[3.9.1] Merging r280837 [X86] Don't reduce the width of vector mul if the target doesn't support SSE2.

The patch is to fix PR30298, which is caused by rL272694. The solution is to
bail out if the target has no SSE2.

Differential Revision: https://reviews.llvm.org/D24288

git-svn-id: https://llvm.org/svn/llvm-project/llvm/branches/release_39@282753 91177308-0d34-0410-b5e6-96231b3b80d8

Author: RKSimon

Diff for: lib/Target/X86/X86ISelLowering.cpp

@@ -27516,7 +27516,8 @@ static SDValue reduceVMULWidth(SDNode *N, SelectionDAG &DAG,
                                const X86Subtarget &Subtarget) {
   // pmulld is supported since SSE41. It is better to use pmulld
   // instead of pmullw+pmulhw.
-  if (Subtarget.hasSSE41())
+  // pmullw/pmulhw are not supported by SSE.
+  if (Subtarget.hasSSE41() || !Subtarget.hasSSE2())
     return SDValue();
 
   ShrinkMode Mode;

Diff for: test/CodeGen/X86/pr30298.ll

@@ -0,0 +1,43 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -mtriple=i386-pc-linux-gnu -mattr=+sse < %s | FileCheck %s
+
+@c = external global i32*, align 8
+
+define void @mul_2xi8(i8* nocapture readonly %a, i8* nocapture readonly %b, i64 %index) nounwind {
+; CHECK-LABEL: mul_2xi8:
+; CHECK:       # BB#0: # %entry
+; CHECK-NEXT:    pushl %ebx
+; CHECK-NEXT:    pushl %edi
+; CHECK-NEXT:    pushl %esi
+; CHECK-NEXT:    movl {{[0-9]+}}(%esp), %eax
+; CHECK-NEXT:    movl {{[0-9]+}}(%esp), %ecx
+; CHECK-NEXT:    movl {{[0-9]+}}(%esp), %edx
+; CHECK-NEXT:    movl c, %esi
+; CHECK-NEXT:    movzbl 1(%edx,%ecx), %edi
+; CHECK-NEXT:    movzbl (%edx,%ecx), %edx
+; CHECK-NEXT:    movzbl 1(%eax,%ecx), %ebx
+; CHECK-NEXT:    movzbl (%eax,%ecx), %eax
+; CHECK-NEXT:    imull %edx, %eax
+; CHECK-NEXT:    imull %edi, %ebx
+; CHECK-NEXT:    movl %ebx, 4(%esi,%ecx,4)
+; CHECK-NEXT:    movl %eax, (%esi,%ecx,4)
+; CHECK-NEXT:    popl %esi
+; CHECK-NEXT:    popl %edi
+; CHECK-NEXT:    popl %ebx
+; CHECK-NEXT:    retl
+entry:
+  %pre = load i32*, i32** @c
+  %tmp6 = getelementptr inbounds i8, i8* %a, i64 %index
+  %tmp7 = bitcast i8* %tmp6 to <2 x i8>*
+  %wide.load = load <2 x i8>, <2 x i8>* %tmp7, align 1
+  %tmp8 = zext <2 x i8> %wide.load to <2 x i32>
+  %tmp10 = getelementptr inbounds i8, i8* %b, i64 %index
+  %tmp11 = bitcast i8* %tmp10 to <2 x i8>*
+  %wide.load17 = load <2 x i8>, <2 x i8>* %tmp11, align 1
+  %tmp12 = zext <2 x i8> %wide.load17 to <2 x i32>
+  %tmp13 = mul nuw nsw <2 x i32> %tmp12, %tmp8
+  %tmp14 = getelementptr inbounds i32, i32* %pre, i64 %index
+  %tmp15 = bitcast i32* %tmp14 to <2 x i32>*
+  store <2 x i32> %tmp13, <2 x i32>* %tmp15, align 4
+  ret void
+}