Page MenuHomePhabricator
Differential D138993

[AMDGPU] Use s_cmp instead of s_cmpk
ClosedPublic
Actions

Authored by foad on Nov 30 2022, 2:42 AM.

Details

Reviewers
arsenm
Group Reviewers
Restricted Project
Commits
rG3d9e226081cf: [AMDGPU] Use s_cmp instead of s_cmpk
Summary

Don't bother pre-shrinking "s_cmp_lg_u32 reg, 0" to s_cmpk_lg_u32
because 0 is already an inline constant so the s_cmpk form is no
smaller.

This is just for consistency with the surrounding code and to simplify a
downstream patch.

Diff Detail

Event Timeline

foad created this revision.Nov 30 2022, 2:42 AM
Herald added a project: Restricted Project. · View Herald TranscriptNov 30 2022, 2:42 AM
Herald added subscribers: kosarev, kerbowa, hiraditya and 6 others. · View Herald Transcript
foad requested review of this revision.Nov 30 2022, 2:42 AM
Herald added a project: Restricted Project. · View Herald TranscriptNov 30 2022, 2:42 AM
Herald added subscribers: llvm-commits, wdng. · View Herald Transcript
Harbormaster completed remote builds in B200213: Diff 478866.Nov 30 2022, 3:46 AM
arsenm accepted this revision.Nov 30 2022, 9:09 AM
This revision is now accepted and ready to land.Nov 30 2022, 9:09 AM
Closed by commit rG3d9e226081cf: [AMDGPU] Use s_cmp instead of s_cmpk (authored by foad). · Explain WhyNov 30 2022, 10:04 AM
This revision was automatically updated to reflect the committed changes.
foad added a commit: rG3d9e226081cf: [AMDGPU] Use s_cmp instead of s_cmpk.

Revision Contents
Changeset List

PathSize
llvm/
lib/
Target/
AMDGPU/
2 lines
test/
CodeGen/
AMDGPU/
8 lines
4 lines

Diff 479004

View Options

llvm/lib/Target/AMDGPU/SIISelLowering.cpp

Loading...
View Options

llvm/test/CodeGen/AMDGPU/expand-scalar-carry-out-select-user.ll

Loading...
View Options

llvm/test/CodeGen/AMDGPU/udiv.ll

Loading...