Files
derek.holloway 7502bf64a4
CodeQL / Analyze (actions) (push) Canceled after 0s
CodeQL / Analyze (python) (push) Canceled after 0s
pre-commit / pre-commit (push) Canceled after 0s
Multi-Arch CI / setup (push) Canceled after 0s
Publish build_manylinux_x86_64 images / publish_build_manylinux_x86_64 (push) Canceled after 0s
Setup (Multi-Arch) / setup (push) Canceled after 0s
Multi-Arch CI / Linux::${{ fromJSON(needs.setup.outputs.linux_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubi10 image / publish_no_rocm_image_ubi10 (push) Canceled after 0s
Multi-Arch CI / Windows::${{ fromJSON(needs.setup.outputs.windows_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Multi-Arch CI / Manifest Diff (push) Canceled after 0s
TheRock Manifest Diff Report / Generate Manifest Diff Report (push) Canceled after 0s
Multi-Arch CI / CI Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_ocl_rt images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_rocgdb images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Unit Tests / Unit Tests :: ubuntu-24.04 (push) Canceled after 0s
Unit Tests / Unit Tests :: windows-2022 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_media (push) Canceled after 0s
Unit Tests / Unit Tests Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_openmpi (push) Canceled after 0s
Flatten subprojects into a single base monorepo
2026-09-02 16:34:47 -07:00

88 lines
5.1 KiB
C++

/*
* Copyright (c) Advanced Micro Devices, Inc., or its affiliates.
*
* SPDX-License-Identifier: MIT
*/
#pragma once
#include "unary_common.hh"
#include "binary_common.hh"
#include "ternary_common.hh"
/********** Unary **********/
#define MATH_UNARY_HP_KERNEL_DEF(func_name) \
__global__ void func_name##_kernel(Float16* const ys, const size_t num_xs, Float16* const xs) { \
const auto tid = cg::this_grid().thread_rank(); \
const auto stride = cg::this_grid().size(); \
\
for (size_t i = tid; i < num_xs; i += stride) { \
ys[i] = func_name(xs[i]); \
} \
}
#define MATH_UNARY_HP_TEST_DEF_IMPL(func_name, ref_func, validator_builder) \
HIP_TEST_CASE(Unit_Device_##func_name##_Accuracy_Positive) { \
UnaryHalfPrecisionTest(func_name##_kernel, ref_func, validator_builder); \
}
#define MATH_UNARY_HP_TEST_DEF(func_name, ref_func) \
MATH_UNARY_HP_TEST_DEF_IMPL(func_name, ref_func, func_name##_validator_builder)
#define MATH_UNARY_HP_VALIDATOR_BUILDER_DEF(func_name) \
static std::unique_ptr<MatcherBase<float>> func_name##_validator_builder(float target, float x)
/********** Binary **********/
#define MATH_BINARY_HP_KERNEL_DEF(func_name) \
__global__ void func_name##_kernel(Float16* const ys, const size_t num_xs, Float16* const x1s, \
Float16* const x2s) { \
const auto tid = cg::this_grid().thread_rank(); \
const auto stride = cg::this_grid().size(); \
\
for (size_t i = tid; i < num_xs; i += stride) { \
ys[i] = func_name(x1s[i], x2s[i]); \
} \
}
#define MATH_BINARY_HP_TEST_DEF_IMPL(func_name, ref_func, validator_builder) \
HIP_TEST_CASE(Unit_Device_##func_name##_Accuracy_Positive) { \
BinaryFloatingPointTest(func_name##_kernel, ref_func, validator_builder); \
}
#define MATH_BINARY_HP_TEST_DEF(func_name, ref_func) \
MATH_BINARY_HP_TEST_IMPL(func_name, ref_func, func_name##_validator_builder)
#define MATH_BINARY_HP_VALIDATOR_BUILDER_DEF(func_name) \
static std::unique_ptr<MatcherBase<float>> func_name##_validator_builder(float target, float x1, \
float x2)
/********** Ternary **********/
#define MATH_TERNARY_HP_KERNEL_DEF(func_name) \
__global__ void func_name##_kernel(Float16* const ys, const size_t num_xs, Float16* const x1s, \
Float16* const x2s, Float16* const x3s) { \
const auto tid = cg::this_grid().thread_rank(); \
const auto stride = cg::this_grid().size(); \
\
for (size_t i = tid; i < num_xs; i += stride) { \
ys[i] = func_name(x1s[i], x2s[i], x3s[i]); \
} \
}
#define MATH_TERNARY_HP_TEST_DEF_IMPL(func_name, ref_func, validator_builder) \
HIP_TEST_CASE(Unit_Device_##func_name##_Accuracy_Positive) { \
TernaryFloatingPointTest(func_name##_kernel, ref_func, validator_builder); \
}
#define MATH_TERNARY_HP_TEST_DEF(func_name, ref_func, validator_builder) \
MATH_TERNARY_HP_TEST_DEF_IMPL(func_name, ref_func, func_name##_validator_builder)
#define MATH_TERNARY_HP_VALIDATOR_BUILDER_DEF(func_name) \
static std::unique_ptr<MatcherBase<float>> func_name##_validator_builder(float target, float x1, \
float x2, float x3)