mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-11 17:00:18 +00:00
f83e9701e9
* Optimize GEMM on MI200/300: 1. Add new blockwise gemm pipeline 2. Add irregular splitk intances * clang format + typo fix * Fix a bug * initial commit * Add more instances to irregular splitk * blkgemm pipeline v1~4 prototype * Sanity Checked. Known issue: 1. Poor performance of splitk 2. Register spill on blkgemmpipeline v3 * Sanity and Performance fix: 1. fix a bug related to sanity in grouped b2c mapping 2. fix a bug related to sanity and performance in splitk offset * Sanity and API update: 1. Remove prefetch stage 2. Fix valid check bug 3, Add first gemm_universal instance into ckProfiler * Add NN instances for gemm universal * 1. Add NT instances for gemm_universal 2. Fix a bug about Kpadding in gemm_universal * Fix a bug regarding padding Odd K number * remove kernel print * Fix KPadding bug... * Update safety check * another try to fix kpadding.. * Sanity checked * new instances.. * clang format+typo fix * remove clang format script's change * Add non-hotloop compile option * 1. Add fp16xfp8 example 2. pull packed convert f8 from pr1150 * Some miscs.. opt and fix * Add pipeline description docs * Split universal gemm instance library to cut profiler compiling time * uncomment cmakefile * Fix a bug caused by blockwise_gemm_pipe_v2 * reduce default splitk to 1 * Add 224x256x64 tile size * update, including: 1. Experiment pipeline 5~7 2. Optimization for pipeline 4 3. Organized instance library * temp save * temp save * Permuted lds layout, sanity and function checked * clang format * Move OOB check from RunRead to RunWrite, for better software pipeline. TODO: agpr spill when NN layout * clangformat * A/B splitpipe scheduler for v3 * Fix two bugs * bug fix * fix a bug in oob check * Example for mixed fp16_fp8 gemm * Clean experimental code blocks * Add mixed precision gemm into profiler * tempsave * optimize m/n major lds layout * Add RRR GEMM mixed precision instances * Optimize f8 matrix transpose * Add test_gemm_universal * A/B spilt schedule for blkpip v5 * Take ds_read2 into iglp scheduling scheme * format * fixed cmake * Add llvm-option into CI cmake flag --------- Co-authored-by: Jing Zhang <jizhan@amd.com>
45 lines
759 B
C++
45 lines
759 B
C++
// SPDX-License-Identifier: MIT
|
|
// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
|
|
|
|
#pragma once
|
|
|
|
#include "ck/ck.hpp"
|
|
|
|
namespace ck {
|
|
|
|
__device__ void block_sync_lds()
|
|
{
|
|
#if CK_EXPERIMENTAL_BLOCK_SYNC_LDS_WITHOUT_SYNC_VMEM
|
|
// asm volatile("\
|
|
// s_waitcnt lgkmcnt(0) \n \
|
|
// s_barrier \
|
|
// " ::);
|
|
__builtin_amdgcn_s_waitcnt(0xc07f);
|
|
__builtin_amdgcn_s_barrier();
|
|
#else
|
|
__syncthreads();
|
|
#endif
|
|
}
|
|
|
|
__device__ void block_sync_lds_direct_load()
|
|
{
|
|
asm volatile("\
|
|
s_waitcnt vmcnt(0) \n \
|
|
s_waitcnt lgkmcnt(0) \n \
|
|
s_barrier \
|
|
" ::);
|
|
}
|
|
|
|
__device__ void s_nop()
|
|
{
|
|
#if 1
|
|
asm volatile("\
|
|
s_nop 0 \n \
|
|
" ::);
|
|
#else
|
|
__builtin_amdgcn_sched_barrier(0);
|
|
#endif
|
|
}
|
|
|
|
} // namespace ck
|