forked from M-Labs/nac3
core/ndstrides: introduce NDArray
NDArray with strides.
This commit is contained in:
DSLstandard
parent
9bc5e96dba
commit
92e7103ec7
@ -4,3 +4,5 @@
|
||||
#include "irrt/math.hpp"
|
||||
#include "irrt/ndarray.hpp"
|
||||
#include "irrt/slice.hpp"
|
||||
#include "irrt/ndarray/basic.hpp"
|
||||
#include "irrt/ndarray/def.hpp"
|
||||
|
||||
@ -2,6 +2,8 @@
|
||||
|
||||
#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) {
|
||||
|
||||
341
nac3core/irrt/irrt/ndarray/basic.hpp
Normal file
341
nac3core/irrt/irrt/ndarray/basic.hpp
Normal file
@ -0,0 +1,341 @@
|
||||
#pragma once
|
||||
|
||||
#include "irrt/debug.hpp"
|
||||
#include "irrt/exception.hpp"
|
||||
#include "irrt/int_types.hpp"
|
||||
#include "irrt/ndarray/def.hpp"
|
||||
|
||||
namespace {
|
||||
namespace ndarray {
|
||||
namespace basic {
|
||||
/**
|
||||
* @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(SizeT ndims, const SizeT* shape) {
|
||||
for (SizeT axis = 0; axis < ndims; axis++) {
|
||||
if (shape[axis] < 0) {
|
||||
raise_exception(SizeT, EXN_VALUE_ERROR,
|
||||
"negative dimensions are not allowed; axis {0} "
|
||||
"has dimension {1}",
|
||||
axis, shape[axis], NO_PARAM);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* @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>
|
||||
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;
|
||||
}
|
||||
|
||||
/**
|
||||
* @brief Compute the array indices of the `nth` (0-based) element of an ndarray given only its shape.
|
||||
*
|
||||
* @param ndims Number of elements in `shape` and `indices`
|
||||
* @param shape The shape of the ndarray
|
||||
* @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 (SizeT i = 0; i < ndims; i++) {
|
||||
SizeT axis = ndims - i - 1;
|
||||
SizeT dim = shape[axis];
|
||||
|
||||
indices[axis] = nth % dim;
|
||||
nth /= dim;
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* @brief Return the number of elements of an `ndarray`
|
||||
*
|
||||
* This function corresponds to `<an_ndarray>.size`
|
||||
*/
|
||||
template<typename SizeT>
|
||||
SizeT size(const NDArray<SizeT>* ndarray) {
|
||||
return calc_size_from_shape(ndarray->ndims, ndarray->shape);
|
||||
}
|
||||
|
||||
/**
|
||||
* @brief Return of the number of its content of an `ndarray`.
|
||||
*
|
||||
* This function corresponds to `<an_ndarray>.nbytes`.
|
||||
*/
|
||||
template<typename SizeT>
|
||||
SizeT nbytes(const NDArray<SizeT>* ndarray) {
|
||||
return size(ndarray) * 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 length.
|
||||
*/
|
||||
template<typename SizeT>
|
||||
SizeT len(const NDArray<SizeT>* ndarray) {
|
||||
// numpy prohibits `__len__` on unsized objects
|
||||
if (ndarray->ndims == 0) {
|
||||
raise_exception(SizeT, EXN_TYPE_ERROR, "len() of unsized object", NO_PARAM, NO_PARAM, NO_PARAM);
|
||||
} else {
|
||||
return ndarray->shape[0];
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* @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
|
||||
*/
|
||||
template<typename SizeT>
|
||||
bool is_c_contiguous(const NDArray<SizeT>* ndarray) {
|
||||
// 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:
|
||||
//
|
||||
// The traditional rule is that for an array to be flagged as C contiguous,
|
||||
// the following must hold:
|
||||
//
|
||||
// strides[-1] == itemsize
|
||||
// strides[i] == shape[i+1] * strides[i + 1]
|
||||
// [...]
|
||||
// According to these rules, a 0- or 1-dimensional array is either both
|
||||
// C- and F-contiguous, or neither; and an array with 2+ dimensions
|
||||
// can be C- or F- contiguous, or neither, but not both. Though there
|
||||
// there are exceptions for arrays with zero or one item, in the first
|
||||
// case the check is relaxed up to and including the first dimension
|
||||
// with shape[i] == 0. In the second case `strides == itemsize` will
|
||||
// can be true for all dimensions and both flags are set.
|
||||
|
||||
if (ndarray->ndims == 0) {
|
||||
return true;
|
||||
}
|
||||
|
||||
if (ndarray->strides[ndarray->ndims - 1] != ndarray->itemsize) {
|
||||
return false;
|
||||
}
|
||||
|
||||
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]) {
|
||||
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>
|
||||
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 of `ndarray` in flattened view.
|
||||
*
|
||||
* This function does no bound check.
|
||||
*/
|
||||
template<typename SizeT>
|
||||
uint8_t* get_nth_pelement(const NDArray<SizeT>* ndarray, SizeT nth) {
|
||||
uint8_t* element = ndarray->data;
|
||||
for (SizeT i = 0; i < ndarray->ndims; i++) {
|
||||
SizeT axis = ndarray->ndims - i - 1;
|
||||
SizeT dim = ndarray->shape[axis];
|
||||
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, uint8_t* pelement, const uint8_t* 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
|
||||
|
||||
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);
|
||||
}
|
||||
|
||||
uint64_t __nac3_ndarray_size64(NDArray<int64_t>* ndarray) {
|
||||
return size(ndarray);
|
||||
}
|
||||
|
||||
uint32_t __nac3_ndarray_nbytes(NDArray<int32_t>* ndarray) {
|
||||
return nbytes(ndarray);
|
||||
}
|
||||
|
||||
uint64_t __nac3_ndarray_nbytes64(NDArray<int64_t>* ndarray) {
|
||||
return nbytes(ndarray);
|
||||
}
|
||||
|
||||
int32_t __nac3_ndarray_len(NDArray<int32_t>* ndarray) {
|
||||
return len(ndarray);
|
||||
}
|
||||
|
||||
int64_t __nac3_ndarray_len64(NDArray<int64_t>* ndarray) {
|
||||
return len(ndarray);
|
||||
}
|
||||
|
||||
bool __nac3_ndarray_is_c_contiguous(NDArray<int32_t>* ndarray) {
|
||||
return is_c_contiguous(ndarray);
|
||||
}
|
||||
|
||||
bool __nac3_ndarray_is_c_contiguous64(NDArray<int64_t>* ndarray) {
|
||||
return is_c_contiguous(ndarray);
|
||||
}
|
||||
|
||||
uint8_t* __nac3_ndarray_get_nth_pelement(const NDArray<int32_t>* ndarray, int32_t nth) {
|
||||
return get_nth_pelement(ndarray, nth);
|
||||
}
|
||||
|
||||
uint8_t* __nac3_ndarray_get_nth_pelement64(const NDArray<int64_t>* ndarray, int64_t nth) {
|
||||
return get_nth_pelement(ndarray, nth);
|
||||
}
|
||||
|
||||
uint8_t* __nac3_ndarray_get_pelement_by_indices(const NDArray<int32_t>* ndarray, int32_t* indices) {
|
||||
return get_pelement_by_indices(ndarray, indices);
|
||||
}
|
||||
|
||||
uint8_t* __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) {
|
||||
copy_data(src_ndarray, dst_ndarray);
|
||||
}
|
||||
}
|
||||
45
nac3core/irrt/irrt/ndarray/def.hpp
Normal file
45
nac3core/irrt/irrt/ndarray/def.hpp
Normal file
@ -0,0 +1,45 @@
|
||||
#pragma once
|
||||
|
||||
#include "irrt/int_types.hpp"
|
||||
|
||||
namespace {
|
||||
/**
|
||||
* @brief The NDArray object
|
||||
*
|
||||
* Official numpy implementation:
|
||||
* https://github.com/numpy/numpy/blob/735a477f0bc2b5b84d0e72d92f224bde78d4e069/doc/source/reference/c-api/types-and-structures.rst
|
||||
*/
|
||||
template<typename SizeT>
|
||||
struct NDArray {
|
||||
/**
|
||||
* @brief The underlying data this `ndarray` is pointing to.
|
||||
*/
|
||||
uint8_t* data;
|
||||
|
||||
/**
|
||||
* @brief The number of bytes of a single element in `data`.
|
||||
*/
|
||||
SizeT itemsize;
|
||||
|
||||
/**
|
||||
* @brief The number of dimensions of this shape.
|
||||
*/
|
||||
SizeT ndims;
|
||||
|
||||
/**
|
||||
* @brief The NDArray shape, with length equal to `ndims`.
|
||||
*
|
||||
* Note that it may contain 0.
|
||||
*/
|
||||
SizeT* shape;
|
||||
|
||||
/**
|
||||
* @brief Array strides, with length equal to `ndims`
|
||||
*
|
||||
* The stride values are in units of bytes, not number of elements.
|
||||
*
|
||||
* Note that `strides` can have negative values or contain 0.
|
||||
*/
|
||||
SizeT* strides;
|
||||
};
|
||||
} // namespace
|
||||
@ -7,9 +7,12 @@ use super::{
|
||||
},
|
||||
llvm_intrinsics,
|
||||
macros::codegen_unreachable,
|
||||
model::*,
|
||||
object::ndarray::NDArray,
|
||||
stmt::gen_for_callback_incrementing,
|
||||
CodeGenContext, CodeGenerator,
|
||||
};
|
||||
use function::FnCall;
|
||||
use inkwell::{
|
||||
attributes::{Attribute, AttributeLoc},
|
||||
context::Context,
|
||||
@ -949,3 +952,134 @@ pub fn call_ndarray_calc_broadcast_index<
|
||||
Box::new(|_, v| v.into()),
|
||||
)
|
||||
}
|
||||
|
||||
// When [`TypeContext::size_type`] is 32-bits, the function name is "{fn_name}".
|
||||
// When [`TypeContext::size_type`] is 64-bits, the function name is "{fn_name}64".
|
||||
#[must_use]
|
||||
pub fn get_sizet_dependent_function_name<G: CodeGenerator + ?Sized>(
|
||||
generator: &mut 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
|
||||
}
|
||||
|
||||
pub fn call_nac3_ndarray_util_assert_shape_no_negative<'ctx, G: CodeGenerator + ?Sized>(
|
||||
generator: &mut G,
|
||||
ctx: &mut CodeGenContext<'ctx, '_>,
|
||||
ndims: Instance<'ctx, Int<SizeT>>,
|
||||
shape: Instance<'ctx, Ptr<Int<SizeT>>>,
|
||||
) {
|
||||
let name = get_sizet_dependent_function_name(
|
||||
generator,
|
||||
ctx,
|
||||
"__nac3_ndarray_util_assert_shape_no_negative",
|
||||
);
|
||||
FnCall::builder(generator, ctx, &name).arg(ndims).arg(shape).returning_void();
|
||||
}
|
||||
|
||||
pub fn call_nac3_ndarray_util_assert_output_shape_same<'ctx, G: CodeGenerator + ?Sized>(
|
||||
generator: &mut G,
|
||||
ctx: &mut CodeGenContext<'ctx, '_>,
|
||||
ndarray_ndims: Instance<'ctx, Int<SizeT>>,
|
||||
ndarray_shape: Instance<'ctx, Ptr<Int<SizeT>>>,
|
||||
output_ndims: Instance<'ctx, Int<SizeT>>,
|
||||
output_shape: Instance<'ctx, Ptr<Int<SizeT>>>,
|
||||
) {
|
||||
let name = get_sizet_dependent_function_name(
|
||||
generator,
|
||||
ctx,
|
||||
"__nac3_ndarray_util_assert_output_shape_same",
|
||||
);
|
||||
FnCall::builder(generator, ctx, &name)
|
||||
.arg(ndarray_ndims)
|
||||
.arg(ndarray_shape)
|
||||
.arg(output_ndims)
|
||||
.arg(output_shape)
|
||||
.returning_void();
|
||||
}
|
||||
|
||||
pub fn call_nac3_ndarray_size<'ctx, G: CodeGenerator + ?Sized>(
|
||||
generator: &mut G,
|
||||
ctx: &mut CodeGenContext<'ctx, '_>,
|
||||
ndarray: Instance<'ctx, Ptr<Struct<NDArray>>>,
|
||||
) -> Instance<'ctx, Int<SizeT>> {
|
||||
let name = get_sizet_dependent_function_name(generator, ctx, "__nac3_ndarray_size");
|
||||
FnCall::builder(generator, ctx, &name).arg(ndarray).returning_auto("size")
|
||||
}
|
||||
|
||||
pub fn call_nac3_ndarray_nbytes<'ctx, G: CodeGenerator + ?Sized>(
|
||||
generator: &mut G,
|
||||
ctx: &mut CodeGenContext<'ctx, '_>,
|
||||
ndarray: Instance<'ctx, Ptr<Struct<NDArray>>>,
|
||||
) -> Instance<'ctx, Int<SizeT>> {
|
||||
let name = get_sizet_dependent_function_name(generator, ctx, "__nac3_ndarray_nbytes");
|
||||
FnCall::builder(generator, ctx, &name).arg(ndarray).returning_auto("nbytes")
|
||||
}
|
||||
|
||||
pub fn call_nac3_ndarray_len<'ctx, G: CodeGenerator + ?Sized>(
|
||||
generator: &mut G,
|
||||
ctx: &mut CodeGenContext<'ctx, '_>,
|
||||
ndarray: Instance<'ctx, Ptr<Struct<NDArray>>>,
|
||||
) -> Instance<'ctx, Int<SizeT>> {
|
||||
let name = get_sizet_dependent_function_name(generator, ctx, "__nac3_ndarray_len");
|
||||
FnCall::builder(generator, ctx, &name).arg(ndarray).returning_auto("len")
|
||||
}
|
||||
|
||||
pub fn call_nac3_ndarray_is_c_contiguous<'ctx, G: CodeGenerator + ?Sized>(
|
||||
generator: &mut G,
|
||||
ctx: &mut CodeGenContext<'ctx, '_>,
|
||||
ndarray: Instance<'ctx, Ptr<Struct<NDArray>>>,
|
||||
) -> Instance<'ctx, Int<Bool>> {
|
||||
let name = get_sizet_dependent_function_name(generator, ctx, "__nac3_ndarray_is_c_contiguous");
|
||||
FnCall::builder(generator, ctx, &name).arg(ndarray).returning_auto("is_c_contiguous")
|
||||
}
|
||||
|
||||
pub fn call_nac3_ndarray_get_nth_pelement<'ctx, G: CodeGenerator + ?Sized>(
|
||||
generator: &mut G,
|
||||
ctx: &mut CodeGenContext<'ctx, '_>,
|
||||
ndarray: Instance<'ctx, Ptr<Struct<NDArray>>>,
|
||||
index: Instance<'ctx, Int<SizeT>>,
|
||||
) -> Instance<'ctx, Ptr<Int<Byte>>> {
|
||||
let name = get_sizet_dependent_function_name(generator, ctx, "__nac3_ndarray_get_nth_pelement");
|
||||
FnCall::builder(generator, ctx, &name).arg(ndarray).arg(index).returning_auto("pelement")
|
||||
}
|
||||
|
||||
pub fn call_nac3_ndarray_get_pelement_by_indices<'ctx, G: CodeGenerator + ?Sized>(
|
||||
generator: &mut G,
|
||||
ctx: &mut CodeGenContext<'ctx, '_>,
|
||||
ndarray: Instance<'ctx, Ptr<Struct<NDArray>>>,
|
||||
indices: Instance<'ctx, Ptr<Int<SizeT>>>,
|
||||
) -> Instance<'ctx, Ptr<Int<Byte>>> {
|
||||
let name =
|
||||
get_sizet_dependent_function_name(generator, ctx, "__nac3_ndarray_get_pelement_by_indices");
|
||||
FnCall::builder(generator, ctx, &name).arg(ndarray).arg(indices).returning_auto("pelement")
|
||||
}
|
||||
|
||||
pub fn call_nac3_ndarray_set_strides_by_shape<'ctx, G: CodeGenerator + ?Sized>(
|
||||
generator: &mut G,
|
||||
ctx: &mut CodeGenContext<'ctx, '_>,
|
||||
ndarray: Instance<'ctx, Ptr<Struct<NDArray>>>,
|
||||
) {
|
||||
let name =
|
||||
get_sizet_dependent_function_name(generator, ctx, "__nac3_ndarray_set_strides_by_shape");
|
||||
FnCall::builder(generator, ctx, &name).arg(ndarray).returning_void();
|
||||
}
|
||||
|
||||
pub fn call_nac3_ndarray_copy_data<'ctx, G: CodeGenerator + ?Sized>(
|
||||
generator: &mut G,
|
||||
ctx: &mut CodeGenContext<'ctx, '_>,
|
||||
src_ndarray: Instance<'ctx, Ptr<Struct<NDArray>>>,
|
||||
dst_ndarray: Instance<'ctx, Ptr<Struct<NDArray>>>,
|
||||
) {
|
||||
let name = get_sizet_dependent_function_name(generator, ctx, "__nac3_ndarray_copy_data");
|
||||
FnCall::builder(generator, ctx, &name).arg(src_ndarray).arg(dst_ndarray).returning_void();
|
||||
}
|
||||
|
||||
@ -1,7 +1,7 @@
|
||||
use crate::{
|
||||
codegen::classes::{ListType, NDArrayType, ProxyType, RangeType},
|
||||
codegen::classes::{ListType, ProxyType, RangeType},
|
||||
symbol_resolver::{StaticValue, SymbolResolver},
|
||||
toplevel::{helper::PrimDef, numpy::unpack_ndarray_var_tys, TopLevelContext, TopLevelDef},
|
||||
toplevel::{helper::PrimDef, TopLevelContext, TopLevelDef},
|
||||
typecheck::{
|
||||
type_inferencer::{CodeLocation, PrimitiveStore},
|
||||
typedef::{CallId, FuncArg, Type, TypeEnum, Unifier},
|
||||
@ -24,7 +24,9 @@ use inkwell::{
|
||||
AddressSpace, IntPredicate, OptimizationLevel,
|
||||
};
|
||||
use itertools::Itertools;
|
||||
use model::*;
|
||||
use nac3parser::ast::{Location, Stmt, StrRef};
|
||||
use object::ndarray::NDArray;
|
||||
use parking_lot::{Condvar, Mutex};
|
||||
use std::collections::{HashMap, HashSet};
|
||||
use std::sync::{
|
||||
@ -507,12 +509,7 @@ fn get_llvm_type<'ctx, G: CodeGenerator + ?Sized>(
|
||||
}
|
||||
|
||||
TObj { obj_id, .. } if *obj_id == PrimDef::NDArray.id() => {
|
||||
let (dtype, _) = unpack_ndarray_var_tys(unifier, ty);
|
||||
let element_type = get_llvm_type(
|
||||
ctx, module, generator, unifier, top_level, type_cache, dtype,
|
||||
);
|
||||
|
||||
NDArrayType::new(generator, ctx, element_type).as_base_type().into()
|
||||
Ptr(Struct(NDArray)).llvm_type(generator, ctx).as_basic_type_enum()
|
||||
}
|
||||
|
||||
_ => unreachable!(
|
||||
|
||||
@ -1 +1,2 @@
|
||||
pub mod any;
|
||||
pub mod ndarray;
|
||||
|
||||
346
nac3core/src/codegen/object/ndarray/mod.rs
Normal file
346
nac3core/src/codegen/object/ndarray/mod.rs
Normal file
@ -0,0 +1,346 @@
|
||||
use inkwell::{context::Context, types::BasicType, values::PointerValue, AddressSpace};
|
||||
|
||||
use crate::{
|
||||
codegen::{
|
||||
irrt::{
|
||||
call_nac3_ndarray_copy_data, call_nac3_ndarray_get_nth_pelement,
|
||||
call_nac3_ndarray_get_pelement_by_indices, call_nac3_ndarray_is_c_contiguous,
|
||||
call_nac3_ndarray_len, call_nac3_ndarray_nbytes,
|
||||
call_nac3_ndarray_set_strides_by_shape, call_nac3_ndarray_size,
|
||||
},
|
||||
model::*,
|
||||
CodeGenContext, CodeGenerator,
|
||||
},
|
||||
toplevel::{helper::extract_ndims, numpy::unpack_ndarray_var_tys},
|
||||
typecheck::typedef::Type,
|
||||
};
|
||||
|
||||
use super::any::AnyObject;
|
||||
|
||||
/// Fields of [`NDArray`]
|
||||
pub struct NDArrayFields<'ctx, F: FieldTraversal<'ctx>> {
|
||||
pub data: F::Output<Ptr<Int<Byte>>>,
|
||||
pub itemsize: F::Output<Int<SizeT>>,
|
||||
pub ndims: F::Output<Int<SizeT>>,
|
||||
pub shape: F::Output<Ptr<Int<SizeT>>>,
|
||||
pub strides: F::Output<Ptr<Int<SizeT>>>,
|
||||
}
|
||||
|
||||
/// A strided ndarray in NAC3.
|
||||
///
|
||||
/// See IRRT implementation for details about its fields.
|
||||
#[derive(Debug, Clone, Copy, Default)]
|
||||
pub struct NDArray;
|
||||
|
||||
impl<'ctx> StructKind<'ctx> for NDArray {
|
||||
type Fields<F: FieldTraversal<'ctx>> = NDArrayFields<'ctx, F>;
|
||||
|
||||
fn iter_fields<F: FieldTraversal<'ctx>>(&self, traversal: &mut F) -> Self::Fields<F> {
|
||||
Self::Fields {
|
||||
data: traversal.add_auto("data"),
|
||||
itemsize: traversal.add_auto("itemsize"),
|
||||
ndims: traversal.add_auto("ndims"),
|
||||
shape: traversal.add_auto("shape"),
|
||||
strides: traversal.add_auto("strides"),
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// A NAC3 Python ndarray object.
|
||||
#[derive(Debug, Clone, Copy)]
|
||||
pub struct NDArrayObject<'ctx> {
|
||||
pub dtype: Type,
|
||||
pub ndims: u64,
|
||||
pub instance: Instance<'ctx, Ptr<Struct<NDArray>>>,
|
||||
}
|
||||
|
||||
impl<'ctx> NDArrayObject<'ctx> {
|
||||
/// Attempt to convert an [`AnyObject`] into an [`NDArrayObject`].
|
||||
pub fn from_object<G: CodeGenerator + ?Sized>(
|
||||
generator: &mut G,
|
||||
ctx: &mut CodeGenContext<'ctx, '_>,
|
||||
object: AnyObject<'ctx>,
|
||||
) -> NDArrayObject<'ctx> {
|
||||
let (dtype, ndims) = unpack_ndarray_var_tys(&mut ctx.unifier, object.ty);
|
||||
let ndims = extract_ndims(&ctx.unifier, ndims);
|
||||
|
||||
let value = Ptr(Struct(NDArray)).check_value(generator, ctx.ctx, object.value).unwrap();
|
||||
NDArrayObject { dtype, ndims, instance: value }
|
||||
}
|
||||
|
||||
/// Get this ndarray's `ndims` as an LLVM constant.
|
||||
pub fn ndims_llvm<G: CodeGenerator + ?Sized>(
|
||||
&self,
|
||||
generator: &mut G,
|
||||
ctx: &'ctx Context,
|
||||
) -> Instance<'ctx, Int<SizeT>> {
|
||||
Int(SizeT).const_int(generator, ctx, self.ndims, false)
|
||||
}
|
||||
|
||||
/// Allocate an ndarray on the stack given its `ndims` and `dtype`.
|
||||
///
|
||||
/// `shape` and `strides` will be automatically allocated onto the stack.
|
||||
///
|
||||
/// The returned ndarray's content will be:
|
||||
/// - `data`: uninitialized.
|
||||
/// - `itemsize`: set to the `sizeof()` of `dtype`.
|
||||
/// - `ndims`: set to the value of `ndims`.
|
||||
/// - `shape`: allocated with an array of length `ndims` with uninitialized values.
|
||||
/// - `strides`: allocated with an array of length `ndims` with uninitialized values.
|
||||
pub fn alloca<G: CodeGenerator + ?Sized>(
|
||||
generator: &mut G,
|
||||
ctx: &mut CodeGenContext<'ctx, '_>,
|
||||
dtype: Type,
|
||||
ndims: u64,
|
||||
) -> Self {
|
||||
let ndarray = Struct(NDArray).alloca(generator, ctx);
|
||||
|
||||
let itemsize = ctx.get_llvm_type(generator, dtype).size_of().unwrap();
|
||||
let itemsize = Int(SizeT).z_extend_or_truncate(generator, ctx, itemsize);
|
||||
ndarray.set(ctx, |f| f.itemsize, itemsize);
|
||||
|
||||
let ndims_val = Int(SizeT).const_int(generator, ctx.ctx, ndims, false);
|
||||
ndarray.set(ctx, |f| f.ndims, ndims_val);
|
||||
|
||||
let shape = Int(SizeT).array_alloca(generator, ctx, ndims_val.value);
|
||||
ndarray.set(ctx, |f| f.shape, shape);
|
||||
|
||||
let strides = Int(SizeT).array_alloca(generator, ctx, ndims_val.value);
|
||||
ndarray.set(ctx, |f| f.strides, strides);
|
||||
|
||||
NDArrayObject { dtype, ndims, instance: ndarray }
|
||||
}
|
||||
|
||||
/// Convenience function. Allocate an [`NDArrayObject`] with a statically known shape.
|
||||
///
|
||||
/// The returned [`NDArrayObject`]'s `data` and `strides` are uninitialized.
|
||||
pub fn alloca_constant_shape<G: CodeGenerator + ?Sized>(
|
||||
generator: &mut G,
|
||||
ctx: &mut CodeGenContext<'ctx, '_>,
|
||||
dtype: Type,
|
||||
shape: &[u64],
|
||||
) -> Self {
|
||||
let ndarray = NDArrayObject::alloca(generator, ctx, dtype, shape.len() as u64);
|
||||
|
||||
// Write shape
|
||||
let dst_shape = ndarray.instance.get(generator, ctx, |f| f.shape);
|
||||
for (i, dim) in shape.iter().enumerate() {
|
||||
let dim = Int(SizeT).const_int(generator, ctx.ctx, *dim, false);
|
||||
dst_shape.offset_const(ctx, i64::try_from(i).unwrap()).store(ctx, dim);
|
||||
}
|
||||
|
||||
ndarray
|
||||
}
|
||||
|
||||
/// Convenience function. Allocate an [`NDArrayObject`] with a dynamically known shape.
|
||||
///
|
||||
/// The returned [`NDArrayObject`]'s `data` and `strides` are uninitialized.
|
||||
pub fn alloca_dynamic_shape<G: CodeGenerator + ?Sized>(
|
||||
generator: &mut G,
|
||||
ctx: &mut CodeGenContext<'ctx, '_>,
|
||||
dtype: Type,
|
||||
shape: &[Instance<'ctx, Int<SizeT>>],
|
||||
) -> Self {
|
||||
let ndarray = NDArrayObject::alloca(generator, ctx, dtype, shape.len() as u64);
|
||||
|
||||
// Write shape
|
||||
let dst_shape = ndarray.instance.get(generator, ctx, |f| f.shape);
|
||||
for (i, dim) in shape.iter().enumerate() {
|
||||
dst_shape.offset_const(ctx, i64::try_from(i).unwrap()).store(ctx, *dim);
|
||||
}
|
||||
|
||||
ndarray
|
||||
}
|
||||
|
||||
/// 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 create_data<G: CodeGenerator + ?Sized>(
|
||||
&self,
|
||||
generator: &mut G,
|
||||
ctx: &mut CodeGenContext<'ctx, '_>,
|
||||
) {
|
||||
let nbytes = self.nbytes(generator, ctx);
|
||||
|
||||
let data = Int(Byte).array_alloca(generator, ctx, nbytes.value);
|
||||
self.instance.set(ctx, |f| f.data, data);
|
||||
|
||||
self.set_strides_contiguous(generator, ctx);
|
||||
}
|
||||
|
||||
/// Copy shape dimensions from an array.
|
||||
pub fn copy_shape_from_array<G: CodeGenerator + ?Sized>(
|
||||
&self,
|
||||
generator: &mut G,
|
||||
ctx: &mut CodeGenContext<'ctx, '_>,
|
||||
shape: Instance<'ctx, Ptr<Int<SizeT>>>,
|
||||
) {
|
||||
let num_items = self.ndims_llvm(generator, ctx.ctx).value;
|
||||
self.instance.get(generator, ctx, |f| f.shape).copy_from(generator, ctx, shape, num_items);
|
||||
}
|
||||
|
||||
/// Copy shape dimensions from an ndarray.
|
||||
/// Panics if `ndims` mismatches.
|
||||
pub fn copy_shape_from_ndarray<G: CodeGenerator + ?Sized>(
|
||||
&self,
|
||||
generator: &mut G,
|
||||
ctx: &mut CodeGenContext<'ctx, '_>,
|
||||
src_ndarray: NDArrayObject<'ctx>,
|
||||
) {
|
||||
assert_eq!(self.ndims, src_ndarray.ndims);
|
||||
let src_shape = src_ndarray.instance.get(generator, ctx, |f| f.shape);
|
||||
self.copy_shape_from_array(generator, ctx, src_shape);
|
||||
}
|
||||
|
||||
/// Copy strides dimensions from an array.
|
||||
pub fn copy_strides_from_array<G: CodeGenerator + ?Sized>(
|
||||
&self,
|
||||
generator: &mut G,
|
||||
ctx: &mut CodeGenContext<'ctx, '_>,
|
||||
strides: Instance<'ctx, Ptr<Int<SizeT>>>,
|
||||
) {
|
||||
let num_items = self.ndims_llvm(generator, ctx.ctx).value;
|
||||
self.instance
|
||||
.get(generator, ctx, |f| f.strides)
|
||||
.copy_from(generator, ctx, strides, num_items);
|
||||
}
|
||||
|
||||
/// Copy strides dimensions from an ndarray.
|
||||
/// Panics if `ndims` mismatches.
|
||||
pub fn copy_strides_from_ndarray<G: CodeGenerator + ?Sized>(
|
||||
&self,
|
||||
generator: &mut G,
|
||||
ctx: &mut CodeGenContext<'ctx, '_>,
|
||||
src_ndarray: NDArrayObject<'ctx>,
|
||||
) {
|
||||
assert_eq!(self.ndims, src_ndarray.ndims);
|
||||
let src_strides = src_ndarray.instance.get(generator, ctx, |f| f.strides);
|
||||
self.copy_strides_from_array(generator, ctx, src_strides);
|
||||
}
|
||||
|
||||
/// Get the `np.size()` of this ndarray.
|
||||
pub fn size<G: CodeGenerator + ?Sized>(
|
||||
&self,
|
||||
generator: &mut G,
|
||||
ctx: &mut CodeGenContext<'ctx, '_>,
|
||||
) -> Instance<'ctx, Int<SizeT>> {
|
||||
call_nac3_ndarray_size(generator, ctx, self.instance)
|
||||
}
|
||||
|
||||
/// Get the `ndarray.nbytes` of this ndarray.
|
||||
pub fn nbytes<G: CodeGenerator + ?Sized>(
|
||||
&self,
|
||||
generator: &mut G,
|
||||
ctx: &mut CodeGenContext<'ctx, '_>,
|
||||
) -> Instance<'ctx, Int<SizeT>> {
|
||||
call_nac3_ndarray_nbytes(generator, ctx, self.instance)
|
||||
}
|
||||
|
||||
/// Get the `len()` of this ndarray.
|
||||
pub fn len<G: CodeGenerator + ?Sized>(
|
||||
&self,
|
||||
generator: &mut G,
|
||||
ctx: &mut CodeGenContext<'ctx, '_>,
|
||||
) -> Instance<'ctx, Int<SizeT>> {
|
||||
call_nac3_ndarray_len(generator, ctx, self.instance)
|
||||
}
|
||||
|
||||
/// Check if this ndarray is C-contiguous.
|
||||
///
|
||||
/// See NumPy's `flags["C_CONTIGUOUS"]`: <https://numpy.org/doc/stable/reference/generated/numpy.ndarray.flags.html#numpy.ndarray.flags>
|
||||
pub fn is_c_contiguous<G: CodeGenerator + ?Sized>(
|
||||
&self,
|
||||
generator: &mut G,
|
||||
ctx: &mut CodeGenContext<'ctx, '_>,
|
||||
) -> Instance<'ctx, Int<Bool>> {
|
||||
call_nac3_ndarray_is_c_contiguous(generator, ctx, self.instance)
|
||||
}
|
||||
|
||||
/// Get the pointer to the n-th (0-based) element.
|
||||
///
|
||||
/// The returned pointer has the element type of the LLVM type of this ndarray's `dtype`.
|
||||
pub fn get_nth_pelement<G: CodeGenerator + ?Sized>(
|
||||
&self,
|
||||
generator: &mut G,
|
||||
ctx: &mut CodeGenContext<'ctx, '_>,
|
||||
nth: Instance<'ctx, Int<SizeT>>,
|
||||
) -> PointerValue<'ctx> {
|
||||
let elem_ty = ctx.get_llvm_type(generator, self.dtype);
|
||||
|
||||
let p = call_nac3_ndarray_get_nth_pelement(generator, ctx, self.instance, nth);
|
||||
ctx.builder
|
||||
.build_pointer_cast(p.value, elem_ty.ptr_type(AddressSpace::default()), "")
|
||||
.unwrap()
|
||||
}
|
||||
|
||||
/// Get the n-th (0-based) scalar.
|
||||
pub fn get_nth_scalar<G: CodeGenerator + ?Sized>(
|
||||
&self,
|
||||
generator: &mut G,
|
||||
ctx: &mut CodeGenContext<'ctx, '_>,
|
||||
nth: Instance<'ctx, Int<SizeT>>,
|
||||
) -> AnyObject<'ctx> {
|
||||
let ptr = self.get_nth_pelement(generator, ctx, nth);
|
||||
let value = ctx.builder.build_load(ptr, "").unwrap();
|
||||
AnyObject { ty: self.dtype, value }
|
||||
}
|
||||
|
||||
/// Get the pointer to the element indexed by `indices`.
|
||||
///
|
||||
/// The returned pointer has the element type of the LLVM type of this ndarray's `dtype`.
|
||||
pub fn get_pelement_by_indices<G: CodeGenerator + ?Sized>(
|
||||
&self,
|
||||
generator: &mut G,
|
||||
ctx: &mut CodeGenContext<'ctx, '_>,
|
||||
indices: Instance<'ctx, Ptr<Int<SizeT>>>,
|
||||
) -> PointerValue<'ctx> {
|
||||
let elem_ty = ctx.get_llvm_type(generator, self.dtype);
|
||||
|
||||
let p = call_nac3_ndarray_get_pelement_by_indices(generator, ctx, self.instance, indices);
|
||||
ctx.builder
|
||||
.build_pointer_cast(p.value, elem_ty.ptr_type(AddressSpace::default()), "")
|
||||
.unwrap()
|
||||
}
|
||||
|
||||
/// Get the scalar indexed by `indices`.
|
||||
pub fn get_scalar_by_indices<G: CodeGenerator + ?Sized>(
|
||||
&self,
|
||||
generator: &mut G,
|
||||
ctx: &mut CodeGenContext<'ctx, '_>,
|
||||
indices: Instance<'ctx, Ptr<Int<SizeT>>>,
|
||||
) -> AnyObject<'ctx> {
|
||||
let ptr = self.get_pelement_by_indices(generator, ctx, indices);
|
||||
let value = ctx.builder.build_load(ptr, "").unwrap();
|
||||
AnyObject { ty: self.dtype, value }
|
||||
}
|
||||
|
||||
/// Call [`call_nac3_ndarray_set_strides_by_shape`] on this ndarray to update `strides`.
|
||||
///
|
||||
/// Update the ndarray's strides to make the ndarray contiguous.
|
||||
pub fn set_strides_contiguous<G: CodeGenerator + ?Sized>(
|
||||
self,
|
||||
generator: &mut G,
|
||||
ctx: &mut CodeGenContext<'ctx, '_>,
|
||||
) {
|
||||
call_nac3_ndarray_set_strides_by_shape(generator, ctx, self.instance);
|
||||
}
|
||||
|
||||
/// Copy data from another ndarray.
|
||||
///
|
||||
/// This ndarray and `src` is that their `np.size()` should be the same. Their shapes
|
||||
/// do not matter. The copying order is determined by how their flattened views look.
|
||||
///
|
||||
/// Panics if the `dtype`s of ndarrays are different.
|
||||
pub fn copy_data_from<G: CodeGenerator + ?Sized>(
|
||||
&self,
|
||||
generator: &mut G,
|
||||
ctx: &mut CodeGenContext<'ctx, '_>,
|
||||
src: NDArrayObject<'ctx>,
|
||||
) {
|
||||
assert!(ctx.unifier.unioned(self.dtype, src.dtype), "self and src dtype should match");
|
||||
call_nac3_ndarray_copy_data(generator, ctx, src.instance, self.instance);
|
||||
}
|
||||
}
|
||||
Loading…
Reference in New Issue
Block a user