core: new np_{zeros,ones,fill} + some irrt model additions

nac3core/irrt/irrt/numpy/ndarray.hpp

@@ -0,0 +1,155 @@
+#pragma once
+
+#include <irrt/int_defs.hpp>
+#include <irrt/numpy/ndarray_util.hpp>
+
+namespace {
+
+// The NDArray object. `SizeT` is the *signed* size type of this ndarray.
+//
+// NOTE: The order of fields is IMPORTANT. DON'T TOUCH IT
+//
+// Some resources you might find helpful:
+// - The official numpy implementations:
+//   - https://github.com/numpy/numpy/blob/735a477f0bc2b5b84d0e72d92f224bde78d4e069/doc/source/reference/c-api/types-and-structures.rst
+// - On strides (about reshaping, slicing, C-contagiousness, etc)
+//   - https://ajcr.net/stride-guide-part-1/.
+//   - https://ajcr.net/stride-guide-part-2/.
+//   - https://ajcr.net/stride-guide-part-3/.
+template <typename SizeT>
+struct NDArray {
+    // The underlying data this `ndarray` is pointing to.
+    //
+    // NOTE: Formally this should be of type `void *`, but clang
+    // translates `void *` to `i8 *` when run with `-S -emit-llvm`,
+    // so we will put `uint8_t *` here for clarity.
+    //
+    // This pointer should point to the first element of the ndarray directly
+    uint8_t *data;
+
+    // The number of bytes of a single element in `data`.
+    //
+    // The `SizeT` is treated as `unsigned`.
+    SizeT itemsize;
+
+    // The number of dimensions of this shape.
+    //
+    // The `SizeT` is treated as `unsigned`.
+    SizeT ndims;
+
+    // Array shape, with length equal to `ndims`.
+    //
+    // The `SizeT` is treated as `unsigned`.
+    //
+    // NOTE: `shape` can contain 0.
+    //   (those appear when the user makes an out of bounds slice into an ndarray, e.g., `np.zeros((3, 3))[400:].shape == (0, 3)`)
+    SizeT *shape;
+
+    // Array strides (stride value is in number of bytes, NOT number of elements), with length equal to `ndims`.
+    //
+    // The `SizeT` is treated as `signed`.
+    //
+    // NOTE: `strides` can have negative numbers.
+    //   (those appear when there is a slice with a negative step, e.g., `my_array[::-1]`)
+    SizeT *strides;
+
+    // Calculate the size/# of elements of an `ndarray`.
+    // This function corresponds to `np.size(<ndarray>)` or `ndarray.size`
+    SizeT size() {
+        return ndarray_util::calc_size_from_shape(ndims, shape);
+    }
+
+    // Calculate the number of bytes of its content of an `ndarray` *in its view*.
+    // This function corresponds to `ndarray.nbytes`
+    SizeT nbytes() {
+        return this->size() * itemsize;
+    }
+
+    // Set the strides of the ndarray with `ndarray_util::set_strides_by_shape`
+    void set_strides_by_shape() {
+        ndarray_util::set_strides_by_shape(itemsize, ndims, strides, shape);
+    }
+
+    uint8_t* get_pelement_by_indices(const SizeT *indices) {
+        uint8_t* element = data;
+        for (SizeT dim_i = 0; dim_i < ndims; dim_i++)
+            element += indices[dim_i] * strides[dim_i];
+        return element;
+    }
+
+    uint8_t* get_nth_pelement(SizeT nth) {
+        SizeT* indices = (SizeT*) __builtin_alloca(sizeof(SizeT) * this->ndims);
+        ndarray_util::set_indices_by_nth(this->ndims, this->shape, indices, nth);
+        return get_pelement_by_indices(indices);
+    }
+
+    // Get the pointer to the nth element of the ndarray as if it were flattened.
+    uint8_t* checked_get_nth_pelement(ErrorContext* errctx, SizeT nth) {
+        SizeT arr_size = this->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(nth);
+    }
+
+    void set_pelement_value(uint8_t* pelement, const uint8_t* pvalue) {
+        __builtin_memcpy(pelement, pvalue, itemsize);
+    }
+
+    // Fill the ndarray with a value
+    void fill_generic(const uint8_t* pvalue) {
+        const SizeT size = this->size();
+        for (SizeT i = 0; i < size; i++) {
+            uint8_t* pelement = get_nth_pelement(i); // No need for checked_get_nth_pelement
+            set_pelement_value(pelement, pvalue);
+        }
+    }
+};
+}
+
+extern "C" {
+uint32_t __nac3_ndarray_size(NDArray<int32_t>* ndarray) {
+    return ndarray->size();
+}
+
+uint64_t __nac3_ndarray_size64(NDArray<int64_t>* ndarray) {
+    return ndarray->size();
+}
+
+uint32_t __nac3_ndarray_nbytes(NDArray<int32_t>* ndarray) {
+    return ndarray->nbytes();
+}
+
+uint64_t __nac3_ndarray_nbytes64(NDArray<int64_t>* ndarray) {
+    return ndarray->nbytes();
+}
+
+void __nac3_ndarray_util_assert_shape_no_negative(ErrorContext* errctx, int32_t ndims, int32_t* shape) {
+    ndarray_util::assert_shape_no_negative(errctx, ndims, shape);
+}
+
+void __nac3_ndarray_util_assert_shape_no_negative64(ErrorContext* errctx, int64_t ndims, int64_t* shape) {
+    ndarray_util::assert_shape_no_negative(errctx, ndims, shape);
+}
+
+void __nac3_ndarray_set_strides_by_shape(NDArray<int32_t>* ndarray) {
+    ndarray->set_strides_by_shape();
+}
+
+void __nac3_ndarray_set_strides_by_shape64(NDArray<int64_t>* ndarray) {
+    ndarray->set_strides_by_shape();
+}
+
+void __nac3_ndarray_fill_generic(NDArray<int32_t>* ndarray, uint8_t* pvalue) {
+    ndarray->fill_generic(pvalue);
+}
+
+void __nac3_ndarray_fill_generic64(NDArray<int64_t>* ndarray, uint8_t* pvalue) {
+    ndarray->fill_generic(pvalue);
+}
+}

nac3core/irrt/irrt/numpy/ndarray_util.hpp

@@ -0,0 +1,107 @@
+#pragma once
+
+#include <irrt/int_defs.hpp>
+
+namespace {
+namespace ndarray_util {
+
+// Throw an error if there is an axis with negative dimension
+template <typename SizeT>
+void assert_shape_no_negative(ErrorContext* errctx, 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;
+        }
+    }
+}
+
+// Compute the size/# of elements of an ndarray given its shape
+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];
+    return size;
+}
+
+// Compute the strides of an ndarray given an ndarray `shape`
+// and assuming that the ndarray is *fully C-contagious*.
+//
+// You might want to read up on https://ajcr.net/stride-guide-part-1/.
+template <typename SizeT>
+void set_strides_by_shape(SizeT itemsize, SizeT ndims, SizeT* dst_strides, const SizeT* shape) {
+    SizeT stride_product = 1;
+    for (SizeT i = 0; i < ndims; i++) {
+        int axis = ndims - i - 1;
+        dst_strides[axis] = stride_product * itemsize;
+        stride_product *= shape[axis];
+    }
+}
+
+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];
+
+        indices[axis] = nth % dim;
+        nth /= dim;
+    }
+}
+
+template <typename SizeT>
+bool can_broadcast_shape_to(
+    const SizeT target_ndims,
+    const SizeT *target_shape,
+    const SizeT src_ndims,
+    const SizeT *src_shape
+) {
+    /*
+        // See https://numpy.org/doc/stable/user/basics.broadcasting.html
+
+        This function handles this example:
+        ```
+        Image  (3d array): 256 x 256 x 3
+        Scale  (1d array):             3
+        Result (3d array): 256 x 256 x 3
+        ```
+
+        Other interesting examples to consider:
+        - `can_broadcast_shape_to([3], [1, 1, 1, 1, 3]) == true`
+        - `can_broadcast_shape_to([3], [3, 1]) == false`
+        - `can_broadcast_shape_to([256, 256, 3], [256, 1, 3]) == true`
+
+        In cases when the shapes contain zero(es):
+        - `can_broadcast_shape_to([0], [1]) == true`
+        - `can_broadcast_shape_to([0], [2]) == false`
+        - `can_broadcast_shape_to([0, 4, 0, 0], [1]) == true`
+        - `can_broadcast_shape_to([0, 4, 0, 0], [1, 1, 1, 1]) == true`
+        - `can_broadcast_shape_to([0, 4, 0, 0], [1, 4, 1, 1]) == true`
+        - `can_broadcast_shape_to([4, 3], [0, 3]) == false`
+        - `can_broadcast_shape_to([4, 3], [0, 0]) == false`
+    */
+
+    // This is essentially doing the following in Python:
+    // `for target_dim, src_dim in itertools.zip_longest(target_shape[::-1], src_shape[::-1], fillvalue=1)`
+    for (SizeT i = 0; i < max(target_ndims, src_ndims); i++) {
+        SizeT target_axis = target_ndims - i - 1;
+        SizeT src_axis = src_ndims - i - 1;
+
+        bool target_dim_exists = target_axis >= 0;
+        bool src_dim_exists = src_axis >= 0;
+
+        SizeT target_dim = target_dim_exists ? target_shape[target_axis] : 1;
+        SizeT src_dim = src_dim_exists ? src_shape[src_axis] : 1;
+
+        bool ok = src_dim == 1 || target_dim == src_dim;
+        if (!ok) return false;
+    }
+
+    return true;
+}
+}
+}

nac3core/irrt/irrt_everything.hpp

@@ -1,6 +1,8 @@
 #pragma once
 
 #include <irrt/core.hpp>
-#include <irrt/int_defs.hpp>
-#include <irrt/utils.hpp>
 #include <irrt/error_context.hpp>
+#include <irrt/int_defs.hpp>
+#include <irrt/numpy/ndarray.hpp>
+#include <irrt/numpy/ndarray_util.hpp>
+#include <irrt/utils.hpp>

nac3core/irrt/irrt_test.cpp

@@ -8,9 +8,11 @@
 #include <irrt_everything.hpp>
 
 #include <test/core.hpp>
+#include <test/ndarray.hpp>
 #include <test/test_core.hpp>
 
 int main() {
     test_int_exp();
+    run_all_tests_ndarray();
     return 0;
 }

nac3core/irrt/test/ndarray.hpp

@@ -0,0 +1,44 @@
+#pragma once
+
+#include <test/core.hpp>
+#include <irrt/numpy/ndarray.hpp>
+#include <irrt/numpy/ndarray_util.hpp>
+
+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_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_util::calc_size_from_shape<int32_t>(4, shape));
+}
+
+void test_set_strides_by_shape() {
+    // Test `set_strides_by_shape()`
+    BEGIN_TEST();
+
+    int32_t shape[4] = { 99, 3, 5, 7 };
+    int32_t strides[4] = { 0 };
+    ndarray_util::set_strides_by_shape((int32_t) sizeof(int32_t), 4, strides, shape);
+
+    int32_t expected_strides[4] = {
+        105 * sizeof(int32_t),
+        35 * sizeof(int32_t),
+        7 * sizeof(int32_t),
+        1 * sizeof(int32_t)
+    };
+    assert_arrays_match(4, expected_strides, strides);
+}
+
+void run_all_tests_ndarray() {
+    test_calc_size_from_shape_normal();
+    test_calc_size_from_shape_has_zero();
+    test_set_strides_by_shape();
+}

nac3core/src/codegen/irrt/mod.rs

@@ -1,6 +1,7 @@
 use crate::typecheck::typedef::Type;
 
 pub mod error_context;
+pub mod numpy;
 mod test;
 mod util;
 

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

@@ -0,0 +1,5 @@
+pub mod ndarray;
+pub mod shape;
+
+pub use ndarray::*;
+pub use shape::*;

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

@@ -0,0 +1,243 @@
+use inkwell::types::{BasicType, BasicTypeEnum};
+
+use crate::codegen::{
+    irrt::{
+        error_context::{check_error_context, prepare_error_context, ErrorContext},
+        util::{get_sized_dependent_function_name, FunctionBuilder},
+    },
+    model::*,
+    CodeGenContext, CodeGenerator,
+};
+
+use super::Producer;
+
+pub struct NpArrayFields<'ctx> {
+    pub data: Field<OpaquePointerModel>,
+    pub itemsize: Field<IntModel<'ctx>>,
+    pub ndims: Field<IntModel<'ctx>>,
+    pub shape: Field<PointerModel<IntModel<'ctx>>>,
+    pub strides: Field<PointerModel<IntModel<'ctx>>>,
+}
+
+#[derive(Debug, Clone, Copy)]
+pub struct NpArray<'ctx> {
+    pub sizet: IntModel<'ctx>,
+}
+
+impl<'ctx> IsStruct<'ctx> for NpArray<'ctx> {
+    type Fields = NpArrayFields<'ctx>;
+
+    fn struct_name(&self) -> &'static str {
+        "NDArray"
+    }
+
+    fn build_fields(&self, builder: &mut FieldBuilder<'ctx>) -> Self::Fields {
+        NpArrayFields {
+            data: builder.add_field_auto("data"),
+            itemsize: builder.add_field("itemsize", self.sizet),
+            ndims: builder.add_field("ndims", self.sizet),
+            shape: builder.add_field("shape", PointerModel(self.sizet)),
+            strides: builder.add_field("strides", PointerModel(self.sizet)),
+        }
+    }
+}
+
+impl<'ctx> Pointer<'ctx, StructModel<NpArray<'ctx>>> {
+    pub fn shape_slice(&self, ctx: &CodeGenContext<'ctx, '_>) -> ArraySlice<'ctx, IntModel<'ctx>> {
+        let ndims = self.gep(ctx, |f| f.ndims).load(ctx, "ndims");
+        let shape_base_ptr = self.gep(ctx, |f| f.shape).load(ctx, "shape");
+        ArraySlice { num_elements: ndims, pointer: shape_base_ptr }
+    }
+
+    pub fn strides_slice(
+        &self,
+        ctx: &CodeGenContext<'ctx, '_>,
+    ) -> ArraySlice<'ctx, IntModel<'ctx>> {
+        let ndims = self.gep(ctx, |f| f.ndims).load(ctx, "ndims");
+        let strides_base_ptr = self.gep(ctx, |f| f.strides).load(ctx, "strides");
+        ArraySlice { num_elements: ndims, pointer: strides_base_ptr }
+    }
+}
+
+pub fn alloca_ndarray<'ctx, G>(
+    generator: &mut G,
+    ctx: &mut CodeGenContext<'ctx, '_>,
+    elem_type: BasicTypeEnum<'ctx>,
+    ndims: &Int<'ctx>,
+    name: &str,
+) -> Result<Pointer<'ctx, StructModel<NpArray<'ctx>>>, String>
+where
+    G: CodeGenerator + ?Sized,
+{
+    let sizet = IntModel(generator.get_size_type(ctx.ctx));
+
+    // Allocate ndarray
+    let ndarray_ptr = StructModel(NpArray { sizet }).alloca(ctx, name);
+
+    // Set ndims
+    ndarray_ptr.gep(ctx, |f| f.ndims).store(ctx, ndims);
+
+    // Set itemsize
+    let itemsize = elem_type.size_of().unwrap();
+    let itemsize =
+        ctx.builder.build_int_s_extend_or_bit_cast(itemsize, sizet.0, "itemsize").unwrap();
+    ndarray_ptr.gep(ctx, |f| f.itemsize).store(ctx, &Int(itemsize));
+
+    // Allocate and set shape
+    let shape_ptr = ctx.builder.build_array_alloca(sizet.0, ndims.0, "shape").unwrap();
+    ndarray_ptr.gep(ctx, |f| f.shape).store(ctx, &Pointer { element: sizet, value: shape_ptr });
+    // .store(ctx, &Pointer { addressee_optic: IntLens(sizet), address: shape_ptr });
+
+    // Allocate and set strides
+    let strides_ptr = ctx.builder.build_array_alloca(sizet.0, ndims.0, "strides").unwrap();
+    ndarray_ptr.gep(ctx, |f| f.strides).store(ctx, &Pointer { element: sizet, value: strides_ptr });
+
+    Ok(ndarray_ptr)
+}
+
+pub enum NDArrayInitMode<'ctx, G: CodeGenerator + ?Sized> {
+    NDims { ndims: Int<'ctx> },
+    Shape { shape: Producer<'ctx, G, IntModel<'ctx>> },
+    ShapeAndAllocaData { shape: Producer<'ctx, G, IntModel<'ctx>> },
+}
+
+/// TODO: DOCUMENT ME
+pub fn alloca_ndarray_and_init<'ctx, G>(
+    generator: &mut G,
+    ctx: &mut CodeGenContext<'ctx, '_>,
+    elem_type: BasicTypeEnum<'ctx>,
+    init_mode: NDArrayInitMode<'ctx, G>,
+    name: &str,
+) -> Result<Pointer<'ctx, StructModel<NpArray<'ctx>>>, String>
+where
+    G: CodeGenerator + ?Sized,
+{
+    // It is implemented verbosely in order to make the initialization modes super clear in their intent.
+    match init_mode {
+        NDArrayInitMode::NDims { ndims } => {
+            let ndarray_ptr = alloca_ndarray(generator, ctx, elem_type, &ndims, name)?;
+            Ok(ndarray_ptr)
+        }
+        NDArrayInitMode::Shape { shape } => {
+            let ndims = shape.count;
+            let ndarray_ptr = alloca_ndarray(generator, ctx, elem_type, &ndims, name)?;
+
+            // Fill `ndarray.shape`
+            (shape.write_to_array)(generator, ctx, &ndarray_ptr.shape_slice(ctx))?;
+
+            // Check if `shape` has bad inputs
+            call_nac3_ndarray_util_assert_shape_no_negative(
+                generator,
+                ctx,
+                &ndims,
+                &ndarray_ptr.gep(ctx, |f| f.shape).load(ctx, "shape"),
+            );
+
+            // NOTE: DO NOT DO `set_strides_by_shape` HERE.
+            // Simply this is because we specified that `SetShape` wouldn't do `set_strides_by_shape`
+
+            Ok(ndarray_ptr)
+        }
+        NDArrayInitMode::ShapeAndAllocaData { shape } => {
+            let ndims = shape.count;
+            let ndarray_ptr = alloca_ndarray(generator, ctx, elem_type, &ndims, name)?;
+
+            // Fill `ndarray.shape`
+            (shape.write_to_array)(generator, ctx, &ndarray_ptr.shape_slice(ctx))?;
+
+            // Check if `shape` has bad inputs
+            call_nac3_ndarray_util_assert_shape_no_negative(
+                generator,
+                ctx,
+                &ndims,
+                &ndarray_ptr.gep(ctx, |f| f.shape).load(ctx, "shape"),
+            );
+
+            // Now we populate `ndarray.data` by alloca-ing.
+            // But first, we need to know the size of the ndarray to know how many elements to alloca,
+            // since calculating nbytes of an ndarray requires `ndarray.shape` to be set.
+            let ndarray_nbytes = call_nac3_ndarray_nbytes(generator, ctx, &ndarray_ptr);
+
+            // Alloca `data` and assign it to `ndarray.data`
+            let data_ptr = OpaquePointer(
+                ctx.builder
+                    .build_array_alloca(ctx.ctx.i8_type(), ndarray_nbytes.0, "data")
+                    .unwrap(),
+            );
+            ndarray_ptr.gep(ctx, |f| f.data).store(ctx, &data_ptr);
+
+            // Finally, do `set_strides_by_shape`
+            // Check out https://ajcr.net/stride-guide-part-1/ to see what numpy "strides" are.
+            call_nac3_ndarray_set_strides_by_shape(generator, ctx, &ndarray_ptr);
+
+            Ok(ndarray_ptr)
+        }
+    }
+}
+
+fn call_nac3_ndarray_util_assert_shape_no_negative<'ctx, G: CodeGenerator + ?Sized>(
+    generator: &mut G,
+    ctx: &mut CodeGenContext<'ctx, '_>,
+    ndims: &Int<'ctx>,
+    shape_ptr: &Pointer<'ctx, IntModel<'ctx>>,
+) {
+    let sizet = IntModel(generator.get_size_type(ctx.ctx));
+
+    let errctx = prepare_error_context(ctx);
+    FunctionBuilder::begin(
+        ctx,
+        &get_sized_dependent_function_name(sizet, "__nac3_ndarray_util_assert_shape_no_negative"),
+    )
+    .arg("errctx", &PointerModel(StructModel(ErrorContext)), &errctx)
+    .arg("ndims", &sizet, ndims)
+    .arg("shape", &PointerModel(sizet), shape_ptr)
+    .returning_void();
+    check_error_context(generator, ctx, &errctx);
+}
+
+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 = IntModel(generator.get_size_type(ctx.ctx));
+
+    FunctionBuilder::begin(
+        ctx,
+        &get_sized_dependent_function_name(sizet, "__nac3_ndarray_util_assert_shape_no_negative"),
+    )
+    .arg("ndarray", &PointerModel(StructModel(NpArray { sizet })), ndarray_ptr)
+    .returning_void();
+}
+
+fn call_nac3_ndarray_nbytes<'ctx, G: CodeGenerator + ?Sized>(
+    generator: &mut G,
+    ctx: &mut CodeGenContext<'ctx, '_>,
+    ndarray_ptr: &Pointer<'ctx, StructModel<NpArray<'ctx>>>,
+) -> Int<'ctx> {
+    let sizet = IntModel(generator.get_size_type(ctx.ctx));
+
+    FunctionBuilder::begin(
+        ctx,
+        &get_sized_dependent_function_name(sizet, "__nac3_ndarray_util_assert_shape_no_negative"),
+    )
+    .arg("ndarray", &PointerModel(StructModel(NpArray { sizet })), ndarray_ptr)
+    .returning("nbytes", &sizet)
+}
+
+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: &OpaquePointer<'ctx>,
+) {
+    let sizet = IntModel(generator.get_size_type(ctx.ctx));
+
+    FunctionBuilder::begin(
+        ctx,
+        &get_sized_dependent_function_name(sizet, "__nac3_ndarray_fill_generic"),
+    )
+    .arg("ndarray", &PointerModel(StructModel(NpArray { sizet })), ndarray_ptr)
+    .arg("pvalue", &OpaquePointerModel, fill_value_ptr)
+    .returning_void();
+}

nac3core/src/codegen/irrt/numpy/shape.rs

@@ -0,0 +1,162 @@
+use inkwell::values::BasicValueEnum;
+
+use crate::{
+    codegen::{
+        classes::{ListValue, UntypedArrayLikeAccessor},
+        model::*,
+        stmt::gen_for_callback_incrementing,
+        CodeGenContext, CodeGenerator,
+    },
+    typecheck::typedef::{Type, TypeEnum},
+};
+
+pub type ProducerWriteToArray<'ctx, G, E> = Box<
+    dyn Fn(&mut G, &mut CodeGenContext<'ctx, '_>, &ArraySlice<'ctx, E>) -> Result<(), String>
+        + 'ctx,
+>;
+
+pub struct Producer<'ctx, G: CodeGenerator + ?Sized, E: Model<'ctx>> {
+    pub count: Int<'ctx>,
+    pub write_to_array: ProducerWriteToArray<'ctx, G, E>,
+}
+
+/// TODO: UPDATE DOCUMENTATION
+/// LLVM-typed implementation for generating a [`Producer`] that sets a list of ints.
+///
+/// * `elem_ty` - The element type of the `NDArray`.
+/// * `shape` - The `shape` parameter used to construct the `NDArray`.
+///
+/// ### Notes on `shape`
+///
+/// Just like numpy, the `shape` argument can be:
+///   1. A list of `int32`;   e.g., `np.empty([600, 800, 3])`
+///   2. A tuple of `int32`;  e.g., `np.empty((600, 800, 3))`
+///   3. A scalar `int32`;     e.g., `np.empty(3)`, this is functionally equivalent to `np.empty([3])`
+///
+/// See also [`typecheck::type_inferencer::fold_numpy_function_call_shape_argument`] to
+/// learn how `shape` gets from being a Python user expression to here.
+pub fn parse_input_shape_arg<'ctx, G>(
+    generator: &mut G,
+    ctx: &mut CodeGenContext<'ctx, '_>,
+    shape: BasicValueEnum<'ctx>,
+    shape_ty: Type,
+) -> Producer<'ctx, G, IntModel<'ctx>>
+where
+    G: CodeGenerator + ?Sized,
+{
+    let sizet = IntModel(generator.get_size_type(ctx.ctx));
+
+    match &*ctx.unifier.get_ty(shape_ty) {
+        TypeEnum::TObj { obj_id, .. }
+            if *obj_id == ctx.primitives.list.obj_id(&ctx.unifier).unwrap() =>
+        {
+            // 1. A list of ints; e.g., `np.empty([600, 800, 3])`
+
+            // A list has to be a PointerValue
+            let shape_list = ListValue::from_ptr_val(shape.into_pointer_value(), sizet.0, None);
+
+            // Create `Producer`
+            let ndims = Int(shape_list.load_size(ctx, Some("count")));
+            Producer {
+                count: ndims,
+                write_to_array: Box::new(move |ctx, generator, dst_array| {
+                    // Basically iterate through the list and write to `dst_slice` accordingly
+                    let init_val = sizet.constant(0).0;
+                    let max_val = (ndims.0, false);
+                    let incr_val = sizet.constant(1).0;
+                    gen_for_callback_incrementing(
+                        ctx,
+                        generator,
+                        init_val,
+                        max_val,
+                        |generator, ctx, _hooks, axis| {
+                            let axis = Int(axis);
+
+                            // Get the dimension at `axis`
+                            let dim = shape_list
+                                .data()
+                                .get(ctx, generator, &axis.0, None)
+                                .into_int_value();
+
+                            // Cast `dim` to SizeT
+                            let dim = ctx
+                                .builder
+                                .build_int_s_extend_or_bit_cast(dim, sizet.0, "dim_casted")
+                                .unwrap();
+
+                            // Write
+                            dst_array.ix(generator, ctx, axis, "dim").store(ctx, &Int(dim));
+                            Ok(())
+                        },
+                        incr_val,
+                    )
+                }),
+            }
+        }
+        TypeEnum::TTuple { ty: tuple_types } => {
+            // 2. A tuple of ints; e.g., `np.empty((600, 800, 3))`
+
+            // Get the length/size of the tuple, which also happens to be the value of `ndims`.
+            let ndims = tuple_types.len();
+
+            // A tuple has to be a StructValue
+            // Read [`codegen::expr::gen_expr`] to see how `nac3core` translates a Python tuple into LLVM.
+            let shape_tuple = shape.into_struct_value();
+
+            Producer {
+                count: sizet.constant(ndims as u64),
+                write_to_array: Box::new(move |generator, ctx, dst_array| {
+                    for axis in 0..ndims {
+                        // Get the dimension at `axis`
+                        let dim = ctx
+                            .builder
+                            .build_extract_value(
+                                shape_tuple,
+                                axis as u32,
+                                format!("dim{axis}").as_str(),
+                            )
+                            .unwrap()
+                            .into_int_value();
+
+                        // Cast `dim` to SizeT
+                        let dim = ctx
+                            .builder
+                            .build_int_s_extend_or_bit_cast(dim, sizet.0, "dim_casted")
+                            .unwrap();
+
+                        // Write
+                        dst_array
+                            .ix(generator, ctx, sizet.constant(axis as u64), "dim")
+                            .store(ctx, &Int(dim));
+                    }
+                    Ok(())
+                }),
+            }
+        }
+        TypeEnum::TObj { obj_id, .. }
+            if *obj_id == ctx.primitives.int32.obj_id(&ctx.unifier).unwrap() =>
+        {
+            // 3. A scalar int; e.g., `np.empty(3)`, this is functionally equivalent to `np.empty([3])`
+
+            // The value has to be an integer
+            let shape_int = shape.into_int_value();
+
+            Producer {
+                count: sizet.constant(1),
+                write_to_array: Box::new(move |generator, ctx, dst_array| {
+                    // Cast `shape_int` to SizeT
+                    let dim = ctx
+                        .builder
+                        .build_int_s_extend_or_bit_cast(shape_int, sizet.0, "dim_casted")
+                        .unwrap();
+
+                    // Set shape[0] = shape_int
+                    dst_array.ix(generator, ctx, sizet.constant(0), "dim").store(ctx, &Int(dim));
+
+                    Ok(())
+                }),
+            }
+        }
+        _ => panic!("parse_input_shape_arg encountered unknown type"),
+    }
+}

nac3core/src/codegen/mod.rs

@@ -45,6 +45,7 @@ pub mod irrt;
 pub mod llvm_intrinsics;
 pub mod model;
 pub mod numpy;
+pub mod numpy_new;
 pub mod stmt;
 
 #[cfg(test)]

nac3core/src/codegen/model/int.rs

@@ -8,6 +8,8 @@ use super::core::*;
 
 #[derive(Debug, Clone, Copy)]
 pub struct IntModel<'ctx>(pub IntType<'ctx>);
+
+#[derive(Debug, Clone, Copy)]
 pub struct Int<'ctx>(pub IntValue<'ctx>);
 
 impl<'ctx> ModelValue<'ctx> for Int<'ctx> {
@@ -30,6 +32,13 @@ impl<'ctx> Model<'ctx> for IntModel<'ctx> {
     }
 }
 
+impl<'ctx> IntModel<'ctx> {
+    #[must_use]
+    pub fn constant(&self, value: u64) -> Int<'ctx> {
+        Int(self.0.const_int(value, false))
+    }
+}
+
 #[derive(Debug, Clone, Default)]
 pub struct FixedIntModel<T>(pub T);
 pub struct FixedInt<'ctx, T: IsFixedInt> {

nac3core/src/codegen/model/pointer.rs

@@ -72,3 +72,9 @@ impl<'ctx> Model<'ctx> for OpaquePointerModel {
         OpaquePointer(ptr)
     }
 }
+
+impl<'ctx> OpaquePointer<'ctx> {
+    pub fn store(&self, ctx: &CodeGenContext<'ctx, '_>, value: BasicValueEnum<'ctx>) {
+        ctx.builder.build_store(self.0, value).unwrap();
+    }
+}

nac3core/src/codegen/model/slice.rs

@@ -1,5 +1,3 @@
-use inkwell::values::IntValue;
-
 use crate::codegen::{CodeGenContext, CodeGenerator};
 
 use super::{Int, Model, Pointer};
@@ -13,11 +11,11 @@ impl<'ctx, E: Model<'ctx>> ArraySlice<'ctx, E> {
     pub fn ix_unchecked(
         &self,
         ctx: &CodeGenContext<'ctx, '_>,
-        idx: IntValue<'ctx>,
+        idx: Int<'ctx>,
         name: &str,
     ) -> Pointer<'ctx, E> {
         let element_addr =
-            unsafe { ctx.builder.build_in_bounds_gep(self.pointer.value, &[idx], name).unwrap() };
+            unsafe { ctx.builder.build_in_bounds_gep(self.pointer.value, &[idx.0], name).unwrap() };
         Pointer { value: element_addr, element: self.pointer.element.clone() }
     }
 
@@ -25,12 +23,12 @@ impl<'ctx, E: Model<'ctx>> ArraySlice<'ctx, E> {
         &self,
         generator: &mut G,
         ctx: &mut CodeGenContext<'ctx, '_>,
-        idx: IntValue<'ctx>,
+        idx: Int<'ctx>,
         name: &str,
     ) -> Pointer<'ctx, E> {
         let int_type = self.num_elements.0.get_type(); // NOTE: Weird get_type(), see comment under `trait Ixed`
 
-        assert_eq!(int_type.get_bit_width(), idx.get_type().get_bit_width()); // Might as well check bit width to catch bugs
+        assert_eq!(int_type.get_bit_width(), idx.0.get_type().get_bit_width()); // Might as well check bit width to catch bugs
 
         // TODO: SGE or UGE? or make it defined by the implementee?
 
@@ -40,7 +38,7 @@ impl<'ctx, E: Model<'ctx>> ArraySlice<'ctx, E> {
             .build_int_compare(
                 inkwell::IntPredicate::SLE,
                 int_type.const_zero(),
-                idx,
+                idx.0,
                 "lower_bounded",
             )
             .unwrap();
@@ -50,7 +48,7 @@ impl<'ctx, E: Model<'ctx>> ArraySlice<'ctx, E> {
             .builder
             .build_int_compare(
                 inkwell::IntPredicate::SLT,
-                idx,
+                idx.0,
                 self.num_elements.0,
                 "upper_bounded",
             )
@@ -65,7 +63,7 @@ impl<'ctx, E: Model<'ctx>> ArraySlice<'ctx, E> {
             bounded,
             "0:IndexError",
             "nac3core LLVM codegen attempting to access out of bounds array index {0}. Must satisfy 0 <= index < {2}",
-            [ Some(idx), Some(self.num_elements.0), None],
+            [ Some(idx.0), Some(self.num_elements.0), None],
             ctx.current_loc
         );
 

nac3core/src/codegen/numpy_new.rs

@@ -0,0 +1,188 @@
+use inkwell::values::{BasicValue, BasicValueEnum, PointerValue};
+use nac3parser::ast::StrRef;
+
+use crate::{
+    symbol_resolver::ValueEnum,
+    toplevel::DefinitionId,
+    typecheck::typedef::{FunSignature, Type},
+};
+
+use super::{
+    irrt::numpy::{
+        alloca_ndarray_and_init, call_nac3_ndarray_fill_generic, parse_input_shape_arg,
+        NDArrayInitMode, NpArray,
+    },
+    model::*,
+    CodeGenContext, CodeGenerator,
+};
+
+/// LLVM-typed implementation for generating the implementation for constructing an empty `NDArray`.
+fn call_ndarray_empty_impl<'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 elem_type = ctx.get_llvm_type(generator, elem_ty);
+    let shape = parse_input_shape_arg(generator, ctx, shape, shape_ty);
+    let ndarray_ptr = alloca_ndarray_and_init(
+        generator,
+        ctx,
+        elem_type,
+        NDArrayInitMode::ShapeAndAllocaData { shape },
+        name,
+    )?;
+    Ok(ndarray_ptr)
+}
+
+fn call_ndarray_full_impl<'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 ndarray_ptr = call_ndarray_empty_impl(generator, ctx, elem_ty, shape, shape_ty, name)?;
+
+    // NOTE: fill_value's type is not checked!! so be careful with logics
+    let fill_value_ptr =
+        OpaquePointer(ctx.builder.build_alloca(fill_value.get_type(), "fill_value_ptr").unwrap());
+    fill_value_ptr.store(ctx, fill_value);
+    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 = call_ndarray_empty_impl(
+        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 = call_ndarray_full_impl(
+        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 = call_ndarray_full_impl(
+        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 `ndarray.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 = call_ndarray_full_impl(
+        generator,
+        context,
+        fill_value_ty,
+        shape_arg,
+        shape_ty,
+        fill_value_arg,
+        "ndarray",
+    )?;
+    Ok(ndarray_ptr.value)
+}

nac3core/src/toplevel/builtins.rs

@@ -18,6 +18,7 @@ use crate::{
         expr::destructure_range,
         irrt::*,
         numpy::*,
+        numpy_new,
         stmt::exn_constructor,
     },
     symbol_resolver::SymbolValue,
@@ -1194,9 +1195,9 @@ impl<'a> BuiltinBuilder<'a> {
             &[(self.ndarray_factory_fn_shape_arg_tvar.ty, "shape")],
             Box::new(move |ctx, obj, fun, args, generator| {
                 let func = match prim {
-                    PrimDef::FunNpNDArray | PrimDef::FunNpEmpty => gen_ndarray_empty,
-                    PrimDef::FunNpZeros => gen_ndarray_zeros,
-                    PrimDef::FunNpOnes => gen_ndarray_ones,
+                    PrimDef::FunNpNDArray | PrimDef::FunNpEmpty => numpy_new::gen_ndarray_empty,
+                    PrimDef::FunNpZeros => numpy_new::gen_ndarray_zeros,
+                    PrimDef::FunNpOnes => numpy_new::gen_ndarray_ones,
                     _ => unreachable!(),
                 };
                 func(ctx, &obj, fun, &args, generator).map(|val| Some(val.as_basic_value_enum()))