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
@@ -16,20 +16,23 @@ This will result in an executable `build/bin/tile_example_flatmm_basic`
|
||||
## example
|
||||
```
|
||||
args:
|
||||
-b batch size (default:1)
|
||||
-m m dimension (default:1024)
|
||||
-n n dimension (default:2048)
|
||||
-k k dimension (default:64)
|
||||
-a_layout Tensor A data layout (default: R)
|
||||
-b_layout Tensor B data layout (default: R)
|
||||
-c_layout Tensor C data layout (default: R)
|
||||
-m m dimension (default:256)
|
||||
-n n dimension (default:256)
|
||||
-k k dimension (default:128)
|
||||
-a_layout A tensor data layout - Row by default (default:R)
|
||||
-b_layout B tensor data layout - Row by default (default:C)
|
||||
-c_layout C tensor data layout - Row by default (default:R)
|
||||
-stride_a Tensor A stride (default:0)
|
||||
-stride_b Tensor B stride (default:0)
|
||||
-stride_c Tensor C stride (default:0)
|
||||
-v 0. No validation, 1. Validation on CPU, 2. Validation on GPU (default:2)
|
||||
-e Absolute error tolerance (default:1e-5)
|
||||
-v 0. No validation, 1. Validation on CPU, 2. Validation on GPU (default:1)
|
||||
-prec data type. fp16/bf16/fp8/bf8 (default:fp16)
|
||||
-warmup number of iterations before benchmark the kernel (default:10)
|
||||
-warmup number of iterations before benchmark the kernel (default:50)
|
||||
-repeat number of iterations to benchmark the kernel (default:100)
|
||||
-timer gpu:gpu timer, cpu:cpu timer (default:gpu)
|
||||
-split_k splitK value (default:1)
|
||||
-init 0:random, 1:linear, 2:constant(1) (default:0)
|
||||
-warp_tile 0: 16x16, 1: 32x32, 2: 16x16x128 (950 only), 3: 32x32x64 (950 only) (default:0)
|
||||
-json 0: No Json, 1: Dump Results in Json format (default:0)
|
||||
-jsonfile json file name to dump results (default:flatmm_basic.json)
|
||||
```
|
||||
|
||||
@@ -183,9 +183,10 @@ auto create_args(int argc, char* argv[])
|
||||
.insert("timer", "gpu", "gpu:gpu timer, cpu:cpu timer")
|
||||
.insert("split_k", "1", "splitK value")
|
||||
.insert("init", "0", "0:random, 1:linear, 2:constant(1)")
|
||||
.insert("warp_tile",
|
||||
"0",
|
||||
"0: 16x16, 1: 32x32, 2: 16x16x128 (950 only), 3: 32x32x64 (950 only)");
|
||||
.insert(
|
||||
"warp_tile", "0", "0: 16x16, 1: 32x32, 2: 16x16x128 (950 only), 3: 32x32x64 (950 only)")
|
||||
.insert("json", "0", "0: No Json, 1: Dump Results in Json format")
|
||||
.insert("jsonfile", "flatmm_basic.json", "json file name to dump results");
|
||||
bool result = arg_parser.parse(argc, argv);
|
||||
return std::make_tuple(result, arg_parser);
|
||||
}
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
// Copyright (c) 2024-2025, Advanced Micro Devices, Inc. All rights reserved.
|
||||
#pragma once
|
||||
#include <type_traits>
|
||||
|
||||
#include "json_dump.hpp"
|
||||
template <typename T>
|
||||
constexpr const char* DataTypeToString()
|
||||
{
|
||||
@@ -140,17 +140,6 @@ float invoke_flatmm(ck_tile::DeviceMem& a_dev_buf,
|
||||
CDEElementWise>(
|
||||
args, ck_tile::stream_config{nullptr, true, 1, n_warmup, n_repeat, true, true, 50});
|
||||
|
||||
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 Flatmm kernel with DataType = " << DataTypeToString<ADataType>()
|
||||
<< " M =" << M << " N =" << N << " K =" << K << " StrideA =" << stride_A
|
||||
<< " StrideB =" << stride_B << " StrideC =" << stride_C << " : " << ave_time
|
||||
<< " ms, " << tflops << " TFlops, " << gb_per_sec << " GB/s, " << std::endl;
|
||||
|
||||
return ave_time;
|
||||
}
|
||||
|
||||
@@ -242,27 +231,38 @@ int run_flatmm_example_with_layouts(int argc,
|
||||
ck_tile::DeviceMem b_shuffle_dev_buf(b_shuffle_host.get_element_space_size_in_bytes());
|
||||
b_shuffle_dev_buf.ToDevice(b_shuffle_host.data());
|
||||
|
||||
invoke_flatmm<FlatmmConfig,
|
||||
ADataType,
|
||||
BDataType,
|
||||
ck_tile::tuple<>,
|
||||
AccDataType,
|
||||
CDataType,
|
||||
ALayout,
|
||||
BLayout,
|
||||
ck_tile::tuple<>,
|
||||
CLayout>(a_dev_buf,
|
||||
b_shuffle_dev_buf,
|
||||
c_dev_buf,
|
||||
M,
|
||||
N,
|
||||
K,
|
||||
stride_A,
|
||||
stride_B,
|
||||
stride_C,
|
||||
kbatch,
|
||||
n_warmup,
|
||||
n_repeat);
|
||||
float ave_time = invoke_flatmm<FlatmmConfig,
|
||||
ADataType,
|
||||
BDataType,
|
||||
ck_tile::tuple<>,
|
||||
AccDataType,
|
||||
CDataType,
|
||||
ALayout,
|
||||
BLayout,
|
||||
ck_tile::tuple<>,
|
||||
CLayout>(a_dev_buf,
|
||||
b_shuffle_dev_buf,
|
||||
c_dev_buf,
|
||||
M,
|
||||
N,
|
||||
K,
|
||||
stride_A,
|
||||
stride_B,
|
||||
stride_C,
|
||||
kbatch,
|
||||
n_warmup,
|
||||
n_repeat);
|
||||
|
||||
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 Flatmm kernel with DataType = " << DataTypeToString<ADataType>()
|
||||
<< " M =" << M << " N =" << N << " K =" << K << " StrideA =" << stride_A
|
||||
<< " StrideB =" << stride_B << " StrideC =" << stride_C << " : " << ave_time
|
||||
<< " ms, " << tflops << " TFlops, " << gb_per_sec << " GB/s, " << std::endl;
|
||||
|
||||
c_dev_buf.FromDevice(c_rslt_host.data());
|
||||
bool pass = true;
|
||||
@@ -350,5 +350,22 @@ int run_flatmm_example_with_layouts(int argc,
|
||||
std::cout << "The GPU veification result is: " << (pass ? "correct" : "fail") << std::endl;
|
||||
}
|
||||
|
||||
if(arg_parser.get_int("json") == 1)
|
||||
{
|
||||
dump_flatmm_json_results(arg_parser.get_str("jsonfile"),
|
||||
DataTypeToString<ADataType>(),
|
||||
M,
|
||||
N,
|
||||
K,
|
||||
stride_A,
|
||||
stride_B,
|
||||
stride_C,
|
||||
kbatch,
|
||||
pass,
|
||||
ave_time,
|
||||
tflops,
|
||||
gb_per_sec);
|
||||
}
|
||||
|
||||
return pass;
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user