[PATCH] D113203: [AMDGPU] Small correction in SITargetLowering::performOrCombine()

Konstantin Pyzhov via Phabricator via llvm-commits llvm-commits at lists.llvm.org
Fri Nov 5 08:29:08 PDT 2021


kpyzhov updated this revision to Diff 385086.

Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D113203/new/

https://reviews.llvm.org/D113203

Files:
  llvm/lib/Target/AMDGPU/SIISelLowering.cpp
  llvm/test/CodeGen/AMDGPU/combine-reg-or-const.ll


Index: llvm/test/CodeGen/AMDGPU/combine-reg-or-const.ll
===================================================================
--- /dev/null
+++ llvm/test/CodeGen/AMDGPU/combine-reg-or-const.ll
@@ -0,0 +1,27 @@
+; RUN: llc  -mtriple=amdgcn-amd-amdhsa -o - %s | FileCheck %s
+
+; The OR instruction should not be eliminated by the "OR Combine" DAG optimization.
+
+; CHECK-LABEL: _Z11test_kernelPii:
+; CHECK: s_or_b32
+
+define protected amdgpu_kernel void @_Z11test_kernelPii(i32 addrspace(1)* nocapture %Ad.coerce, i32 %s) local_unnamed_addr #5 {
+entry:
+  %rem.lhs.trunc = trunc i32 %s to i16
+  %rem4 = urem i16 %rem.lhs.trunc, 12
+  %rem.zext = zext i16 %rem4 to i32
+  %cmp = icmp eq i32 %s, 3
+  br i1 %cmp, label %if.then, label %if.end
+
+if.then:                                          ; preds = %entry
+  %idxprom = zext i32 %s to i64
+  %arrayidx3 = getelementptr inbounds i32, i32 addrspace(1)* %Ad.coerce, i64 %idxprom
+  %div = lshr i32 %rem.zext, 3
+  %or = or i32 %rem.zext, 192
+  %add = add nuw nsw i32 %or, %div
+  store i32 %add, i32 addrspace(1)* %arrayidx3, align 4
+  br label %if.end
+
+if.end:                                           ; preds = %if.then, %entry
+  ret void
+}
Index: llvm/lib/Target/AMDGPU/SIISelLowering.cpp
===================================================================
--- llvm/lib/Target/AMDGPU/SIISelLowering.cpp
+++ llvm/lib/Target/AMDGPU/SIISelLowering.cpp
@@ -9474,7 +9474,8 @@
   const ConstantSDNode *CRHS = dyn_cast<ConstantSDNode>(N->getOperand(1));
   if (CRHS) {
     if (SDValue Split
-          = splitBinaryBitConstantOp(DCI, SDLoc(N), ISD::OR, LHS, CRHS))
+          = splitBinaryBitConstantOp(DCI, SDLoc(N), ISD::OR,
+                                     N->getOperand(0), CRHS))
       return Split;
   }
 


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D113203.385086.patch
Type: text/x-patch
Size: 1776 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20211105/5f8e94ad/attachment.bin>


More information about the llvm-commits mailing list