mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-04-20 14:59:17 +00:00
Add json dump support to output details from CK/CKTile Examples. (#2551)
* Adding RapidJson Library * Adding Json Dumps in all CK_Tile Examples Not verified yet * Adding json to cktile Batched Transpose * adding json dumps to layernorm2d_fwd * Adding json dump to flatmm_basic * Adding RapidJson Library * Adding Json Dumps in all CK_Tile Examples Not verified yet * Adding json to cktile Batched Transpose * adding json dumps to layernorm2d_fwd * Adding json dump to flatmm_basic * Adding json in 03_gemm * Add json dump to 16_batched_gemm * Add json dump to gemm_multi_d_fp16 * Add json dump to grouped_gemm * fix fmha_bwd/fwd * Fix clang-format errors exclude include/rapidjson in jenkins as its a third-party library * Saparating function and defination. * Update Documentation of 03_gemm * Refactoring as per code review * Disable fp8 instances on unsupported targets (#2592) * Restrict building of gemm_universal_preshuffle_f8 instances to specific targets in CMakeLists.txt * Add condition to skip gemm_xdl_universal_preshuffle_f8 instances for unsupported targets in CMakeLists.txt * Add conditions to skip unsupported targets for gemm_universal_preshuffle_f8 and gemm_xdl_universal_preshuffle_f8 instances in CMakeLists.txt * Refine conditions to exclude gemm_universal_preshuffle_f8 instances for unsupported targets in CMakeLists.txt --------- Co-authored-by: AviralGoelAMD <aviralgoel@amd.com> * fix clang format * remove duplicate lines of code from library/src/tensor_operation_instance/gpu/CMakeLists.txt * Fixing Readme and unifying jsondumps * adding moe_smoothquant * adding fused_moe * Fixing Readme for batched_gemm * Fixing Readme for grouped_gemm * adding flatmm * adding gemm_multi_d_fp16 * adding elementwise * adding File name when json is dumped * Fixing Reduce after merge * adding batched_transpose * Adding Warptile in Gemm * Fixing Clang Format --------- Co-authored-by: Aviral Goel <aviral.goel@amd.com> Co-authored-by: AviralGoelAMD <aviralgoel@amd.com> Co-authored-by: illsilin_amdeng <Illia.Silin@amd.com>
This commit is contained in:
rahjain-amd
@@ -1,7 +1,6 @@
|
||||
// SPDX-License-Identifier: MIT
|
||||
// Copyright (c) 2024-2025, Advanced Micro Devices, Inc. All rights reserved.
|
||||
#pragma once
|
||||
|
||||
template <typename Layout>
|
||||
static constexpr inline auto is_row_major(Layout layout_)
|
||||
{
|
||||
@@ -236,23 +235,6 @@ float invoke_gemm(ck_tile::DeviceMem& a_m_k_dev_buf,
|
||||
nullptr, true, 1, n_warmup, n_repeat, true, flush_cache, rotating_count});
|
||||
}
|
||||
|
||||
std::size_t flop = std::size_t(2) * M * N * K;
|
||||
std::size_t num_byte =
|
||||
sizeof(ADataType) * M * K + sizeof(BDataType) * N * K + sizeof(CDataType) * M * N;
|
||||
float tflops = static_cast<float>(flop) / 1.E9 / ave_time;
|
||||
float gb_per_sec = num_byte / 1.E6 / ave_time;
|
||||
|
||||
std::cout << "Run Gemm kernel with \n M=" << M << " N=" << N << " K=" << K
|
||||
<< " StrideA=" << stride_A << " StrideB=" << stride_B << " StrideC=" << stride_C
|
||||
<< " A_Layout=" << ALayout::name << " B_Layout =" << BLayout::name
|
||||
<< " C_Layout=" << CLayout::name << " A_Type=" << DataTypeTraits<ADataType>::name
|
||||
<< " B_Type=" << DataTypeTraits<BDataType>::name
|
||||
<< " C_Type=" << DataTypeTraits<CDataType>::name
|
||||
<< " StructuredSparsity=" << (GemmConfig::UseStructuredSparsity ? "on" : "off")
|
||||
<< " Persistent=" << (persistent ? "on" : "off") << " : \n"
|
||||
<< ave_time << " ms, " << tflops << " TFlops, " << gb_per_sec << " GB/s, "
|
||||
<< std::endl;
|
||||
|
||||
return ave_time;
|
||||
}
|
||||
|
||||
@@ -416,32 +398,49 @@ int run_gemm_example_with_layouts(ck_tile::ArgParser& arg_parser,
|
||||
c_m_n_dev_buf.SetZero();
|
||||
c_m_n_dev_result.SetZero();
|
||||
|
||||
invoke_gemm<GemmConfig,
|
||||
ADataType,
|
||||
BDataType,
|
||||
ck_tile::tuple<>,
|
||||
AccDataType,
|
||||
CDataType,
|
||||
ALayout,
|
||||
BLayout,
|
||||
ck_tile::tuple<>,
|
||||
CLayout>(a_m_k_dev_buf,
|
||||
b_k_n_dev_buf,
|
||||
c_m_n_dev_buf,
|
||||
M,
|
||||
N,
|
||||
K,
|
||||
stride_A,
|
||||
stride_B,
|
||||
stride_C,
|
||||
kbatch,
|
||||
n_warmup,
|
||||
n_repeat,
|
||||
persistent,
|
||||
flush_cache,
|
||||
rotating_count);
|
||||
float ave_time = invoke_gemm<GemmConfig,
|
||||
ADataType,
|
||||
BDataType,
|
||||
ck_tile::tuple<>,
|
||||
AccDataType,
|
||||
CDataType,
|
||||
ALayout,
|
||||
BLayout,
|
||||
ck_tile::tuple<>,
|
||||
CLayout>(a_m_k_dev_buf,
|
||||
b_k_n_dev_buf,
|
||||
c_m_n_dev_buf,
|
||||
M,
|
||||
N,
|
||||
K,
|
||||
stride_A,
|
||||
stride_B,
|
||||
stride_C,
|
||||
kbatch,
|
||||
n_warmup,
|
||||
n_repeat,
|
||||
persistent,
|
||||
flush_cache,
|
||||
rotating_count);
|
||||
|
||||
c_m_n_dev_buf.FromDevice(c_m_n_dev_result.data());
|
||||
|
||||
std::size_t flop = std::size_t(2) * M * N * K;
|
||||
std::size_t num_byte =
|
||||
sizeof(ADataType) * M * K + sizeof(BDataType) * N * K + sizeof(CDataType) * M * N;
|
||||
float tflops = static_cast<float>(flop) / 1.E9 / ave_time;
|
||||
float gb_per_sec = num_byte / 1.E6 / ave_time;
|
||||
|
||||
std::cout << "Run Gemm kernel with M=" << M << " N=" << N << " K=" << K
|
||||
<< " StrideA=" << stride_A << " StrideB=" << stride_B << " StrideC=" << stride_C
|
||||
<< " A_Layout=" << ALayout::name << " B_Layout =" << BLayout::name
|
||||
<< " C_Layout=" << CLayout::name << " A_Type=" << DataTypeTraits<ADataType>::name
|
||||
<< " B_Type=" << DataTypeTraits<BDataType>::name
|
||||
<< " C_Type=" << DataTypeTraits<CDataType>::name
|
||||
<< " StructuredSparsity=" << (GemmConfig::UseStructuredSparsity ? "on" : "off")
|
||||
<< " Persistent=" << (persistent ? "on" : "off") << " : " << ave_time << " ms, "
|
||||
<< tflops << " TFlops, " << gb_per_sec << " GB/s, " << std::endl;
|
||||
|
||||
bool pass = true;
|
||||
|
||||
// memory on host to store gpu reference result
|
||||
@@ -496,5 +495,28 @@ int run_gemm_example_with_layouts(ck_tile::ArgParser& arg_parser,
|
||||
pass = do_verify(c_m_n_dev_result, c_m_n_ref, rtol_atol, "GPU");
|
||||
}
|
||||
|
||||
if(arg_parser.get_int("json") == 1)
|
||||
{
|
||||
dump_gemm_json_results<ALayout,
|
||||
BLayout,
|
||||
CLayout,
|
||||
ADataType,
|
||||
BDataType,
|
||||
CDataType,
|
||||
GemmConfig,
|
||||
DataTypeTraits>(arg_parser.get_str("jsonfile"),
|
||||
M,
|
||||
N,
|
||||
K,
|
||||
stride_A,
|
||||
stride_B,
|
||||
stride_C,
|
||||
persistent,
|
||||
pass,
|
||||
ave_time,
|
||||
tflops,
|
||||
gb_per_sec);
|
||||
}
|
||||
|
||||
return pass;
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user