Index: lib/CodeGen/SelectionDAG/DAGCombiner.cpp
===================================================================
--- lib/CodeGen/SelectionDAG/DAGCombiner.cpp
+++ lib/CodeGen/SelectionDAG/DAGCombiner.cpp
@@ -14469,7 +14469,7 @@
       MaxIndex = std::max(MaxIndex, Index);
     }
 
-    NearestPow2 = PowerOf2Ceil(MaxIndex);
+    NearestPow2 = PowerOf2Ceil(MaxIndex + 1);
     if (InVT.isSimple() && (NearestPow2 > 2) &&
         ((NumElems * 2) < NearestPow2)) {
       unsigned SplitSize = NearestPow2 / 2;
Index: test/CodeGen/ARM/crash-on-pow2-shufflevector.ll
===================================================================
--- /dev/null
+++ test/CodeGen/ARM/crash-on-pow2-shufflevector.ll
@@ -0,0 +1,24 @@
+; RUN: llc < %s -mtriple=armv7 | FileCheck %s
+;
+; Ensure that don't crash given a largeish power-of-two shufflevector index.
+
+%struct.desc = type { i32, [7 x i32] }
+
+define i32 @foo(%struct.desc* %descs, i32 %num, i32 %cw) local_unnamed_addr #0 {
+; CHECK-LABEL: foo:
+; CHECK:       @ BB#0: @ %entry
+; CHECK-NEXT:    mov r1, #32
+; CHECK-NEXT:    vld1.32 {d16, d17}, [r0], r1
+; CHECK-NEXT:    vld1.32 {d18, d19}, [r0]
+; CHECK-NEXT:    vtrn.32 q8, q9
+; CHECK-NEXT:    vadd.i32 d16, d16, d16
+; CHECK-NEXT:    vmov.32 r0, d16[1]
+; CHECK-NEXT:    bx lr
+entry:
+  %descs.vec = bitcast %struct.desc* %descs to <16 x i32>*
+  %wide.vec = load <16 x i32>, <16 x i32>* %descs.vec, align 4
+  %strided.vec = shufflevector <16 x i32> %wide.vec, <16 x i32> undef, <2 x i32> <i32 0, i32 8>
+  %bin.rdx20 = add <2 x i32> %strided.vec, %strided.vec
+  %0 = extractelement <2 x i32> %bin.rdx20, i32 1
+  ret i32 %0
+}
Index: test/CodeGen/X86/avx512-shuffles/partial_permute.ll
===================================================================
--- test/CodeGen/X86/avx512-shuffles/partial_permute.ll
+++ test/CodeGen/X86/avx512-shuffles/partial_permute.ll
@@ -2682,10 +2682,9 @@
 define <2 x i64> @test_8xi64_to_2xi64_perm_mem_mask0(<8 x i64>* %vp) {
 ; CHECK-LABEL: test_8xi64_to_2xi64_perm_mem_mask0:
 ; CHECK:       # BB#0:
-; CHECK-NEXT:    vmovdqa64 (%rdi), %zmm0
-; CHECK-NEXT:    vextracti32x4 $2, %zmm0, %xmm1
-; CHECK-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
-; CHECK-NEXT:    vpunpcklqdq {{.*#+}} xmm0 = xmm1[0],xmm0[0]
+; CHECK-NEXT:    vmovaps (%rdi), %zmm0
+; CHECK-NEXT:    vextractf64x4 $1, %zmm0, %ymm1
+; CHECK-NEXT:    vblendps {{.*#+}} xmm0 = xmm1[0,1],xmm0[2,3]
 ; CHECK-NEXT:    vzeroupper
 ; CHECK-NEXT:    retq
   %vec = load <8 x i64>, <8 x i64>* %vp
@@ -2696,11 +2695,11 @@
 ; CHECK-LABEL: test_masked_8xi64_to_2xi64_perm_mem_mask0:
 ; CHECK:       # BB#0:
 ; CHECK-NEXT:    vmovdqa64 (%rdi), %zmm1
-; CHECK-NEXT:    vextracti32x4 $2, %zmm1, %xmm2
-; CHECK-NEXT:    vpshufd {{.*#+}} xmm1 = xmm1[2,3,0,1]
+; CHECK-NEXT:    vextracti64x4 $1, %zmm1, %ymm2
+; CHECK-NEXT:    vpblendd {{.*#+}} xmm1 = xmm2[0,1],xmm1[2,3]
 ; CHECK-NEXT:    movb $2, %al
 ; CHECK-NEXT:    kmovd %eax, %k1
-; CHECK-NEXT:    vpunpcklqdq {{.*#+}} xmm0 = xmm2[0],xmm1[0]
+; CHECK-NEXT:    vmovdqa64 %xmm1, %xmm0 {%k1}
 ; CHECK-NEXT:    vzeroupper
 ; CHECK-NEXT:    retq
   %vec = load <8 x i64>, <8 x i64>* %vp
@@ -2713,11 +2712,11 @@
 ; CHECK-LABEL: test_masked_z_8xi64_to_2xi64_perm_mem_mask0:
 ; CHECK:       # BB#0:
 ; CHECK-NEXT:    vmovdqa64 (%rdi), %zmm0
-; CHECK-NEXT:    vextracti32x4 $2, %zmm0, %xmm1
-; CHECK-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
+; CHECK-NEXT:    vextracti64x4 $1, %zmm0, %ymm1
+; CHECK-NEXT:    vpblendd {{.*#+}} xmm0 = xmm1[0,1],xmm0[2,3]
 ; CHECK-NEXT:    movb $2, %al
 ; CHECK-NEXT:    kmovd %eax, %k1
-; CHECK-NEXT:    vpunpcklqdq {{.*#+}} xmm0 = xmm1[0],xmm0[0]
+; CHECK-NEXT:    vmovdqa64 %xmm0, %xmm0 {%k1} {z}
 ; CHECK-NEXT:    vzeroupper
 ; CHECK-NEXT:    retq
   %vec = load <8 x i64>, <8 x i64>* %vp
@@ -4527,7 +4526,7 @@
 ; CHECK-LABEL: test_masked_8xdouble_to_2xdouble_perm_mem_mask1:
 ; CHECK:       # BB#0:
 ; CHECK-NEXT:    vmovapd (%rdi), %zmm1
-; CHECK-NEXT:    vextractf32x4 $2, %zmm1, %xmm2
+; CHECK-NEXT:    vextractf64x4 $1, %zmm1, %ymm2
 ; CHECK-NEXT:    movb $1, %al
 ; CHECK-NEXT:    kmovd %eax, %k1
 ; CHECK-NEXT:    vshufpd {{.*#+}} xmm0 {%k1} = xmm1[1],xmm2[0]
@@ -4543,7 +4542,7 @@
 ; CHECK-LABEL: test_masked_z_8xdouble_to_2xdouble_perm_mem_mask1:
 ; CHECK:       # BB#0:
 ; CHECK-NEXT:    vmovapd (%rdi), %zmm0
-; CHECK-NEXT:    vextractf32x4 $2, %zmm0, %xmm1
+; CHECK-NEXT:    vextractf64x4 $1, %zmm0, %ymm1
 ; CHECK-NEXT:    movb $1, %al
 ; CHECK-NEXT:    kmovd %eax, %k1
 ; CHECK-NEXT:    vshufpd {{.*#+}} xmm0 {%k1} {z} = xmm0[1],xmm1[0]
Index: test/CodeGen/X86/vector-shuffle-512-v8.ll
===================================================================
--- test/CodeGen/X86/vector-shuffle-512-v8.ll
+++ test/CodeGen/X86/vector-shuffle-512-v8.ll
@@ -2685,17 +2685,19 @@
 define <2 x double> @test_v8f64_34 (<8 x double> %v) {
 ; AVX512F-LABEL: test_v8f64_34:
 ; AVX512F:       # BB#0:
-; AVX512F-NEXT:    vextractf32x4 $2, %zmm0, %xmm1
-; AVX512F-NEXT:    vextractf128 $1, %ymm0, %xmm0
-; AVX512F-NEXT:    vshufpd {{.*#+}} xmm0 = xmm0[1],xmm1[0]
+; AVX512F-NEXT:    vextractf64x4 $1, %zmm0, %ymm1
+; AVX512F-NEXT:    vshufpd {{.*#+}} ymm0 = ymm0[1],ymm1[0],ymm0[3],ymm1[2]
+; AVX512F-NEXT:    vpermpd {{.*#+}} ymm0 = ymm0[2,1,2,3]
+; AVX512F-NEXT:      # kill: %XMM0<def> %XMM0<kill> %YMM0<kill>
 ; AVX512F-NEXT:    vzeroupper
 ; AVX512F-NEXT:    retq
 ;
 ; AVX512F-32-LABEL: test_v8f64_34:
 ; AVX512F-32:       # BB#0:
-; AVX512F-32-NEXT:    vextractf32x4 $2, %zmm0, %xmm1
-; AVX512F-32-NEXT:    vextractf128 $1, %ymm0, %xmm0
-; AVX512F-32-NEXT:    vshufpd {{.*#+}} xmm0 = xmm0[1],xmm1[0]
+; AVX512F-32-NEXT:    vextractf64x4 $1, %zmm0, %ymm1
+; AVX512F-32-NEXT:    vshufpd {{.*#+}} ymm0 = ymm0[1],ymm1[0],ymm0[3],ymm1[2]
+; AVX512F-32-NEXT:    vpermpd {{.*#+}} ymm0 = ymm0[2,1,2,3]
+; AVX512F-32-NEXT:      # kill: %XMM0<def> %XMM0<kill> %YMM0<kill>
 ; AVX512F-32-NEXT:    vzeroupper
 ; AVX512F-32-NEXT:    retl
   %res = shufflevector <8 x double> %v, <8 x double> undef, <2 x i32> <i32 3, i32 4>