-
Notifications
You must be signed in to change notification settings - Fork 15.2k
[AMDGPU] Make sort ordering in AMDGPURewriteAGPRCopyMFMAImpl::eliminateSpillsOfReassignedVGPRs()
strict weak.
#162493
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
Changes from 1 commit
56f9ded
a364ce6
e7e2598
d6fc4ef
b17feb7
File filter
Filter by extension
Conversations
Jump to
Diff view
Diff view
There are no files selected for viewing
Original file line number | Diff line number | Diff line change |
---|---|---|
|
@@ -490,7 +490,9 @@ void AMDGPURewriteAGPRCopyMFMAImpl::eliminateSpillsOfReassignedVGPRs() const { | |
return true; | ||
|
||
// Tie breaker by number to avoid need for stable sort | ||
return A->reg().stackSlotIndex() < B->reg().stackSlotIndex(); | ||
// The ordering have to be strictly weak. | ||
return (A->reg().stackSlotIndex() < B->reg().stackSlotIndex()) && | ||
((A->weight() <= B->weight()) && (A->getSize() <= B->getSize())); | ||
|
||
}); | ||
|
||
// FIXME: The APIs for dealing with the LiveInterval of a frame index are | ||
|
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.