Index: llvm/trunk/lib/Target/X86/X86ISelLowering.cpp
===================================================================
--- llvm/trunk/lib/Target/X86/X86ISelLowering.cpp
+++ llvm/trunk/lib/Target/X86/X86ISelLowering.cpp
@@ -12007,18 +12007,22 @@
     // subvector.
     bool OnlyUsesV1 = isShuffleEquivalent(V1, V2, Mask, {0, 1, 0, 1});
     if (OnlyUsesV1 || isShuffleEquivalent(V1, V2, Mask, {0, 1, 4, 5})) {
-      // With AVX2 we should use VPERMQ/VPERMPD to allow memory folding.
+      // With AVX2, use VPERMQ/VPERMPD to allow memory folding.
       if (Subtarget.hasAVX2() && V2.isUndef())
         return SDValue();
 
-      MVT SubVT = MVT::getVectorVT(VT.getVectorElementType(),
-                                   VT.getVectorNumElements() / 2);
-      SDValue LoV = DAG.getNode(ISD::EXTRACT_SUBVECTOR, DL, SubVT, V1,
-                                DAG.getIntPtrConstant(0, DL));
-      SDValue HiV = DAG.getNode(ISD::EXTRACT_SUBVECTOR, DL, SubVT,
-                                OnlyUsesV1 ? V1 : V2,
-                                DAG.getIntPtrConstant(0, DL));
-      return DAG.getNode(ISD::CONCAT_VECTORS, DL, VT, LoV, HiV);
+      // With AVX1, use vperm2f128 (below) to allow load folding. Otherwise,
+      // this will likely become vinsertf128 which can't fold a 256-bit memop.
+      if (!isa<LoadSDNode>(peekThroughBitcasts(V1))) {
+        MVT SubVT = MVT::getVectorVT(VT.getVectorElementType(),
+                                     VT.getVectorNumElements() / 2);
+        SDValue LoV = DAG.getNode(ISD::EXTRACT_SUBVECTOR, DL, SubVT, V1,
+                                  DAG.getIntPtrConstant(0, DL));
+        SDValue HiV = DAG.getNode(ISD::EXTRACT_SUBVECTOR, DL, SubVT,
+                                  OnlyUsesV1 ? V1 : V2,
+                                  DAG.getIntPtrConstant(0, DL));
+        return DAG.getNode(ISD::CONCAT_VECTORS, DL, VT, LoV, HiV);
+      }
     }
   }
 
Index: llvm/trunk/test/CodeGen/X86/avx-vperm2x128.ll
===================================================================
--- llvm/trunk/test/CodeGen/X86/avx-vperm2x128.ll
+++ llvm/trunk/test/CodeGen/X86/avx-vperm2x128.ll
@@ -50,16 +50,10 @@
 }
 
 define <8 x float> @shuffle_v8f32_01230123_mem(<8 x float>* %pa, <8 x float>* %pb) nounwind uwtable readnone ssp {
-; AVX1-LABEL: shuffle_v8f32_01230123_mem:
-; AVX1:       ## BB#0: ## %entry
-; AVX1-NEXT:    vmovaps (%rdi), %ymm0
-; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm0, %ymm0
-; AVX1-NEXT:    retq
-;
-; AVX2-LABEL: shuffle_v8f32_01230123_mem:
-; AVX2:       ## BB#0: ## %entry
-; AVX2-NEXT:    vperm2f128 {{.*#+}} ymm0 = mem[0,1,0,1]
-; AVX2-NEXT:    retq
+; ALL-LABEL: shuffle_v8f32_01230123_mem:
+; ALL:       ## BB#0: ## %entry
+; ALL-NEXT:    vperm2f128 {{.*#+}} ymm0 = mem[0,1,0,1]
+; ALL-NEXT:    retq
 entry:
   %a = load <8 x float>, <8 x float>* %pa
   %b = load <8 x float>, <8 x float>* %pb
@@ -195,17 +189,15 @@
 ; AVX1-LABEL: shuffle_v16i16_4501_mem:
 ; AVX1:       ## BB#0: ## %entry
 ; AVX1-NEXT:    vmovdqa (%rdi), %ymm0
-; AVX1-NEXT:    vmovaps (%rsi), %ymm1
 ; AVX1-NEXT:    vpaddw {{.*}}(%rip), %xmm0, %xmm0
-; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
+; AVX1-NEXT:    vperm2f128 {{.*#+}} ymm0 = mem[0,1],ymm0[0,1]
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: shuffle_v16i16_4501_mem:
 ; AVX2:       ## BB#0: ## %entry
 ; AVX2-NEXT:    vmovdqa (%rdi), %ymm0
-; AVX2-NEXT:    vmovdqa (%rsi), %ymm1
 ; AVX2-NEXT:    vpaddw {{.*}}(%rip), %ymm0, %ymm0
-; AVX2-NEXT:    vinserti128 $1, %xmm0, %ymm1, %ymm0
+; AVX2-NEXT:    vperm2i128 {{.*#+}} ymm0 = mem[0,1],ymm0[0,1]
 ; AVX2-NEXT:    retq
 entry:
   %c = load <16 x i16>, <16 x i16>* %a
Index: llvm/trunk/test/CodeGen/X86/x86-interleaved-access.ll
===================================================================
--- llvm/trunk/test/CodeGen/X86/x86-interleaved-access.ll
+++ llvm/trunk/test/CodeGen/X86/x86-interleaved-access.ll
@@ -9,8 +9,8 @@
 ; AVX-NEXT:    vmovupd 32(%rdi), %ymm1
 ; AVX-NEXT:    vmovupd 64(%rdi), %ymm2
 ; AVX-NEXT:    vmovupd 96(%rdi), %ymm3
-; AVX-NEXT:    vinsertf128 $1, %xmm2, %ymm0, %ymm4
-; AVX-NEXT:    vinsertf128 $1, %xmm3, %ymm1, %ymm5
+; AVX-NEXT:    vperm2f128 {{.*#+}} ymm4 = ymm0[0,1],ymm2[0,1]
+; AVX-NEXT:    vperm2f128 {{.*#+}} ymm5 = ymm1[0,1],ymm3[0,1]
 ; AVX-NEXT:    vhaddpd %ymm5, %ymm4, %ymm4
 ; AVX-NEXT:    vperm2f128 {{.*#+}} ymm0 = ymm0[2,3],ymm2[2,3]
 ; AVX-NEXT:    vperm2f128 {{.*#+}} ymm1 = ymm1[2,3],ymm3[2,3]
@@ -37,8 +37,8 @@
 ; AVX-NEXT:    vmovupd 32(%rdi), %ymm1
 ; AVX-NEXT:    vmovupd 64(%rdi), %ymm2
 ; AVX-NEXT:    vmovupd 96(%rdi), %ymm3
-; AVX-NEXT:    vinsertf128 $1, %xmm2, %ymm0, %ymm4
-; AVX-NEXT:    vinsertf128 $1, %xmm3, %ymm1, %ymm5
+; AVX-NEXT:    vperm2f128 {{.*#+}} ymm4 = ymm0[0,1],ymm2[0,1]
+; AVX-NEXT:    vperm2f128 {{.*#+}} ymm5 = ymm1[0,1],ymm3[0,1]
 ; AVX-NEXT:    vunpcklpd {{.*#+}} ymm4 = ymm4[0],ymm5[0],ymm4[2],ymm5[2]
 ; AVX-NEXT:    vperm2f128 {{.*#+}} ymm0 = ymm0[2,3],ymm2[2,3]
 ; AVX-NEXT:    vperm2f128 {{.*#+}} ymm1 = ymm1[2,3],ymm3[2,3]
@@ -53,25 +53,15 @@
 }
 
 define <4 x double> @load_factorf64_1(<16 x double>* %ptr) {
-; AVX1-LABEL: load_factorf64_1:
-; AVX1:       # BB#0:
-; AVX1-NEXT:    vmovups (%rdi), %ymm0
-; AVX1-NEXT:    vmovups 32(%rdi), %ymm1
-; AVX1-NEXT:    vinsertf128 $1, 64(%rdi), %ymm0, %ymm0
-; AVX1-NEXT:    vinsertf128 $1, 96(%rdi), %ymm1, %ymm1
-; AVX1-NEXT:    vunpcklpd {{.*#+}} ymm0 = ymm0[0],ymm1[0],ymm0[2],ymm1[2]
-; AVX1-NEXT:    vmulpd %ymm0, %ymm0, %ymm0
-; AVX1-NEXT:    retq
-;
-; AVX2-LABEL: load_factorf64_1:
-; AVX2:       # BB#0:
-; AVX2-NEXT:    vmovupd (%rdi), %ymm0
-; AVX2-NEXT:    vmovupd 32(%rdi), %ymm1
-; AVX2-NEXT:    vinsertf128 $1, 64(%rdi), %ymm0, %ymm0
-; AVX2-NEXT:    vinsertf128 $1, 96(%rdi), %ymm1, %ymm1
-; AVX2-NEXT:    vunpcklpd {{.*#+}} ymm0 = ymm0[0],ymm1[0],ymm0[2],ymm1[2]
-; AVX2-NEXT:    vmulpd %ymm0, %ymm0, %ymm0
-; AVX2-NEXT:    retq
+; AVX-LABEL: load_factorf64_1:
+; AVX:       # BB#0:
+; AVX-NEXT:    vmovupd (%rdi), %ymm0
+; AVX-NEXT:    vmovupd 32(%rdi), %ymm1
+; AVX-NEXT:    vperm2f128 {{.*#+}} ymm0 = ymm0[0,1],mem[0,1]
+; AVX-NEXT:    vperm2f128 {{.*#+}} ymm1 = ymm1[0,1],mem[0,1]
+; AVX-NEXT:    vunpcklpd {{.*#+}} ymm0 = ymm0[0],ymm1[0],ymm0[2],ymm1[2]
+; AVX-NEXT:    vmulpd %ymm0, %ymm0, %ymm0
+; AVX-NEXT:    retq
   %wide.vec = load <16 x double>, <16 x double>* %ptr, align 16
   %strided.v0 = shufflevector <16 x double> %wide.vec, <16 x double> undef, <4 x i32> <i32 0, i32 4, i32 8, i32 12>
   %strided.v3 = shufflevector <16 x double> %wide.vec, <16 x double> undef, <4 x i32> <i32 0, i32 4, i32 8, i32 12>
@@ -86,8 +76,8 @@
 ; AVX1-NEXT:    vmovupd 32(%rdi), %ymm1
 ; AVX1-NEXT:    vmovupd 64(%rdi), %ymm2
 ; AVX1-NEXT:    vmovupd 96(%rdi), %ymm3
-; AVX1-NEXT:    vinsertf128 $1, %xmm2, %ymm0, %ymm4
-; AVX1-NEXT:    vinsertf128 $1, %xmm3, %ymm1, %ymm5
+; AVX1-NEXT:    vperm2f128 {{.*#+}} ymm4 = ymm0[0,1],ymm2[0,1]
+; AVX1-NEXT:    vperm2f128 {{.*#+}} ymm5 = ymm1[0,1],ymm3[0,1]
 ; AVX1-NEXT:    vperm2f128 {{.*#+}} ymm0 = ymm0[2,3],ymm2[2,3]
 ; AVX1-NEXT:    vperm2f128 {{.*#+}} ymm1 = ymm1[2,3],ymm3[2,3]
 ; AVX1-NEXT:    vunpcklpd {{.*#+}} ymm2 = ymm4[0],ymm5[0],ymm4[2],ymm5[2]
@@ -113,8 +103,8 @@
 ; AVX2-NEXT:    vmovdqu 32(%rdi), %ymm1
 ; AVX2-NEXT:    vmovdqu 64(%rdi), %ymm2
 ; AVX2-NEXT:    vmovdqu 96(%rdi), %ymm3
-; AVX2-NEXT:    vinserti128 $1, %xmm2, %ymm0, %ymm4
-; AVX2-NEXT:    vinserti128 $1, %xmm3, %ymm1, %ymm5
+; AVX2-NEXT:    vperm2i128 {{.*#+}} ymm4 = ymm0[0,1],ymm2[0,1]
+; AVX2-NEXT:    vperm2i128 {{.*#+}} ymm5 = ymm1[0,1],ymm3[0,1]
 ; AVX2-NEXT:    vperm2i128 {{.*#+}} ymm0 = ymm0[2,3],ymm2[2,3]
 ; AVX2-NEXT:    vperm2i128 {{.*#+}} ymm1 = ymm1[2,3],ymm3[2,3]
 ; AVX2-NEXT:    vpunpcklqdq {{.*#+}} ymm2 = ymm4[0],ymm5[0],ymm4[2],ymm5[2]