2 files changed, 6 insertions, 4 deletions
diff --git a/llvm/lib/Target/X86/X86InstrSSE.td b/llvm/lib/Target/X86/X86InstrSSE.td
index 3797d91fb31..c8ad7d9eabb 100644
--- a/llvm/lib/Target/X86/X86InstrSSE.td
+++ b/llvm/lib/Target/X86/X86InstrSSE.td
@@ -725,7 +725,8 @@ let Predicates = [UseSSE1] in {
 
   // This pattern helps select MOVLPS on SSE1 only targets. With SSE2 we'll
   // end up with a movsd or bleand instead of shufp.
-  def : Pat<(X86Shufp (memopv4f32 addr:$src2), VR128:$src1, (i8 -28)),
+  // No need for aligned load, we're only loading 64-bits.
+  def : Pat<(X86Shufp (loadv4f32 addr:$src2), VR128:$src1, (i8 -28)),
             (MOVLPSrm VR128:$src1, addr:$src2)>;
 }
 
@@ -801,7 +802,8 @@ let Predicates = [UseSSE1] in {
 
   // This pattern helps select MOVHPS on SSE1 only targets. With SSE2 we'll
   // end up with a movsd or bleand instead of shufp.
-  def : Pat<(X86Movlhps VR128:$src1, (memopv4f32 addr:$src2)),
+  // No need for aligned load, we're only loading 64-bits.
+  def : Pat<(X86Movlhps VR128:$src1, (loadv4f32 addr:$src2)),
             (MOVHPSrm VR128:$src1, addr:$src2)>;
 }
 
diff --git a/llvm/test/CodeGen/X86/vector-shuffle-sse1.ll b/llvm/test/CodeGen/X86/vector-shuffle-sse1.ll
index dda46e062d5..eb0f0b043e2 100644
--- a/llvm/test/CodeGen/X86/vector-shuffle-sse1.ll
+++ b/llvm/test/CodeGen/X86/vector-shuffle-sse1.ll
@@ -280,7 +280,7 @@ define <4 x float> @shuffle_mem_v4f32_0145(<4 x float> %a, <4 x float>* %pb) {
 ; SSE1:       # %bb.0:
 ; SSE1-NEXT:    movhps {{.*#+}} xmm0 = xmm0[0,1],mem[0,1]
 ; SSE1-NEXT:    retq
-  %b = load <4 x float>, <4 x float>* %pb, align 16
+  %b = load <4 x float>, <4 x float>* %pb, align 1
   %shuffle = shufflevector <4 x float> %a, <4 x float> %b, <4 x i32> <i32 0, i32 1, i32 4, i32 5>
   ret <4 x float> %shuffle
 }
@@ -300,7 +300,7 @@ define <4 x float> @shuffle_mem_v4f32_4523(<4 x float> %a, <4 x float>* %pb) {
 ; SSE1:       # %bb.0:
 ; SSE1-NEXT:    movlps {{.*#+}} xmm0 = mem[0,1],xmm0[2,3]
 ; SSE1-NEXT:    retq
-  %b = load <4 x float>, <4 x float>* %pb, align 16
+  %b = load <4 x float>, <4 x float>* %pb, align 1
   %shuffle = shufflevector <4 x float> %a, <4 x float> %b, <4 x i32> <i32 4, i32 5, i32 2, i32 3>
   ret <4 x float> %shuffle
 }