ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-13 01:36:06 +00:00
Code Issues Packages Projects Releases Wiki Activity

Standalone sweep once softmax kernel w/ ckProfiler (#295)

Browse Source 
* use 'sweep once' softmax kernel where applicable

* threadwise copy's dst buffer can specify invalid element value

* add int8 in/out float compute softmax support

give a bit of leeway for int absolute tolerance as there's a single data point of all test cases showing off-by-1 error

* format

* softmax inherits DeviceNormalization

* softmax profiler stub

* tighten up reference softmax interface

* example prints tensor dimension

* add fp32 to softmax profiler

* rename header

* hook with ckProfiler

* format

* resolve merge conflict

* resolve merge conflicts

* update normalization profiler help string

* resolve conflict

* typo

* remove residual

* softmax profiler: address feedback

* test for mixed precision input/output

* fully qualify ck::math::isnan

* add comment for device normalization interface

* revise wording

* constness for alpha/beta scaler pointer
This commit is contained in:
Anthony Chang
2022-07-01 01:08:50 +08:00
committed by GitHub
parent eccf8773a6
commit 93c99f3d87
24 changed files with 809 additions and 106 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
profiler/src/profiler.cpp
View File

@@ -20,6 +20,7 @@ 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_weight(int, char*[]);
int profile_normalization(int, char*[]);
int profile_reduce(int, char*[]);
static void print_helper_message()
@@ -130,6 +131,11 @@ int main(int argc, char* argv[])
{
return profile_gemm_add_add_fastgelu(argc, argv);
}
else if(strcmp(argv[1], "batchnorm") == 0 || strcmp(argv[1], "layernorm") == 0 ||
strcmp(argv[1], "softmax") == 0)
{
return profile_normalization(argc, argv);
}
else
{
print_helper_message();