ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-04-19 22:39:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fixing 0ms and inf GB/s issue in img2col (#2565)

Browse Source 
issue :
====
``` sh
$ bin/tile_example_img2col
Perf: 0 ms, inf GB/s
```

solution :
======
Problem occured because config.time_kernel is false by default.
if false, then no need to calculate perf, just print proper message

`image_to_coloumn: pass, No Perf generated due to config.time_kernel=0`
This commit is contained in:
rahjain-amd
2025-07-25 21:15:50 +05:30
committed by GitHub
parent c8eb2f995c
commit 78082855d8
1 changed files with 10 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
example/ck_tile/04_img2col/image_to_column.cpp
View File

@@ -149,9 +149,16 @@ int main(int argc, char* argv[])
float ave_time =
image_to_column(traits, args, ck_tile::stream_config{nullptr, config.time_kernel});
std::size_t num_btype = G * NHoWo * CYX * (sizeof(OutDataType) + sizeof(InDataType));
float gb_per_sec = num_btype / 1.E6 / ave_time;
std::cout << "Perf: " << ave_time << " ms, " << gb_per_sec << " GB/s" << std::endl;
if (config.time_kernel)
{
std::size_t num_btype = G * NHoWo * CYX * (sizeof(OutDataType) + sizeof(InDataType));
float gb_per_sec = num_btype / 1.E6 / ave_time;
std::cout << "Perf: " << ave_time << " ms, " << gb_per_sec << " GB/s" << std::endl;
}
else
{
std::cout << "image_to_column: pass, No Perf generated due to config.time_kernel=0" << std::endl;
}
bool pass = true;