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
100 lines
2.8 KiB
C++
100 lines
2.8 KiB
C++
// Copyright (c) Advanced Micro Devices, Inc., or its affiliates.
|
|
// SPDX-License-Identifier: MIT
|
|
|
|
#include "ck/ck.hpp"
|
|
#pragma once
|
|
|
|
namespace ck {
|
|
|
|
template <index_t MPerWave, index_t NPerWave>
|
|
struct intrin_smfmac_f32_16x16x32f16;
|
|
|
|
// for every smfmac instruction if CBSZ[1:0]=0, ABID[1:0] selects one of four 8-bit sets of sparse
|
|
// indices from reg_idx
|
|
template <>
|
|
struct intrin_smfmac_f32_16x16x32f16<16, 16>
|
|
{
|
|
template <class FloatC, index_t abid = 0>
|
|
__device__ static void
|
|
Run(const half4_t& reg_a, const half8_t& reg_b, const index_t& reg_idx, FloatC& reg_c)
|
|
{
|
|
#if defined(__gfx94__)
|
|
reg_c.template AsType<float4_t>()(Number<0>{}) = __builtin_amdgcn_smfmac_f32_16x16x32_f16(
|
|
reg_a, reg_b, reg_c.template AsType<float4_t>()[Number<0>{}], reg_idx, 0, abid);
|
|
#else
|
|
ignore = reg_a;
|
|
ignore = reg_b;
|
|
ignore = reg_c;
|
|
ignore = reg_idx;
|
|
#endif
|
|
}
|
|
};
|
|
|
|
template <index_t MPerWave, index_t NPerWave>
|
|
struct intrin_smfmac_f32_16x16x32bf16;
|
|
|
|
template <>
|
|
struct intrin_smfmac_f32_16x16x32bf16<16, 16>
|
|
{
|
|
template <class FloatC, index_t abid = 0>
|
|
__device__ static void
|
|
Run(const bhalf4_t& reg_a, const bhalf8_t& reg_b, const index_t& reg_idx, FloatC& reg_c)
|
|
{
|
|
#if defined(__gfx94__)
|
|
reg_c.template AsType<float4_t>()(Number<0>{}) = __builtin_amdgcn_smfmac_f32_16x16x32_bf16(
|
|
reg_a, reg_b, reg_c.template AsType<float4_t>()[Number<0>{}], reg_idx, 0, abid);
|
|
#else
|
|
ignore = reg_a;
|
|
ignore = reg_b;
|
|
ignore = reg_c;
|
|
ignore = reg_idx;
|
|
#endif
|
|
}
|
|
};
|
|
|
|
template <index_t MPerWave, index_t NPerWave>
|
|
struct intrin_smfmac_f32_32x32x16f16;
|
|
|
|
template <>
|
|
struct intrin_smfmac_f32_32x32x16f16<32, 32>
|
|
{
|
|
template <class FloatC, index_t abid = 0>
|
|
__device__ static void
|
|
Run(const half4_t& reg_a, const half8_t& reg_b, const index_t& reg_idx, FloatC& reg_c)
|
|
{
|
|
#if defined(__gfx94__)
|
|
reg_c.template AsType<float16_t>()(Number<0>{}) = __builtin_amdgcn_smfmac_f32_32x32x16_f16(
|
|
reg_a, reg_b, reg_c.template AsType<float16_t>()[Number<0>{}], reg_idx, 0, abid);
|
|
#else
|
|
ignore = reg_a;
|
|
ignore = reg_b;
|
|
ignore = reg_c;
|
|
ignore = reg_idx;
|
|
#endif
|
|
}
|
|
};
|
|
|
|
template <index_t MPerWave, index_t NPerWave>
|
|
struct intrin_smfmac_f32_32x32x16bf16;
|
|
|
|
template <>
|
|
struct intrin_smfmac_f32_32x32x16bf16<32, 32>
|
|
{
|
|
template <class FloatC, index_t abid = 0>
|
|
__device__ static void
|
|
Run(const bhalf4_t& reg_a, const bhalf8_t& reg_b, const index_t& reg_idx, FloatC& reg_c)
|
|
{
|
|
#if defined(__gfx94__)
|
|
reg_c.template AsType<float16_t>()(Number<0>{}) = __builtin_amdgcn_smfmac_f32_32x32x16_bf16(
|
|
reg_a, reg_b, reg_c.template AsType<float16_t>()[Number<0>{}], reg_idx, 0, abid);
|
|
#else
|
|
ignore = reg_a;
|
|
ignore = reg_b;
|
|
ignore = reg_c;
|
|
ignore = reg_idx;
|
|
#endif
|
|
}
|
|
};
|
|
|
|
} // namespace ck
|