[SLPVectorizer] Add operand bundles to vectorized functions

SLPVectorizing a call site should result in further propagation of its
bundles.

llvm-svn: 268004

2 files changed, 64 insertions, 2 deletions

diff --git a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
index 60d1f2910cf..997716199fd 100644
--- a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
+++ b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
@@ -1419,7 +1419,8 @@ void BoUpSLP::buildTree_rec(ArrayRef<Value *> VL, unsigned Depth) {
       for (unsigned i = 1, e = VL.size(); i != e; ++i) {
         CallInst *CI2 = dyn_cast<CallInst>(VL[i]);
         if (!CI2 || CI2->getCalledFunction() != Int ||
-            getVectorIntrinsicIDForCall(CI2, TLI) != ID) {
+            getVectorIntrinsicIDForCall(CI2, TLI) != ID ||
+            !CI->hasIdenticalOperandBundleSchema(*CI2)) {
           BS.cancelScheduling(VL);
           newTreeEntry(VL, false);
           DEBUG(dbgs() << "SLP: mismatched calls:" << *CI << "!=" << *VL[i]
@@ -1439,6 +1440,17 @@ void BoUpSLP::buildTree_rec(ArrayRef<Value *> VL, unsigned Depth) {
             return;
           }
         }
+        // Verify that the bundle operands are identical between the two calls.
+        if (CI->hasOperandBundles() &&
+            !std::equal(CI->op_begin() + CI->getBundleOperandsStartIndex(),
+                        CI->op_begin() + CI->getBundleOperandsEndIndex(),
+                        CI2->op_begin() + CI2->getBundleOperandsStartIndex())) {
+          BS.cancelScheduling(VL);
+          newTreeEntry(VL, false);
+          DEBUG(dbgs() << "SLP: mismatched bundle operands in calls:" << *CI << "!="
+                       << *VL[i] << '\n');
+          return;
+        }
       }
 
       newTreeEntry(VL, true);
@@ -2554,7 +2566,9 @@ Value *BoUpSLP::vectorizeTree(TreeEntry *E) {
       Intrinsic::ID ID = getVectorIntrinsicIDForCall(CI, TLI);
       Type *Tys[] = { VectorType::get(CI->getType(), E->Scalars.size()) };
       Function *CF = Intrinsic::getDeclaration(M, ID, Tys);
-      Value *V = Builder.CreateCall(CF, OpVecs);
+      SmallVector<OperandBundleDef, 1> OpBundles;
+      CI->getOperandBundlesAsDefs(OpBundles);
+      Value *V = Builder.CreateCall(CF, OpVecs, OpBundles);
 
       // The scalar argument uses an in-tree scalar so we add the new vectorized
       // call to ExternalUses list to make sure that an extract will be
diff --git a/llvm/test/Transforms/SLPVectorizer/X86/funclet.ll b/llvm/test/Transforms/SLPVectorizer/X86/funclet.ll
new file mode 100644
index 00000000000..11d0bd94090
--- /dev/null
+++ b/llvm/test/Transforms/SLPVectorizer/X86/funclet.ll
@@ -0,0 +1,48 @@
+; RUN: opt -S -slp-vectorizer < %s | FileCheck %s
+target datalayout = "e-m:x-p:32:32-i64:64-f80:32-n8:16:32-a:0:32-S32"
+target triple = "i686-pc-windows-msvc18.0.0"
+
+define void @test1(double* %a, double* %b, double* %c) #0 personality i32 (...)* @__CxxFrameHandler3 {
+entry:
+  invoke void @_CxxThrowException(i8* null, i8* null)
+          to label %unreachable unwind label %catch.dispatch
+
+catch.dispatch:                                   ; preds = %entry
+  %0 = catchswitch within none [label %catch] unwind to caller
+
+catch:                                            ; preds = %catch.dispatch
+  %1 = catchpad within %0 [i8* null, i32 64, i8* null]
+  %i0 = load double, double* %a, align 8
+  %i1 = load double, double* %b, align 8
+  %mul = fmul double %i0, %i1
+  %call = tail call double @floor(double %mul) #1 [ "funclet"(token %1) ]
+  %arrayidx3 = getelementptr inbounds double, double* %a, i64 1
+  %i3 = load double, double* %arrayidx3, align 8
+  %arrayidx4 = getelementptr inbounds double, double* %b, i64 1
+  %i4 = load double, double* %arrayidx4, align 8
+  %mul5 = fmul double %i3, %i4
+  %call5 = tail call double @floor(double %mul5) #1 [ "funclet"(token %1) ]
+  store double %call, double* %c, align 8
+  %arrayidx5 = getelementptr inbounds double, double* %c, i64 1
+  store double %call5, double* %arrayidx5, align 8
+  catchret from %1 to label %try.cont
+
+try.cont:                                         ; preds = %for.cond.cleanup
+  ret void
+
+unreachable:                                      ; preds = %entry
+  unreachable
+}
+
+; CHECK-LABEL: define void @test1(
+; CHECK: %[[cpad:.*]] = catchpad within {{.*}} [i8* null, i32 64, i8* null]
+; CHECK: call <2 x double> @llvm.floor.v2f64(<2 x double> {{.*}}) [ "funclet"(token %[[cpad]]) ]
+
+declare x86_stdcallcc void @_CxxThrowException(i8*, i8*)
+
+declare i32 @__CxxFrameHandler3(...)
+
+declare double @floor(double) #1
+
+attributes #0 = { "target-features"="+sse2" }
+attributes #1 = { nounwind readnone }