Skip to content

[hipblaslt] Fix hazard in TF32 cvt sequence #1092

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.

Sign up for GitHub

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

Merged
b-shi merged 1 commit into from
Aug 7, 2025
Merged

[hipblaslt] Fix hazard in TF32 cvt sequence #1092

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion projects/hipblaslt/tensilelite/Tensile/KernelWriter.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1445,7 +1445,7 @@ def calculateRangeAndUpdateCounter(itemCounter, writeCounters, length):
iterCode.add(SNop(waitState=1, comment="VALU packing writes to be consumed by matrix instruction"))
curPackIdx += 1
break
if not kernel["SourceSwap"] and kernel["UseF32XEmulation"]:
if kernel["UseF32XEmulation"]:
# HACK add dummy waits btween swap and mfmas. TODO: improve pack scheduling to avoid this
numDummy = 1 if kernel["MatrixInstM"] == 16 and kernel["MatrixInstK"] == 16 else 2
for numd in range(numDummy):
Expand Down