| ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --check-globals all --version 6 | |
| ; RUN: opt -S -mtriple=amdgpu12.00-- -passes=amdgpu-lower-exec-sync,amdgpu-lower-module-lds < %s 2>&1 | FileCheck %s | |
| ; RUN: llc < %s -enable-new-pm -stop-after=amdgpu-lower-module-lds -mtriple=amdgpu12.00-amd-amdhsa | FileCheck %s | |
| ; Test to ensure that LDS variables like named barriers are lowered correctly, | |
| ; where amdgpu-lower-module-lds pass runs in pipeline after amdgpu-lower-exec-sync pass. | |
| %class.ExpAmdWorkgroupWaveBarrier = type { target("amdgcn.named.barrier", 0) } | |
| @bar2 = internal addrspace(15) global [2 x target("amdgcn.named.barrier", 0)] poison | |
| @bar3 = internal addrspace(15) global target("amdgcn.named.barrier", 0) poison | |
| @bar1 = internal addrspace(15) global [4 x %class.ExpAmdWorkgroupWaveBarrier] poison | |
| @lds1 = internal addrspace(3) global [1 x i8] poison, align 4 | |
| ;. | |
| ; CHECK: @bar2 = internal addrspace(15) global [2 x target("amdgcn.named.barrier", 0)] poison, !absolute_symbol [[META0:![0-9]+]] | |
| ; CHECK: @bar3 = internal addrspace(15) global target("amdgcn.named.barrier", 0) poison, !absolute_symbol [[META1:![0-9]+]] | |
| ; CHECK: @bar1 = internal addrspace(15) global [4 x %class.ExpAmdWorkgroupWaveBarrier] poison, !absolute_symbol [[META2:![0-9]+]] | |
| ; CHECK: @llvm.amdgcn.module.lds = internal addrspace(3) global %llvm.amdgcn.module.lds.t poison, align 4, !absolute_symbol [[META3:![0-9]+]] | |
| ; CHECK: @llvm.compiler.used = appending addrspace(1) global [1 x ptr] [ptr addrspacecast (ptr addrspace(3) @llvm.amdgcn.module.lds to ptr)], section "llvm.metadata" | |
| ;. | |
| define void @func1() #0 { | |
| ; CHECK-LABEL: define void @func1( | |
| ; CHECK-SAME: ) #[[ATTR0:[0-9]+]] { | |
| ; CHECK-NEXT: call void @llvm.amdgcn.s.barrier.join(ptr addrspace(15) @bar3) | |
| ; CHECK-NEXT: call void @llvm.amdgcn.s.barrier.signal.var(ptr addrspace(15) @bar3, i32 7) | |
| ; CHECK-NEXT: call void @llvm.amdgcn.s.barrier.wait(i16 1) | |
| ; CHECK-NEXT: ret void | |
| ; | |
| call void @llvm.amdgcn.s.barrier.join(ptr addrspace(15) @bar3) | |
| call void @llvm.amdgcn.s.barrier.signal.var(ptr addrspace(15) @bar3, i32 7) | |
| call void @llvm.amdgcn.s.barrier.wait(i16 1) | |
| ret void | |
| } | |
| define void @func2() #0 { | |
| ; CHECK-LABEL: define void @func2( | |
| ; CHECK-SAME: ) #[[ATTR0]] { | |
| ; CHECK-NEXT: call void @llvm.amdgcn.s.barrier.join(ptr addrspace(15) @bar2) | |
| ; CHECK-NEXT: call void @llvm.amdgcn.s.barrier.signal.var(ptr addrspace(15) @bar2, i32 7) | |
| ; CHECK-NEXT: call void @llvm.amdgcn.s.barrier.wait(i16 1) | |
| ; CHECK-NEXT: store i8 7, ptr addrspace(3) @llvm.amdgcn.module.lds, align 4 | |
| ; CHECK-NEXT: ret void | |
| ; | |
| call void @llvm.amdgcn.s.barrier.join(ptr addrspace(15) @bar2) | |
| call void @llvm.amdgcn.s.barrier.signal.var(ptr addrspace(15) @bar2, i32 7) | |
| call void @llvm.amdgcn.s.barrier.wait(i16 1) | |
| store i8 7, ptr addrspace(3) @lds1, align 4 | |
| ret void | |
| } | |
| define amdgpu_kernel void @kernel1() #0 { | |
| ; CHECK-LABEL: define amdgpu_kernel void @kernel1( | |
| ; CHECK-SAME: ) #[[ATTR1:[0-9]+]] { | |
| ; CHECK-NEXT: call void @llvm.donothing() [ "ExplicitUse"(ptr addrspace(3) @llvm.amdgcn.module.lds) ] | |
| ; CHECK-NEXT: call void @llvm.amdgcn.s.barrier.join(ptr addrspace(15) @bar1) | |
| ; CHECK-NEXT: call void @llvm.amdgcn.s.barrier.signal.var(ptr addrspace(15) @bar1, i32 11) | |
| ; 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(15) @bar1) | |
| ; CHECK-NEXT: call void @llvm.amdgcn.s.barrier() | |
| ; CHECK-NEXT: call void @func1() | |
| ; CHECK-NEXT: call void @func2() | |
| ; CHECK-NEXT: store i8 9, ptr addrspace(3) @llvm.amdgcn.module.lds, align 4 | |
| ; CHECK-NEXT: ret void | |
| ; | |
| call void @llvm.amdgcn.s.barrier.join(ptr addrspace(15) @bar1) | |
| call void @llvm.amdgcn.s.barrier.signal.var(ptr addrspace(15) @bar1, i32 11) | |
| call void @llvm.amdgcn.s.barrier.wait(i16 1) | |
| %state = call i32 @llvm.amdgcn.s.get.named.barrier.state(ptr addrspace(15) @bar1) | |
| call void @llvm.amdgcn.s.barrier() | |
| call void @func1() | |
| call void @func2() | |
| store i8 9, ptr addrspace(3) @lds1, align 4 | |
| ret void | |
| } | |
| define amdgpu_kernel void @kernel2() #0 { | |
| ; CHECK-LABEL: define amdgpu_kernel void @kernel2( | |
| ; CHECK-SAME: ) #[[ATTR1]] { | |
| ; CHECK-NEXT: call void @llvm.donothing() [ "ExplicitUse"(ptr addrspace(3) @llvm.amdgcn.module.lds) ] | |
| ; CHECK-NEXT: call void @llvm.amdgcn.s.barrier.join(ptr addrspace(15) @bar1) | |
| ; CHECK-NEXT: call void @llvm.amdgcn.s.barrier.signal.var(ptr addrspace(15) @bar1, i32 9) | |
| ; CHECK-NEXT: call void @llvm.amdgcn.s.barrier.wait(i16 1) | |
| ; CHECK-NEXT: call void @func2() | |
| ; CHECK-NEXT: store i8 10, ptr addrspace(3) @llvm.amdgcn.module.lds, align 4 | |
| ; CHECK-NEXT: ret void | |
| ; | |
| call void @llvm.amdgcn.s.barrier.join(ptr addrspace(15) @bar1) | |
| call void @llvm.amdgcn.s.barrier.signal.var(ptr addrspace(15) @bar1, i32 9) | |
| call void @llvm.amdgcn.s.barrier.wait(i16 1) | |
| call void @func2() | |
| store i8 10, ptr addrspace(3) @lds1, align 4 | |
| 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(15), i32) #1 | |
| declare i1 @llvm.amdgcn.s.barrier.signal.isfirst(i32) #1 | |
| declare void @llvm.amdgcn.s.barrier.init(ptr addrspace(15), i32) #1 | |
| declare void @llvm.amdgcn.s.barrier.join(ptr addrspace(15)) #1 | |
| declare void @llvm.amdgcn.s.barrier.leave(i16) #1 | |
| declare void @llvm.amdgcn.s.wakeup.barrier(ptr addrspace(15)) #1 | |
| declare i32 @llvm.amdgcn.s.get.named.barrier.state(ptr addrspace(15)) #1 | |
| attributes #0 = { nounwind } | |
| attributes #1 = { convergent nounwind } | |
| attributes #2 = { nounwind readnone } | |
| ;. | |
| ; CHECK: attributes #[[ATTR0]] = { nounwind } | |
| ; CHECK: attributes #[[ATTR1]] = { nounwind "amdgpu-lds-size"="1" } | |
| ; CHECK: attributes #[[ATTR2:[0-9]+]] = { convergent nocallback nofree nounwind willreturn } | |
| ; CHECK: attributes #[[ATTR3:[0-9]+]] = { nocallback nofree nosync nounwind willreturn memory(none) } | |
| ;. | |
| ; CHECK: [[META0]] = !{i32 5, i32 6} | |
| ; CHECK: [[META1]] = !{i32 7, i32 8} | |
| ; CHECK: [[META2]] = !{i32 1, i32 2} | |
| ; CHECK: [[META3]] = !{i32 0, i32 1} | |
| ;. |