Files
TheRock/rocm-libraries/projects/composablekernel/include/ck/utility/amd_transpose_load.hpp
T
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

38 lines
1.2 KiB
C++

// Copyright (c) Advanced Micro Devices, Inc., or its affiliates.
// SPDX-License-Identifier: MIT
#pragma once
#include "data_type.hpp"
namespace ck {
#if defined(__gfx12__)
template <typename T>
__device__ auto amd_global_load_transpose_to_vgpr(const T* in_ptr)
{
using vector_t = typename vector_type<T, 8>::type;
if constexpr(sizeof(T) == 2)
{
typedef __attribute__((__vector_size__(8 * sizeof(__fp16)))) __fp16 llvm_fp16x8_t;
__attribute__((address_space(1))) llvm_fp16x8_t* glb_ptr =
reinterpret_cast<__attribute__((address_space(1))) llvm_fp16x8_t*>(
reinterpret_cast<uintptr_t>(in_ptr));
return bit_cast<vector_t>(__builtin_amdgcn_global_load_tr_b128_v8f16(glb_ptr));
}
else if constexpr(sizeof(T) == 1)
{
typedef __attribute__((__vector_size__(2 * sizeof(int)))) int llvm_intx2_t;
__attribute__((address_space(1))) llvm_intx2_t* glb_ptr =
reinterpret_cast<__attribute__((address_space(1))) llvm_intx2_t*>(
reinterpret_cast<uintptr_t>(in_ptr));
return bit_cast<vector_t>(__builtin_amdgcn_global_load_tr_b64_v2i32(glb_ptr));
}
else
{
static_assert(false, "not implemented");
}
}
#endif
} // namespace ck