-
Notifications
You must be signed in to change notification settings - Fork 221
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
naive_conv_nonpacked_fwd_nchw_half_double_half in KDB cache breaks after #2863 #3023
Comments
It should be changes in this file which are causing this problem: and similar issues might be in other directions too |
By removing these lines: MIOpen/src/solver/conv_direct_naive_conv.cpp Lines 441 to 442 in 9064d09
It starts to work properly again. So the KDB cache does not accept these parameters. However, why the refreshed KDB still does not accept them? @cderb |
@atamazov FYI, this issue and the other GPU Target embedded in compiler issues are related. We will branch soon and need to regenerate quite a few KDBs with all fixes merged in develop branch first. |
Of course! If a PR changes the number of input arguments, or their types, then KDB must be regenerated. And changing the number of input arguments is a substantial change (see https://github.com/ROCm/MIOpen/pull/2863/files#r1641574996). [Note] Unfortunately, I see that some deeper redesign is required in order to make this bilinear stuff (alpha/beta) working correctly, see #2863 (comment). |
[Observations}:
Reproducer:
and
However, if we delete the system KDB, this workload can run through
[Analysis]
Something in #2863 has caused the incompatibility
MIOpen/src/kernels/gpu_reference_kernel/fp8_naive_conv.cpp
Lines 237 to 239 in 9064d09
FYI: @JehandadKhan @atamazov
The text was updated successfully, but these errors were encountered: