104 lines
4.7 KiB
LLVM
104 lines
4.7 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --check-globals all --version 6
|
|
; RUN: opt -S -mtriple=amdgcn-- -amdgpu-lower-exec-sync < %s 2>&1 | FileCheck %s
|
|
; RUN: llc < %s -enable-new-pm -stop-after=amdgpu-lower-exec-sync -mtriple=amdgcn-amd-amdhsa | FileCheck %s
|
|
|
|
%class.ExpAmdWorkgroupWaveBarrier = type { target("amdgcn.named.barrier", 0) }
|
|
|
|
@bar2 = internal addrspace(3) global [2 x target("amdgcn.named.barrier", 0)] poison
|
|
@bar3 = internal addrspace(3) global target("amdgcn.named.barrier", 0) poison
|
|
@bar1 = internal addrspace(3) global [4 x %class.ExpAmdWorkgroupWaveBarrier] poison
|
|
|
|
;.
|
|
; CHECK: @bar2 = internal addrspace(3) global [2 x target("amdgcn.named.barrier", 0)] poison, !absolute_symbol [[META0:![0-9]+]]
|
|
; CHECK: @bar3 = internal addrspace(3) global target("amdgcn.named.barrier", 0) poison, !absolute_symbol [[META1:![0-9]+]]
|
|
; CHECK: @bar1 = internal addrspace(3) global [4 x %class.ExpAmdWorkgroupWaveBarrier] poison, !absolute_symbol [[META2:![0-9]+]]
|
|
; CHECK: @bar1.kernel1 = internal addrspace(3) global [4 x %class.ExpAmdWorkgroupWaveBarrier] poison, !absolute_symbol [[META2]]
|
|
;.
|
|
define void @func1() {
|
|
; CHECK-LABEL: define void @func1() {
|
|
; CHECK-NEXT: call void @llvm.amdgcn.s.barrier.signal.var(ptr addrspace(3) @bar3, i32 7)
|
|
; CHECK-NEXT: call void @llvm.amdgcn.s.barrier.join(ptr addrspace(3) @bar3)
|
|
; CHECK-NEXT: call void @llvm.amdgcn.s.barrier.wait(i16 1)
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
call void @llvm.amdgcn.s.barrier.signal.var(ptr addrspace(3) @bar3, i32 7)
|
|
call void @llvm.amdgcn.s.barrier.join(ptr addrspace(3) @bar3)
|
|
call void @llvm.amdgcn.s.barrier.wait(i16 1)
|
|
ret void
|
|
}
|
|
|
|
define void @func2() {
|
|
; CHECK-LABEL: define void @func2() {
|
|
; CHECK-NEXT: call void @llvm.amdgcn.s.barrier.signal.var(ptr addrspace(3) @bar2, i32 7)
|
|
; CHECK-NEXT: call void @llvm.amdgcn.s.barrier.join(ptr addrspace(3) @bar2)
|
|
; CHECK-NEXT: call void @llvm.amdgcn.s.barrier.wait(i16 1)
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
call void @llvm.amdgcn.s.barrier.signal.var(ptr addrspace(3) @bar2, i32 7)
|
|
call void @llvm.amdgcn.s.barrier.join(ptr addrspace(3) @bar2)
|
|
call void @llvm.amdgcn.s.barrier.wait(i16 1)
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @kernel1() #0 {
|
|
; CHECK-LABEL: define amdgpu_kernel void @kernel1(
|
|
; CHECK-SAME: ) #[[ATTR0:[0-9]+]] {
|
|
; CHECK-NEXT: call void @llvm.amdgcn.s.barrier.signal.var(ptr addrspace(3) @bar1.kernel1, i32 11)
|
|
; CHECK-NEXT: call void @llvm.amdgcn.s.barrier.join(ptr addrspace(3) @bar1.kernel1)
|
|
; CHECK-NEXT: call void @llvm.amdgcn.s.barrier.wait(i16 1)
|
|
; CHECK-NEXT: [[STATE:%.*]] = call i32 @llvm.amdgcn.s.get.named.barrier.state(ptr addrspace(3) @bar1.kernel1)
|
|
; CHECK-NEXT: call void @llvm.amdgcn.s.barrier()
|
|
; CHECK-NEXT: call void @func1()
|
|
; CHECK-NEXT: call void @func2()
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
call void @llvm.amdgcn.s.barrier.signal.var(ptr addrspace(3) @bar1, i32 11)
|
|
call void @llvm.amdgcn.s.barrier.join(ptr addrspace(3) @bar1)
|
|
call void @llvm.amdgcn.s.barrier.wait(i16 1)
|
|
%state = call i32 @llvm.amdgcn.s.get.named.barrier.state(ptr addrspace(3) @bar1)
|
|
call void @llvm.amdgcn.s.barrier()
|
|
call void @func1()
|
|
call void @func2()
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @kernel2() #0 {
|
|
; CHECK-LABEL: define amdgpu_kernel void @kernel2(
|
|
; CHECK-SAME: ) #[[ATTR0]] {
|
|
; CHECK-NEXT: call void @llvm.amdgcn.s.barrier.signal.var(ptr addrspace(3) @bar1, i32 9)
|
|
; CHECK-NEXT: call void @llvm.amdgcn.s.barrier.join(ptr addrspace(3) @bar1)
|
|
; CHECK-NEXT: call void @llvm.amdgcn.s.barrier.wait(i16 1)
|
|
; CHECK-NEXT: call void @func2()
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
call void @llvm.amdgcn.s.barrier.signal.var(ptr addrspace(3) @bar1, i32 9)
|
|
call void @llvm.amdgcn.s.barrier.join(ptr addrspace(3) @bar1)
|
|
call void @llvm.amdgcn.s.barrier.wait(i16 1)
|
|
|
|
call void @func2()
|
|
ret void
|
|
}
|
|
|
|
declare void @llvm.amdgcn.s.barrier() #1
|
|
declare void @llvm.amdgcn.s.barrier.wait(i16) #1
|
|
declare void @llvm.amdgcn.s.barrier.signal(i32) #1
|
|
declare void @llvm.amdgcn.s.barrier.signal.var(ptr addrspace(3), i32) #1
|
|
declare i1 @llvm.amdgcn.s.barrier.signal.isfirst(i32) #1
|
|
declare void @llvm.amdgcn.s.barrier.init(ptr addrspace(3), i32) #1
|
|
declare void @llvm.amdgcn.s.barrier.join(ptr addrspace(3)) #1
|
|
declare void @llvm.amdgcn.s.barrier.leave(i16) #1
|
|
declare void @llvm.amdgcn.s.wakeup.barrier(ptr addrspace(3)) #1
|
|
declare i32 @llvm.amdgcn.s.get.named.barrier.state(ptr addrspace(3)) #1
|
|
|
|
attributes #0 = { nounwind }
|
|
attributes #1 = { convergent nounwind }
|
|
attributes #2 = { nounwind readnone }
|
|
;.
|
|
; CHECK: attributes #[[ATTR0]] = { nounwind }
|
|
; CHECK: attributes #[[ATTR1:[0-9]+]] = { convergent nocallback nofree nounwind willreturn }
|
|
;.
|
|
; CHECK: [[META0]] = !{i32 8396816, i32 8396817}
|
|
; CHECK: [[META1]] = !{i32 8396912, i32 8396913}
|
|
; CHECK: [[META2]] = !{i32 8396848, i32 8396849}
|
|
;.
|