AMDGPU: Make fneg combine handle fcanonicalize

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@338243 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Target/AMDGPU/AMDGPUISelLowering.cpp b/lib/Target/AMDGPU/AMDGPUISelLowering.cpp
index 002ee7fcc7279c05789fd95386d0ca7e487d6c13..21e44e9589d3c4f7a4e98cf6f00d51d7e4f1dd9e 100644 (file)
--- a/lib/Target/AMDGPU/AMDGPUISelLowering.cpp
+++ b/lib/Target/AMDGPU/AMDGPUISelLowering.cpp
@@ -554,6 +554,7 @@ static bool fnegFoldsIntoOp(unsigned Opc) {
   case ISD::FTRUNC:
   case ISD::FRINT:
   case ISD::FNEARBYINT:
+  case ISD::FCANONICALIZE:
   case AMDGPUISD::RCP:
   case AMDGPUISD::RCP_LEGACY:
   case AMDGPUISD::RCP_IFLAG:
@@ -3595,6 +3596,7 @@ SDValue AMDGPUTargetLowering::performFNegCombine(SDNode *N,
   case ISD::FRINT:
   case ISD::FNEARBYINT: // XXX - Should fround be handled?
   case ISD::FSIN:
+  case ISD::FCANONICALIZE:
   case AMDGPUISD::RCP:
   case AMDGPUISD::RCP_LEGACY:
   case AMDGPUISD::RCP_IFLAG:

diff --git a/test/CodeGen/AMDGPU/fneg-combines.ll b/test/CodeGen/AMDGPU/fneg-combines.ll
index fd3d4f053e957069e2f772e9e966c1933af6cfd0..520309e0a9fd0acb8bd820c6e75ffafdbeefc21a 100644 (file)
--- a/test/CodeGen/AMDGPU/fneg-combines.ll
+++ b/test/CodeGen/AMDGPU/fneg-combines.ll
@@ -1724,6 +1724,26 @@ define amdgpu_kernel void @v_fneg_nearbyint_f32(float addrspace(1)* %out, float
   ret void
 }
 
+; --------------------------------------------------------------------------------
+; fcanonicalize tests
+; --------------------------------------------------------------------------------
+
+; GCN-LABEL: {{^}}v_fneg_canonicalize_f32:
+; GCN: {{buffer|flat}}_load_dword [[A:v[0-9]+]]
+; GCN: v_mul_f32_e64 [[RESULT:v[0-9]+]], 1.0, -[[A]]
+; GCN: buffer_store_dword [[RESULT]]
+define amdgpu_kernel void @v_fneg_canonicalize_f32(float addrspace(1)* %out, float addrspace(1)* %a.ptr) #0 {
+  %tid = call i32 @llvm.amdgcn.workitem.id.x()
+  %tid.ext = sext i32 %tid to i64
+  %a.gep = getelementptr inbounds float, float addrspace(1)* %a.ptr, i64 %tid.ext
+  %out.gep = getelementptr inbounds float, float addrspace(1)* %out, i64 %tid.ext
+  %a = load volatile float, float addrspace(1)* %a.gep
+  %trunc = call float @llvm.canonicalize.f32(float %a)
+  %fneg = fsub float -0.0, %trunc
+  store float %fneg, float addrspace(1)* %out.gep
+  ret void
+}
+
 ; --------------------------------------------------------------------------------
 ; vintrp tests
 ; --------------------------------------------------------------------------------
@@ -2117,6 +2137,7 @@ declare float @llvm.trunc.f32(float) #1
 declare float @llvm.round.f32(float) #1
 declare float @llvm.rint.f32(float) #1
 declare float @llvm.nearbyint.f32(float) #1
+declare float @llvm.canonicalize.f32(float) #1
 declare float @llvm.minnum.f32(float, float) #1
 declare float @llvm.maxnum.f32(float, float) #1