diff --git a/llvm/test/CodeGen/X86/2012-1-10-buildvector.ll b/llvm/test/CodeGen/X86/2012-1-10-buildvector.ll
index 2d1b596..85f4c9e 100644
--- a/llvm/test/CodeGen/X86/2012-1-10-buildvector.ll
+++ b/llvm/test/CodeGen/X86/2012-1-10-buildvector.ll
@@ -19,7 +19,7 @@
 ; CHECK-LABEL: bad_insert:
 ; CHECK:       # BB#0:
 ; CHECK-NEXT:    vmovd {{.*#+}} xmm0 = mem[0],zero,zero,zero
-; CHECK-NEXT:    vmovaps %ymm0, (%eax)
+; CHECK-NEXT:    vmovdqa %ymm0, (%eax)
 ; CHECK-NEXT:    vzeroupper
 ; CHECK-NEXT:    retl
   %v2 = insertelement <8 x i32> zeroinitializer, i32 %t, i32 0
diff --git a/llvm/test/CodeGen/X86/avx2-vbroadcast.ll b/llvm/test/CodeGen/X86/avx2-vbroadcast.ll
index 54f8098..22d017e 100644
--- a/llvm/test/CodeGen/X86/avx2-vbroadcast.ll
+++ b/llvm/test/CodeGen/X86/avx2-vbroadcast.ll
@@ -793,7 +793,7 @@
 ; X64-AVX2-LABEL: _inreg0:
 ; X64-AVX2:       ## BB#0:
 ; X64-AVX2-NEXT:    vmovd %edi, %xmm0
-; X64-AVX2-NEXT:    vbroadcastss %xmm0, %ymm0
+; X64-AVX2-NEXT:    vpbroadcastd %xmm0, %ymm0
 ; X64-AVX2-NEXT:    retq
 ;
 ; X64-AVX512VL-LABEL: _inreg0:
@@ -1469,9 +1469,9 @@
 ; X64-AVX2-NEXT:    vmovaps %xmm0, -{{[0-9]+}}(%rsp)
 ; X64-AVX2-NEXT:    movl (%rdi), %eax
 ; X64-AVX2-NEXT:    vmovd %eax, %xmm1
-; X64-AVX2-NEXT:    vbroadcastss %xmm1, %xmm1
+; X64-AVX2-NEXT:    vpbroadcastd %xmm1, %xmm1
 ; X64-AVX2-NEXT:    vmovaps %xmm0, -{{[0-9]+}}(%rsp)
-; X64-AVX2-NEXT:    vmovaps %xmm1, -{{[0-9]+}}(%rsp)
+; X64-AVX2-NEXT:    vmovdqa %xmm1, -{{[0-9]+}}(%rsp)
 ; X64-AVX2-NEXT:    retq
 ;
 ; X64-AVX512VL-LABEL: isel_crash_4d:
@@ -1538,9 +1538,9 @@
 ; X64-AVX2-NEXT:    vmovaps %ymm0, (%rsp)
 ; X64-AVX2-NEXT:    movl (%rdi), %eax
 ; X64-AVX2-NEXT:    vmovd %eax, %xmm1
-; X64-AVX2-NEXT:    vbroadcastss %xmm1, %ymm1
+; X64-AVX2-NEXT:    vpbroadcastd %xmm1, %ymm1
 ; X64-AVX2-NEXT:    vmovaps %ymm0, {{[0-9]+}}(%rsp)
-; X64-AVX2-NEXT:    vmovaps %ymm1, {{[0-9]+}}(%rsp)
+; X64-AVX2-NEXT:    vmovdqa %ymm1, {{[0-9]+}}(%rsp)
 ; X64-AVX2-NEXT:    movq %rbp, %rsp
 ; X64-AVX2-NEXT:    popq %rbp
 ; X64-AVX2-NEXT:    vzeroupper
@@ -1723,9 +1723,9 @@
 ; X64-AVX2-NEXT:    vmovaps %ymm0, (%rsp)
 ; X64-AVX2-NEXT:    movq (%rdi), %rax
 ; X64-AVX2-NEXT:    vmovq %rax, %xmm1
-; X64-AVX2-NEXT:    vbroadcastsd %xmm1, %ymm1
+; X64-AVX2-NEXT:    vpbroadcastq %xmm1, %ymm1
 ; X64-AVX2-NEXT:    vmovaps %ymm0, {{[0-9]+}}(%rsp)
-; X64-AVX2-NEXT:    vmovaps %ymm1, {{[0-9]+}}(%rsp)
+; X64-AVX2-NEXT:    vmovdqa %ymm1, {{[0-9]+}}(%rsp)
 ; X64-AVX2-NEXT:    movq %rbp, %rsp
 ; X64-AVX2-NEXT:    popq %rbp
 ; X64-AVX2-NEXT:    vzeroupper
diff --git a/llvm/test/CodeGen/X86/clear_upper_vector_element_bits.ll b/llvm/test/CodeGen/X86/clear_upper_vector_element_bits.ll
index 9ae3483..693bf2e 100644
--- a/llvm/test/CodeGen/X86/clear_upper_vector_element_bits.ll
+++ b/llvm/test/CodeGen/X86/clear_upper_vector_element_bits.ll
@@ -303,7 +303,7 @@
 ; SSE:       # BB#0:
 ; SSE-NEXT:    xorl %eax, %eax
 ; SSE-NEXT:    movd %eax, %xmm2
-; SSE-NEXT:    movaps %xmm2, %xmm1
+; SSE-NEXT:    movdqa %xmm2, %xmm1
 ; SSE-NEXT:    shufps {{.*#+}} xmm1 = xmm1[0,0],xmm0[0,0]
 ; SSE-NEXT:    shufps {{.*#+}} xmm1 = xmm1[2,0],xmm0[2,3]
 ; SSE-NEXT:    shufps {{.*#+}} xmm2 = xmm2[0,0],xmm1[2,0]
diff --git a/llvm/test/CodeGen/X86/exedepsfix-broadcast.ll b/llvm/test/CodeGen/X86/exedepsfix-broadcast.ll
index 992b3a3..e67bb0f 100644
--- a/llvm/test/CodeGen/X86/exedepsfix-broadcast.ll
+++ b/llvm/test/CodeGen/X86/exedepsfix-broadcast.ll
@@ -38,8 +38,8 @@
 ; CHECK-LABEL: ExeDepsFix_broadcastss_inreg:
 ; CHECK:       ## BB#0:
 ; CHECK-NEXT:    vmovd %edi, %xmm2
-; CHECK-NEXT:    vbroadcastss %xmm2, %xmm2
-; CHECK-NEXT:    vandps %xmm2, %xmm0, %xmm0
+; CHECK-NEXT:    vpbroadcastd %xmm2, %xmm2
+; CHECK-NEXT:    vpand %xmm2, %xmm0, %xmm0
 ; CHECK-NEXT:    vmaxps %xmm1, %xmm0, %xmm0
 ; CHECK-NEXT:    retq
   %bitcast = bitcast <4 x float> %arg to <4 x i32>
@@ -56,8 +56,8 @@
 ; CHECK-LABEL: ExeDepsFix_broadcastss256_inreg:
 ; CHECK:       ## BB#0:
 ; CHECK-NEXT:    vmovd %edi, %xmm2
-; CHECK-NEXT:    vbroadcastss %xmm2, %ymm2
-; CHECK-NEXT:    vandps %ymm2, %ymm0, %ymm0
+; CHECK-NEXT:    vpbroadcastd %xmm2, %ymm2
+; CHECK-NEXT:    vpand %ymm2, %ymm0, %ymm0
 ; CHECK-NEXT:    vmaxps %ymm1, %ymm0, %ymm0
 ; CHECK-NEXT:    retq
   %bitcast = bitcast <8 x float> %arg to <8 x i32>
@@ -124,8 +124,8 @@
 ; CHECK-LABEL: ExeDepsFix_broadcastsd256_inreg:
 ; CHECK:       ## BB#0:
 ; CHECK-NEXT:    vmovq %rdi, %xmm2
-; CHECK-NEXT:    vbroadcastsd %xmm2, %ymm2
-; CHECK-NEXT:    vandpd %ymm2, %ymm0, %ymm0
+; CHECK-NEXT:    vpbroadcastq %xmm2, %ymm2
+; CHECK-NEXT:    vpand %ymm2, %ymm0, %ymm0
 ; CHECK-NEXT:    vmaxpd %ymm1, %ymm0, %ymm0
 ; CHECK-NEXT:    retq
   %bitcast = bitcast <4 x double> %arg to <4 x i64>
diff --git a/llvm/test/CodeGen/X86/extractelement-index.ll b/llvm/test/CodeGen/X86/extractelement-index.ll
index fc34c56..13448a1 100644
--- a/llvm/test/CodeGen/X86/extractelement-index.ll
+++ b/llvm/test/CodeGen/X86/extractelement-index.ll
@@ -244,12 +244,19 @@
 ; SSE-NEXT:    movd %xmm1, %eax
 ; SSE-NEXT:    retq
 ;
-; AVX-LABEL: extractelement_v8i32_0:
-; AVX:       # BB#0:
-; AVX-NEXT:    vextractf128 $1, %ymm0, %xmm0
-; AVX-NEXT:    vmovd %xmm0, %eax
-; AVX-NEXT:    vzeroupper
-; AVX-NEXT:    retq
+; AVX1-LABEL: extractelement_v8i32_0:
+; AVX1:       # BB#0:
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm0
+; AVX1-NEXT:    vmovd %xmm0, %eax
+; AVX1-NEXT:    vzeroupper
+; AVX1-NEXT:    retq
+;
+; AVX2-LABEL: extractelement_v8i32_0:
+; AVX2:       # BB#0:
+; AVX2-NEXT:    vextracti128 $1, %ymm0, %xmm0
+; AVX2-NEXT:    vmovd %xmm0, %eax
+; AVX2-NEXT:    vzeroupper
+; AVX2-NEXT:    retq
   %b = extractelement <8 x i32> %a, i256 4
   ret i32 %b
 }
@@ -260,12 +267,19 @@
 ; SSE-NEXT:    movd %xmm1, %eax
 ; SSE-NEXT:    retq
 ;
-; AVX-LABEL: extractelement_v8i32_4:
-; AVX:       # BB#0:
-; AVX-NEXT:    vextractf128 $1, %ymm0, %xmm0
-; AVX-NEXT:    vmovd %xmm0, %eax
-; AVX-NEXT:    vzeroupper
-; AVX-NEXT:    retq
+; AVX1-LABEL: extractelement_v8i32_4:
+; AVX1:       # BB#0:
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm0
+; AVX1-NEXT:    vmovd %xmm0, %eax
+; AVX1-NEXT:    vzeroupper
+; AVX1-NEXT:    retq
+;
+; AVX2-LABEL: extractelement_v8i32_4:
+; AVX2:       # BB#0:
+; AVX2-NEXT:    vextracti128 $1, %ymm0, %xmm0
+; AVX2-NEXT:    vmovd %xmm0, %eax
+; AVX2-NEXT:    vzeroupper
+; AVX2-NEXT:    retq
   %b = extractelement <8 x i32> %a, i256 4
   ret i32 %b
 }
diff --git a/llvm/test/CodeGen/X86/fp-logic.ll b/llvm/test/CodeGen/X86/fp-logic.ll
index 301fa8f..d940101 100644
--- a/llvm/test/CodeGen/X86/fp-logic.ll
+++ b/llvm/test/CodeGen/X86/fp-logic.ll
@@ -76,7 +76,7 @@
 ; CHECK-LABEL: f5:
 ; CHECK:       # BB#0:
 ; CHECK-NEXT:    movd %edi, %xmm1
-; CHECK-NEXT:    andps %xmm1, %xmm0
+; CHECK-NEXT:    pand %xmm1, %xmm0
 ; CHECK-NEXT:    retq
 ;
   %bc1 = bitcast float %x to i32
@@ -91,7 +91,7 @@
 ; CHECK-LABEL: f6:
 ; CHECK:       # BB#0:
 ; CHECK-NEXT:    movd %edi, %xmm1
-; CHECK-NEXT:    andps %xmm1, %xmm0
+; CHECK-NEXT:    pand %xmm1, %xmm0
 ; CHECK-NEXT:    retq
 ;
   %bc1 = bitcast float %x to i32
@@ -135,7 +135,7 @@
 define i32 @f9(float %x, float %y) {
 ; CHECK-LABEL: f9:
 ; CHECK:       # BB#0:
-; CHECK-NEXT:    andps %xmm1, %xmm0
+; CHECK-NEXT:    pand %xmm1, %xmm0
 ; CHECK-NEXT:    movd %xmm0, %eax
 ; CHECK-NEXT:    retq
 ;
diff --git a/llvm/test/CodeGen/X86/masked_memop.ll b/llvm/test/CodeGen/X86/masked_memop.ll
index 98b1e87..7e1837c 100644
--- a/llvm/test/CodeGen/X86/masked_memop.ll
+++ b/llvm/test/CodeGen/X86/masked_memop.ll
@@ -1019,7 +1019,7 @@
 ; AVX512F-LABEL: one_mask_bit_set3:
 ; AVX512F:       ## BB#0:
 ; AVX512F-NEXT:    vextractf128 $1, %ymm0, %xmm0
-; AVX512F-NEXT:    vmovq %xmm0, 16(%rdi)
+; AVX512F-NEXT:    vmovlps %xmm0, 16(%rdi)
 ; AVX512F-NEXT:    retq
 ;
 ; SKX-LABEL: one_mask_bit_set3:
diff --git a/llvm/test/CodeGen/X86/merge-consecutive-loads-128.ll b/llvm/test/CodeGen/X86/merge-consecutive-loads-128.ll
index bb60440..1f2bd4b 100644
--- a/llvm/test/CodeGen/X86/merge-consecutive-loads-128.ll
+++ b/llvm/test/CodeGen/X86/merge-consecutive-loads-128.ll
@@ -935,26 +935,14 @@
 ; SSE-LABEL: merge_4i32_i32_combine:
 ; SSE:       # BB#0:
 ; SSE-NEXT:    movd {{.*#+}} xmm0 = mem[0],zero,zero,zero
-; SSE-NEXT:    movaps %xmm0, (%rdi)
+; SSE-NEXT:    movdqa %xmm0, (%rdi)
 ; SSE-NEXT:    retq
 ;
-; AVX1-LABEL: merge_4i32_i32_combine:
-; AVX1:       # BB#0:
-; AVX1-NEXT:    vmovd {{.*#+}} xmm0 = mem[0],zero,zero,zero
-; AVX1-NEXT:    vmovaps %xmm0, (%rdi)
-; AVX1-NEXT:    retq
-;
-; AVX2-LABEL: merge_4i32_i32_combine:
-; AVX2:       # BB#0:
-; AVX2-NEXT:    vmovd {{.*#+}} xmm0 = mem[0],zero,zero,zero
-; AVX2-NEXT:    vmovaps %xmm0, (%rdi)
-; AVX2-NEXT:    retq
-;
-; AVX512F-LABEL: merge_4i32_i32_combine:
-; AVX512F:       # BB#0:
-; AVX512F-NEXT:    vmovd {{.*#+}} xmm0 = mem[0],zero,zero,zero
-; AVX512F-NEXT:    vmovdqa %xmm0, (%rdi)
-; AVX512F-NEXT:    retq
+; AVX-LABEL: merge_4i32_i32_combine:
+; AVX:       # BB#0:
+; AVX-NEXT:    vmovd {{.*#+}} xmm0 = mem[0],zero,zero,zero
+; AVX-NEXT:    vmovdqa %xmm0, (%rdi)
+; AVX-NEXT:    retq
 ;
 ; X32-SSE1-LABEL: merge_4i32_i32_combine:
 ; X32-SSE1:       # BB#0:
@@ -972,7 +960,7 @@
 ; X32-SSE41-NEXT:    movl {{[0-9]+}}(%esp), %eax
 ; X32-SSE41-NEXT:    movl {{[0-9]+}}(%esp), %ecx
 ; X32-SSE41-NEXT:    movd {{.*#+}} xmm0 = mem[0],zero,zero,zero
-; X32-SSE41-NEXT:    movaps %xmm0, (%eax)
+; X32-SSE41-NEXT:    movdqa %xmm0, (%eax)
 ; X32-SSE41-NEXT:    retl
  %1 = getelementptr i32, i32* %src, i32 0
  %2 = load i32, i32* %1
diff --git a/llvm/test/CodeGen/X86/pshufb-mask-comments.ll b/llvm/test/CodeGen/X86/pshufb-mask-comments.ll
index 8364915..d447bf9 100644
--- a/llvm/test/CodeGen/X86/pshufb-mask-comments.ll
+++ b/llvm/test/CodeGen/X86/pshufb-mask-comments.ll
@@ -56,7 +56,7 @@
 ; CHECK:       # BB#0:
 ; CHECK-NEXT:    movl $1, %eax
 ; CHECK-NEXT:    movd %rax, %xmm1
-; CHECK-NEXT:    movaps %xmm1, (%rax)
+; CHECK-NEXT:    movdqa %xmm1, (%rax)
 ; CHECK-NEXT:    movdqa {{.*#+}} xmm1 = [1,1]
 ; CHECK-NEXT:    movdqa %xmm1, (%rax)
 ; CHECK-NEXT:    pshufb %xmm1, %xmm0
diff --git a/llvm/test/CodeGen/X86/scalar-int-to-fp.ll b/llvm/test/CodeGen/X86/scalar-int-to-fp.ll
index 9ea86b0..d39b206 100644
--- a/llvm/test/CodeGen/X86/scalar-int-to-fp.ll
+++ b/llvm/test/CodeGen/X86/scalar-int-to-fp.ll
@@ -75,7 +75,7 @@
 
 ; CHECK-LABEL: u64_to_f
 ; AVX512_32: vmovq {{.*#+}} xmm0 = mem[0],zero
-; AVX512_32: vmovlps %xmm0, {{[0-9]+}}(%esp)
+; AVX512_32: vmovq %xmm0, {{[0-9]+}}(%esp)
 ; AVX512_32: fildll
 
 ; AVX512_64: vcvtusi2ssq
diff --git a/llvm/test/CodeGen/X86/uint_to_fp-2.ll b/llvm/test/CodeGen/X86/uint_to_fp-2.ll
index d2b78a8..fbfd1bd 100644
--- a/llvm/test/CodeGen/X86/uint_to_fp-2.ll
+++ b/llvm/test/CodeGen/X86/uint_to_fp-2.ll
@@ -8,7 +8,7 @@
 ; CHECK-NEXT:    pushl %eax
 ; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
 ; CHECK-NEXT:    movd {{.*#+}} xmm1 = mem[0],zero,zero,zero
-; CHECK-NEXT:    orpd %xmm0, %xmm1
+; CHECK-NEXT:    por %xmm0, %xmm1
 ; CHECK-NEXT:    subsd %xmm0, %xmm1
 ; CHECK-NEXT:    xorps %xmm0, %xmm0
 ; CHECK-NEXT:    cvtsd2ss %xmm1, %xmm0
diff --git a/llvm/test/CodeGen/X86/vec_fp_to_int.ll b/llvm/test/CodeGen/X86/vec_fp_to_int.ll
index 4641e4a..4ae95ba 100644
--- a/llvm/test/CodeGen/X86/vec_fp_to_int.ll
+++ b/llvm/test/CodeGen/X86/vec_fp_to_int.ll
@@ -2343,7 +2343,7 @@
 ; SSE-NEXT:    movq %rcx, %rsi
 ; SSE-NEXT:    callq __fixtfdi
 ; SSE-NEXT:    movd %rax, %xmm0
-; SSE-NEXT:    movaps %xmm0, (%rsp) # 16-byte Spill
+; SSE-NEXT:    movdqa %xmm0, (%rsp) # 16-byte Spill
 ; SSE-NEXT:    movq %rbx, %rdi
 ; SSE-NEXT:    movq %r14, %rsi
 ; SSE-NEXT:    callq __fixtfdi
@@ -2368,7 +2368,7 @@
 ; VEX-NEXT:    movq %rcx, %rsi
 ; VEX-NEXT:    callq __fixtfdi
 ; VEX-NEXT:    vmovq %rax, %xmm0
-; VEX-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
+; VEX-NEXT:    vmovdqa %xmm0, (%rsp) # 16-byte Spill
 ; VEX-NEXT:    movq %rbx, %rdi
 ; VEX-NEXT:    movq %r14, %rsi
 ; VEX-NEXT:    callq __fixtfdi
diff --git a/llvm/test/CodeGen/X86/vec_ins_extract-1.ll b/llvm/test/CodeGen/X86/vec_ins_extract-1.ll
index 8019e11..8adc0e6 100644
--- a/llvm/test/CodeGen/X86/vec_ins_extract-1.ll
+++ b/llvm/test/CodeGen/X86/vec_ins_extract-1.ll
@@ -90,7 +90,7 @@
 ; X32-NEXT:    movl %esp, %ebp
 ; X32-NEXT:    andl $-16, %esp
 ; X32-NEXT:    subl $32, %esp
-; X32-NEXT:    movaps %xmm0, (%esp)
+; X32-NEXT:    movdqa %xmm0, (%esp)
 ; X32-NEXT:    movd %xmm0, (%esp,%eax,4)
 ; X32-NEXT:    movaps (%esp), %xmm0
 ; X32-NEXT:    movl %ebp, %esp
@@ -99,7 +99,7 @@
 ;
 ; X64-LABEL: t3:
 ; X64:       # BB#0:
-; X64-NEXT:    movaps %xmm0, -{{[0-9]+}}(%rsp)
+; X64-NEXT:    movdqa %xmm0, -{{[0-9]+}}(%rsp)
 ; X64-NEXT:    movslq %edi, %rax
 ; X64-NEXT:    movd %xmm0, -24(%rsp,%rax,4)
 ; X64-NEXT:    movaps -{{[0-9]+}}(%rsp), %xmm0