ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-04-20 14:59:17 +00:00
Code Issues Packages Projects Releases Wiki Activity

TF32 POC in Conv3d on MI30x platform #2763 (second attempt) (#2852)

Browse Source 
* Revert "Revert "feature:tf32:add initial conv3d fwd kernel support (#2763)" (#2848)"

This reverts commit 03b59f8c76.

* fix compile error on gf12x

* only run tf32 example on gfx942

* only build tf32 instance on gfx942

* ckProfiler:only support tf32 in gfx942

* delete unuseful messages
This commit is contained in:
yinglu
2025-09-18 05:50:15 +08:00
committed by GitHub
parent 7c934b72ab
commit dd7af118d7
45 changed files with 1147 additions and 181 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
include/ck/library/utility/check_err.hpp
View File

@@ -180,13 +180,13 @@ check_err(const Range& out,
if(err > atol + rtol * std::abs(r) || !std::isfinite(o) || !std::isfinite(r))
{
max_err = err > max_err ? err : max_err;
err_count++;
if(err_count < 5)
{
std::cerr << msg << std::setw(12) << std::setprecision(7) << " out[" << i
<< "] != ref[" << i << "]: " << o << " != " << r << std::endl;
}
res = false;
err_count++;
}
}
if(!res)