38eebe843b
We don't want to execute s_sethalt when all lanes want to skip it. Co-authored-by: Junda Liu <Junda.Liu@amd.com>
50 lines
1.5 KiB
LLVM
50 lines
1.5 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -mtriple=amdgcn -mcpu=gfx900 < %s | FileCheck -check-prefix=GCN %s
|
|
; RUN: llc -global-isel -new-reg-bank-select -mtriple=amdgcn -mcpu=gfx900 < %s | FileCheck -check-prefix=GCN %s
|
|
|
|
define amdgpu_kernel void @test_s_sethalt() {
|
|
; GCN-LABEL: test_s_sethalt:
|
|
; GCN: ; %bb.0:
|
|
; GCN-NEXT: s_sethalt 0
|
|
; GCN-NEXT: s_sethalt 1
|
|
; GCN-NEXT: s_sethalt 2
|
|
; GCN-NEXT: s_sethalt 3
|
|
; GCN-NEXT: s_sethalt 4
|
|
; GCN-NEXT: s_sethalt 5
|
|
; GCN-NEXT: s_sethalt 6
|
|
; GCN-NEXT: s_sethalt 7
|
|
; GCN-NEXT: s_endpgm
|
|
call void @llvm.amdgcn.s.sethalt(i32 0)
|
|
call void @llvm.amdgcn.s.sethalt(i32 1)
|
|
call void @llvm.amdgcn.s.sethalt(i32 2)
|
|
call void @llvm.amdgcn.s.sethalt(i32 3)
|
|
call void @llvm.amdgcn.s.sethalt(i32 4)
|
|
call void @llvm.amdgcn.s.sethalt(i32 5)
|
|
call void @llvm.amdgcn.s.sethalt(i32 6)
|
|
call void @llvm.amdgcn.s.sethalt(i32 7)
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_gs void @if_sethalt(i32 %flag) #0 {
|
|
; GCN-LABEL: if_sethalt:
|
|
; GCN: ; %bb.0:
|
|
; GCN-NEXT: v_cmp_eq_u32_e32 vcc, 0, v0
|
|
; GCN-NEXT: s_and_saveexec_b64 s[0:1], vcc
|
|
; GCN-NEXT: s_cbranch_execz .LBB1_2
|
|
; GCN-NEXT: ; %bb.1: ; %sethalt
|
|
; GCN-NEXT: s_sethalt 1
|
|
; GCN-NEXT: .LBB1_2: ; %end
|
|
; GCN-NEXT: s_endpgm
|
|
%cond = icmp eq i32 %flag, 0
|
|
br i1 %cond, label %sethalt, label %end
|
|
|
|
sethalt:
|
|
call void @llvm.amdgcn.s.sethalt(i32 1)
|
|
br label %end
|
|
|
|
end:
|
|
ret void
|
|
}
|
|
|
|
declare void @llvm.amdgcn.s.sethalt(i32)
|