[llvm] r260491 - AMDGPU: Fix not handling new workitem intrinsics in DivergenceAnalysis

[Matt Arsenault via llvm-commits]

Author: arsenm
Date: Wed Feb 10 23:32:51 2016
New Revision: 260491

URL: http://llvm.org/viewvc/llvm-project?rev=260491&view=rev
Log:
AMDGPU: Fix not handling new workitem intrinsics in DivergenceAnalysis

Added:
    llvm/trunk/test/Analysis/DivergenceAnalysis/AMDGPU/workitem-intrinsics.ll
Modified:
    llvm/trunk/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp

Modified: llvm/trunk/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp?rev=260491&r1=260490&r2=260491&view=diff
==============================================================================
--- llvm/trunk/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp (original)
+++ llvm/trunk/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp Wed Feb 10 23:32:51 2016
@@ -115,6 +115,9 @@ static bool isIntrinsicSourceOfDivergenc
     // IntrinsicsAMDGPU.td
     break;
 
+  case Intrinsic::amdgcn_workitem_id_x:
+  case Intrinsic::amdgcn_workitem_id_y:
+  case Intrinsic::amdgcn_workitem_id_z:
   case Intrinsic::amdgcn_interp_p1:
   case Intrinsic::amdgcn_interp_p2:
   case Intrinsic::amdgcn_mbcnt_hi:

Added: llvm/trunk/test/Analysis/DivergenceAnalysis/AMDGPU/workitem-intrinsics.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/Analysis/DivergenceAnalysis/AMDGPU/workitem-intrinsics.ll?rev=260491&view=auto
==============================================================================
--- llvm/trunk/test/Analysis/DivergenceAnalysis/AMDGPU/workitem-intrinsics.ll (added)
+++ llvm/trunk/test/Analysis/DivergenceAnalysis/AMDGPU/workitem-intrinsics.ll Wed Feb 10 23:32:51 2016
@@ -0,0 +1,45 @@
+; RUN: opt  -mtriple amdgcn-unknown-amdhsa -analyze -divergence %s | FileCheck %s
+
+declare i32 @llvm.amdgcn.workitem.id.x() #0
+declare i32 @llvm.amdgcn.workitem.id.y() #0
+declare i32 @llvm.amdgcn.workitem.id.z() #0
+declare i32 @llvm.amdgcn.mbcnt.lo(i32, i32) #0
+declare i32 @llvm.amdgcn.mbcnt.hi(i32, i32) #0
+
+; CHECK: DIVERGENT:  %id.x = call i32 @llvm.amdgcn.workitem.id.x()
+define void @workitem_id_x() #1 {
+  %id.x = call i32 @llvm.amdgcn.workitem.id.x()
+  store volatile i32 %id.x, i32 addrspace(1)* undef
+  ret void
+}
+
+; CHECK: DIVERGENT:  %id.y = call i32 @llvm.amdgcn.workitem.id.y()
+define void @workitem_id_y() #1 {
+  %id.y = call i32 @llvm.amdgcn.workitem.id.y()
+  store volatile i32 %id.y, i32 addrspace(1)* undef
+  ret void
+}
+
+; CHECK: DIVERGENT:  %id.z = call i32 @llvm.amdgcn.workitem.id.z()
+define void @workitem_id_z() #1 {
+  %id.z = call i32 @llvm.amdgcn.workitem.id.z()
+  store volatile i32 %id.z, i32 addrspace(1)* undef
+  ret void
+}
+
+; CHECK: DIVERGENT:  %mbcnt.lo = call i32 @llvm.amdgcn.mbcnt.lo(i32 0, i32 0)
+define void @mbcnt_lo() #1 {
+  %mbcnt.lo = call i32 @llvm.amdgcn.mbcnt.lo(i32 0, i32 0)
+  store volatile i32 %mbcnt.lo, i32 addrspace(1)* undef
+  ret void
+}
+
+; CHECK: DIVERGENT:  %mbcnt.hi = call i32 @llvm.amdgcn.mbcnt.hi(i32 0, i32 0)
+define void @mbcnt_hi() #1 {
+  %mbcnt.hi = call i32 @llvm.amdgcn.mbcnt.hi(i32 0, i32 0)
+  store volatile i32 %mbcnt.hi, i32 addrspace(1)* undef
+  ret void
+}
+
+attributes #0 = { nounwind readnone }
+attributes #1 = { nounwind }