
-use inkwell::{
-    context::Context,
-    types::BasicTypeEnum,
-    values::{BasicValue, BasicValueEnum},
-};
-
-use super::*;
-
-/// A [`Model`] that holds an arbitrary [`BasicTypeEnum`].
-///
-/// Use this and [`Opaque`] when you are dealing with a [`BasicTypeEnum<'ctx>`]
-/// at runtime and there is no way to abstract your implementation
-/// with [`Model`].
-#[derive(Debug, Clone, Copy, PartialEq, Eq)]
-pub struct OpaqueModel<'ctx>(pub BasicTypeEnum<'ctx>);
-
-impl<'ctx> CanCheckLLVMType<'ctx> for OpaqueModel<'ctx> {
-    fn check_llvm_type_impl(
-        &self,
-        _ctx: &'ctx Context,
-        ty: BasicTypeEnum<'ctx>,
-    ) -> Result<(), ModelError> {
-        if ty == self.0 {
-            Ok(())
-        } else {
-            Err(ModelError(format!("Expecting {}, but got {}", self.0, ty)))
-        }
-    }
-}
-
-impl<'ctx> Model<'ctx> for OpaqueModel<'ctx> {
-    type Value = BasicValueEnum<'ctx>;
-    type Type = BasicTypeEnum<'ctx>;
-
-    fn get_type(&self, _ctx: &'ctx Context) -> BasicTypeEnum<'ctx> {
-        self.0
-    }
-
-    fn review_value<V: BasicValue<'ctx>>(
-        &self,
-        ctx: &'ctx Context,
-        value: V,
-    ) -> Result<Opaque<'ctx>, ModelError> {
-        let value = value.as_basic_value_enum();
-        self.check_type(ctx, value.get_type())?;
-        Ok(self.believe_value(value))
-    }
-}
-
-pub type Opaque<'ctx> = Instance<'ctx, OpaqueModel<'ctx>>;
-
-impl<'ctx> From<BasicValueEnum<'ctx>> for Opaque<'ctx> {
-    fn from(value: BasicValueEnum<'ctx>) -> Self {
-        let model = OpaqueModel(value.get_type());
-        model.believe_value(value)
-    }
-}

nac3core/src/codegen/model/pointer.rs

@@ -1,126 +0,0 @@
-use inkwell::{
-    context::Context,
-    types::{BasicType, BasicTypeEnum, PointerType},
-    values::{BasicValue, PointerValue},
-    AddressSpace,
-};
-
-use crate::codegen::{model::*, CodeGenContext};
-
-use super::{core::*, OpaqueModel};
-
-/// A [`Model<'ctx>`] representing an LLVM [`PointerType<'ctx>`]
-/// with *full* information on the element u
-///
-/// [`self.0`] contains [`Model<'ctx>`] that represents the
-/// LLVM type of element of the [`PointerType<'ctx>`] is pointing at
-/// (like `PointerType<'ctx>::get_element_type()`, but abstracted as a [`Model<'ctx>`]).
-#[derive(Debug, Clone, Copy, Default, PartialEq, Eq)]
-pub struct PointerModel<E>(pub E);
-
-pub type Pointer<'ctx, E> = Instance<'ctx, PointerModel<E>>;
-
-impl<'ctx, E: Model<'ctx>> CanCheckLLVMType<'ctx> for PointerModel<E> {
-    fn check_llvm_type_impl(
-        &self,
-        ctx: &'ctx Context,
-        ty: BasicTypeEnum<'ctx>,
-    ) -> Result<(), ModelError> {
-        // Check if scrutinee is even a PointerValue
-        let BasicTypeEnum::PointerType(ty) = ty else {
-            return Err(ModelError(format!("Expecting a pointer value, but got {ty:?}")));
-        };
-
-        // Check the type of what the pointer is pointing at
-        // TODO: This will be deprecated by inkwell > llvm14 because `get_element_type()` will be gone
-        let Ok(element_ty) = BasicTypeEnum::try_from(ty.get_element_type()) else {
-            return Err(ModelError(format!(
-                "Expecting pointer to point to an inkwell BasicValue, but got {ty:?}"
-            )));
-        };
-
-        self.0.check_type(ctx, element_ty) // TODO: Include backtrace?
-    }
-}
-
-impl<'ctx, E: Model<'ctx>> Model<'ctx> for PointerModel<E> {
-    type Value = PointerValue<'ctx>;
-    type Type = PointerType<'ctx>;
-
-    fn get_type(&self, ctx: &'ctx Context) -> Self::Type {
-        self.0.get_type(ctx).ptr_type(AddressSpace::default())
-    }
-
-    fn review_value<V: BasicValue<'ctx>>(
-        &self,
-        ctx: &'ctx Context,
-        value: V,
-    ) -> Result<Pointer<'ctx, E>, ModelError> {
-        let value = value.as_basic_value_enum();
-        self.check_type(ctx, value.get_type())?;
-        Ok(self.believe_value(value.into_pointer_value()))
-    }
-}
-
-impl<'ctx, E: Model<'ctx>> PointerModel<E> {
-    /// Create a null [`Pointer`] of this [`PointerModel`]
-    pub fn nullptr(&self, ctx: &'ctx Context) -> Pointer<'ctx, E> {
-        let nullptr = self.get_type(ctx).const_null();
-        self.believe_value(nullptr)
-    }
-}
-
-impl<'ctx, E: Model<'ctx>> Pointer<'ctx, E> {
-    /// Build an instruction to store a value into this pointer
-    pub fn store(&self, ctx: &CodeGenContext<'ctx, '_>, instance: Instance<'ctx, E>) {
-        assert_eq!(
-            self.model.0, instance.model,
-            "Attempting to store an Instance of a different type"
-        );
-        ctx.builder.build_store(self.value, instance.value).unwrap();
-    }
-
-    /// Build an instruction to load a value from this pointer
-    pub fn load(&self, ctx: &CodeGenContext<'ctx, '_>, name: &str) -> Instance<'ctx, E> {
-        let value = ctx.builder.build_load(self.value, name).unwrap();
-        self.model.0.review_value(ctx.ctx, value).unwrap() // If unwrap() panics, there is a logic error in your code.
-    }
-
-    /// "Demote" the [`Model`] of the thing this pointer is pointing to.
-    pub fn cast_to_opaque(self, ctx: &'ctx Context) -> Pointer<'ctx, OpaqueModel<'ctx>> {
-        let ptr_model = PointerModel(OpaqueModel(self.model.get_type(ctx).as_basic_type_enum()));
-        ptr_model.believe_value(self.value)
-    }
-
-    /// Cast the [`Model`] of the thing this pointer is pointing to
-    /// and uses inkwell's [`Builder::build_pointer_cast`] to cast the LLVM pointer type.
-    pub fn cast_to<K: Model<'ctx>>(
-        self,
-        ctx: &CodeGenContext<'ctx, '_>,
-        element: K,
-        name: &str,
-    ) -> Pointer<'ctx, K> {
-        let casted_ptr_model = PointerModel(element);
-        let casted_ptr = ctx
-            .builder
-            .build_pointer_cast(
-                self.value,
-                element.get_type(ctx.ctx).ptr_type(AddressSpace::default()),
-                name,
-            )
-            .unwrap();
-        casted_ptr_model.believe_value(casted_ptr)
-    }
-
-    pub fn is_null(&self, ctx: &CodeGenContext<'ctx, '_>, name: &str) -> NInt<'ctx, Bool> {
-        let model = NIntModel(Bool);
-        let value = ctx.builder.build_is_null(self.value, name).unwrap();
-        model.believe_value(value)
-    }
-
-    pub fn is_not_null(&self, ctx: &CodeGenContext<'ctx, '_>, name: &str) -> NInt<'ctx, Bool> {
-        let model = NIntModel(Bool);
-        let value = ctx.builder.build_is_not_null(self.value, name).unwrap();
-        model.believe_value(value)
-    }
-}

nac3core/src/codegen/model/slice.rs

@@ -1,94 +0,0 @@
-use inkwell::{types::IntType, values::IntValue};
-
-use crate::codegen::{CodeGenContext, CodeGenerator};
-
-use super::{int_util::int_constant, Instance, Model, Pointer};
-
-/// An LLVM "slice" - literally just a pointer and a length value.
-/// The pointer points to a location with `num_elements` **contiguously** placed
-/// values of [`E`][`Model<ctx>`] in memory.
-///
-/// NOTE: This is NOT a [`Model`]! This is simply a helper
-/// structure to aggregate a length value and a pointer together.
-pub struct ArraySlice<'ctx, N, E>
-where
-    N: Model<'ctx, Value = IntValue<'ctx>, Type = IntType<'ctx>>,
-    E: Model<'ctx>,
-{
-    pub pointer: Pointer<'ctx, E>,
-    pub num_elements: Instance<'ctx, N>,
-}
-
-impl<'ctx, N, E> ArraySlice<'ctx, N, E>
-where
-    N: Model<'ctx, Value = IntValue<'ctx>, Type = IntType<'ctx>>,
-    E: Model<'ctx>,
-{
-    /// Get the [Model][`super::Model`] of the element type of this [`ArraySlice`]
-    pub fn get_element_model(&self) -> E {
-        self.pointer.model.0
-    }
-
-    /// 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,
-        ctx: &CodeGenContext<'ctx, '_>,
-        idx: Instance<'ctx, N>,
-        name: &str,
-    ) -> Pointer<'ctx, E> {
-        assert_eq!(idx.model, self.num_elements.model);
-        let element_ptr = unsafe {
-            ctx.builder.build_in_bounds_gep(self.pointer.value, &[idx.value], name).unwrap()
-        };
-        self.pointer.model.review_value(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: Instance<'ctx, N>,
-        name: &str,
-    ) -> Pointer<'ctx, E> {
-        assert_eq!(idx.model, self.num_elements.model);
-        let int_type = self.num_elements.model;
-
-        // 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,
-                int_constant(ctx.ctx, int_type, 0).value,
-                idx.value,
-                "lower_bounded",
-            )
-            .unwrap();
-        let upper_bounded = ctx
-            .builder
-            .build_int_compare(
-                inkwell::IntPredicate::SLT,
-                idx.value,
-                self.num_elements.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.num_elements.value), None],
-            ctx.current_loc
-        );
-
-        self.ix_unchecked(ctx, idx, name)
-    }
-}

nac3core/src/codegen/model/structure.rs

@@ -1,384 +0,0 @@
-use core::fmt;
-
-use inkwell::{
-    context::Context,
-    types::{BasicType, BasicTypeEnum, StructType},
-    values::{BasicValue, StructValue},
-};
-use itertools::{izip, Itertools};
-
-use crate::codegen::CodeGenContext;
-
-use super::{core::CanCheckLLVMType, Instance, Model, ModelError, Pointer, PointerModel};
-
-/// An LLVM struct's "field".
-#[derive(Debug, Clone, Copy)]
-pub struct Field<E> {
-    /// The GEP index of this field.
-    pub gep_index: u64,
-
-    /// The name of this field. Generally named
-    /// to how the field is named in ARTIQ or IRRT.
-    ///
-    /// NOTE: This is only used for debugging.
-    pub name: &'static str,
-
-    /// The [`Model`] of this field.
-    pub model: E,
-}
-
-// A helper struct for [`FieldBuilder`]
-struct FieldLLVM<'ctx> {
-    gep_index: u64,
-    name: &'ctx str,
-
-    // Only CanCheckLLVMType is needed, dont use `Model<'ctx>`
-    llvm_type_model: Box<dyn CanCheckLLVMType<'ctx> + 'ctx>,
-    llvm_type: BasicTypeEnum<'ctx>,
-}
-
-/// A helper struct to create [`Field`]-s in [`StructKind::build_fields`].
-///
-/// See [`StructKind`] for more details and see how [`FieldBuilder`] is put
-/// into action.
-pub struct FieldBuilder<'ctx> {
-    /// The [`Context`] this [`FieldBuilder`] is under.
-    ///
-    /// Can be used in [`StructKind::build_fields`].
-    /// See [`StructKind`] for more details and see how [`FieldBuilder`] is put
-    /// into action.
-    pub ctx: &'ctx Context,
-
-    /// An incrementing counter for GEP indices when
-    /// doing [`FieldBuilder::add_field`] or [`FieldBuilder::add_field_auto`].
-    gep_index_counter: u64,
-
-    /// Name of the `struct` this [`FieldBuilder`] is currently
-    /// building.
-    ///
-    /// NOTE: This is only used for debugging.
-    struct_name: &'ctx str,
-
-    /// The fields added so far.
-    fields: Vec<FieldLLVM<'ctx>>,
-}
-
-impl<'ctx> FieldBuilder<'ctx> {
-    #[must_use]
-    pub fn new(ctx: &'ctx Context, struct_name: &'ctx str) -> Self {
-        FieldBuilder { ctx, gep_index_counter: 0, struct_name, fields: Vec::new() }
-    }
-
-    fn next_gep_index(&mut self) -> u64 {
-        let index = self.gep_index_counter;
-        self.gep_index_counter += 1;
-        index
-    }
-
-    /// Add a new field.
-    ///
-    /// - `name`: The name of the field. See [`Field::name`].
-    /// - `element`: The [`Model`] of the type of the field. See [`Field::element`].
-    pub fn add_field<E: Model<'ctx> + 'ctx>(&mut self, name: &'static str, element: E) -> Field<E> {
-        let gep_index = self.next_gep_index();
-
-        self.fields.push(FieldLLVM {
-            gep_index,
-            name,
-            llvm_type: element.get_type(self.ctx).as_basic_type_enum(),
-            llvm_type_model: Box::new(element),
-        });
-
-        Field { gep_index, name, model: element }
-    }
-
-    /// Like [`FieldBuilder::add_field`] but `element` can be **automatically derived**
-    /// if it has the `Default` instance.
-    ///
-    /// Certain [`Model`] has a [`Default`] trait - [`Model`]s that are just singletons,
-    /// By deriving the [`Default`] trait on those [`Model`]s, Rust could automatically
-    /// construct the [`Model`] with [`Default::default`].
-    ///
-    /// This function is equivalent to
-    /// ```ignore
-    /// self.add_field(name, E::default())
-    /// ```
-    pub fn add_field_auto<E: Model<'ctx> + Default + 'ctx>(
-        &mut self,
-        name: &'static str,
-    ) -> Field<E> {
-        self.add_field(name, E::default())
-    }
-}
-
-/// A marker trait to mark singleton struct that
-/// describes a particular LLVM structure.
-///
-/// It is a powerful inkwell abstraction that can reduce
-/// a lot of inkwell boilerplate when dealing with LLVM structs,
-/// `getelementptr`, `load`-ing and `store`-ing fields.
-///
-/// ### Usage
-pub trait StructKind<'ctx>: fmt::Debug + Clone + Copy + PartialEq + Eq {
-    /// The type of the Rust `struct` that holds all the fields of this LLVM struct.
-    type Fields;
-
-    // TODO:
-    /// The name of this [`StructKind`].
-    ///
-    /// The name should be the name of in
-    /// IRRT's `struct` or ARTIQ's definition.
-    fn struct_name(&self) -> &'static str;
-
-    /// Define the [`Field`]s of this [`StructKind`]
-    ///
-    ///
-    /// ### Syntax
-    ///
-    /// Suppose you want to define the following C++ `struct`s in `nac3core`:
-    /// ```cpp
-    /// template <typename SizeT>
-    /// struct Str {
-    ///     uint8_t* content; // NOTE: could be `void *`
-    ///     SizeT length;
-    /// }
-    ///
-    /// template <typename SizeT>
-    /// struct Exception {
-    ///     uint32_t id;
-    ///     Str message;
-    ///     uint64_t param0;
-    ///     uint64_t param1;
-    ///     uint64_t param2;
-    /// }
-    /// ```
-    ///
-    /// You write this in nac3core:
-    /// ```ignore
-    /// struct Str<'ctx> {
-    ///     sizet: IntModel<'ctx>,
-    /// }
-    ///
-    /// struct StrFields<'ctx> {
-    ///     content: Field<PointerModel<ByteModel>>, // equivalent to `NIntModel<Byte>`.
-    ///     length: Field<IntModel<'ctx>>, // `SizeT` is only known in runtime - `CodeGenerator::get_size_type()`.  /// }
-    /// }
-    ///
-    /// impl StructKind<'ctx> for Str<'ctx> {
-    ///     fn struct_name() {
-    ///         "Str"
-    ///     }
-    ///
-    ///     fn build_fields(&self, builder: &mut FieldBuilder<'ctx>) -> Self::Fields {
-    ///         // THE order of `builder.add_field*` is IMPORTANT!!!
-    ///         // so the GEP indices would be correct.
-    ///         StrFields {
-    ///             content: builder.add_field_auto("content"), // `PointerModel<ByteModel>` has `Default` trait.
-    ///             length: builder.add_field("length", IntModel(self.sizet)), // `PointerModel<ByteModel>` has `Default` trait.
-    ///         }
-    ///     }
-    /// }
-    ///
-    /// struct Exception<'ctx> {
-    ///     sizet: IntModel<'ctx>,
-    /// }
-    ///
-    /// struct ExceptionFields<'ctx> {
-    ///     id: Field<NIntModel<Int32>>,
-    ///     message: Field<StructModel<Str>>,
-    ///     param0: Field<NIntModel<Int64>>,
-    ///     param1: Field<NIntModel<Int64>>,
-    ///     param2: Field<NIntModel<Int64>>,
-    /// }
-    ///
-    /// impl StructKind<'ctx> for Exception<'ctx> {
-    ///     fn struct_name() {
-    ///         "Exception"
-    ///     }
-    ///
-    ///     fn build_fields(&self, builder: &mut FieldBuilder<'ctx>) -> Self::Fields {
-    ///         // THE order of `builder.add_field*` is IMPORTANT!!!
-    ///         // so the GEP indices would be correct.
-    ///         ExceptionFields {
-    ///             id: builder.add_field_auto("content"), // `NIntModel<Int32>` has `Default` trait.
-    ///             message: builder.add_field("message", StructModel(Str { sizet: self.sizet })),
-    ///             param0: builder.add_field_auto("param0"), // has `Default` trait
-    ///             param1: builder.add_field_auto("param1"), // has `Default` trait
-    ///             param2: builder.add_field_auto("param2"), // has `Default` trait
-    ///         }
-    ///     }
-    /// }
-    /// ```
-    ///
-    /// Then to `alloca` an `Exception`, do this:
-    /// ```ignore
-    /// let generator: dyn CodeGenerator<'ctx>;
-    /// let ctx: &CodeGenContext<'ctx, '_>;
-    /// let sizet = generator.get_size_type();
-    /// let exn_model = StructModel(Exception { sizet });
-    /// let exn = exn_model.alloca(ctx, "my_exception"); // Every [`Model<'ctx>`] has an `.alloca()` function.
-    /// // exn: Pointer<'ctx, StructModel<Exception>>
-    /// ```
-    ///
-    /// NOTE: In fact, it is possible to define `Str` and `Exception` like this:
-    /// ```ignore
-    /// struct Str<SizeT: NIntModel> {
-    ///     _phantom: PhantomData<SizeT>,
-    /// }
-    ///
-    /// struct Exception<T: NIntModel> {
-    ///     _phantom: PhantomData<SizeT>,
-    /// }
-    /// ```
-    /// But issues arise by you don't know the nac3core
-    /// `CodeGenerator`'s `get_size_type()` before hand.
-    fn build_fields(&self, builder: &mut FieldBuilder<'ctx>) -> Self::Fields;
-}
-
-/// A [`Model<'ctx>`] that represents an LLVM struct.
-///
-/// `self.0` contains a [`StructKind<'ctx>`] that gives the details of the LLVM struct.
-#[derive(Debug, Clone, Copy, Default, PartialEq, Eq)]
-pub struct StructModel<S>(pub S);
-pub type Struct<'ctx, S> = Instance<'ctx, StructModel<S>>;
-
-impl<'ctx, S: StructKind<'ctx>> CanCheckLLVMType<'ctx> for StructModel<S> {
-    fn check_llvm_type_impl(
-        &self,
-        ctx: &'ctx Context,
-        ty: BasicTypeEnum<'ctx>,
-    ) -> Result<(), ModelError> {
-        // Check if scrutinee is even a struct type
-        let BasicTypeEnum::StructType(ty) = ty else {
-            return Err(ModelError(format!("Expecting a struct type, but got {ty:?}")));
-        };
-
-        // Ok. now check the struct type thoroughly
-        self.check_struct_type(ctx, ty)
-    }
-}
-
-impl<'ctx, S: StructKind<'ctx>> Model<'ctx> for StructModel<S> {
-    type Value = StructValue<'ctx>;
-    type Type = StructType<'ctx>;
-
-    fn get_type(&self, ctx: &'ctx Context) -> Self::Type {
-        self.get_struct_type(ctx)
-    }
-
-    fn review_value<V: BasicValue<'ctx>>(
-        &self,
-        ctx: &'ctx Context,
-        value: V,
-    ) -> Result<Struct<'ctx, S>, ModelError> {
-        let value = value.as_basic_value_enum();
-        self.check_type(ctx, value.get_type())?;
-        Ok(self.believe_value(value.into_struct_value()))
-    }
-}
-
-impl<'ctx, S: StructKind<'ctx>> StructModel<S> {
-    /// Get the [`S::Fields`] of this [`StructModel`].
-    pub fn get_fields(&self, ctx: &'ctx Context) -> S::Fields {
-        let mut builder = FieldBuilder::new(ctx, self.0.struct_name());
-        self.0.build_fields(&mut builder)
-    }
-
-    /// Get the LLVM struct type this [`IsStruct<'ctx>`] is representing.
-    pub fn get_struct_type(&self, ctx: &'ctx Context) -> StructType<'ctx> {
-        let mut builder = FieldBuilder::new(ctx, self.0.struct_name());
-        self.0.build_fields(&mut builder); // Self::Fields is discarded
-
-        let field_types = builder.fields.iter().map(|f| f.llvm_type).collect_vec();
-        ctx.struct_type(&field_types, false)
-    }
-
-    /// Check if `scrutinee` matches the [`StructType<'ctx>`] this [`IsStruct<'ctx>`] is representing.
-    pub fn check_struct_type(
-        &self,
-        ctx: &'ctx Context,
-        scrutinee: StructType<'ctx>,
-    ) -> Result<(), ModelError> {
-        // Details about scrutinee
-        let scrutinee_field_types = scrutinee.get_field_types();
-
-        // Details about the defined specifications of this struct
-        // We will access them through builder
-        let mut builder = FieldBuilder::new(ctx, self.0.struct_name());
-        self.0.build_fields(&mut builder);
-
-        // Check # of fields
-        if builder.fields.len() != scrutinee_field_types.len() {
-            return Err(ModelError(format!(
-                "Expecting struct to have {} field(s), but scrutinee has {} field(s)",
-                builder.fields.len(),
-                scrutinee_field_types.len()
-            )));
-        }
-
-        // Check the types of each field
-        // TODO: Traceback?
-        for (f, scrutinee_field_type) in izip!(builder.fields, scrutinee_field_types) {
-            f.llvm_type_model
-                .check_llvm_type_impl(ctx, scrutinee_field_type.as_basic_type_enum())?;
-        }
-
-        Ok(())
-    }
-}
-
-impl<'ctx, S: StructKind<'ctx>> Pointer<'ctx, StructModel<S>> {
-    /// Build an instruction that does `getelementptr` on an LLVM structure referenced by this pointer.
-    ///
-    /// This provides a nice syntax to chain up `getelementptr` in an intuitive and type-safe way:
-    ///
-    /// ```ignore
-    /// let ctx: &CodeGenContext<'ctx, '_>;
-    /// let ndarray: Pointer<'ctx, StructModel<NpArray<'ctx>>>;
-    /// ndarray.gep(ctx, |f| f.ndims).store();
-    /// ```
-    ///
-    /// You might even write chains `gep`, i.e.,
-    /// ```ignore
-    /// let exn_ptr: Pointer<'ctx, StructModel<Exception>>;
-    /// let value: Int<'ctx>; // Suppose it has the correct inkwell `IntType<'ctx>`.
-    ///
-    /// // To do `exn.message.length = value`:
-    /// let exn_message_ptr = exn_ptr.gep(ctx, |f| f.message);
-    /// let exn_message_length_ptr = exn_message_ptr.gep(ctx, |f| f.length);
-    /// exn_message_length_ptr.store(ctx, my_value);
-    ///
-    /// // or simply:
-    /// exn_ptr
-    ///     .gep(ctx, |f| f.message)
-    ///     .gep(ctx, |f| f.length)
-    ///     .store(ctx, my_value) // Equivalent to `my_struct.thing1.value = my_value`
-    /// ```
-    pub fn gep<E, GetFieldFn>(
-        &self,
-        ctx: &CodeGenContext<'ctx, '_>,
-        get_field: GetFieldFn,
-    ) -> Pointer<'ctx, E>
-    where
-        E: Model<'ctx>,
-        GetFieldFn: FnOnce(S::Fields) -> Field<E>,
-    {
-        let fields = self.model.0.get_fields(ctx.ctx);
-        let field = get_field(fields);
-
-        // TODO: I think I'm not supposed to *just* use i32 for GEP like that
-        let llvm_i32 = ctx.ctx.i32_type();
-
-        let ptr_model = PointerModel(field.model);
-        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()
-        };
-        ptr_model.believe_value(ptr)
-    }
-}

nac3core/src/codegen/numpy_new/factory.rs

@@ -1,213 +0,0 @@
-use inkwell::{
-    types::BasicType,
-    values::{BasicValue, BasicValueEnum, PointerValue},
-};
-use nac3parser::ast::StrRef;
-
-use crate::{
-    codegen::{
-        irrt::ndarray::{
-            allocation::{alloca_ndarray, init_ndarray_data_by_alloca, init_ndarray_shape},
-            fill::call_nac3_ndarray_fill_generic,
-        },
-        model::*,
-        structs::ndarray::NpArray,
-        util::shape::parse_input_shape_arg,
-        CodeGenContext, CodeGenerator,
-    },
-    symbol_resolver::ValueEnum,
-    toplevel::DefinitionId,
-    typecheck::typedef::{FunSignature, Type},
-};
-
-/// 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<Pointer<'ctx, StructModel<NpArray<'ctx>>>, String>
-where
-    G: CodeGenerator + ?Sized,
-{
-    let sizet = generator.get_sizet(ctx.ctx);
-
-    let shape_writer = parse_input_shape_arg(generator, ctx, shape, shape_ty);
-    let ndims = shape_writer.count;
-
-    let ndarray = alloca_ndarray(generator, ctx, ndims, name)?;
-    init_ndarray_shape(generator, ctx, ndarray, &shape_writer)?;
-
-    let itemsize = sizet
-        .review_value(ctx.ctx, ctx.get_llvm_type(generator, elem_ty).size_of().unwrap())
-        .unwrap();
-    ndarray.gep(ctx, |f| f.itemsize).store(ctx, itemsize);
-
-    init_ndarray_data_by_alloca(generator, ctx, ndarray); // Needs `itemsize` and `shape` initialized first
-
-    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<Pointer<'ctx, StructModel<NpArray<'ctx>>>, String>
-where
-    G: CodeGenerator + ?Sized,
-{
-    let byte_model = NIntModel(Byte);
-    let fill_value_model = OpaqueModel(fill_value.get_type());
-
-    // Caller has to put fill_value on the stack and pass its address
-    let fill_value_ptr = fill_value_model.alloca(ctx, "fill_value_ptr");
-    fill_value_ptr.store(ctx, fill_value_model.believe_value(fill_value));
-    let fill_value_ptr = fill_value_ptr.cast_to(ctx, byte_model, "fill_value_bytes_ptr");
-
-    let ndarray_ptr = create_empty_ndarray(generator, ctx, elem_ty, shape, shape_ty, name)?;
-    call_nac3_ndarray_fill_generic(generator, ctx, ndarray_ptr, fill_value_ptr);
-
-    Ok(ndarray_ptr)
-}
-
-/// 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/mod.rs

@@ -1,2 +0,0 @@
-pub mod factory;
-pub mod view;

nac3core/src/codegen/numpy_new/view.rs

@@ -1,169 +0,0 @@
-use inkwell::values::PointerValue;
-use nac3parser::ast::StrRef;
-
-use crate::{
-    codegen::{
-        irrt::ndarray::{
-            allocation::{alloca_ndarray, init_ndarray_shape},
-            basic::{
-                call_nac3_ndarray_is_c_contiguous, call_nac3_ndarray_nbytes,
-                call_nac3_ndarray_set_strides_by_shape, call_nac3_ndarray_size,
-            },
-            reshape::call_nac3_ndarray_resolve_and_check_new_shape,
-            transpose::call_nac3_ndarray_transpose,
-        },
-        model::*,
-        structs::{list::List, ndarray::NpArray},
-        util::{array_writer::ArrayWriter, shape::parse_input_shape_arg},
-        CodeGenContext, CodeGenerator,
-    },
-    symbol_resolver::ValueEnum,
-    toplevel::DefinitionId,
-    typecheck::typedef::{FunSignature, Type},
-};
-
-fn reshape_ndarray_or_copy<'ctx, G: CodeGenerator + ?Sized>(
-    generator: &mut G,
-    ctx: &mut CodeGenContext<'ctx, '_>,
-    src_ndarray: Pointer<'ctx, StructModel<NpArray<'ctx>>>,
-    new_shape: &ArrayWriter<'ctx, G, SizeTModel<'ctx>, SizeTModel<'ctx>>,
-) -> Result<Pointer<'ctx, StructModel<NpArray<'ctx>>>, String> {
-    let byte_model = NIntModel(Byte);
-
-    /*
-        Reference pseudo-code:
-        ```c
-        NDArray<SizeT>* src_ndarray;
-
-        NDArray<SizeT>* dst_ndarray = __builtin_alloca(...);
-        dst_ndarray->ndims = ...
-        dst_ndarray->strides = __builtin_alloca(...);
-        dst_ndarray->shape = ... // Directly set by user, may contain -1, or even illegal values.
-        dst_ndarray->itemsize = src_ndarray->itemsize;
-        set_strides_by_shape(dst_ndarray);
-
-        // Do assertions on `dst_ndarray->shape` and resolve -1
-
-        resolve_and_check_new_shape(ndarray_size(src_ndarray), dst_ndarray->shape);
-
-        if (is_c_contiguous(src_ndarray)) {
-            dst_ndarray->data = src_ndarray->data;
-        } else {
-            dst_ndarray->data = __builtin_alloca( ndarray_nbytes(dst_ndarray) );
-            copy_data(src_ndarray, dst_ndarray);
-        }
-
-        return dst_ndarray;
-        ```
-    */
-
-    let current_bb = ctx.builder.get_insert_block().unwrap();
-    let then_bb = ctx.ctx.insert_basic_block_after(current_bb, "then");
-    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");
-
-    // current_bb
-    let dst_ndarray = alloca_ndarray(generator, ctx, new_shape.count, "ndarray").unwrap();
-
-    init_ndarray_shape(generator, ctx, dst_ndarray, new_shape)?;
-    dst_ndarray
-        .gep(ctx, |f| f.itemsize)
-        .store(ctx, src_ndarray.gep(ctx, |f| f.itemsize).load(ctx, "itemsize"));
-
-    call_nac3_ndarray_set_strides_by_shape(generator, ctx, dst_ndarray);
-
-    let src_ndarray_size = call_nac3_ndarray_size(generator, ctx, src_ndarray);
-    call_nac3_ndarray_resolve_and_check_new_shape(
-        generator,
-        ctx,
-        src_ndarray_size,
-        dst_ndarray.gep(ctx, |f| f.ndims).load(ctx, "ndims"),
-        dst_ndarray.gep(ctx, |f| f.shape).load(ctx, "shape"),
-    );
-
-    let is_c_contiguous = call_nac3_ndarray_is_c_contiguous(generator, ctx, src_ndarray);
-    ctx.builder.build_conditional_branch(is_c_contiguous.value, then_bb, else_bb).unwrap();
-
-    // then_bb: reshape is possible without copying
-    ctx.builder.position_at_end(then_bb);
-    dst_ndarray.gep(ctx, |f| f.data).store(ctx, src_ndarray.gep(ctx, |f| f.data).load(ctx, "data"));
-    ctx.builder.build_unconditional_branch(end_bb).unwrap();
-
-    // else_bb: reshape is impossible without copying
-    ctx.builder.position_at_end(else_bb);
-    let dst_ndarray_nbytes = call_nac3_ndarray_nbytes(generator, ctx, dst_ndarray);
-    let data = byte_model.array_alloca(ctx, dst_ndarray_nbytes, "new_data").pointer;
-    dst_ndarray.gep(ctx, |f| f.data).store(ctx, data);
-    ctx.builder.build_unconditional_branch(end_bb).unwrap();
-
-    // Reposition for continuation
-    ctx.builder.position_at_end(end_bb);
-
-    Ok(dst_ndarray)
-}
-
-/// Generates LLVM IR for `np.reshape`.
-pub fn gen_ndarray_reshape<'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 ndarray
-    let ndarray_ty = fun.0.args[0].ty;
-    let ndarray_arg = args[0].1.clone().to_basic_value_enum(context, generator, ndarray_ty)?;
-
-    // Parse argument #2 shape
-    let shape_ty = fun.0.args[1].ty;
-    let shape_arg = args[1].1.clone().to_basic_value_enum(context, generator, shape_ty)?;
-
-    let sizet = generator.get_sizet(context.ctx);
-    let pndarray_model = PointerModel(StructModel(NpArray { sizet }));
-
-    let src_ndarray = pndarray_model.review_value(context.ctx, ndarray_arg).unwrap();
-    let new_shape = parse_input_shape_arg(generator, context, shape_arg, shape_ty);
-
-    let reshaped_ndarray = reshape_ndarray_or_copy(generator, context, src_ndarray, &new_shape)?;
-    Ok(reshaped_ndarray.value)
-}
-
-pub fn gen_ndarray_transpose<'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!(matches!(args.len(), 1 | 2));
-
-    let sizet = generator.get_sizet(context.ctx);
-    let in_axes_model = PointerModel(StructModel(List { sizet, element: NIntModel(Int32) }));
-
-    // Parse argument #1 ndarray
-    let ndarray_ty = fun.0.args[0].ty;
-    let ndarray_arg = args[0].1.clone().to_basic_value_enum(context, generator, ndarray_ty)?;
-
-    // Parse argument #2 axes (optional)
-    let in_axes = if args.len() == 2 {
-        let in_shape_ty = fun.0.args[1].ty;
-        let in_shape_arg =
-            args[1].1.clone().to_basic_value_enum(context, generator, in_shape_ty)?;
-
-        let in_shape = in_axes_model.review_value(context.ctx, in_shape_arg).unwrap();
-
-        let num_axes = in_shape.gep(context, |f| f.size).load(context, "num_axes");
-        let axes = sizet.array_alloca(context, num_axes, "num_axes");
-
-        Some((in_shape_ty, in_shape_arg))
-    } else {
-        None
-    };
-    // call_nac3_ndarray_transpose(generator, ctx, src_ndarray, dst_ndarray, axes_or_none)
-
-    todo!()
-}

nac3core/src/codegen/structs/cslice.rs

@@ -1,50 +0,0 @@
-use crate::codegen::{model::*, CodeGenContext};
-
-/// Fields of [`CSlice<'ctx>`].
-pub struct CSliceFields<'ctx> {
-    /// Pointer to the data.
-    pub base: Field<PointerModel<ByteModel>>,
-    /// Number of bytes of the data.
-    pub len: Field<SizeTModel<'ctx>>,
-}
-
-/// 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, PartialEq, Eq)]
-pub struct CSlice<'ctx> {
-    pub sizet: SizeTModel<'ctx>,
-}
-
-impl<'ctx> StructKind<'ctx> for CSlice<'ctx> {
-    type Fields = CSliceFields<'ctx>;
-
-    fn struct_name(&self) -> &'static str {
-        "CSlice"
-    }
-
-    fn build_fields(&self, builder: &mut FieldBuilder<'ctx>) -> Self::Fields {
-        Self::Fields {
-            base: builder.add_field_auto("content"),
-            len: builder.add_field("length", self.sizet),
-        }
-    }
-}
-
-impl<'ctx> StructModel<CSlice<'ctx>> {
-    /// Create a [`CSlice`].
-    ///
-    /// `base` and `len` must be LLVM global constants.
-    pub fn create_const(
-        &self,
-        ctx: &CodeGenContext<'ctx, '_>,
-        base: Pointer<'ctx, ByteModel>,
-        len: SizeT<'ctx>,
-    ) -> Struct<'ctx, CSlice<'ctx>> {
-        let value = self
-            .get_struct_type(ctx.ctx)
-            .const_named_struct(&[base.value.into(), len.value.into()]);
-        self.believe_value(value)
-    }
-}