projects
/
oota-llvm.git
/ blobdiff
commit
grep
author
committer
pickaxe
?
search:
re
summary
|
shortlog
|
log
|
commit
|
commitdiff
|
tree
raw
| inline |
side by side
AMDGPU: Switch barrier intrinsics to using convergent
[oota-llvm.git]
/
test
/
CodeGen
/
AMDGPU
/
ds-sub-offset.ll
diff --git
a/test/CodeGen/AMDGPU/ds-sub-offset.ll
b/test/CodeGen/AMDGPU/ds-sub-offset.ll
index ffa45f6398fd80c1abab3de31f75c97069e8de67..7d6eddb01993c6e37785793b2eaf91bc451140d9 100644
(file)
--- a/
test/CodeGen/AMDGPU/ds-sub-offset.ll
+++ b/
test/CodeGen/AMDGPU/ds-sub-offset.ll
@@
-122,4
+122,4
@@
define void @add_x_shl_neg_to_sub_misaligned_i64_max_offset_p1() #1 {
attributes #0 = { nounwind readnone }
attributes #1 = { nounwind }
-attributes #2 = { nounwind
noduplicate
convergent }
+attributes #2 = { nounwind convergent }