[PATCH] D49976: AMDGPU: Make fneg combine handle fcanonicalize

[Matt Arsenault via Phabricator via llvm-commits]

arsenm created this revision.
arsenm added a reviewer: rampitec.
Herald added subscribers: t-tye, tpr, dstuttard, yaxunl, nhaehnle, wdng, kzhuravl.

https://reviews.llvm.org/D49976

Files:
  lib/Target/AMDGPU/AMDGPUISelLowering.cpp
  test/CodeGen/AMDGPU/fneg-combines.ll


Index: test/CodeGen/AMDGPU/fneg-combines.ll
===================================================================
--- test/CodeGen/AMDGPU/fneg-combines.ll
+++ test/CodeGen/AMDGPU/fneg-combines.ll
@@ -1724,6 +1724,26 @@
   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.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
 
Index: lib/Target/AMDGPU/AMDGPUISelLowering.cpp
===================================================================
--- lib/Target/AMDGPU/AMDGPUISelLowering.cpp
+++ lib/Target/AMDGPU/AMDGPUISelLowering.cpp
@@ -554,6 +554,7 @@
   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 @@
   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:


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D49976.157938.patch
Type: text/x-patch
Size: 2306 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20180730/92720c91/attachment.bin>