maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/CodeGen/AMDGPU/barrier-elimination.ll

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

32 lines
867 B
LLVM
Raw Normal View History

[AMDGPU] Eliminate barrier if workgroup size is not greater than wavefront size If a workgroup size is known to be not greater than wavefront size the s_barrier instruction is not needed since all threads are guarantied to come to the same point at the same time. Differential Revision: https://reviews.llvm.org/D31731 llvm-svn: 299659
2017-04-07 00:48:30 +08:00
; RUN: llc -march=amdgcn < %s | FileCheck %s
[AMDGPU][GlobalISel] Eliminate barrier if workgroup size is not greater than wavefront size If a workgroup size is known to be not greater than wavefront size the s_barrier instruction is not needed since all threads are guaranteed to come to the same point at the same time. This is the same optimization that was implemented for SelectionDAG in D31731. Differential Revision: https://reviews.llvm.org/D86609
2020-08-26 18:41:39 +08:00
; RUN: llc -march=amdgcn < %s -global-isel | FileCheck %s
[AMDGPU] Eliminate barrier if workgroup size is not greater than wavefront size If a workgroup size is known to be not greater than wavefront size the s_barrier instruction is not needed since all threads are guarantied to come to the same point at the same time. Differential Revision: https://reviews.llvm.org/D31731 llvm-svn: 299659
2017-04-07 00:48:30 +08:00
; CHECK-LABEL: {{^}}unknown_wgs:
; CHECK: s_barrier
define amdgpu_kernel void @unknown_wgs() {
tail call void @llvm.amdgcn.s.barrier() #0
ret void
}
; CHECK-LABEL: {{^}}flat_wgs_attr_32_128:
; CHECK: s_barrier
define amdgpu_kernel void @flat_wgs_attr_32_128() #1 {
tail call void @llvm.amdgcn.s.barrier() #0
ret void
}
; CHECK-LABEL: {{^}}flat_wgs_attr_32_64:
; CHECK: :
; CHECK-NEXT: ; wave barrier
; CHECK-NEXT: s_endpgm
define amdgpu_kernel void @flat_wgs_attr_32_64() #2 {
tail call void @llvm.amdgcn.s.barrier() #0
ret void
}
declare void @llvm.amdgcn.s.barrier() #0
attributes #0 = { convergent nounwind }
attributes #1 = { nounwind "amdgpu-flat-work-group-size"="32,128" }
attributes #2 = { nounwind "amdgpu-flat-work-group-size"="32,64" }