Fixed the lost FastMathFlags for FCmp operations in SLPVectorizer.

Reviewer: Michael Zolotukhin.
Differential Revision: https://reviews.llvm.org/D26543

llvm-svn: 286626

diff --git a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
index 73dca75..6b27ac6 100644 (file)
--- a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
+++ b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
@@ -211,12 +211,12 @@ static unsigned getSameOpcode(ArrayRef<Value *> VL) {
 /// of each scalar operation (VL) that will be converted into a vector (I).
 /// Flag set: NSW, NUW, exact, and all of fast-math.
 static void propagateIRFlags(Value *I, ArrayRef<Value *> VL) {
-  if (auto *VecOp = dyn_cast<BinaryOperator>(I)) {
-    if (auto *Intersection = dyn_cast<BinaryOperator>(VL[0])) {
+  if (auto *VecOp = dyn_cast<Instruction>(I)) {
+    if (auto *Intersection = dyn_cast<Instruction>(VL[0])) {
       // Intersection is initialized to the 0th scalar,
       // so start counting from index '1'.
       for (int i = 1, e = VL.size(); i < e; ++i) {
-        if (auto *Scalar = dyn_cast<BinaryOperator>(VL[i]))
+        if (auto *Scalar = dyn_cast<Instruction>(VL[i]))
           Intersection->andIRFlags(Scalar);
       }
       VecOp->copyIRFlags(Intersection);
@@ -2430,6 +2430,7 @@ Value *BoUpSLP::vectorizeTree(TreeEntry *E) {
         V = Builder.CreateICmp(P0, L, R);
 
       E->VectorizedValue = V;
+      propagateIRFlags(E->VectorizedValue, E->Scalars);
       ++NumVectorInstructions;
       return V;
     }

diff --git a/llvm/test/Transforms/SLPVectorizer/X86/propagate_ir_flags.ll b/llvm/test/Transforms/SLPVectorizer/X86/propagate_ir_flags.ll
index a3b0c8f..3f26c81 100644 (file)
--- a/llvm/test/Transforms/SLPVectorizer/X86/propagate_ir_flags.ll
+++ b/llvm/test/Transforms/SLPVectorizer/X86/propagate_ir_flags.ll
@@ -348,3 +348,55 @@ define void @addsub_no_nsw(i32* %x) {
   ret void
 }
  
+; CHECK-LABEL: @fcmp_fast
+; CHECK: fcmp fast oge <2 x double>
+; CHECK: sub fast <2 x double>
+define void @fcmp_fast(double* %x) #1 {
+  %idx1 = getelementptr inbounds double, double* %x, i64 0
+  %idx2 = getelementptr inbounds double, double* %x, i64 1
+
+  %load1 = load double, double* %idx1, align 8
+  %load2 = load double, double* %idx2, align 8
+
+  %cmp1 = fcmp fast oge double %load1, 0.000000e+00
+  %cmp2 = fcmp fast oge double %load2, 0.000000e+00
+
+  %sub1 = fsub fast double -0.000000e+00, %load1
+  %sub2 = fsub fast double -0.000000e+00, %load2
+
+  %sel1 = select i1 %cmp1, double %load1, double %sub1
+  %sel2 = select i1 %cmp2, double %load2, double %sub2
+
+  store double %sel1, double* %idx1, align 8
+  store double %sel2, double* %idx2, align 8
+
+  ret void
+}
+
+; CHECK-LABEL: @fcmp_no_fast
+; CHECK: fcmp oge <2 x double>
+; CHECK: sub <2 x double>
+define void @fcmp_no_fast(double* %x) #1 {
+  %idx1 = getelementptr inbounds double, double* %x, i64 0
+  %idx2 = getelementptr inbounds double, double* %x, i64 1
+
+  %load1 = load double, double* %idx1, align 8
+  %load2 = load double, double* %idx2, align 8
+
+  %cmp1 = fcmp fast oge double %load1, 0.000000e+00
+  %cmp2 = fcmp oge double %load2, 0.000000e+00
+
+  %sub1 = fsub fast double -0.000000e+00, %load1
+  %sub2 = fsub double -0.000000e+00, %load2
+
+  %sel1 = select i1 %cmp1, double %load1, double %sub1
+  %sel2 = select i1 %cmp2, double %load2, double %sub2
+
+  store double %sel1, double* %idx1, align 8
+  store double %sel2, double* %idx2, align 8
+
+  ret void
+}
+
+attributes #1 = { "target-features"="+avx" }
+