Index: llvm/trunk/lib/Target/X86/X86ISelLowering.cpp
===================================================================
--- llvm/trunk/lib/Target/X86/X86ISelLowering.cpp
+++ llvm/trunk/lib/Target/X86/X86ISelLowering.cpp
@@ -10068,6 +10068,15 @@
     // type.
     MVT BlendVT = MVT::getVectorVT(MVT::i8, VT.getSizeInBits() / 8);
 
+    // x86 allows load folding with blendvb from the 2nd source operand. But
+    // we are still using LLVM select here (see comment below), so that's V1.
+    // If V2 can be load-folded and V1 cannot be load-folded, then commute to
+    // allow that load-folding possibility.
+    if (!ISD::isNormalLoad(V1.getNode()) && ISD::isNormalLoad(V2.getNode())) {
+      ShuffleVectorSDNode::commuteMask(Mask);
+      std::swap(V1, V2);
+    }
+
     // Compute the VSELECT mask. Note that VSELECT is really confusing in the
     // mix of LLVM's code generator and the x86 backend. We tell the code
     // generator that boolean values in the elements of an x86 vector register
Index: llvm/trunk/test/CodeGen/X86/vector-shuffle-128-v16.ll
===================================================================
--- llvm/trunk/test/CodeGen/X86/vector-shuffle-128-v16.ll
+++ llvm/trunk/test/CodeGen/X86/vector-shuffle-128-v16.ll
@@ -601,17 +601,15 @@
 ; SSE41-LABEL: load_fold_pblendvb:
 ; SSE41:       # %bb.0:
 ; SSE41-NEXT:    movdqa %xmm0, %xmm1
-; SSE41-NEXT:    movdqa (%rdi), %xmm2
-; SSE41-NEXT:    movaps {{.*#+}} xmm0 = [255,255,0,255,0,0,0,255,255,255,0,255,0,0,0,255]
-; SSE41-NEXT:    pblendvb %xmm0, %xmm1, %xmm2
-; SSE41-NEXT:    movdqa %xmm2, %xmm0
+; SSE41-NEXT:    movaps {{.*#+}} xmm0 = [0,0,255,0,255,255,255,0,0,0,255,0,255,255,255,0]
+; SSE41-NEXT:    pblendvb %xmm0, (%rdi), %xmm1
+; SSE41-NEXT:    movdqa %xmm1, %xmm0
 ; SSE41-NEXT:    retq
 ;
 ; AVX1OR2-LABEL: load_fold_pblendvb:
 ; AVX1OR2:       # %bb.0:
-; AVX1OR2-NEXT:    vmovdqa (%rdi), %xmm1
-; AVX1OR2-NEXT:    vmovdqa {{.*#+}} xmm2 = [255,255,0,255,0,0,0,255,255,255,0,255,0,0,0,255]
-; AVX1OR2-NEXT:    vpblendvb %xmm2, %xmm0, %xmm1, %xmm0
+; AVX1OR2-NEXT:    vmovdqa {{.*#+}} xmm1 = [0,0,255,0,255,255,255,0,0,0,255,0,255,255,255,0]
+; AVX1OR2-NEXT:    vpblendvb %xmm1, (%rdi), %xmm0, %xmm0
 ; AVX1OR2-NEXT:    retq
 ;
 ; AVX512VL-LABEL: load_fold_pblendvb:
Index: llvm/trunk/test/CodeGen/X86/vector-shuffle-256-v32.ll
===================================================================
--- llvm/trunk/test/CodeGen/X86/vector-shuffle-256-v32.ll
+++ llvm/trunk/test/CodeGen/X86/vector-shuffle-256-v32.ll
@@ -1656,9 +1656,8 @@
 ;
 ; AVX2-LABEL: load_fold_pblendvb:
 ; AVX2:       # %bb.0:
-; AVX2-NEXT:    vmovdqa (%rdi), %ymm1
-; AVX2-NEXT:    vmovdqa {{.*#+}} ymm2 = [255,255,0,255,0,0,0,255,255,255,0,255,0,0,0,255,255,255,0,255,0,0,0,255,255,255,0,255,0,0,0,255]
-; AVX2-NEXT:    vpblendvb %ymm2, %ymm0, %ymm1, %ymm0
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm1 = [0,0,255,0,255,255,255,0,0,0,255,0,255,255,255,0,0,0,255,0,255,255,255,0,0,0,255,0,255,255,255,0]
+; AVX2-NEXT:    vpblendvb %ymm1, (%rdi), %ymm0, %ymm0
 ; AVX2-NEXT:    retq
 ;
 ; AVX512VL-LABEL: load_fold_pblendvb: