[PATCH] D29900: [SLP] Fix for PR31879: vectorize repeated scalar ops that don't get put back into a vector

[Alexey Bataev via Phabricator via llvm-commits]

ABataev updated this revision to Diff 88239.
ABataev added a comment.

Update after review


https://reviews.llvm.org/D29900

Files:
  lib/Transforms/Vectorize/SLPVectorizer.cpp
  test/Transforms/SLPVectorizer/X86/extractelement.ll


Index: test/Transforms/SLPVectorizer/X86/extractelement.ll
===================================================================
--- test/Transforms/SLPVectorizer/X86/extractelement.ll
+++ test/Transforms/SLPVectorizer/X86/extractelement.ll
@@ -3,11 +3,10 @@
 
 define float @f(<2 x float> %x) {
 ; CHECK-LABEL: @f(
-; CHECK-NEXT:    [[X0:%.*]] = extractelement <2 x float> [[X:%.*]], i32 0
-; CHECK-NEXT:    [[X1:%.*]] = extractelement <2 x float> [[X]], i32 1
-; CHECK-NEXT:    [[X0X0:%.*]] = fmul float [[X0]], [[X0]]
-; CHECK-NEXT:    [[X1X1:%.*]] = fmul float [[X1]], [[X1]]
-; CHECK-NEXT:    [[ADD:%.*]] = fadd float [[X0X0]], [[X1X1]]
+; CHECK-NEXT:    [[TMP1:%.*]] = fmul <2 x float> [[X:%.*]], [[X]]
+; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <2 x float> [[TMP1]], i32 0
+; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <2 x float> [[TMP1]], i32 1
+; CHECK-NEXT:    [[ADD:%.*]] = fadd float [[TMP2]], [[TMP3]]
 ; CHECK-NEXT:    ret float [[ADD]]
 ;
   %x0 = extractelement <2 x float> %x, i32 0
Index: lib/Transforms/Vectorize/SLPVectorizer.cpp
===================================================================
--- lib/Transforms/Vectorize/SLPVectorizer.cpp
+++ lib/Transforms/Vectorize/SLPVectorizer.cpp
@@ -1625,6 +1625,15 @@
   return true;
 }
 
+/// Checks that \p I is used in the single instruction.
+static bool hasOneUser(Instruction *I) {
+  if (I->hasOneUse())
+     return true;
+  User *U0 = *I->user_begin();
+  return std::all_of(I->user_begin(), I->user_end(),
+                     [U0](User *U) -> bool { return U0 == U; });
+}
+
 int BoUpSLP::getEntryCost(TreeEntry *E) {
   ArrayRef<Value*> VL = E->Scalars;
 
@@ -1660,7 +1669,7 @@
         int DeadCost = 0;
         for (unsigned i = 0, e = VL.size(); i < e; ++i) {
           Instruction *E = cast<Instruction>(VL[i]);
-          if (E->hasOneUse())
+          if (hasOneUser(E))
             // Take credit for instruction that will become dead.
             DeadCost +=
                 TTI->getVectorInstrCost(Instruction::ExtractElement, VecTy, i);


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D29900.88239.patch
Type: text/x-patch
Size: 2038 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20170213/2d0080ed/attachment.bin>