diff --git a/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp b/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
index ecdfb867cc708..f35f663d6ba1b 100644
--- a/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
@@ -22243,6 +22243,19 @@ SDValue DAGCombiner::visitEXTRACT_VECTOR_ELT(SDNode *N) {
   unsigned NumElts = VecVT.getVectorNumElements();
   unsigned VecEltBitWidth = VecVT.getScalarSizeInBits();
 
+  // See if the extracted element is constant, in which case fold it if its
+  // a legal fp immediate.
+  if (IndexC && ScalarVT.isFloatingPoint()) {
+    APInt EltMask = APInt::getOneBitSet(NumElts, IndexC->getZExtValue());
+    KnownBits KnownElt = DAG.computeKnownBits(VecOp, EltMask);
+    if (KnownElt.isConstant()) {
+      APFloat CstFP =
+          APFloat(DAG.EVTToAPFloatSemantics(ScalarVT), KnownElt.getConstant());
+      if (TLI.isFPImmLegal(CstFP, ScalarVT))
+        return DAG.getConstantFP(CstFP, DL, ScalarVT);
+    }
+  }
+
   // TODO: These transforms should not require the 'hasOneUse' restriction, but
   // there are regressions on multiple targets without it. We can end up with a
   // mess of scalar and vector code if we reduce only part of the DAG to scalar.
diff --git a/llvm/test/CodeGen/AArch64/aarch64-neon-vector-insert-uaddlv.ll b/llvm/test/CodeGen/AArch64/aarch64-neon-vector-insert-uaddlv.ll
index 55750ab34e17a..3c8aca5145261 100644
--- a/llvm/test/CodeGen/AArch64/aarch64-neon-vector-insert-uaddlv.ll
+++ b/llvm/test/CodeGen/AArch64/aarch64-neon-vector-insert-uaddlv.ll
@@ -69,11 +69,10 @@ define void @insert_vec_v23i32_uaddlv_from_v8i16(ptr %0) {
 ; CHECK:       ; %bb.0: ; %entry
 ; CHECK-NEXT:    movi.2d v0, #0000000000000000
 ; CHECK-NEXT:    movi.2d v2, #0000000000000000
-; CHECK-NEXT:    add x8, x0, #88
+; CHECK-NEXT:    str wzr, [x0, #88]
 ; CHECK-NEXT:    uaddlv.8h s1, v0
 ; CHECK-NEXT:    stp q0, q0, [x0, #16]
 ; CHECK-NEXT:    stp q0, q0, [x0, #48]
-; CHECK-NEXT:    st1.s { v0 }[2], [x8]
 ; CHECK-NEXT:    str d0, [x0, #80]
 ; CHECK-NEXT:    mov.s v2[0], v1[0]
 ; CHECK-NEXT:    ucvtf.4s v1, v2
diff --git a/llvm/test/CodeGen/AArch64/arm64-promote-const-complex-initializers.ll b/llvm/test/CodeGen/AArch64/arm64-promote-const-complex-initializers.ll
index 86ebf803c5783..bbd2acbab4246 100644
--- a/llvm/test/CodeGen/AArch64/arm64-promote-const-complex-initializers.ll
+++ b/llvm/test/CodeGen/AArch64/arm64-promote-const-complex-initializers.ll
@@ -30,10 +30,10 @@ define [1 x <4 x float>] @test1() {
 define [1 x <4 x float>] @test2() {
 ; CHECK-LABEL:    .p2align    4, 0x0              ; -- Begin function test2
 ; CHECK-NEXT: lCPI1_0:
-; CHECK-NEXT:     .long   0x00000000              ; float 0
-; CHECK-NEXT:     .long   0x00000000              ; float 0
-; CHECK-NEXT:     .long   0x00000000              ; float 0
-; CHECK-NEXT:     .long   0x3f800000              ; float 1
+; CHECK-NEXT:     .long   0x80000000              ; float -0
+; CHECK-NEXT:     .long   0x80000000              ; float -0
+; CHECK-NEXT:     .long   0x80000000              ; float -0
+; CHECK-NEXT:     .long   0xbf800000              ; float -1
 ; CHECK-NEXT:     .section    __TEXT,__text,regular,pure_instructions
 ; CHECK-NEXT:     .globl  _test2
 ; CHECK-NEXT:     .p2align    2
@@ -43,17 +43,7 @@ define [1 x <4 x float>] @test2() {
 ; CHECK-NEXT: Lloh2:
 ; CHECK-NEXT:     adrp    x8, lCPI1_0@PAGE
 ; CHECK-NEXT: Lloh3:
-; CHECK-NEXT:     ldr q1, [x8, lCPI1_0@PAGEOFF]
-; CHECK-NEXT:     mov s2, v1[1]
-; CHECK-NEXT:     fneg    s0, s1
-; CHECK-NEXT:     mov s3, v1[2]
-; CHECK-NEXT:     mov s1, v1[3]
-; CHECK-NEXT:     fneg    s2, s2
-; CHECK-NEXT:     fneg    s3, s3
-; CHECK-NEXT:     fneg    s1, s1
-; CHECK-NEXT:     mov.s   v0[1], v2[0]
-; CHECK-NEXT:     mov.s   v0[2], v3[0]
-; CHECK-NEXT:     mov.s   v0[3], v1[0]
+; CHECK-NEXT:     ldr q0, [x8, lCPI1_0@PAGEOFF]
 ; CHECK-NEXT:     ret
 ;
   %constexpr = fneg float extractelement (<4 x float> bitcast (<1 x i128> <i128 84405977732342157929391748327801880576> to <4 x float>), i32 0)
diff --git a/llvm/test/CodeGen/X86/2011-10-19-widen_vselect.ll b/llvm/test/CodeGen/X86/2011-10-19-widen_vselect.ll
index e7f62b9dfc221..171e16e35fc2f 100644
--- a/llvm/test/CodeGen/X86/2011-10-19-widen_vselect.ll
+++ b/llvm/test/CodeGen/X86/2011-10-19-widen_vselect.ll
@@ -50,13 +50,12 @@ define void @zero_test() {
 ; X86-LABEL: zero_test:
 ; X86:       # %bb.0: # %entry
 ; X86-NEXT:    xorps %xmm0, %xmm0
-; X86-NEXT:    movlps %xmm0, (%eax)
+; X86-NEXT:    movsd %xmm0, (%eax)
 ; X86-NEXT:    retl
 ;
 ; X64-LABEL: zero_test:
 ; X64:       # %bb.0: # %entry
-; X64-NEXT:    xorps %xmm0, %xmm0
-; X64-NEXT:    movlps %xmm0, (%rax)
+; X64-NEXT:    movq $0, (%rax)
 ; X64-NEXT:    retq
 entry:
   %0 = select <2 x i1> undef, <2 x float> undef, <2 x float> zeroinitializer
diff --git a/llvm/test/CodeGen/X86/2012-07-10-extload64.ll b/llvm/test/CodeGen/X86/2012-07-10-extload64.ll
index b6ec3b34eb107..6db17251cd599 100644
--- a/llvm/test/CodeGen/X86/2012-07-10-extload64.ll
+++ b/llvm/test/CodeGen/X86/2012-07-10-extload64.ll
@@ -30,7 +30,7 @@ define void @store_64(ptr %ptr) {
 ; X86:       # %bb.0: # %BB
 ; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
 ; X86-NEXT:    xorps %xmm0, %xmm0
-; X86-NEXT:    movlps %xmm0, (%eax)
+; X86-NEXT:    movsd %xmm0, (%eax)
 ; X86-NEXT:    retl
 ;
 ; X64-LABEL: store_64:
diff --git a/llvm/test/CodeGen/X86/fold-load-vec.ll b/llvm/test/CodeGen/X86/fold-load-vec.ll
index 348929cdf9f79..0bf846a0930bb 100644
--- a/llvm/test/CodeGen/X86/fold-load-vec.ll
+++ b/llvm/test/CodeGen/X86/fold-load-vec.ll
@@ -10,8 +10,8 @@ define void @sample_test(ptr %source, ptr %dest) nounwind {
 ; CHECK-NEXT:    subq $24, %rsp
 ; CHECK-NEXT:    movq %rdi, {{[0-9]+}}(%rsp)
 ; CHECK-NEXT:    movq %rsi, {{[0-9]+}}(%rsp)
+; CHECK-NEXT:    movq $0, (%rsp)
 ; CHECK-NEXT:    xorps %xmm0, %xmm0
-; CHECK-NEXT:    movlps %xmm0, (%rsp)
 ; CHECK-NEXT:    unpcklps {{.*#+}} xmm0 = xmm0[0],mem[0],xmm0[1],mem[1]
 ; CHECK-NEXT:    movlps %xmm0, (%rsp)
 ; CHECK-NEXT:    movlps %xmm0, (%rsi)
diff --git a/llvm/test/CodeGen/X86/half.ll b/llvm/test/CodeGen/X86/half.ll
index 596e465ee8cac..7225257203161 100644
--- a/llvm/test/CodeGen/X86/half.ll
+++ b/llvm/test/CodeGen/X86/half.ll
@@ -1082,12 +1082,11 @@ define void @main.158() #0 {
 ; BWON-F16C-LABEL: main.158:
 ; BWON-F16C:       # %bb.0: # %entry
 ; BWON-F16C-NEXT:    vxorps %xmm0, %xmm0, %xmm0
-; BWON-F16C-NEXT:    vcvtps2ph $4, %xmm0, %xmm0
-; BWON-F16C-NEXT:    vpmovzxwq {{.*#+}} xmm0 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero
-; BWON-F16C-NEXT:    vcvtph2ps %xmm0, %xmm0
-; BWON-F16C-NEXT:    vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero
-; BWON-F16C-NEXT:    vucomiss %xmm0, %xmm1
-; BWON-F16C-NEXT:    vxorps %xmm0, %xmm0, %xmm0
+; BWON-F16C-NEXT:    vcvtps2ph $4, %xmm0, %xmm1
+; BWON-F16C-NEXT:    vpmovzxwq {{.*#+}} xmm1 = xmm1[0],zero,zero,zero,xmm1[1],zero,zero,zero
+; BWON-F16C-NEXT:    vcvtph2ps %xmm1, %xmm1
+; BWON-F16C-NEXT:    vmovss {{.*#+}} xmm2 = mem[0],zero,zero,zero
+; BWON-F16C-NEXT:    vucomiss %xmm1, %xmm2
 ; BWON-F16C-NEXT:    jae .LBB20_2
 ; BWON-F16C-NEXT:  # %bb.1: # %entry
 ; BWON-F16C-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
@@ -1100,8 +1099,7 @@ define void @main.158() #0 {
 ; CHECK-I686-LABEL: main.158:
 ; CHECK-I686:       # %bb.0: # %entry
 ; CHECK-I686-NEXT:    subl $12, %esp
-; CHECK-I686-NEXT:    pxor %xmm0, %xmm0
-; CHECK-I686-NEXT:    movd %xmm0, (%esp)
+; CHECK-I686-NEXT:    movl $0, (%esp)
 ; CHECK-I686-NEXT:    calll __truncsfhf2
 ; CHECK-I686-NEXT:    pextrw $0, %xmm0, %eax
 ; CHECK-I686-NEXT:    movw %ax, (%esp)
diff --git a/llvm/test/CodeGen/X86/nontemporal-3.ll b/llvm/test/CodeGen/X86/nontemporal-3.ll
index a2d2c5ca43011..f9872b10097a1 100644
--- a/llvm/test/CodeGen/X86/nontemporal-3.ll
+++ b/llvm/test/CodeGen/X86/nontemporal-3.ll
@@ -93,247 +93,66 @@ define void @test_zero_v4f64_align1(ptr %dst) nounwind {
 }
 
 define void @test_zero_v8f32_align1(ptr %dst) nounwind {
-; SSE2-LABEL: test_zero_v8f32_align1:
-; SSE2:       # %bb.0:
-; SSE2-NEXT:    xorl %eax, %eax
-; SSE2-NEXT:    movntiq %rax, 8(%rdi)
-; SSE2-NEXT:    movntiq %rax, (%rdi)
-; SSE2-NEXT:    movntiq %rax, 24(%rdi)
-; SSE2-NEXT:    movntiq %rax, 16(%rdi)
-; SSE2-NEXT:    retq
-;
-; SSE4A-LABEL: test_zero_v8f32_align1:
-; SSE4A:       # %bb.0:
-; SSE4A-NEXT:    xorl %eax, %eax
-; SSE4A-NEXT:    movntiq %rax, 8(%rdi)
-; SSE4A-NEXT:    movntiq %rax, 24(%rdi)
-; SSE4A-NEXT:    xorps %xmm0, %xmm0
-; SSE4A-NEXT:    movntsd %xmm0, (%rdi)
-; SSE4A-NEXT:    movntsd %xmm0, 16(%rdi)
-; SSE4A-NEXT:    retq
-;
-; SSE41-LABEL: test_zero_v8f32_align1:
-; SSE41:       # %bb.0:
-; SSE41-NEXT:    xorl %eax, %eax
-; SSE41-NEXT:    movntiq %rax, 8(%rdi)
-; SSE41-NEXT:    movntiq %rax, (%rdi)
-; SSE41-NEXT:    movntiq %rax, 24(%rdi)
-; SSE41-NEXT:    movntiq %rax, 16(%rdi)
-; SSE41-NEXT:    retq
-;
-; AVX-LABEL: test_zero_v8f32_align1:
-; AVX:       # %bb.0:
-; AVX-NEXT:    xorl %eax, %eax
-; AVX-NEXT:    movntiq %rax, 8(%rdi)
-; AVX-NEXT:    movntiq %rax, (%rdi)
-; AVX-NEXT:    movntiq %rax, 24(%rdi)
-; AVX-NEXT:    movntiq %rax, 16(%rdi)
-; AVX-NEXT:    retq
-;
-; AVX512-LABEL: test_zero_v8f32_align1:
-; AVX512:       # %bb.0:
-; AVX512-NEXT:    xorl %eax, %eax
-; AVX512-NEXT:    movntiq %rax, 8(%rdi)
-; AVX512-NEXT:    movntiq %rax, (%rdi)
-; AVX512-NEXT:    movntiq %rax, 24(%rdi)
-; AVX512-NEXT:    movntiq %rax, 16(%rdi)
-; AVX512-NEXT:    retq
+; CHECK-LABEL: test_zero_v8f32_align1:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    xorl %eax, %eax
+; CHECK-NEXT:    movntiq %rax, 8(%rdi)
+; CHECK-NEXT:    movntiq %rax, (%rdi)
+; CHECK-NEXT:    movntiq %rax, 24(%rdi)
+; CHECK-NEXT:    movntiq %rax, 16(%rdi)
+; CHECK-NEXT:    retq
   store <8 x float> zeroinitializer, ptr %dst, align 1, !nontemporal !1
   ret void
 }
 
 define void @test_zero_v4i64_align1(ptr %dst) nounwind {
-; SSE2-LABEL: test_zero_v4i64_align1:
-; SSE2:       # %bb.0:
-; SSE2-NEXT:    xorl %eax, %eax
-; SSE2-NEXT:    movntiq %rax, 8(%rdi)
-; SSE2-NEXT:    movntiq %rax, (%rdi)
-; SSE2-NEXT:    movntiq %rax, 24(%rdi)
-; SSE2-NEXT:    movntiq %rax, 16(%rdi)
-; SSE2-NEXT:    retq
-;
-; SSE4A-LABEL: test_zero_v4i64_align1:
-; SSE4A:       # %bb.0:
-; SSE4A-NEXT:    xorps %xmm0, %xmm0
-; SSE4A-NEXT:    movntsd %xmm0, 8(%rdi)
-; SSE4A-NEXT:    movntsd %xmm0, (%rdi)
-; SSE4A-NEXT:    movntsd %xmm0, 24(%rdi)
-; SSE4A-NEXT:    movntsd %xmm0, 16(%rdi)
-; SSE4A-NEXT:    retq
-;
-; SSE41-LABEL: test_zero_v4i64_align1:
-; SSE41:       # %bb.0:
-; SSE41-NEXT:    xorl %eax, %eax
-; SSE41-NEXT:    movntiq %rax, 8(%rdi)
-; SSE41-NEXT:    movntiq %rax, (%rdi)
-; SSE41-NEXT:    movntiq %rax, 24(%rdi)
-; SSE41-NEXT:    movntiq %rax, 16(%rdi)
-; SSE41-NEXT:    retq
-;
-; AVX-LABEL: test_zero_v4i64_align1:
-; AVX:       # %bb.0:
-; AVX-NEXT:    xorl %eax, %eax
-; AVX-NEXT:    movntiq %rax, 8(%rdi)
-; AVX-NEXT:    movntiq %rax, (%rdi)
-; AVX-NEXT:    movntiq %rax, 24(%rdi)
-; AVX-NEXT:    movntiq %rax, 16(%rdi)
-; AVX-NEXT:    retq
-;
-; AVX512-LABEL: test_zero_v4i64_align1:
-; AVX512:       # %bb.0:
-; AVX512-NEXT:    xorl %eax, %eax
-; AVX512-NEXT:    movntiq %rax, 8(%rdi)
-; AVX512-NEXT:    movntiq %rax, (%rdi)
-; AVX512-NEXT:    movntiq %rax, 24(%rdi)
-; AVX512-NEXT:    movntiq %rax, 16(%rdi)
-; AVX512-NEXT:    retq
+; CHECK-LABEL: test_zero_v4i64_align1:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    xorl %eax, %eax
+; CHECK-NEXT:    movntiq %rax, 8(%rdi)
+; CHECK-NEXT:    movntiq %rax, (%rdi)
+; CHECK-NEXT:    movntiq %rax, 24(%rdi)
+; CHECK-NEXT:    movntiq %rax, 16(%rdi)
+; CHECK-NEXT:    retq
   store <4 x i64> zeroinitializer, ptr %dst, align 1, !nontemporal !1
   ret void
 }
 
 define void @test_zero_v8i32_align1(ptr %dst) nounwind {
-; SSE2-LABEL: test_zero_v8i32_align1:
-; SSE2:       # %bb.0:
-; SSE2-NEXT:    xorl %eax, %eax
-; SSE2-NEXT:    movntiq %rax, 8(%rdi)
-; SSE2-NEXT:    movntiq %rax, (%rdi)
-; SSE2-NEXT:    movntiq %rax, 24(%rdi)
-; SSE2-NEXT:    movntiq %rax, 16(%rdi)
-; SSE2-NEXT:    retq
-;
-; SSE4A-LABEL: test_zero_v8i32_align1:
-; SSE4A:       # %bb.0:
-; SSE4A-NEXT:    xorps %xmm0, %xmm0
-; SSE4A-NEXT:    movntsd %xmm0, 8(%rdi)
-; SSE4A-NEXT:    movntsd %xmm0, (%rdi)
-; SSE4A-NEXT:    movntsd %xmm0, 24(%rdi)
-; SSE4A-NEXT:    movntsd %xmm0, 16(%rdi)
-; SSE4A-NEXT:    retq
-;
-; SSE41-LABEL: test_zero_v8i32_align1:
-; SSE41:       # %bb.0:
-; SSE41-NEXT:    xorl %eax, %eax
-; SSE41-NEXT:    movntiq %rax, 8(%rdi)
-; SSE41-NEXT:    movntiq %rax, (%rdi)
-; SSE41-NEXT:    movntiq %rax, 24(%rdi)
-; SSE41-NEXT:    movntiq %rax, 16(%rdi)
-; SSE41-NEXT:    retq
-;
-; AVX-LABEL: test_zero_v8i32_align1:
-; AVX:       # %bb.0:
-; AVX-NEXT:    xorl %eax, %eax
-; AVX-NEXT:    movntiq %rax, 8(%rdi)
-; AVX-NEXT:    movntiq %rax, (%rdi)
-; AVX-NEXT:    movntiq %rax, 24(%rdi)
-; AVX-NEXT:    movntiq %rax, 16(%rdi)
-; AVX-NEXT:    retq
-;
-; AVX512-LABEL: test_zero_v8i32_align1:
-; AVX512:       # %bb.0:
-; AVX512-NEXT:    xorl %eax, %eax
-; AVX512-NEXT:    movntiq %rax, 8(%rdi)
-; AVX512-NEXT:    movntiq %rax, (%rdi)
-; AVX512-NEXT:    movntiq %rax, 24(%rdi)
-; AVX512-NEXT:    movntiq %rax, 16(%rdi)
-; AVX512-NEXT:    retq
+; CHECK-LABEL: test_zero_v8i32_align1:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    xorl %eax, %eax
+; CHECK-NEXT:    movntiq %rax, 8(%rdi)
+; CHECK-NEXT:    movntiq %rax, (%rdi)
+; CHECK-NEXT:    movntiq %rax, 24(%rdi)
+; CHECK-NEXT:    movntiq %rax, 16(%rdi)
+; CHECK-NEXT:    retq
   store <8 x i32> zeroinitializer, ptr %dst, align 1, !nontemporal !1
   ret void
 }
 
 define void @test_zero_v16i16_align1(ptr %dst) nounwind {
-; SSE2-LABEL: test_zero_v16i16_align1:
-; SSE2:       # %bb.0:
-; SSE2-NEXT:    xorl %eax, %eax
-; SSE2-NEXT:    movntiq %rax, 8(%rdi)
-; SSE2-NEXT:    movntiq %rax, (%rdi)
-; SSE2-NEXT:    movntiq %rax, 24(%rdi)
-; SSE2-NEXT:    movntiq %rax, 16(%rdi)
-; SSE2-NEXT:    retq
-;
-; SSE4A-LABEL: test_zero_v16i16_align1:
-; SSE4A:       # %bb.0:
-; SSE4A-NEXT:    xorps %xmm0, %xmm0
-; SSE4A-NEXT:    movntsd %xmm0, 8(%rdi)
-; SSE4A-NEXT:    movntsd %xmm0, (%rdi)
-; SSE4A-NEXT:    movntsd %xmm0, 24(%rdi)
-; SSE4A-NEXT:    movntsd %xmm0, 16(%rdi)
-; SSE4A-NEXT:    retq
-;
-; SSE41-LABEL: test_zero_v16i16_align1:
-; SSE41:       # %bb.0:
-; SSE41-NEXT:    xorl %eax, %eax
-; SSE41-NEXT:    movntiq %rax, 8(%rdi)
-; SSE41-NEXT:    movntiq %rax, (%rdi)
-; SSE41-NEXT:    movntiq %rax, 24(%rdi)
-; SSE41-NEXT:    movntiq %rax, 16(%rdi)
-; SSE41-NEXT:    retq
-;
-; AVX-LABEL: test_zero_v16i16_align1:
-; AVX:       # %bb.0:
-; AVX-NEXT:    xorl %eax, %eax
-; AVX-NEXT:    movntiq %rax, 8(%rdi)
-; AVX-NEXT:    movntiq %rax, (%rdi)
-; AVX-NEXT:    movntiq %rax, 24(%rdi)
-; AVX-NEXT:    movntiq %rax, 16(%rdi)
-; AVX-NEXT:    retq
-;
-; AVX512-LABEL: test_zero_v16i16_align1:
-; AVX512:       # %bb.0:
-; AVX512-NEXT:    xorl %eax, %eax
-; AVX512-NEXT:    movntiq %rax, 8(%rdi)
-; AVX512-NEXT:    movntiq %rax, (%rdi)
-; AVX512-NEXT:    movntiq %rax, 24(%rdi)
-; AVX512-NEXT:    movntiq %rax, 16(%rdi)
-; AVX512-NEXT:    retq
+; CHECK-LABEL: test_zero_v16i16_align1:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    xorl %eax, %eax
+; CHECK-NEXT:    movntiq %rax, 8(%rdi)
+; CHECK-NEXT:    movntiq %rax, (%rdi)
+; CHECK-NEXT:    movntiq %rax, 24(%rdi)
+; CHECK-NEXT:    movntiq %rax, 16(%rdi)
+; CHECK-NEXT:    retq
   store <16 x i16> zeroinitializer, ptr %dst, align 1, !nontemporal !1
   ret void
 }
 
 define void @test_zero_v32i8_align1(ptr %dst) nounwind {
-; SSE2-LABEL: test_zero_v32i8_align1:
-; SSE2:       # %bb.0:
-; SSE2-NEXT:    xorl %eax, %eax
-; SSE2-NEXT:    movntiq %rax, 8(%rdi)
-; SSE2-NEXT:    movntiq %rax, (%rdi)
-; SSE2-NEXT:    movntiq %rax, 24(%rdi)
-; SSE2-NEXT:    movntiq %rax, 16(%rdi)
-; SSE2-NEXT:    retq
-;
-; SSE4A-LABEL: test_zero_v32i8_align1:
-; SSE4A:       # %bb.0:
-; SSE4A-NEXT:    xorps %xmm0, %xmm0
-; SSE4A-NEXT:    movntsd %xmm0, 8(%rdi)
-; SSE4A-NEXT:    movntsd %xmm0, (%rdi)
-; SSE4A-NEXT:    movntsd %xmm0, 24(%rdi)
-; SSE4A-NEXT:    movntsd %xmm0, 16(%rdi)
-; SSE4A-NEXT:    retq
-;
-; SSE41-LABEL: test_zero_v32i8_align1:
-; SSE41:       # %bb.0:
-; SSE41-NEXT:    xorl %eax, %eax
-; SSE41-NEXT:    movntiq %rax, 8(%rdi)
-; SSE41-NEXT:    movntiq %rax, (%rdi)
-; SSE41-NEXT:    movntiq %rax, 24(%rdi)
-; SSE41-NEXT:    movntiq %rax, 16(%rdi)
-; SSE41-NEXT:    retq
-;
-; AVX-LABEL: test_zero_v32i8_align1:
-; AVX:       # %bb.0:
-; AVX-NEXT:    xorl %eax, %eax
-; AVX-NEXT:    movntiq %rax, 8(%rdi)
-; AVX-NEXT:    movntiq %rax, (%rdi)
-; AVX-NEXT:    movntiq %rax, 24(%rdi)
-; AVX-NEXT:    movntiq %rax, 16(%rdi)
-; AVX-NEXT:    retq
-;
-; AVX512-LABEL: test_zero_v32i8_align1:
-; AVX512:       # %bb.0:
-; AVX512-NEXT:    xorl %eax, %eax
-; AVX512-NEXT:    movntiq %rax, 8(%rdi)
-; AVX512-NEXT:    movntiq %rax, (%rdi)
-; AVX512-NEXT:    movntiq %rax, 24(%rdi)
-; AVX512-NEXT:    movntiq %rax, 16(%rdi)
-; AVX512-NEXT:    retq
+; CHECK-LABEL: test_zero_v32i8_align1:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    xorl %eax, %eax
+; CHECK-NEXT:    movntiq %rax, 8(%rdi)
+; CHECK-NEXT:    movntiq %rax, (%rdi)
+; CHECK-NEXT:    movntiq %rax, 24(%rdi)
+; CHECK-NEXT:    movntiq %rax, 16(%rdi)
+; CHECK-NEXT:    retq
   store <32 x i8> zeroinitializer, ptr %dst, align 1, !nontemporal !1
   ret void
 }
@@ -508,347 +327,86 @@ define void @test_zero_v8f64_align1(ptr %dst) nounwind {
 }
 
 define void @test_zero_v16f32_align1(ptr %dst) nounwind {
-; SSE2-LABEL: test_zero_v16f32_align1:
-; SSE2:       # %bb.0:
-; SSE2-NEXT:    xorl %eax, %eax
-; SSE2-NEXT:    movntiq %rax, 8(%rdi)
-; SSE2-NEXT:    movntiq %rax, (%rdi)
-; SSE2-NEXT:    movntiq %rax, 24(%rdi)
-; SSE2-NEXT:    movntiq %rax, 16(%rdi)
-; SSE2-NEXT:    movntiq %rax, 40(%rdi)
-; SSE2-NEXT:    movntiq %rax, 32(%rdi)
-; SSE2-NEXT:    movntiq %rax, 56(%rdi)
-; SSE2-NEXT:    movntiq %rax, 48(%rdi)
-; SSE2-NEXT:    retq
-;
-; SSE4A-LABEL: test_zero_v16f32_align1:
-; SSE4A:       # %bb.0:
-; SSE4A-NEXT:    xorl %eax, %eax
-; SSE4A-NEXT:    movntiq %rax, 8(%rdi)
-; SSE4A-NEXT:    movntiq %rax, 24(%rdi)
-; SSE4A-NEXT:    movntiq %rax, 40(%rdi)
-; SSE4A-NEXT:    movntiq %rax, 56(%rdi)
-; SSE4A-NEXT:    xorps %xmm0, %xmm0
-; SSE4A-NEXT:    movntsd %xmm0, (%rdi)
-; SSE4A-NEXT:    movntsd %xmm0, 16(%rdi)
-; SSE4A-NEXT:    movntsd %xmm0, 32(%rdi)
-; SSE4A-NEXT:    movntsd %xmm0, 48(%rdi)
-; SSE4A-NEXT:    retq
-;
-; SSE41-LABEL: test_zero_v16f32_align1:
-; SSE41:       # %bb.0:
-; SSE41-NEXT:    xorl %eax, %eax
-; SSE41-NEXT:    movntiq %rax, 8(%rdi)
-; SSE41-NEXT:    movntiq %rax, (%rdi)
-; SSE41-NEXT:    movntiq %rax, 24(%rdi)
-; SSE41-NEXT:    movntiq %rax, 16(%rdi)
-; SSE41-NEXT:    movntiq %rax, 40(%rdi)
-; SSE41-NEXT:    movntiq %rax, 32(%rdi)
-; SSE41-NEXT:    movntiq %rax, 56(%rdi)
-; SSE41-NEXT:    movntiq %rax, 48(%rdi)
-; SSE41-NEXT:    retq
-;
-; AVX-LABEL: test_zero_v16f32_align1:
-; AVX:       # %bb.0:
-; AVX-NEXT:    xorl %eax, %eax
-; AVX-NEXT:    movntiq %rax, 8(%rdi)
-; AVX-NEXT:    movntiq %rax, (%rdi)
-; AVX-NEXT:    movntiq %rax, 24(%rdi)
-; AVX-NEXT:    movntiq %rax, 16(%rdi)
-; AVX-NEXT:    movntiq %rax, 40(%rdi)
-; AVX-NEXT:    movntiq %rax, 32(%rdi)
-; AVX-NEXT:    movntiq %rax, 56(%rdi)
-; AVX-NEXT:    movntiq %rax, 48(%rdi)
-; AVX-NEXT:    retq
-;
-; AVX512-LABEL: test_zero_v16f32_align1:
-; AVX512:       # %bb.0:
-; AVX512-NEXT:    xorl %eax, %eax
-; AVX512-NEXT:    movntiq %rax, 8(%rdi)
-; AVX512-NEXT:    movntiq %rax, (%rdi)
-; AVX512-NEXT:    movntiq %rax, 24(%rdi)
-; AVX512-NEXT:    movntiq %rax, 16(%rdi)
-; AVX512-NEXT:    movntiq %rax, 40(%rdi)
-; AVX512-NEXT:    movntiq %rax, 32(%rdi)
-; AVX512-NEXT:    movntiq %rax, 56(%rdi)
-; AVX512-NEXT:    movntiq %rax, 48(%rdi)
-; AVX512-NEXT:    retq
+; CHECK-LABEL: test_zero_v16f32_align1:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    xorl %eax, %eax
+; CHECK-NEXT:    movntiq %rax, 8(%rdi)
+; CHECK-NEXT:    movntiq %rax, (%rdi)
+; CHECK-NEXT:    movntiq %rax, 24(%rdi)
+; CHECK-NEXT:    movntiq %rax, 16(%rdi)
+; CHECK-NEXT:    movntiq %rax, 40(%rdi)
+; CHECK-NEXT:    movntiq %rax, 32(%rdi)
+; CHECK-NEXT:    movntiq %rax, 56(%rdi)
+; CHECK-NEXT:    movntiq %rax, 48(%rdi)
+; CHECK-NEXT:    retq
   store <16 x float> zeroinitializer, ptr %dst, align 1, !nontemporal !1
   ret void
 }
 
 define void @test_zero_v8i64_align1(ptr %dst) nounwind {
-; SSE2-LABEL: test_zero_v8i64_align1:
-; SSE2:       # %bb.0:
-; SSE2-NEXT:    xorl %eax, %eax
-; SSE2-NEXT:    movntiq %rax, 8(%rdi)
-; SSE2-NEXT:    movntiq %rax, (%rdi)
-; SSE2-NEXT:    movntiq %rax, 24(%rdi)
-; SSE2-NEXT:    movntiq %rax, 16(%rdi)
-; SSE2-NEXT:    movntiq %rax, 40(%rdi)
-; SSE2-NEXT:    movntiq %rax, 32(%rdi)
-; SSE2-NEXT:    movntiq %rax, 56(%rdi)
-; SSE2-NEXT:    movntiq %rax, 48(%rdi)
-; SSE2-NEXT:    retq
-;
-; SSE4A-LABEL: test_zero_v8i64_align1:
-; SSE4A:       # %bb.0:
-; SSE4A-NEXT:    xorps %xmm0, %xmm0
-; SSE4A-NEXT:    movntsd %xmm0, 8(%rdi)
-; SSE4A-NEXT:    movntsd %xmm0, (%rdi)
-; SSE4A-NEXT:    movntsd %xmm0, 24(%rdi)
-; SSE4A-NEXT:    movntsd %xmm0, 16(%rdi)
-; SSE4A-NEXT:    movntsd %xmm0, 40(%rdi)
-; SSE4A-NEXT:    movntsd %xmm0, 32(%rdi)
-; SSE4A-NEXT:    movntsd %xmm0, 56(%rdi)
-; SSE4A-NEXT:    movntsd %xmm0, 48(%rdi)
-; SSE4A-NEXT:    retq
-;
-; SSE41-LABEL: test_zero_v8i64_align1:
-; SSE41:       # %bb.0:
-; SSE41-NEXT:    xorl %eax, %eax
-; SSE41-NEXT:    movntiq %rax, 8(%rdi)
-; SSE41-NEXT:    movntiq %rax, (%rdi)
-; SSE41-NEXT:    movntiq %rax, 24(%rdi)
-; SSE41-NEXT:    movntiq %rax, 16(%rdi)
-; SSE41-NEXT:    movntiq %rax, 40(%rdi)
-; SSE41-NEXT:    movntiq %rax, 32(%rdi)
-; SSE41-NEXT:    movntiq %rax, 56(%rdi)
-; SSE41-NEXT:    movntiq %rax, 48(%rdi)
-; SSE41-NEXT:    retq
-;
-; AVX-LABEL: test_zero_v8i64_align1:
-; AVX:       # %bb.0:
-; AVX-NEXT:    xorl %eax, %eax
-; AVX-NEXT:    movntiq %rax, 8(%rdi)
-; AVX-NEXT:    movntiq %rax, (%rdi)
-; AVX-NEXT:    movntiq %rax, 24(%rdi)
-; AVX-NEXT:    movntiq %rax, 16(%rdi)
-; AVX-NEXT:    movntiq %rax, 40(%rdi)
-; AVX-NEXT:    movntiq %rax, 32(%rdi)
-; AVX-NEXT:    movntiq %rax, 56(%rdi)
-; AVX-NEXT:    movntiq %rax, 48(%rdi)
-; AVX-NEXT:    retq
-;
-; AVX512-LABEL: test_zero_v8i64_align1:
-; AVX512:       # %bb.0:
-; AVX512-NEXT:    xorl %eax, %eax
-; AVX512-NEXT:    movntiq %rax, 8(%rdi)
-; AVX512-NEXT:    movntiq %rax, (%rdi)
-; AVX512-NEXT:    movntiq %rax, 24(%rdi)
-; AVX512-NEXT:    movntiq %rax, 16(%rdi)
-; AVX512-NEXT:    movntiq %rax, 40(%rdi)
-; AVX512-NEXT:    movntiq %rax, 32(%rdi)
-; AVX512-NEXT:    movntiq %rax, 56(%rdi)
-; AVX512-NEXT:    movntiq %rax, 48(%rdi)
-; AVX512-NEXT:    retq
+; CHECK-LABEL: test_zero_v8i64_align1:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    xorl %eax, %eax
+; CHECK-NEXT:    movntiq %rax, 8(%rdi)
+; CHECK-NEXT:    movntiq %rax, (%rdi)
+; CHECK-NEXT:    movntiq %rax, 24(%rdi)
+; CHECK-NEXT:    movntiq %rax, 16(%rdi)
+; CHECK-NEXT:    movntiq %rax, 40(%rdi)
+; CHECK-NEXT:    movntiq %rax, 32(%rdi)
+; CHECK-NEXT:    movntiq %rax, 56(%rdi)
+; CHECK-NEXT:    movntiq %rax, 48(%rdi)
+; CHECK-NEXT:    retq
   store <8 x i64> zeroinitializer, ptr %dst, align 1, !nontemporal !1
   ret void
 }
 
 define void @test_zero_v16i32_align1(ptr %dst) nounwind {
-; SSE2-LABEL: test_zero_v16i32_align1:
-; SSE2:       # %bb.0:
-; SSE2-NEXT:    xorl %eax, %eax
-; SSE2-NEXT:    movntiq %rax, 8(%rdi)
-; SSE2-NEXT:    movntiq %rax, (%rdi)
-; SSE2-NEXT:    movntiq %rax, 24(%rdi)
-; SSE2-NEXT:    movntiq %rax, 16(%rdi)
-; SSE2-NEXT:    movntiq %rax, 40(%rdi)
-; SSE2-NEXT:    movntiq %rax, 32(%rdi)
-; SSE2-NEXT:    movntiq %rax, 56(%rdi)
-; SSE2-NEXT:    movntiq %rax, 48(%rdi)
-; SSE2-NEXT:    retq
-;
-; SSE4A-LABEL: test_zero_v16i32_align1:
-; SSE4A:       # %bb.0:
-; SSE4A-NEXT:    xorps %xmm0, %xmm0
-; SSE4A-NEXT:    movntsd %xmm0, 8(%rdi)
-; SSE4A-NEXT:    movntsd %xmm0, (%rdi)
-; SSE4A-NEXT:    movntsd %xmm0, 24(%rdi)
-; SSE4A-NEXT:    movntsd %xmm0, 16(%rdi)
-; SSE4A-NEXT:    movntsd %xmm0, 40(%rdi)
-; SSE4A-NEXT:    movntsd %xmm0, 32(%rdi)
-; SSE4A-NEXT:    movntsd %xmm0, 56(%rdi)
-; SSE4A-NEXT:    movntsd %xmm0, 48(%rdi)
-; SSE4A-NEXT:    retq
-;
-; SSE41-LABEL: test_zero_v16i32_align1:
-; SSE41:       # %bb.0:
-; SSE41-NEXT:    xorl %eax, %eax
-; SSE41-NEXT:    movntiq %rax, 8(%rdi)
-; SSE41-NEXT:    movntiq %rax, (%rdi)
-; SSE41-NEXT:    movntiq %rax, 24(%rdi)
-; SSE41-NEXT:    movntiq %rax, 16(%rdi)
-; SSE41-NEXT:    movntiq %rax, 40(%rdi)
-; SSE41-NEXT:    movntiq %rax, 32(%rdi)
-; SSE41-NEXT:    movntiq %rax, 56(%rdi)
-; SSE41-NEXT:    movntiq %rax, 48(%rdi)
-; SSE41-NEXT:    retq
-;
-; AVX-LABEL: test_zero_v16i32_align1:
-; AVX:       # %bb.0:
-; AVX-NEXT:    xorl %eax, %eax
-; AVX-NEXT:    movntiq %rax, 8(%rdi)
-; AVX-NEXT:    movntiq %rax, (%rdi)
-; AVX-NEXT:    movntiq %rax, 24(%rdi)
-; AVX-NEXT:    movntiq %rax, 16(%rdi)
-; AVX-NEXT:    movntiq %rax, 40(%rdi)
-; AVX-NEXT:    movntiq %rax, 32(%rdi)
-; AVX-NEXT:    movntiq %rax, 56(%rdi)
-; AVX-NEXT:    movntiq %rax, 48(%rdi)
-; AVX-NEXT:    retq
-;
-; AVX512-LABEL: test_zero_v16i32_align1:
-; AVX512:       # %bb.0:
-; AVX512-NEXT:    xorl %eax, %eax
-; AVX512-NEXT:    movntiq %rax, 8(%rdi)
-; AVX512-NEXT:    movntiq %rax, (%rdi)
-; AVX512-NEXT:    movntiq %rax, 24(%rdi)
-; AVX512-NEXT:    movntiq %rax, 16(%rdi)
-; AVX512-NEXT:    movntiq %rax, 40(%rdi)
-; AVX512-NEXT:    movntiq %rax, 32(%rdi)
-; AVX512-NEXT:    movntiq %rax, 56(%rdi)
-; AVX512-NEXT:    movntiq %rax, 48(%rdi)
-; AVX512-NEXT:    retq
+; CHECK-LABEL: test_zero_v16i32_align1:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    xorl %eax, %eax
+; CHECK-NEXT:    movntiq %rax, 8(%rdi)
+; CHECK-NEXT:    movntiq %rax, (%rdi)
+; CHECK-NEXT:    movntiq %rax, 24(%rdi)
+; CHECK-NEXT:    movntiq %rax, 16(%rdi)
+; CHECK-NEXT:    movntiq %rax, 40(%rdi)
+; CHECK-NEXT:    movntiq %rax, 32(%rdi)
+; CHECK-NEXT:    movntiq %rax, 56(%rdi)
+; CHECK-NEXT:    movntiq %rax, 48(%rdi)
+; CHECK-NEXT:    retq
   store <16 x i32> zeroinitializer, ptr %dst, align 1, !nontemporal !1
   ret void
 }
 
 define void @test_zero_v32i16_align1(ptr %dst) nounwind {
-; SSE2-LABEL: test_zero_v32i16_align1:
-; SSE2:       # %bb.0:
-; SSE2-NEXT:    xorl %eax, %eax
-; SSE2-NEXT:    movntiq %rax, 8(%rdi)
-; SSE2-NEXT:    movntiq %rax, (%rdi)
-; SSE2-NEXT:    movntiq %rax, 24(%rdi)
-; SSE2-NEXT:    movntiq %rax, 16(%rdi)
-; SSE2-NEXT:    movntiq %rax, 40(%rdi)
-; SSE2-NEXT:    movntiq %rax, 32(%rdi)
-; SSE2-NEXT:    movntiq %rax, 56(%rdi)
-; SSE2-NEXT:    movntiq %rax, 48(%rdi)
-; SSE2-NEXT:    retq
-;
-; SSE4A-LABEL: test_zero_v32i16_align1:
-; SSE4A:       # %bb.0:
-; SSE4A-NEXT:    xorps %xmm0, %xmm0
-; SSE4A-NEXT:    movntsd %xmm0, 8(%rdi)
-; SSE4A-NEXT:    movntsd %xmm0, (%rdi)
-; SSE4A-NEXT:    movntsd %xmm0, 24(%rdi)
-; SSE4A-NEXT:    movntsd %xmm0, 16(%rdi)
-; SSE4A-NEXT:    movntsd %xmm0, 40(%rdi)
-; SSE4A-NEXT:    movntsd %xmm0, 32(%rdi)
-; SSE4A-NEXT:    movntsd %xmm0, 56(%rdi)
-; SSE4A-NEXT:    movntsd %xmm0, 48(%rdi)
-; SSE4A-NEXT:    retq
-;
-; SSE41-LABEL: test_zero_v32i16_align1:
-; SSE41:       # %bb.0:
-; SSE41-NEXT:    xorl %eax, %eax
-; SSE41-NEXT:    movntiq %rax, 8(%rdi)
-; SSE41-NEXT:    movntiq %rax, (%rdi)
-; SSE41-NEXT:    movntiq %rax, 24(%rdi)
-; SSE41-NEXT:    movntiq %rax, 16(%rdi)
-; SSE41-NEXT:    movntiq %rax, 40(%rdi)
-; SSE41-NEXT:    movntiq %rax, 32(%rdi)
-; SSE41-NEXT:    movntiq %rax, 56(%rdi)
-; SSE41-NEXT:    movntiq %rax, 48(%rdi)
-; SSE41-NEXT:    retq
-;
-; AVX-LABEL: test_zero_v32i16_align1:
-; AVX:       # %bb.0:
-; AVX-NEXT:    xorl %eax, %eax
-; AVX-NEXT:    movntiq %rax, 8(%rdi)
-; AVX-NEXT:    movntiq %rax, (%rdi)
-; AVX-NEXT:    movntiq %rax, 24(%rdi)
-; AVX-NEXT:    movntiq %rax, 16(%rdi)
-; AVX-NEXT:    movntiq %rax, 40(%rdi)
-; AVX-NEXT:    movntiq %rax, 32(%rdi)
-; AVX-NEXT:    movntiq %rax, 56(%rdi)
-; AVX-NEXT:    movntiq %rax, 48(%rdi)
-; AVX-NEXT:    retq
-;
-; AVX512-LABEL: test_zero_v32i16_align1:
-; AVX512:       # %bb.0:
-; AVX512-NEXT:    xorl %eax, %eax
-; AVX512-NEXT:    movntiq %rax, 8(%rdi)
-; AVX512-NEXT:    movntiq %rax, (%rdi)
-; AVX512-NEXT:    movntiq %rax, 24(%rdi)
-; AVX512-NEXT:    movntiq %rax, 16(%rdi)
-; AVX512-NEXT:    movntiq %rax, 40(%rdi)
-; AVX512-NEXT:    movntiq %rax, 32(%rdi)
-; AVX512-NEXT:    movntiq %rax, 56(%rdi)
-; AVX512-NEXT:    movntiq %rax, 48(%rdi)
-; AVX512-NEXT:    retq
+; CHECK-LABEL: test_zero_v32i16_align1:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    xorl %eax, %eax
+; CHECK-NEXT:    movntiq %rax, 8(%rdi)
+; CHECK-NEXT:    movntiq %rax, (%rdi)
+; CHECK-NEXT:    movntiq %rax, 24(%rdi)
+; CHECK-NEXT:    movntiq %rax, 16(%rdi)
+; CHECK-NEXT:    movntiq %rax, 40(%rdi)
+; CHECK-NEXT:    movntiq %rax, 32(%rdi)
+; CHECK-NEXT:    movntiq %rax, 56(%rdi)
+; CHECK-NEXT:    movntiq %rax, 48(%rdi)
+; CHECK-NEXT:    retq
   store <32 x i16> zeroinitializer, ptr %dst, align 1, !nontemporal !1
   ret void
 }
 
 define void @test_zero_v64i8_align1(ptr %dst) nounwind {
-; SSE2-LABEL: test_zero_v64i8_align1:
-; SSE2:       # %bb.0:
-; SSE2-NEXT:    xorl %eax, %eax
-; SSE2-NEXT:    movntiq %rax, 8(%rdi)
-; SSE2-NEXT:    movntiq %rax, (%rdi)
-; SSE2-NEXT:    movntiq %rax, 24(%rdi)
-; SSE2-NEXT:    movntiq %rax, 16(%rdi)
-; SSE2-NEXT:    movntiq %rax, 40(%rdi)
-; SSE2-NEXT:    movntiq %rax, 32(%rdi)
-; SSE2-NEXT:    movntiq %rax, 56(%rdi)
-; SSE2-NEXT:    movntiq %rax, 48(%rdi)
-; SSE2-NEXT:    retq
-;
-; SSE4A-LABEL: test_zero_v64i8_align1:
-; SSE4A:       # %bb.0:
-; SSE4A-NEXT:    xorps %xmm0, %xmm0
-; SSE4A-NEXT:    movntsd %xmm0, 8(%rdi)
-; SSE4A-NEXT:    movntsd %xmm0, (%rdi)
-; SSE4A-NEXT:    movntsd %xmm0, 24(%rdi)
-; SSE4A-NEXT:    movntsd %xmm0, 16(%rdi)
-; SSE4A-NEXT:    movntsd %xmm0, 40(%rdi)
-; SSE4A-NEXT:    movntsd %xmm0, 32(%rdi)
-; SSE4A-NEXT:    movntsd %xmm0, 56(%rdi)
-; SSE4A-NEXT:    movntsd %xmm0, 48(%rdi)
-; SSE4A-NEXT:    retq
-;
-; SSE41-LABEL: test_zero_v64i8_align1:
-; SSE41:       # %bb.0:
-; SSE41-NEXT:    xorl %eax, %eax
-; SSE41-NEXT:    movntiq %rax, 8(%rdi)
-; SSE41-NEXT:    movntiq %rax, (%rdi)
-; SSE41-NEXT:    movntiq %rax, 24(%rdi)
-; SSE41-NEXT:    movntiq %rax, 16(%rdi)
-; SSE41-NEXT:    movntiq %rax, 40(%rdi)
-; SSE41-NEXT:    movntiq %rax, 32(%rdi)
-; SSE41-NEXT:    movntiq %rax, 56(%rdi)
-; SSE41-NEXT:    movntiq %rax, 48(%rdi)
-; SSE41-NEXT:    retq
-;
-; AVX-LABEL: test_zero_v64i8_align1:
-; AVX:       # %bb.0:
-; AVX-NEXT:    xorl %eax, %eax
-; AVX-NEXT:    movntiq %rax, 8(%rdi)
-; AVX-NEXT:    movntiq %rax, (%rdi)
-; AVX-NEXT:    movntiq %rax, 24(%rdi)
-; AVX-NEXT:    movntiq %rax, 16(%rdi)
-; AVX-NEXT:    movntiq %rax, 40(%rdi)
-; AVX-NEXT:    movntiq %rax, 32(%rdi)
-; AVX-NEXT:    movntiq %rax, 56(%rdi)
-; AVX-NEXT:    movntiq %rax, 48(%rdi)
-; AVX-NEXT:    retq
-;
-; AVX512-LABEL: test_zero_v64i8_align1:
-; AVX512:       # %bb.0:
-; AVX512-NEXT:    xorl %eax, %eax
-; AVX512-NEXT:    movntiq %rax, 8(%rdi)
-; AVX512-NEXT:    movntiq %rax, (%rdi)
-; AVX512-NEXT:    movntiq %rax, 24(%rdi)
-; AVX512-NEXT:    movntiq %rax, 16(%rdi)
-; AVX512-NEXT:    movntiq %rax, 40(%rdi)
-; AVX512-NEXT:    movntiq %rax, 32(%rdi)
-; AVX512-NEXT:    movntiq %rax, 56(%rdi)
-; AVX512-NEXT:    movntiq %rax, 48(%rdi)
-; AVX512-NEXT:    retq
+; CHECK-LABEL: test_zero_v64i8_align1:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    xorl %eax, %eax
+; CHECK-NEXT:    movntiq %rax, 8(%rdi)
+; CHECK-NEXT:    movntiq %rax, (%rdi)
+; CHECK-NEXT:    movntiq %rax, 24(%rdi)
+; CHECK-NEXT:    movntiq %rax, 16(%rdi)
+; CHECK-NEXT:    movntiq %rax, 40(%rdi)
+; CHECK-NEXT:    movntiq %rax, 32(%rdi)
+; CHECK-NEXT:    movntiq %rax, 56(%rdi)
+; CHECK-NEXT:    movntiq %rax, 48(%rdi)
+; CHECK-NEXT:    retq
   store <64 x i8> zeroinitializer, ptr %dst, align 1, !nontemporal !1
   ret void
 }
@@ -1214,3 +772,7 @@ define void @test_zero_v64i8_align32(ptr %dst) nounwind {
 }
 
 !1 = !{i32 1}
+;; NOTE: These prefixes are unused and the list is autogenerated. Do not add tests below this line:
+; SSE2: {{.*}}
+; SSE41: {{.*}}
+; SSE4A: {{.*}}
diff --git a/llvm/test/CodeGen/X86/pr41619.ll b/llvm/test/CodeGen/X86/pr41619.ll
index 7d1d139a38a52..88dcd7798f0c3 100644
--- a/llvm/test/CodeGen/X86/pr41619.ll
+++ b/llvm/test/CodeGen/X86/pr41619.ll
@@ -7,10 +7,9 @@ define void @foo(double %arg) {
 ; CHECK:       ## %bb.0: ## %bb
 ; CHECK-NEXT:    vmovq %xmm0, %rax
 ; CHECK-NEXT:    vmovd %eax, %xmm0
-; CHECK-NEXT:    vxorps %xmm1, %xmm1, %xmm1
 ; CHECK-NEXT:    vmovq %xmm0, %rax
 ; CHECK-NEXT:    movl %eax, (%rax)
-; CHECK-NEXT:    vmovlps %xmm1, (%rax)
+; CHECK-NEXT:    movq $0, (%rax)
 ; CHECK-NEXT:    retq
 bb:
   %tmp = bitcast double %arg to i64
diff --git a/llvm/test/CodeGen/X86/vec_zero_cse.ll b/llvm/test/CodeGen/X86/vec_zero_cse.ll
index 21da191d8d693..d4357aeb2e1de 100644
--- a/llvm/test/CodeGen/X86/vec_zero_cse.ll
+++ b/llvm/test/CodeGen/X86/vec_zero_cse.ll
@@ -16,7 +16,7 @@ define void @test1() {
 ; X86-NEXT:    movl $0, M1+4
 ; X86-NEXT:    movl $0, M1
 ; X86-NEXT:    xorps %xmm0, %xmm0
-; X86-NEXT:    movlps %xmm0, M2
+; X86-NEXT:    movsd %xmm0, M2
 ; X86-NEXT:    retl
 ;
 ; X64-LABEL: test1:
diff --git a/llvm/test/CodeGen/X86/vector-shuffle-combining.ll b/llvm/test/CodeGen/X86/vector-shuffle-combining.ll
index 1b6d2a2c6298e..be4253b6d5d10 100644
--- a/llvm/test/CodeGen/X86/vector-shuffle-combining.ll
+++ b/llvm/test/CodeGen/X86/vector-shuffle-combining.ll
@@ -3225,7 +3225,7 @@ define void @PR43024() {
 ; AVX-NEXT:    vaddss {{\.?LCPI[0-9]+_[0-9]+}}+4(%rip), %xmm0, %xmm0
 ; AVX-NEXT:    vxorps %xmm1, %xmm1, %xmm1
 ; AVX-NEXT:    vaddss %xmm1, %xmm0, %xmm0
-; AVX-NEXT:    vaddss {{\.?LCPI[0-9]+_[0-9]+}}+12(%rip), %xmm0, %xmm0
+; AVX-NEXT:    vaddss %xmm1, %xmm0, %xmm0
 ; AVX-NEXT:    vmovss %xmm0, (%rax)
 ; AVX-NEXT:    retq
   store <4 x float> <float 0x7FF8000000000000, float 0x7FF8000000000000, float 0x0, float 0x0>, ptr undef, align 16