ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-14 18:17:44 +00:00
Code Issues Packages Projects Releases Wiki Activity

Clean up conv example, Instances, profiler and test (#324)

Browse Source 
* convnd_fwd fp16 example

* update example

* update example

* update instance

* updating refernce conv

* update reference conv

* update conv fwd profiler

* update conv 1d and 3d instance

* update include path

* clean

* update profiler for conv bwd data and weight

* update conv bwd weight

* clean

* update conv example

* update profiler for conv bwd weight

* update ckprofiler for conv bwd data

* fix reference conv bwd data bug; update conv bwd data test

* update examples

* fix initialization issue

* update test for conv fwd

* clean

* clean

* remove test case too sensitive to error threshhold

* fix test

* clean

* fix build

* adding conv multiple d

* adding conv multiple D

* add matrix padder

* add gemm padding to convnd

* adding group conv

* update gemm multi-d

* refactor

* refactor

* refactor

* clean

* clean

* refactor

* refactor

* reorg

* add ds

* add bias

* clean

* add G

* adding group

* adding group

* adding group

* update Tensor

* clean

* update example

* update DeviceGemmMultipleD_Xdl_CShuffle

* update conv bwd-data and bwd-weight

* upate contraction example

* update gemm and batch gemm with e permute

* fix example build

* instance for grouped conv1d

* update example

* adding group conv instance

* update gemm bilinear instance

* update gemm+add+add+fastgelu instance

* update profiler

* update profiler

* update test

* update test and client example

* clean

* add grouped conv into profiler

* update profiler

* clean

* add test grouped conv, update all conv test to gtest

* update test

[ROCm/composable_kernel commit: 500fa99512]
This commit is contained in:
Chao Liu
2022-07-29 18:19:25 -05:00
committed by GitHub
parent 1450273dc5
commit 236f946292
373 changed files with 17544 additions and 17013 deletions
Download Patch File Download Diff File Expand all files Collapse all files

45
profiler/src/profiler.cpp
View File

@@ -15,12 +15,11 @@ int profile_grouped_gemm(int, char*[]);
int profile_conv_fwd(int, char*[]);
int profile_conv_fwd_bias_relu(int, char*[]);
int profile_conv_fwd_bias_relu_add(int, char*[]);
int profile_convnd_fwd(int argc, char* argv[]);
int profile_convnd_bwd_data(int, char*[], int);
int profile_conv_bwd_data(int, char*[]);
int profile_conv_bwd_weight(int, char*[]);
int profile_grouped_conv_fwd(int, char*[]);
int profile_normalization(int, char*[]);
int profile_reduce(int, char*[]);
int profile_convnd_bwd_weight(int, char*[], int);
static void print_helper_message()
{
@@ -34,13 +33,12 @@ static void print_helper_message()
" batched_gemm: Batched GEMM\n"
" batched_gemm_reduce: Batched GEMM+Reduce\n"
" grouped_gemm: Grouped GEMM\n"
" conv_fwd: ForwardConvolution\n"
" conv_fwd: Convolution Forward\n"
" conv_fwd_bias_relu: ForwardConvolution+Bias+ReLU\n"
" conv_fwd_bias_relu_add: ForwardConvolution+Bias+ReLU+Add\n"
" conv1d_bwd_data: BackwardConvolution data 1 dim\n"
" conv2d_bwd_data: BackwardConvolution data 2 dim\n"
" conv3d_bwd_data: BackwardConvolution data 3 dim\n"
" conv2d_bwd_weight: Backward Weight Convolution 2d\n"
" conv_bwd_data: Convolution Backward Data\n"
" conv_bwd_weight: Convolution Backward Weight\n"
" grouped_conv_fwd: Grouped Convolution Forward\n"
" reduce: Reduce\n");
// clang-format on
}
@@ -53,8 +51,7 @@ int main(int argc, char* argv[])
return 0;
}
if(strcmp(argv[1], "gemm") == 0)
else if(strcmp(argv[1], "gemm") == 0)
{
return profile_gemm(argc, argv);
}
@@ -92,7 +89,7 @@ int main(int argc, char* argv[])
}
else if(strcmp(argv[1], "conv_fwd") == 0)
{
return profile_convnd_fwd(argc, argv);
return profile_conv_fwd(argc, argv);
}
else if(strcmp(argv[1], "conv_fwd_bias_relu") == 0)
{
@@ -102,33 +99,17 @@ int main(int argc, char* argv[])
{
return profile_conv_fwd_bias_relu_add(argc, argv);
}
else if(strcmp(argv[1], "conv1d_bwd_data") == 0)
else if(strcmp(argv[1], "conv_bwd_data") == 0)
{
return profile_convnd_bwd_data(argc, argv, 1);
return profile_conv_bwd_data(argc, argv);
}
else if(strcmp(argv[1], "conv2d_bwd_data") == 0)
{
return profile_convnd_bwd_data(argc, argv, 2);
}
else if(strcmp(argv[1], "conv3d_bwd_data") == 0)
{
return profile_convnd_bwd_data(argc, argv, 3);
}
else if(strcmp(argv[1], "conv2d_bwd_weight") == 0)
else if(strcmp(argv[1], "conv_bwd_weight") == 0)
{
return profile_conv_bwd_weight(argc, argv);
}
else if(strcmp(argv[1], "convnd1d_bwd_weight") == 0)
else if(strcmp(argv[1], "grouped_conv_fwd") == 0)
{
return profile_convnd_bwd_weight(argc, argv, 1);
}
else if(strcmp(argv[1], "convnd2d_bwd_weight") == 0)
{
return profile_convnd_bwd_weight(argc, argv, 2);
}
else if(strcmp(argv[1], "convnd3d_bwd_weight") == 0)
{
return profile_convnd_bwd_weight(argc, argv, 3);
return profile_grouped_conv_fwd(argc, argv);
}
else if(strcmp(argv[1], "reduce") == 0)
{