[SLPVectorizer] Pass the right type argument to getCmpSelInstrCost()

In getEntryCost(), make the scalar type for a compare instruction that of the
operands, not i1. This is needed in order to call getCmpSelInstrCost() for a
compare in a sensible way, the same way as the LoopVectorizer does.

New test: test/Transforms/SLPVectorizer/SystemZ/SLP-cmp-cost-query.ll

Review: Matthew Simpson
https://reviews.llvm.org/D31601

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@300061 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Transforms/Vectorize/SLPVectorizer.cpp b/lib/Transforms/Vectorize/SLPVectorizer.cpp
index df7dc2ac67f271397b915d71560dc4562448a19e..da3ac06ab464eb99ac4bd658da784836b5181a84 100644 (file)
--- a/lib/Transforms/Vectorize/SLPVectorizer.cpp
+++ b/lib/Transforms/Vectorize/SLPVectorizer.cpp
@@ -1702,6 +1702,8 @@ int BoUpSLP::getEntryCost(TreeEntry *E) {
   Type *ScalarTy = VL[0]->getType();
   if (StoreInst *SI = dyn_cast<StoreInst>(VL[0]))
     ScalarTy = SI->getValueOperand()->getType();
+  else if (CmpInst *CI = dyn_cast<CmpInst>(VL[0]))
+    ScalarTy = CI->getOperand(0)->getType();
   VectorType *VecTy = VectorType::get(ScalarTy, VL.size());
 
   // If we have computed a smaller type for the expression, update VecTy so

diff --git a/test/Transforms/SLPVectorizer/SystemZ/SLP-cmp-cost-query.ll b/test/Transforms/SLPVectorizer/SystemZ/SLP-cmp-cost-query.ll
new file mode 100644 (file)
index 0000000..535003a
--- /dev/null
+++ b/test/Transforms/SLPVectorizer/SystemZ/SLP-cmp-cost-query.ll
@@ -0,0 +1,36 @@
+; REQUIRES: asserts
+; RUN: opt -mtriple=systemz-unknown -mcpu=z13 -slp-vectorizer -debug-only=SLP \
+; RUN:   -S -disable-output < %s |& FileCheck %s
+;
+; Check that SLP vectorizer gets the right cost difference for a compare
+; node.
+
+; Function Attrs: norecurse nounwind readonly
+define void @fun(i8* nocapture, i32 zeroext) local_unnamed_addr #0 {
+.lr.ph.preheader:
+  br label %.lr.ph
+
+.lr.ph:                                           ; preds = %.lr.ph.preheader, %.lr.ph
+  %2 = phi i32 [ %., %.lr.ph ], [ undef, %.lr.ph.preheader ]
+  %3 = phi i32 [ %.9, %.lr.ph ], [ undef, %.lr.ph.preheader ]
+  %4 = icmp ult i32 %2, %1
+  %5 = select i1 %4, i32 0, i32 %1
+  %. = sub i32 %2, %5
+  %6 = icmp ult i32 %3, %1
+  %7 = select i1 %6, i32 0, i32 %1
+  %.9 = sub i32 %3, %7
+  %8 = zext i32 %. to i64
+  %9 = getelementptr inbounds i8, i8* %0, i64 %8
+  %10 = load i8, i8* %9, align 1
+  %11 = zext i32 %.9 to i64
+  %12 = getelementptr inbounds i8, i8* %0, i64 %11
+  %13 = load i8, i8* %12, align 1
+  %14 = icmp eq i8 %10, %13
+  br i1 %14, label %.lr.ph, label %._crit_edge
+
+._crit_edge:                                      ; preds = %.lr.ph
+  ret void
+
+; CHECK: SLP: Adding cost -1 for bundle that starts with   %4 = icmp ult i32 %2, %1.
+}
+