deepen my MMX/SRoA hack to avoid hurting non-x86 codegen.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@112763 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Transforms/Scalar/ScalarReplAggregates.cpp b/lib/Transforms/Scalar/ScalarReplAggregates.cpp
index c245b1432739223ee271d0ac4a3ac4b08998c6da..fee317dbd9ab5d4ddcf63ea23f3fd7771c6b10b2 100644 (file)
--- a/lib/Transforms/Scalar/ScalarReplAggregates.cpp
+++ b/lib/Transforms/Scalar/ScalarReplAggregates.cpp
@@ -28,6 +28,7 @@
 #include "llvm/Instructions.h"
 #include "llvm/IntrinsicInst.h"
 #include "llvm/LLVMContext.h"
+#include "llvm/Module.h"
 #include "llvm/Pass.h"
 #include "llvm/Analysis/Dominators.h"
 #include "llvm/Target/TargetData.h"
@@ -197,7 +198,12 @@ private:
 /// IsVerbotenVectorType - Return true if this is a vector type ScalarRepl isn't
 /// allowed to form.  We do this to avoid MMX types, which is a complete hack,
 /// but is required until the backend is fixed.
-static bool IsVerbotenVectorType(const VectorType *VTy) {
+static bool IsVerbotenVectorType(const VectorType *VTy, const Instruction *I) {
+  StringRef Triple(I->getParent()->getParent()->getParent()->getTargetTriple());
+  if (!Triple.startswith("i386") &&
+      !Triple.startswith("x86_64"))
+    return false;
+  
   // Reject all the MMX vector types.
   switch (VTy->getNumElements()) {
   default: return false;
@@ -226,7 +232,7 @@ AllocaInst *ConvertToScalarInfo::TryConvert(AllocaInst *AI) {
   // involved, then we probably really do have a union of vector/array.
   const Type *NewTy;
   if (VectorTy && VectorTy->isVectorTy() && HadAVector &&
-      !IsVerbotenVectorType(cast<VectorType>(VectorTy))) {
+      !IsVerbotenVectorType(cast<VectorType>(VectorTy), AI)) {
     DEBUG(dbgs() << "CONVERT TO VECTOR: " << *AI << "\n  TYPE = "
           << *VectorTy << '\n');
     NewTy = VectorTy;  // Use the vector type.

diff --git a/test/Transforms/ScalarRepl/vector_promote.ll b/test/Transforms/ScalarRepl/vector_promote.ll
index 5287cbe38bfe78005f65b8887e37f1a6e295d002..fe55426b24a19743c042edbb534c8d1f1278b465 100644 (file)
--- a/test/Transforms/ScalarRepl/vector_promote.ll
+++ b/test/Transforms/ScalarRepl/vector_promote.ll
@@ -1,5 +1,6 @@
 ; RUN: opt < %s -scalarrepl -S | FileCheck %s
 target datalayout = "E-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64"
+target triple = "x86_64-apple-darwin10.0.0"
 
 define void @test1(<4 x float>* %F, float %f) {
 entry: