[PATCH] D58481: [AMDGPU] fix commuted case of sub combine

[Stanislav Mekhanoshin via Phabricator via llvm-commits]

rampitec created this revision.
rampitec added a reviewer: arsenm.
Herald added subscribers: t-tye, tpr, dstuttard, yaxunl, nhaehnle, wdng, jvesely, kzhuravl.
rampitec retitled this revision from "PATCH] AMDGPU: fix commuted case of sub combine" to "[AMDGPU] fix commuted case of sub combine".

https://reviews.llvm.org/D58481

Files:
  lib/Target/AMDGPU/SIISelLowering.cpp
  test/CodeGen/AMDGPU/combine-cond-add-sub.ll


Index: test/CodeGen/AMDGPU/combine-cond-add-sub.ll
===================================================================
--- test/CodeGen/AMDGPU/combine-cond-add-sub.ll
+++ test/CodeGen/AMDGPU/combine-cond-add-sub.ll
@@ -127,6 +127,28 @@
   ret void
 }
 
+; GCN-LABEL: {{^}}sub_sube2:
+; GCN-DAG: v_cmp_gt_u32_e{{32|64}} [[CC:[^,]+]], v{{[0-9]+}}, v{{[0-9]+}}
+; GCN-DAG: _load_dword [[V:v[0-9]+]],
+; GCN:     {{v_subb_co_u32|v_subb_u32}}_e{{32|64}} [[SUB:v[0-9]+]], {{[^,]+}}, v{{[0-9]+}}, [[V]], [[CC]]
+; GCN:     v_add_{{[ui]}}32_e32 {{.*}}, 0x64, [[SUB]]
+; GCN-NOT: v_cndmask
+; GCN-NOT: v_sub
+define amdgpu_kernel void @sub_sube2(i32 addrspace(1)* nocapture %arg, i32 %a) {
+bb:
+  %x = tail call i32 @llvm.amdgcn.workitem.id.x()
+  %y = tail call i32 @llvm.amdgcn.workitem.id.y()
+  %gep = getelementptr inbounds i32, i32 addrspace(1)* %arg, i32 %x
+  %v = load i32, i32 addrspace(1)* %gep, align 4
+  %cmp = icmp ugt i32 %x, %y
+  %ext = sext i1 %cmp to i32
+  %adde = add i32 %v, %ext
+  %sub = sub i32 %adde, %a
+  %sub2 = sub i32 100, %sub
+  store i32 %sub2, i32 addrspace(1)* %gep, align 4
+  ret void
+}
+
 ; GCN-LABEL: {{^}}sube_sub:
 ; GCN: v_cmp_gt_u32_e{{32|64}} [[CC:[^,]+]], v{{[0-9]+}}, v{{[0-9]+}}
 ; GCN: v_subb_u32_e{{32|64}} v{{[0-9]+}}, {{[^,]+}}, v{{[0-9]+}}, v{{[0-9]+}}, [[CC]]
Index: lib/Target/AMDGPU/SIISelLowering.cpp
===================================================================
--- lib/Target/AMDGPU/SIISelLowering.cpp
+++ lib/Target/AMDGPU/SIISelLowering.cpp
@@ -8617,7 +8617,8 @@
   SDValue RHS = N->getOperand(1);
 
   unsigned Opc = LHS.getOpcode();
-  if (Opc != ISD::SUBCARRY)
+  bool NeedCommute = Opc != ISD::SUBCARRY;
+  if (NeedCommute)
     std::swap(RHS, LHS);
 
   if (LHS.getOpcode() == ISD::SUBCARRY) {
@@ -8626,6 +8627,8 @@
     if (!C || C->getZExtValue() != 0)
       return SDValue();
     SDValue Args[] = { LHS.getOperand(0), RHS, LHS.getOperand(2) };
+    if (NeedCommute)
+      std::swap(Args[0], Args[1]);
     return DAG.getNode(ISD::SUBCARRY, SDLoc(N), LHS->getVTList(), Args);
   }
   return SDValue();


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D58481.187692.patch
Type: text/x-patch
Size: 2073 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20190221/49cc0f6b/attachment-0001.bin>