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
88 lines
1.7 KiB
C++
88 lines
1.7 KiB
C++
// Copyright (c) Advanced Micro Devices, Inc., or its affiliates.
|
|
// SPDX-License-Identifier: MIT
|
|
|
|
#pragma once
|
|
|
|
#include "ck/ck.hpp"
|
|
|
|
namespace ck {
|
|
|
|
#if CK_EXPERIMENTAL_BLOCK_SYNC_LDS_WITHOUT_SYNC_VMEM
|
|
#ifdef __gfx12__
|
|
__device__ void llvm_amdgcn_s_wait_dscnt(short cnt) __asm("llvm.amdgcn.s.wait.dscnt");
|
|
#endif
|
|
#endif
|
|
|
|
__device__ void block_sync_lds()
|
|
{
|
|
#if CK_EXPERIMENTAL_BLOCK_SYNC_LDS_WITHOUT_SYNC_VMEM
|
|
#if defined(__gfx12__)
|
|
llvm_amdgcn_s_wait_dscnt(0);
|
|
__builtin_amdgcn_s_barrier_signal(-1);
|
|
__builtin_amdgcn_s_barrier_wait(-1);
|
|
#elif defined(__gfx11__)
|
|
// asm volatile("\
|
|
// s_waitcnt lgkmcnt(0) \n \
|
|
// s_barrier \
|
|
// " ::);
|
|
__builtin_amdgcn_s_waitcnt(0xfc07);
|
|
__builtin_amdgcn_s_barrier();
|
|
#else
|
|
// asm volatile("\
|
|
// s_waitcnt lgkmcnt(0) \n \
|
|
// s_barrier \
|
|
// " ::);
|
|
__builtin_amdgcn_s_waitcnt(0xc07f);
|
|
__builtin_amdgcn_s_barrier();
|
|
#endif
|
|
#else
|
|
__syncthreads();
|
|
#endif
|
|
}
|
|
|
|
__device__ void block_sync_lds_direct_load()
|
|
{
|
|
#if defined(__gfx125__)
|
|
__builtin_amdgcn_s_wait_asynccnt(0);
|
|
__builtin_amdgcn_s_barrier_signal(-1);
|
|
__builtin_amdgcn_s_barrier_wait(-1);
|
|
#elif defined(__gfx12__)
|
|
asm volatile("\
|
|
s_wait_loadcnt 0x0 \n \
|
|
s_wait_dscnt 0x0 \n \
|
|
s_barrier_signal -1 \n \
|
|
s_barrier_wait -1 \
|
|
" ::);
|
|
#else
|
|
asm volatile("\
|
|
s_waitcnt vmcnt(0) \n \
|
|
s_waitcnt lgkmcnt(0) \n \
|
|
s_barrier \
|
|
" ::);
|
|
#endif
|
|
}
|
|
|
|
__device__ void block_sync_lds_async_load()
|
|
{
|
|
#if defined(__gfx125__)
|
|
__builtin_amdgcn_s_wait_asynccnt(0);
|
|
__syncthreads();
|
|
#else
|
|
// fall back
|
|
block_sync_lds();
|
|
#endif
|
|
}
|
|
|
|
__device__ void s_nop()
|
|
{
|
|
#if 1
|
|
asm volatile("\
|
|
s_nop 0 \n \
|
|
" ::);
|
|
#else
|
|
__builtin_amdgcn_sched_barrier(0);
|
|
#endif
|
|
}
|
|
|
|
} // namespace ck
|