llvm-project/llvm/test/CodeGen/X86/avx512bwvl-intrinsics.ll

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=+avx512bw,+avx512vl --show-mc-encoding | FileCheck %s --check-prefixes=CHECK,X86
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512bw,+avx512vl --show-mc-encoding | FileCheck %s --check-prefixes=CHECK,X64

define <8 x i16> @test_mask_packs_epi32_rr_128(<4 x i32> %a, <4 x i32> %b) {
; CHECK-LABEL: test_mask_packs_epi32_rr_128:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vpackssdw %xmm1, %xmm0, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6b,0xc1]
; CHECK-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
  %1 = call <8 x i16> @llvm.x86.sse2.packssdw.128(<4 x i32> %a, <4 x i32> %b)
  ret <8 x i16> %1
}

define <8 x i16> @test_mask_packs_epi32_rrk_128(<4 x i32> %a, <4 x i32> %b, <8 x i16> %passThru, i8 %mask) {
; X86-LABEL: test_mask_packs_epi32_rrk_128:
; X86:       # %bb.0:
; X86-NEXT:    movzbl {{[0-9]+}}(%esp), %eax # encoding: [0x0f,0xb6,0x44,0x24,0x04]
; X86-NEXT:    kmovd %eax, %k1 # encoding: [0xc5,0xfb,0x92,0xc8]
; X86-NEXT:    vpackssdw %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf1,0x7d,0x09,0x6b,0xd1]
; X86-NEXT:    vmovdqa %xmm2, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xc2]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_packs_epi32_rrk_128:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpackssdw %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf1,0x7d,0x09,0x6b,0xd1]
; X64-NEXT:    vmovdqa %xmm2, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xc2]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = call <8 x i16> @llvm.x86.sse2.packssdw.128(<4 x i32> %a, <4 x i32> %b)
  %2 = bitcast i8 %mask to <8 x i1>
  %3 = select <8 x i1> %2, <8 x i16> %1, <8 x i16> %passThru
  ret <8 x i16> %3
}

define <8 x i16> @test_mask_packs_epi32_rrkz_128(<4 x i32> %a, <4 x i32> %b, i8 %mask) {
; X86-LABEL: test_mask_packs_epi32_rrkz_128:
; X86:       # %bb.0:
; X86-NEXT:    movzbl {{[0-9]+}}(%esp), %eax # encoding: [0x0f,0xb6,0x44,0x24,0x04]
; X86-NEXT:    kmovd %eax, %k1 # encoding: [0xc5,0xfb,0x92,0xc8]
; X86-NEXT:    vpackssdw %xmm1, %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf1,0x7d,0x89,0x6b,0xc1]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_packs_epi32_rrkz_128:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpackssdw %xmm1, %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf1,0x7d,0x89,0x6b,0xc1]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = call <8 x i16> @llvm.x86.sse2.packssdw.128(<4 x i32> %a, <4 x i32> %b)
  %2 = bitcast i8 %mask to <8 x i1>
  %3 = select <8 x i1> %2, <8 x i16> %1, <8 x i16> zeroinitializer
  ret <8 x i16> %3
}

define <8 x i16> @test_mask_packs_epi32_rm_128(<4 x i32> %a, <4 x i32>* %ptr_b) {
; X86-LABEL: test_mask_packs_epi32_rm_128:
; X86:       # %bb.0:
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT:    vpackssdw (%eax), %xmm0, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6b,0x00]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_packs_epi32_rm_128:
; X64:       # %bb.0:
; X64-NEXT:    vpackssdw (%rdi), %xmm0, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6b,0x07]
; X64-NEXT:    retq # encoding: [0xc3]
  %b = load <4 x i32>, <4 x i32>* %ptr_b
  %1 = call <8 x i16> @llvm.x86.sse2.packssdw.128(<4 x i32> %a, <4 x i32> %b)
  ret <8 x i16> %1
}

define <8 x i16> @test_mask_packs_epi32_rmk_128(<4 x i32> %a, <4 x i32>* %ptr_b, <8 x i16> %passThru, i8 %mask) {
; X86-LABEL: test_mask_packs_epi32_rmk_128:
; X86:       # %bb.0:
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT:    movzbl {{[0-9]+}}(%esp), %ecx # encoding: [0x0f,0xb6,0x4c,0x24,0x08]
; X86-NEXT:    kmovd %ecx, %k1 # encoding: [0xc5,0xfb,0x92,0xc9]
; X86-NEXT:    vpackssdw (%eax), %xmm0, %xmm1 {%k1} # encoding: [0x62,0xf1,0x7d,0x09,0x6b,0x08]
; X86-NEXT:    vmovdqa %xmm1, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xc1]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_packs_epi32_rmk_128:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT:    vpackssdw (%rdi), %xmm0, %xmm1 {%k1} # encoding: [0x62,0xf1,0x7d,0x09,0x6b,0x0f]
; X64-NEXT:    vmovdqa %xmm1, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xc1]
; X64-NEXT:    retq # encoding: [0xc3]
  %b = load <4 x i32>, <4 x i32>* %ptr_b
  %1 = call <8 x i16> @llvm.x86.sse2.packssdw.128(<4 x i32> %a, <4 x i32> %b)
  %2 = bitcast i8 %mask to <8 x i1>
  %3 = select <8 x i1> %2, <8 x i16> %1, <8 x i16> %passThru
  ret <8 x i16> %3
}

define <8 x i16> @test_mask_packs_epi32_rmkz_128(<4 x i32> %a, <4 x i32>* %ptr_b, i8 %mask) {
; X86-LABEL: test_mask_packs_epi32_rmkz_128:
; X86:       # %bb.0:
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT:    movzbl {{[0-9]+}}(%esp), %ecx # encoding: [0x0f,0xb6,0x4c,0x24,0x08]
; X86-NEXT:    kmovd %ecx, %k1 # encoding: [0xc5,0xfb,0x92,0xc9]
; X86-NEXT:    vpackssdw (%eax), %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf1,0x7d,0x89,0x6b,0x00]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_packs_epi32_rmkz_128:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT:    vpackssdw (%rdi), %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf1,0x7d,0x89,0x6b,0x07]
; X64-NEXT:    retq # encoding: [0xc3]
  %b = load <4 x i32>, <4 x i32>* %ptr_b
  %1 = call <8 x i16> @llvm.x86.sse2.packssdw.128(<4 x i32> %a, <4 x i32> %b)
  %2 = bitcast i8 %mask to <8 x i1>
  %3 = select <8 x i1> %2, <8 x i16> %1, <8 x i16> zeroinitializer
  ret <8 x i16> %3
}

define <8 x i16> @test_mask_packs_epi32_rmb_128(<4 x i32> %a, i32* %ptr_b) {
; X86-LABEL: test_mask_packs_epi32_rmb_128:
; X86:       # %bb.0:
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT:    vpackssdw (%eax){1to4}, %xmm0, %xmm0 # encoding: [0x62,0xf1,0x7d,0x18,0x6b,0x00]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_packs_epi32_rmb_128:
; X64:       # %bb.0:
; X64-NEXT:    vpackssdw (%rdi){1to4}, %xmm0, %xmm0 # encoding: [0x62,0xf1,0x7d,0x18,0x6b,0x07]
; X64-NEXT:    retq # encoding: [0xc3]
  %q = load i32, i32* %ptr_b
  %vecinit.i = insertelement <4 x i32> undef, i32 %q, i32 0
  %b = shufflevector <4 x i32> %vecinit.i, <4 x i32> undef, <4 x i32> zeroinitializer
  %1 = call <8 x i16> @llvm.x86.sse2.packssdw.128(<4 x i32> %a, <4 x i32> %b)
  ret <8 x i16> %1
}

define <8 x i16> @test_mask_packs_epi32_rmbk_128(<4 x i32> %a, i32* %ptr_b, <8 x i16> %passThru, i8 %mask) {
; X86-LABEL: test_mask_packs_epi32_rmbk_128:
; X86:       # %bb.0:
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT:    movzbl {{[0-9]+}}(%esp), %ecx # encoding: [0x0f,0xb6,0x4c,0x24,0x08]
; X86-NEXT:    kmovd %ecx, %k1 # encoding: [0xc5,0xfb,0x92,0xc9]
; X86-NEXT:    vpackssdw (%eax){1to4}, %xmm0, %xmm1 {%k1} # encoding: [0x62,0xf1,0x7d,0x19,0x6b,0x08]
; X86-NEXT:    vmovdqa %xmm1, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xc1]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_packs_epi32_rmbk_128:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT:    vpackssdw (%rdi){1to4}, %xmm0, %xmm1 {%k1} # encoding: [0x62,0xf1,0x7d,0x19,0x6b,0x0f]
; X64-NEXT:    vmovdqa %xmm1, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xc1]
; X64-NEXT:    retq # encoding: [0xc3]
  %q = load i32, i32* %ptr_b
  %vecinit.i = insertelement <4 x i32> undef, i32 %q, i32 0
  %b = shufflevector <4 x i32> %vecinit.i, <4 x i32> undef, <4 x i32> zeroinitializer
  %1 = call <8 x i16> @llvm.x86.sse2.packssdw.128(<4 x i32> %a, <4 x i32> %b)
  %2 = bitcast i8 %mask to <8 x i1>
  %3 = select <8 x i1> %2, <8 x i16> %1, <8 x i16> %passThru
  ret <8 x i16> %3
}

define <8 x i16> @test_mask_packs_epi32_rmbkz_128(<4 x i32> %a, i32* %ptr_b, i8 %mask) {
; X86-LABEL: test_mask_packs_epi32_rmbkz_128:
; X86:       # %bb.0:
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT:    movzbl {{[0-9]+}}(%esp), %ecx # encoding: [0x0f,0xb6,0x4c,0x24,0x08]
; X86-NEXT:    kmovd %ecx, %k1 # encoding: [0xc5,0xfb,0x92,0xc9]
; X86-NEXT:    vpackssdw (%eax){1to4}, %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf1,0x7d,0x99,0x6b,0x00]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_packs_epi32_rmbkz_128:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT:    vpackssdw (%rdi){1to4}, %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf1,0x7d,0x99,0x6b,0x07]
; X64-NEXT:    retq # encoding: [0xc3]
  %q = load i32, i32* %ptr_b
  %vecinit.i = insertelement <4 x i32> undef, i32 %q, i32 0
  %b = shufflevector <4 x i32> %vecinit.i, <4 x i32> undef, <4 x i32> zeroinitializer
  %1 = call <8 x i16> @llvm.x86.sse2.packssdw.128(<4 x i32> %a, <4 x i32> %b)
  %2 = bitcast i8 %mask to <8 x i1>
  %3 = select <8 x i1> %2, <8 x i16> %1, <8 x i16> zeroinitializer
  ret <8 x i16> %3
}

declare <8 x i16> @llvm.x86.sse2.packssdw.128(<4 x i32>, <4 x i32>)

define <16 x i16> @test_mask_packs_epi32_rr_256(<8 x i32> %a, <8 x i32> %b) {
; CHECK-LABEL: test_mask_packs_epi32_rr_256:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vpackssdw %ymm1, %ymm0, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6b,0xc1]
; CHECK-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
  %1 = call <16 x i16> @llvm.x86.avx2.packssdw(<8 x i32> %a, <8 x i32> %b)
  ret <16 x i16> %1
}

define <16 x i16> @test_mask_packs_epi32_rrk_256(<8 x i32> %a, <8 x i32> %b, <16 x i16> %passThru, i16 %mask) {
; X86-LABEL: test_mask_packs_epi32_rrk_256:
; X86:       # %bb.0:
; X86-NEXT:    kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x04]
; X86-NEXT:    vpackssdw %ymm1, %ymm0, %ymm2 {%k1} # encoding: [0x62,0xf1,0x7d,0x29,0x6b,0xd1]
; X86-NEXT:    vmovdqa %ymm2, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xc2]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_packs_epi32_rrk_256:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpackssdw %ymm1, %ymm0, %ymm2 {%k1} # encoding: [0x62,0xf1,0x7d,0x29,0x6b,0xd1]
; X64-NEXT:    vmovdqa %ymm2, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xc2]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = call <16 x i16> @llvm.x86.avx2.packssdw(<8 x i32> %a, <8 x i32> %b)
  %2 = bitcast i16 %mask to <16 x i1>
  %3 = select <16 x i1> %2, <16 x i16> %1, <16 x i16> %passThru
  ret <16 x i16> %3
}

define <16 x i16> @test_mask_packs_epi32_rrkz_256(<8 x i32> %a, <8 x i32> %b, i16 %mask) {
; X86-LABEL: test_mask_packs_epi32_rrkz_256:
; X86:       # %bb.0:
; X86-NEXT:    kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x04]
; X86-NEXT:    vpackssdw %ymm1, %ymm0, %ymm0 {%k1} {z} # encoding: [0x62,0xf1,0x7d,0xa9,0x6b,0xc1]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_packs_epi32_rrkz_256:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpackssdw %ymm1, %ymm0, %ymm0 {%k1} {z} # encoding: [0x62,0xf1,0x7d,0xa9,0x6b,0xc1]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = call <16 x i16> @llvm.x86.avx2.packssdw(<8 x i32> %a, <8 x i32> %b)
  %2 = bitcast i16 %mask to <16 x i1>
  %3 = select <16 x i1> %2, <16 x i16> %1, <16 x i16> zeroinitializer
  ret <16 x i16> %3
}

define <16 x i16> @test_mask_packs_epi32_rm_256(<8 x i32> %a, <8 x i32>* %ptr_b) {
; X86-LABEL: test_mask_packs_epi32_rm_256:
; X86:       # %bb.0:
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT:    vpackssdw (%eax), %ymm0, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6b,0x00]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_packs_epi32_rm_256:
; X64:       # %bb.0:
; X64-NEXT:    vpackssdw (%rdi), %ymm0, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6b,0x07]
; X64-NEXT:    retq # encoding: [0xc3]
  %b = load <8 x i32>, <8 x i32>* %ptr_b
  %1 = call <16 x i16> @llvm.x86.avx2.packssdw(<8 x i32> %a, <8 x i32> %b)
  ret <16 x i16> %1
}

define <16 x i16> @test_mask_packs_epi32_rmk_256(<8 x i32> %a, <8 x i32>* %ptr_b, <16 x i16> %passThru, i16 %mask) {
; X86-LABEL: test_mask_packs_epi32_rmk_256:
; X86:       # %bb.0:
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT:    kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x08]
; X86-NEXT:    vpackssdw (%eax), %ymm0, %ymm1 {%k1} # encoding: [0x62,0xf1,0x7d,0x29,0x6b,0x08]
; X86-NEXT:    vmovdqa %ymm1, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xc1]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_packs_epi32_rmk_256:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT:    vpackssdw (%rdi), %ymm0, %ymm1 {%k1} # encoding: [0x62,0xf1,0x7d,0x29,0x6b,0x0f]
; X64-NEXT:    vmovdqa %ymm1, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xc1]
; X64-NEXT:    retq # encoding: [0xc3]
  %b = load <8 x i32>, <8 x i32>* %ptr_b
  %1 = call <16 x i16> @llvm.x86.avx2.packssdw(<8 x i32> %a, <8 x i32> %b)
  %2 = bitcast i16 %mask to <16 x i1>
  %3 = select <16 x i1> %2, <16 x i16> %1, <16 x i16> %passThru
  ret <16 x i16> %3
}

define <16 x i16> @test_mask_packs_epi32_rmkz_256(<8 x i32> %a, <8 x i32>* %ptr_b, i16 %mask) {
; X86-LABEL: test_mask_packs_epi32_rmkz_256:
; X86:       # %bb.0:
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT:    kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x08]
; X86-NEXT:    vpackssdw (%eax), %ymm0, %ymm0 {%k1} {z} # encoding: [0x62,0xf1,0x7d,0xa9,0x6b,0x00]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_packs_epi32_rmkz_256:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT:    vpackssdw (%rdi), %ymm0, %ymm0 {%k1} {z} # encoding: [0x62,0xf1,0x7d,0xa9,0x6b,0x07]
; X64-NEXT:    retq # encoding: [0xc3]
  %b = load <8 x i32>, <8 x i32>* %ptr_b
  %1 = call <16 x i16> @llvm.x86.avx2.packssdw(<8 x i32> %a, <8 x i32> %b)
  %2 = bitcast i16 %mask to <16 x i1>
  %3 = select <16 x i1> %2, <16 x i16> %1, <16 x i16> zeroinitializer
  ret <16 x i16> %3
}

define <16 x i16> @test_mask_packs_epi32_rmb_256(<8 x i32> %a, i32* %ptr_b) {
; X86-LABEL: test_mask_packs_epi32_rmb_256:
; X86:       # %bb.0:
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT:    vpackssdw (%eax){1to8}, %ymm0, %ymm0 # encoding: [0x62,0xf1,0x7d,0x38,0x6b,0x00]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_packs_epi32_rmb_256:
; X64:       # %bb.0:
; X64-NEXT:    vpackssdw (%rdi){1to8}, %ymm0, %ymm0 # encoding: [0x62,0xf1,0x7d,0x38,0x6b,0x07]
; X64-NEXT:    retq # encoding: [0xc3]
  %q = load i32, i32* %ptr_b
  %vecinit.i = insertelement <8 x i32> undef, i32 %q, i32 0
  %b = shufflevector <8 x i32> %vecinit.i, <8 x i32> undef, <8 x i32> zeroinitializer
  %1 = call <16 x i16> @llvm.x86.avx2.packssdw(<8 x i32> %a, <8 x i32> %b)
  ret <16 x i16> %1
}

define <16 x i16> @test_mask_packs_epi32_rmbk_256(<8 x i32> %a, i32* %ptr_b, <16 x i16> %passThru, i16 %mask) {
; X86-LABEL: test_mask_packs_epi32_rmbk_256:
; X86:       # %bb.0:
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT:    kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x08]
; X86-NEXT:    vpackssdw (%eax){1to8}, %ymm0, %ymm1 {%k1} # encoding: [0x62,0xf1,0x7d,0x39,0x6b,0x08]
; X86-NEXT:    vmovdqa %ymm1, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xc1]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_packs_epi32_rmbk_256:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT:    vpackssdw (%rdi){1to8}, %ymm0, %ymm1 {%k1} # encoding: [0x62,0xf1,0x7d,0x39,0x6b,0x0f]
; X64-NEXT:    vmovdqa %ymm1, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xc1]
; X64-NEXT:    retq # encoding: [0xc3]
  %q = load i32, i32* %ptr_b
  %vecinit.i = insertelement <8 x i32> undef, i32 %q, i32 0
  %b = shufflevector <8 x i32> %vecinit.i, <8 x i32> undef, <8 x i32> zeroinitializer
  %1 = call <16 x i16> @llvm.x86.avx2.packssdw(<8 x i32> %a, <8 x i32> %b)
  %2 = bitcast i16 %mask to <16 x i1>
  %3 = select <16 x i1> %2, <16 x i16> %1, <16 x i16> %passThru
  ret <16 x i16> %3
}

define <16 x i16> @test_mask_packs_epi32_rmbkz_256(<8 x i32> %a, i32* %ptr_b, i16 %mask) {
; X86-LABEL: test_mask_packs_epi32_rmbkz_256:
; X86:       # %bb.0:
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT:    kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x08]
; X86-NEXT:    vpackssdw (%eax){1to8}, %ymm0, %ymm0 {%k1} {z} # encoding: [0x62,0xf1,0x7d,0xb9,0x6b,0x00]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_packs_epi32_rmbkz_256:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT:    vpackssdw (%rdi){1to8}, %ymm0, %ymm0 {%k1} {z} # encoding: [0x62,0xf1,0x7d,0xb9,0x6b,0x07]
; X64-NEXT:    retq # encoding: [0xc3]
  %q = load i32, i32* %ptr_b
  %vecinit.i = insertelement <8 x i32> undef, i32 %q, i32 0
  %b = shufflevector <8 x i32> %vecinit.i, <8 x i32> undef, <8 x i32> zeroinitializer
  %1 = call <16 x i16> @llvm.x86.avx2.packssdw(<8 x i32> %a, <8 x i32> %b)
  %2 = bitcast i16 %mask to <16 x i1>
  %3 = select <16 x i1> %2, <16 x i16> %1, <16 x i16> zeroinitializer
  ret <16 x i16> %3
}

declare <16 x i16> @llvm.x86.avx2.packssdw(<8 x i32>, <8 x i32>)

define <16 x i8> @test_mask_packs_epi16_rr_128(<8 x i16> %a, <8 x i16> %b) {
; CHECK-LABEL: test_mask_packs_epi16_rr_128:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vpacksswb %xmm1, %xmm0, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x63,0xc1]
; CHECK-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
  %1 = call <16 x i8> @llvm.x86.sse2.packsswb.128(<8 x i16> %a, <8 x i16> %b)
  ret <16 x i8> %1
}

define <16 x i8> @test_mask_packs_epi16_rrk_128(<8 x i16> %a, <8 x i16> %b, <16 x i8> %passThru, i16 %mask) {
; X86-LABEL: test_mask_packs_epi16_rrk_128:
; X86:       # %bb.0:
; X86-NEXT:    kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x04]
; X86-NEXT:    vpacksswb %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf1,0x7d,0x09,0x63,0xd1]
; X86-NEXT:    vmovdqa %xmm2, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xc2]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_packs_epi16_rrk_128:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpacksswb %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf1,0x7d,0x09,0x63,0xd1]
; X64-NEXT:    vmovdqa %xmm2, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xc2]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = call <16 x i8> @llvm.x86.sse2.packsswb.128(<8 x i16> %a, <8 x i16> %b)
  %2 = bitcast i16 %mask to <16 x i1>
  %3 = select <16 x i1> %2, <16 x i8> %1, <16 x i8> %passThru
  ret <16 x i8> %3
}

define <16 x i8> @test_mask_packs_epi16_rrkz_128(<8 x i16> %a, <8 x i16> %b, i16 %mask) {
; X86-LABEL: test_mask_packs_epi16_rrkz_128:
; X86:       # %bb.0:
; X86-NEXT:    kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x04]
; X86-NEXT:    vpacksswb %xmm1, %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf1,0x7d,0x89,0x63,0xc1]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_packs_epi16_rrkz_128:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpacksswb %xmm1, %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf1,0x7d,0x89,0x63,0xc1]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = call <16 x i8> @llvm.x86.sse2.packsswb.128(<8 x i16> %a, <8 x i16> %b)
  %2 = bitcast i16 %mask to <16 x i1>
  %3 = select <16 x i1> %2, <16 x i8> %1, <16 x i8> zeroinitializer
  ret <16 x i8> %3
}

define <16 x i8> @test_mask_packs_epi16_rm_128(<8 x i16> %a, <8 x i16>* %ptr_b) {
; X86-LABEL: test_mask_packs_epi16_rm_128:
; X86:       # %bb.0:
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT:    vpacksswb (%eax), %xmm0, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x63,0x00]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_packs_epi16_rm_128:
; X64:       # %bb.0:
; X64-NEXT:    vpacksswb (%rdi), %xmm0, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x63,0x07]
; X64-NEXT:    retq # encoding: [0xc3]
  %b = load <8 x i16>, <8 x i16>* %ptr_b
  %1 = call <16 x i8> @llvm.x86.sse2.packsswb.128(<8 x i16> %a, <8 x i16> %b)
  ret <16 x i8> %1
}

define <16 x i8> @test_mask_packs_epi16_rmk_128(<8 x i16> %a, <8 x i16>* %ptr_b, <16 x i8> %passThru, i16 %mask) {
; X86-LABEL: test_mask_packs_epi16_rmk_128:
; X86:       # %bb.0:
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT:    kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x08]
; X86-NEXT:    vpacksswb (%eax), %xmm0, %xmm1 {%k1} # encoding: [0x62,0xf1,0x7d,0x09,0x63,0x08]
; X86-NEXT:    vmovdqa %xmm1, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xc1]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_packs_epi16_rmk_128:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT:    vpacksswb (%rdi), %xmm0, %xmm1 {%k1} # encoding: [0x62,0xf1,0x7d,0x09,0x63,0x0f]
; X64-NEXT:    vmovdqa %xmm1, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xc1]
; X64-NEXT:    retq # encoding: [0xc3]
  %b = load <8 x i16>, <8 x i16>* %ptr_b
  %1 = call <16 x i8> @llvm.x86.sse2.packsswb.128(<8 x i16> %a, <8 x i16> %b)
  %2 = bitcast i16 %mask to <16 x i1>
  %3 = select <16 x i1> %2, <16 x i8> %1, <16 x i8> %passThru
  ret <16 x i8> %3
}

define <16 x i8> @test_mask_packs_epi16_rmkz_128(<8 x i16> %a, <8 x i16>* %ptr_b, i16 %mask) {
; X86-LABEL: test_mask_packs_epi16_rmkz_128:
; X86:       # %bb.0:
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT:    kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x08]
; X86-NEXT:    vpacksswb (%eax), %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf1,0x7d,0x89,0x63,0x00]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_packs_epi16_rmkz_128:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT:    vpacksswb (%rdi), %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf1,0x7d,0x89,0x63,0x07]
; X64-NEXT:    retq # encoding: [0xc3]
  %b = load <8 x i16>, <8 x i16>* %ptr_b
  %1 = call <16 x i8> @llvm.x86.sse2.packsswb.128(<8 x i16> %a, <8 x i16> %b)
  %2 = bitcast i16 %mask to <16 x i1>
  %3 = select <16 x i1> %2, <16 x i8> %1, <16 x i8> zeroinitializer
  ret <16 x i8> %3
}

declare <16 x i8> @llvm.x86.sse2.packsswb.128(<8 x i16>, <8 x i16>)

define <32 x i8> @test_mask_packs_epi16_rr_256(<16 x i16> %a, <16 x i16> %b) {
; CHECK-LABEL: test_mask_packs_epi16_rr_256:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vpacksswb %ymm1, %ymm0, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x63,0xc1]
; CHECK-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
  %1 = call <32 x i8> @llvm.x86.avx2.packsswb(<16 x i16> %a, <16 x i16> %b)
  ret <32 x i8> %1
}

define <32 x i8> @test_mask_packs_epi16_rrk_256(<16 x i16> %a, <16 x i16> %b, <32 x i8> %passThru, i32 %mask) {
; X86-LABEL: test_mask_packs_epi16_rrk_256:
; X86:       # %bb.0:
; X86-NEXT:    kmovd {{[0-9]+}}(%esp), %k1 # encoding: [0xc4,0xe1,0xf9,0x90,0x4c,0x24,0x04]
; X86-NEXT:    vpacksswb %ymm1, %ymm0, %ymm2 {%k1} # encoding: [0x62,0xf1,0x7d,0x29,0x63,0xd1]
; X86-NEXT:    vmovdqa %ymm2, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xc2]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_packs_epi16_rrk_256:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpacksswb %ymm1, %ymm0, %ymm2 {%k1} # encoding: [0x62,0xf1,0x7d,0x29,0x63,0xd1]
; X64-NEXT:    vmovdqa %ymm2, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xc2]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = call <32 x i8> @llvm.x86.avx2.packsswb(<16 x i16> %a, <16 x i16> %b)
  %2 = bitcast i32 %mask to <32 x i1>
  %3 = select <32 x i1> %2, <32 x i8> %1, <32 x i8> %passThru
  ret <32 x i8> %3
}

define <32 x i8> @test_mask_packs_epi16_rrkz_256(<16 x i16> %a, <16 x i16> %b, i32 %mask) {
; X86-LABEL: test_mask_packs_epi16_rrkz_256:
; X86:       # %bb.0:
; X86-NEXT:    kmovd {{[0-9]+}}(%esp), %k1 # encoding: [0xc4,0xe1,0xf9,0x90,0x4c,0x24,0x04]
; X86-NEXT:    vpacksswb %ymm1, %ymm0, %ymm0 {%k1} {z} # encoding: [0x62,0xf1,0x7d,0xa9,0x63,0xc1]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_packs_epi16_rrkz_256:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpacksswb %ymm1, %ymm0, %ymm0 {%k1} {z} # encoding: [0x62,0xf1,0x7d,0xa9,0x63,0xc1]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = call <32 x i8> @llvm.x86.avx2.packsswb(<16 x i16> %a, <16 x i16> %b)
  %2 = bitcast i32 %mask to <32 x i1>
  %3 = select <32 x i1> %2, <32 x i8> %1, <32 x i8> zeroinitializer
  ret <32 x i8> %3
}

define <32 x i8> @test_mask_packs_epi16_rm_256(<16 x i16> %a, <16 x i16>* %ptr_b) {
; X86-LABEL: test_mask_packs_epi16_rm_256:
; X86:       # %bb.0:
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT:    vpacksswb (%eax), %ymm0, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x63,0x00]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_packs_epi16_rm_256:
; X64:       # %bb.0:
; X64-NEXT:    vpacksswb (%rdi), %ymm0, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x63,0x07]
; X64-NEXT:    retq # encoding: [0xc3]
  %b = load <16 x i16>, <16 x i16>* %ptr_b
  %1 = call <32 x i8> @llvm.x86.avx2.packsswb(<16 x i16> %a, <16 x i16> %b)
  ret <32 x i8> %1
}

define <32 x i8> @test_mask_packs_epi16_rmk_256(<16 x i16> %a, <16 x i16>* %ptr_b, <32 x i8> %passThru, i32 %mask) {
; X86-LABEL: test_mask_packs_epi16_rmk_256:
; X86:       # %bb.0:
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT:    kmovd {{[0-9]+}}(%esp), %k1 # encoding: [0xc4,0xe1,0xf9,0x90,0x4c,0x24,0x08]
; X86-NEXT:    vpacksswb (%eax), %ymm0, %ymm1 {%k1} # encoding: [0x62,0xf1,0x7d,0x29,0x63,0x08]
; X86-NEXT:    vmovdqa %ymm1, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xc1]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_packs_epi16_rmk_256:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT:    vpacksswb (%rdi), %ymm0, %ymm1 {%k1} # encoding: [0x62,0xf1,0x7d,0x29,0x63,0x0f]
; X64-NEXT:    vmovdqa %ymm1, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xc1]
; X64-NEXT:    retq # encoding: [0xc3]
  %b = load <16 x i16>, <16 x i16>* %ptr_b
  %1 = call <32 x i8> @llvm.x86.avx2.packsswb(<16 x i16> %a, <16 x i16> %b)
  %2 = bitcast i32 %mask to <32 x i1>
  %3 = select <32 x i1> %2, <32 x i8> %1, <32 x i8> %passThru
  ret <32 x i8> %3
}

define <32 x i8> @test_mask_packs_epi16_rmkz_256(<16 x i16> %a, <16 x i16>* %ptr_b, i32 %mask) {
; X86-LABEL: test_mask_packs_epi16_rmkz_256:
; X86:       # %bb.0:
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT:    kmovd {{[0-9]+}}(%esp), %k1 # encoding: [0xc4,0xe1,0xf9,0x90,0x4c,0x24,0x08]
; X86-NEXT:    vpacksswb (%eax), %ymm0, %ymm0 {%k1} {z} # encoding: [0x62,0xf1,0x7d,0xa9,0x63,0x00]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_packs_epi16_rmkz_256:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT:    vpacksswb (%rdi), %ymm0, %ymm0 {%k1} {z} # encoding: [0x62,0xf1,0x7d,0xa9,0x63,0x07]
; X64-NEXT:    retq # encoding: [0xc3]
  %b = load <16 x i16>, <16 x i16>* %ptr_b
  %1 = call <32 x i8> @llvm.x86.avx2.packsswb(<16 x i16> %a, <16 x i16> %b)
  %2 = bitcast i32 %mask to <32 x i1>
  %3 = select <32 x i1> %2, <32 x i8> %1, <32 x i8> zeroinitializer
  ret <32 x i8> %3
}

declare <32 x i8> @llvm.x86.avx2.packsswb(<16 x i16>, <16 x i16>)


define <8 x i16> @test_mask_packus_epi32_rr_128(<4 x i32> %a, <4 x i32> %b) {
; CHECK-LABEL: test_mask_packus_epi32_rr_128:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vpackusdw %xmm1, %xmm0, %xmm0 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0x79,0x2b,0xc1]
; CHECK-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
  %1 = call <8 x i16> @llvm.x86.sse41.packusdw(<4 x i32> %a, <4 x i32> %b)
  ret <8 x i16> %1
}

define <8 x i16> @test_mask_packus_epi32_rrk_128(<4 x i32> %a, <4 x i32> %b, <8 x i16> %passThru, i8 %mask) {
; X86-LABEL: test_mask_packus_epi32_rrk_128:
; X86:       # %bb.0:
; X86-NEXT:    movzbl {{[0-9]+}}(%esp), %eax # encoding: [0x0f,0xb6,0x44,0x24,0x04]
; X86-NEXT:    kmovd %eax, %k1 # encoding: [0xc5,0xfb,0x92,0xc8]
; X86-NEXT:    vpackusdw %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf2,0x7d,0x09,0x2b,0xd1]
; X86-NEXT:    vmovdqa %xmm2, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xc2]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_packus_epi32_rrk_128:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpackusdw %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf2,0x7d,0x09,0x2b,0xd1]
; X64-NEXT:    vmovdqa %xmm2, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xc2]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = call <8 x i16> @llvm.x86.sse41.packusdw(<4 x i32> %a, <4 x i32> %b)
  %2 = bitcast i8 %mask to <8 x i1>
  %3 = select <8 x i1> %2, <8 x i16> %1, <8 x i16> %passThru
  ret <8 x i16> %3
}

define <8 x i16> @test_mask_packus_epi32_rrkz_128(<4 x i32> %a, <4 x i32> %b, i8 %mask) {
; X86-LABEL: test_mask_packus_epi32_rrkz_128:
; X86:       # %bb.0:
; X86-NEXT:    movzbl {{[0-9]+}}(%esp), %eax # encoding: [0x0f,0xb6,0x44,0x24,0x04]
; X86-NEXT:    kmovd %eax, %k1 # encoding: [0xc5,0xfb,0x92,0xc8]
; X86-NEXT:    vpackusdw %xmm1, %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf2,0x7d,0x89,0x2b,0xc1]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_packus_epi32_rrkz_128:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpackusdw %xmm1, %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf2,0x7d,0x89,0x2b,0xc1]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = call <8 x i16> @llvm.x86.sse41.packusdw(<4 x i32> %a, <4 x i32> %b)
  %2 = bitcast i8 %mask to <8 x i1>
  %3 = select <8 x i1> %2, <8 x i16> %1, <8 x i16> zeroinitializer
  ret <8 x i16> %3
}

define <8 x i16> @test_mask_packus_epi32_rm_128(<4 x i32> %a, <4 x i32>* %ptr_b) {
; X86-LABEL: test_mask_packus_epi32_rm_128:
; X86:       # %bb.0:
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT:    vpackusdw (%eax), %xmm0, %xmm0 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0x79,0x2b,0x00]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_packus_epi32_rm_128:
; X64:       # %bb.0:
; X64-NEXT:    vpackusdw (%rdi), %xmm0, %xmm0 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0x79,0x2b,0x07]
; X64-NEXT:    retq # encoding: [0xc3]
  %b = load <4 x i32>, <4 x i32>* %ptr_b
  %1 = call <8 x i16> @llvm.x86.sse41.packusdw(<4 x i32> %a, <4 x i32> %b)
  ret <8 x i16> %1
}

define <8 x i16> @test_mask_packus_epi32_rmk_128(<4 x i32> %a, <4 x i32>* %ptr_b, <8 x i16> %passThru, i8 %mask) {
; X86-LABEL: test_mask_packus_epi32_rmk_128:
; X86:       # %bb.0:
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT:    movzbl {{[0-9]+}}(%esp), %ecx # encoding: [0x0f,0xb6,0x4c,0x24,0x08]
; X86-NEXT:    kmovd %ecx, %k1 # encoding: [0xc5,0xfb,0x92,0xc9]
; X86-NEXT:    vpackusdw (%eax), %xmm0, %xmm1 {%k1} # encoding: [0x62,0xf2,0x7d,0x09,0x2b,0x08]
; X86-NEXT:    vmovdqa %xmm1, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xc1]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_packus_epi32_rmk_128:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT:    vpackusdw (%rdi), %xmm0, %xmm1 {%k1} # encoding: [0x62,0xf2,0x7d,0x09,0x2b,0x0f]
; X64-NEXT:    vmovdqa %xmm1, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xc1]
; X64-NEXT:    retq # encoding: [0xc3]
  %b = load <4 x i32>, <4 x i32>* %ptr_b
  %1 = call <8 x i16> @llvm.x86.sse41.packusdw(<4 x i32> %a, <4 x i32> %b)
  %2 = bitcast i8 %mask to <8 x i1>
  %3 = select <8 x i1> %2, <8 x i16> %1, <8 x i16> %passThru
  ret <8 x i16> %3
}

define <8 x i16> @test_mask_packus_epi32_rmkz_128(<4 x i32> %a, <4 x i32>* %ptr_b, i8 %mask) {
; X86-LABEL: test_mask_packus_epi32_rmkz_128:
; X86:       # %bb.0:
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT:    movzbl {{[0-9]+}}(%esp), %ecx # encoding: [0x0f,0xb6,0x4c,0x24,0x08]
; X86-NEXT:    kmovd %ecx, %k1 # encoding: [0xc5,0xfb,0x92,0xc9]
; X86-NEXT:    vpackusdw (%eax), %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf2,0x7d,0x89,0x2b,0x00]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_packus_epi32_rmkz_128:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT:    vpackusdw (%rdi), %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf2,0x7d,0x89,0x2b,0x07]
; X64-NEXT:    retq # encoding: [0xc3]
  %b = load <4 x i32>, <4 x i32>* %ptr_b
  %1 = call <8 x i16> @llvm.x86.sse41.packusdw(<4 x i32> %a, <4 x i32> %b)
  %2 = bitcast i8 %mask to <8 x i1>
  %3 = select <8 x i1> %2, <8 x i16> %1, <8 x i16> zeroinitializer
  ret <8 x i16> %3
}

define <8 x i16> @test_mask_packus_epi32_rmb_128(<4 x i32> %a, i32* %ptr_b) {
; X86-LABEL: test_mask_packus_epi32_rmb_128:
; X86:       # %bb.0:
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT:    vpackusdw (%eax){1to4}, %xmm0, %xmm0 # encoding: [0x62,0xf2,0x7d,0x18,0x2b,0x00]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_packus_epi32_rmb_128:
; X64:       # %bb.0:
; X64-NEXT:    vpackusdw (%rdi){1to4}, %xmm0, %xmm0 # encoding: [0x62,0xf2,0x7d,0x18,0x2b,0x07]
; X64-NEXT:    retq # encoding: [0xc3]
  %q = load i32, i32* %ptr_b
  %vecinit.i = insertelement <4 x i32> undef, i32 %q, i32 0
  %b = shufflevector <4 x i32> %vecinit.i, <4 x i32> undef, <4 x i32> zeroinitializer
  %1 = call <8 x i16> @llvm.x86.sse41.packusdw(<4 x i32> %a, <4 x i32> %b)
  ret <8 x i16> %1
}

define <8 x i16> @test_mask_packus_epi32_rmbk_128(<4 x i32> %a, i32* %ptr_b, <8 x i16> %passThru, i8 %mask) {
; X86-LABEL: test_mask_packus_epi32_rmbk_128:
; X86:       # %bb.0:
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT:    movzbl {{[0-9]+}}(%esp), %ecx # encoding: [0x0f,0xb6,0x4c,0x24,0x08]
; X86-NEXT:    kmovd %ecx, %k1 # encoding: [0xc5,0xfb,0x92,0xc9]
; X86-NEXT:    vpackusdw (%eax){1to4}, %xmm0, %xmm1 {%k1} # encoding: [0x62,0xf2,0x7d,0x19,0x2b,0x08]
; X86-NEXT:    vmovdqa %xmm1, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xc1]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_packus_epi32_rmbk_128:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT:    vpackusdw (%rdi){1to4}, %xmm0, %xmm1 {%k1} # encoding: [0x62,0xf2,0x7d,0x19,0x2b,0x0f]
; X64-NEXT:    vmovdqa %xmm1, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xc1]
; X64-NEXT:    retq # encoding: [0xc3]
  %q = load i32, i32* %ptr_b
  %vecinit.i = insertelement <4 x i32> undef, i32 %q, i32 0
  %b = shufflevector <4 x i32> %vecinit.i, <4 x i32> undef, <4 x i32> zeroinitializer
  %1 = call <8 x i16> @llvm.x86.sse41.packusdw(<4 x i32> %a, <4 x i32> %b)
  %2 = bitcast i8 %mask to <8 x i1>
  %3 = select <8 x i1> %2, <8 x i16> %1, <8 x i16> %passThru
  ret <8 x i16> %3
}

define <8 x i16> @test_mask_packus_epi32_rmbkz_128(<4 x i32> %a, i32* %ptr_b, i8 %mask) {
; X86-LABEL: test_mask_packus_epi32_rmbkz_128:
; X86:       # %bb.0:
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT:    movzbl {{[0-9]+}}(%esp), %ecx # encoding: [0x0f,0xb6,0x4c,0x24,0x08]
; X86-NEXT:    kmovd %ecx, %k1 # encoding: [0xc5,0xfb,0x92,0xc9]
; X86-NEXT:    vpackusdw (%eax){1to4}, %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf2,0x7d,0x99,0x2b,0x00]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_packus_epi32_rmbkz_128:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT:    vpackusdw (%rdi){1to4}, %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf2,0x7d,0x99,0x2b,0x07]
; X64-NEXT:    retq # encoding: [0xc3]
  %q = load i32, i32* %ptr_b
  %vecinit.i = insertelement <4 x i32> undef, i32 %q, i32 0
  %b = shufflevector <4 x i32> %vecinit.i, <4 x i32> undef, <4 x i32> zeroinitializer
  %1 = call <8 x i16> @llvm.x86.sse41.packusdw(<4 x i32> %a, <4 x i32> %b)
  %2 = bitcast i8 %mask to <8 x i1>
  %3 = select <8 x i1> %2, <8 x i16> %1, <8 x i16> zeroinitializer
  ret <8 x i16> %3
}

declare <8 x i16> @llvm.x86.sse41.packusdw(<4 x i32>, <4 x i32>)

define <16 x i16> @test_mask_packus_epi32_rr_256(<8 x i32> %a, <8 x i32> %b) {
; CHECK-LABEL: test_mask_packus_epi32_rr_256:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vpackusdw %ymm1, %ymm0, %ymm0 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0x7d,0x2b,0xc1]
; CHECK-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
  %1 = call <16 x i16> @llvm.x86.avx2.packusdw(<8 x i32> %a, <8 x i32> %b)
  ret <16 x i16> %1
}

define <16 x i16> @test_mask_packus_epi32_rrk_256(<8 x i32> %a, <8 x i32> %b, <16 x i16> %passThru, i16 %mask) {
; X86-LABEL: test_mask_packus_epi32_rrk_256:
; X86:       # %bb.0:
; X86-NEXT:    kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x04]
; X86-NEXT:    vpackusdw %ymm1, %ymm0, %ymm2 {%k1} # encoding: [0x62,0xf2,0x7d,0x29,0x2b,0xd1]
; X86-NEXT:    vmovdqa %ymm2, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xc2]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_packus_epi32_rrk_256:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpackusdw %ymm1, %ymm0, %ymm2 {%k1} # encoding: [0x62,0xf2,0x7d,0x29,0x2b,0xd1]
; X64-NEXT:    vmovdqa %ymm2, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xc2]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = call <16 x i16> @llvm.x86.avx2.packusdw(<8 x i32> %a, <8 x i32> %b)
  %2 = bitcast i16 %mask to <16 x i1>
  %3 = select <16 x i1> %2, <16 x i16> %1, <16 x i16> %passThru
  ret <16 x i16> %3
}

define <16 x i16> @test_mask_packus_epi32_rrkz_256(<8 x i32> %a, <8 x i32> %b, i16 %mask) {
; X86-LABEL: test_mask_packus_epi32_rrkz_256:
; X86:       # %bb.0:
; X86-NEXT:    kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x04]
; X86-NEXT:    vpackusdw %ymm1, %ymm0, %ymm0 {%k1} {z} # encoding: [0x62,0xf2,0x7d,0xa9,0x2b,0xc1]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_packus_epi32_rrkz_256:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpackusdw %ymm1, %ymm0, %ymm0 {%k1} {z} # encoding: [0x62,0xf2,0x7d,0xa9,0x2b,0xc1]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = call <16 x i16> @llvm.x86.avx2.packusdw(<8 x i32> %a, <8 x i32> %b)
  %2 = bitcast i16 %mask to <16 x i1>
  %3 = select <16 x i1> %2, <16 x i16> %1, <16 x i16> zeroinitializer
  ret <16 x i16> %3
}

define <16 x i16> @test_mask_packus_epi32_rm_256(<8 x i32> %a, <8 x i32>* %ptr_b) {
; X86-LABEL: test_mask_packus_epi32_rm_256:
; X86:       # %bb.0:
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT:    vpackusdw (%eax), %ymm0, %ymm0 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0x7d,0x2b,0x00]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_packus_epi32_rm_256:
; X64:       # %bb.0:
; X64-NEXT:    vpackusdw (%rdi), %ymm0, %ymm0 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0x7d,0x2b,0x07]
; X64-NEXT:    retq # encoding: [0xc3]
  %b = load <8 x i32>, <8 x i32>* %ptr_b
  %1 = call <16 x i16> @llvm.x86.avx2.packusdw(<8 x i32> %a, <8 x i32> %b)
  ret <16 x i16> %1
}

define <16 x i16> @test_mask_packus_epi32_rmk_256(<8 x i32> %a, <8 x i32>* %ptr_b, <16 x i16> %passThru, i16 %mask) {
; X86-LABEL: test_mask_packus_epi32_rmk_256:
; X86:       # %bb.0:
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT:    kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x08]
; X86-NEXT:    vpackusdw (%eax), %ymm0, %ymm1 {%k1} # encoding: [0x62,0xf2,0x7d,0x29,0x2b,0x08]
; X86-NEXT:    vmovdqa %ymm1, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xc1]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_packus_epi32_rmk_256:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT:    vpackusdw (%rdi), %ymm0, %ymm1 {%k1} # encoding: [0x62,0xf2,0x7d,0x29,0x2b,0x0f]
; X64-NEXT:    vmovdqa %ymm1, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xc1]
; X64-NEXT:    retq # encoding: [0xc3]
  %b = load <8 x i32>, <8 x i32>* %ptr_b
  %1 = call <16 x i16> @llvm.x86.avx2.packusdw(<8 x i32> %a, <8 x i32> %b)
  %2 = bitcast i16 %mask to <16 x i1>
  %3 = select <16 x i1> %2, <16 x i16> %1, <16 x i16> %passThru
  ret <16 x i16> %3
}

define <16 x i16> @test_mask_packus_epi32_rmkz_256(<8 x i32> %a, <8 x i32>* %ptr_b, i16 %mask) {
; X86-LABEL: test_mask_packus_epi32_rmkz_256:
; X86:       # %bb.0:
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT:    kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x08]
; X86-NEXT:    vpackusdw (%eax), %ymm0, %ymm0 {%k1} {z} # encoding: [0x62,0xf2,0x7d,0xa9,0x2b,0x00]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_packus_epi32_rmkz_256:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT:    vpackusdw (%rdi), %ymm0, %ymm0 {%k1} {z} # encoding: [0x62,0xf2,0x7d,0xa9,0x2b,0x07]
; X64-NEXT:    retq # encoding: [0xc3]
  %b = load <8 x i32>, <8 x i32>* %ptr_b
  %1 = call <16 x i16> @llvm.x86.avx2.packusdw(<8 x i32> %a, <8 x i32> %b)
  %2 = bitcast i16 %mask to <16 x i1>
  %3 = select <16 x i1> %2, <16 x i16> %1, <16 x i16> zeroinitializer
  ret <16 x i16> %3
}

define <16 x i16> @test_mask_packus_epi32_rmb_256(<8 x i32> %a, i32* %ptr_b) {
; X86-LABEL: test_mask_packus_epi32_rmb_256:
; X86:       # %bb.0:
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT:    vpackusdw (%eax){1to8}, %ymm0, %ymm0 # encoding: [0x62,0xf2,0x7d,0x38,0x2b,0x00]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_packus_epi32_rmb_256:
; X64:       # %bb.0:
; X64-NEXT:    vpackusdw (%rdi){1to8}, %ymm0, %ymm0 # encoding: [0x62,0xf2,0x7d,0x38,0x2b,0x07]
; X64-NEXT:    retq # encoding: [0xc3]
  %q = load i32, i32* %ptr_b
  %vecinit.i = insertelement <8 x i32> undef, i32 %q, i32 0
  %b = shufflevector <8 x i32> %vecinit.i, <8 x i32> undef, <8 x i32> zeroinitializer
  %1 = call <16 x i16> @llvm.x86.avx2.packusdw(<8 x i32> %a, <8 x i32> %b)
  ret <16 x i16> %1
}

define <16 x i16> @test_mask_packus_epi32_rmbk_256(<8 x i32> %a, i32* %ptr_b, <16 x i16> %passThru, i16 %mask) {
; X86-LABEL: test_mask_packus_epi32_rmbk_256:
; X86:       # %bb.0:
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT:    kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x08]
; X86-NEXT:    vpackusdw (%eax){1to8}, %ymm0, %ymm1 {%k1} # encoding: [0x62,0xf2,0x7d,0x39,0x2b,0x08]
; X86-NEXT:    vmovdqa %ymm1, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xc1]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_packus_epi32_rmbk_256:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT:    vpackusdw (%rdi){1to8}, %ymm0, %ymm1 {%k1} # encoding: [0x62,0xf2,0x7d,0x39,0x2b,0x0f]
; X64-NEXT:    vmovdqa %ymm1, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xc1]
; X64-NEXT:    retq # encoding: [0xc3]
  %q = load i32, i32* %ptr_b
  %vecinit.i = insertelement <8 x i32> undef, i32 %q, i32 0
  %b = shufflevector <8 x i32> %vecinit.i, <8 x i32> undef, <8 x i32> zeroinitializer
  %1 = call <16 x i16> @llvm.x86.avx2.packusdw(<8 x i32> %a, <8 x i32> %b)
  %2 = bitcast i16 %mask to <16 x i1>
  %3 = select <16 x i1> %2, <16 x i16> %1, <16 x i16> %passThru
  ret <16 x i16> %3
}

define <16 x i16> @test_mask_packus_epi32_rmbkz_256(<8 x i32> %a, i32* %ptr_b, i16 %mask) {
; X86-LABEL: test_mask_packus_epi32_rmbkz_256:
; X86:       # %bb.0:
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT:    kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x08]
; X86-NEXT:    vpackusdw (%eax){1to8}, %ymm0, %ymm0 {%k1} {z} # encoding: [0x62,0xf2,0x7d,0xb9,0x2b,0x00]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_packus_epi32_rmbkz_256:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT:    vpackusdw (%rdi){1to8}, %ymm0, %ymm0 {%k1} {z} # encoding: [0x62,0xf2,0x7d,0xb9,0x2b,0x07]
; X64-NEXT:    retq # encoding: [0xc3]
  %q = load i32, i32* %ptr_b
  %vecinit.i = insertelement <8 x i32> undef, i32 %q, i32 0
  %b = shufflevector <8 x i32> %vecinit.i, <8 x i32> undef, <8 x i32> zeroinitializer
  %1 = call <16 x i16> @llvm.x86.avx2.packusdw(<8 x i32> %a, <8 x i32> %b)
  %2 = bitcast i16 %mask to <16 x i1>
  %3 = select <16 x i1> %2, <16 x i16> %1, <16 x i16> zeroinitializer
  ret <16 x i16> %3
}

declare <16 x i16> @llvm.x86.avx2.packusdw(<8 x i32>, <8 x i32>)

define <16 x i8> @test_mask_packus_epi16_rr_128(<8 x i16> %a, <8 x i16> %b) {
; CHECK-LABEL: test_mask_packus_epi16_rr_128:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vpackuswb %xmm1, %xmm0, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x67,0xc1]
; CHECK-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
  %1 = call <16 x i8> @llvm.x86.sse2.packuswb.128(<8 x i16> %a, <8 x i16> %b)
  ret <16 x i8> %1
}

define <16 x i8> @test_mask_packus_epi16_rrk_128(<8 x i16> %a, <8 x i16> %b, <16 x i8> %passThru, i16 %mask) {
; X86-LABEL: test_mask_packus_epi16_rrk_128:
; X86:       # %bb.0:
; X86-NEXT:    kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x04]
; X86-NEXT:    vpackuswb %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf1,0x7d,0x09,0x67,0xd1]
; X86-NEXT:    vmovdqa %xmm2, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xc2]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_packus_epi16_rrk_128:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpackuswb %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf1,0x7d,0x09,0x67,0xd1]
; X64-NEXT:    vmovdqa %xmm2, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xc2]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = call <16 x i8> @llvm.x86.sse2.packuswb.128(<8 x i16> %a, <8 x i16> %b)
  %2 = bitcast i16 %mask to <16 x i1>
  %3 = select <16 x i1> %2, <16 x i8> %1, <16 x i8> %passThru
  ret <16 x i8> %3
}

define <16 x i8> @test_mask_packus_epi16_rrkz_128(<8 x i16> %a, <8 x i16> %b, i16 %mask) {
; X86-LABEL: test_mask_packus_epi16_rrkz_128:
; X86:       # %bb.0:
; X86-NEXT:    kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x04]
; X86-NEXT:    vpackuswb %xmm1, %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf1,0x7d,0x89,0x67,0xc1]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_packus_epi16_rrkz_128:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpackuswb %xmm1, %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf1,0x7d,0x89,0x67,0xc1]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = call <16 x i8> @llvm.x86.sse2.packuswb.128(<8 x i16> %a, <8 x i16> %b)
  %2 = bitcast i16 %mask to <16 x i1>
  %3 = select <16 x i1> %2, <16 x i8> %1, <16 x i8> zeroinitializer
  ret <16 x i8> %3
}

define <16 x i8> @test_mask_packus_epi16_rm_128(<8 x i16> %a, <8 x i16>* %ptr_b) {
; X86-LABEL: test_mask_packus_epi16_rm_128:
; X86:       # %bb.0:
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT:    vpackuswb (%eax), %xmm0, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x67,0x00]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_packus_epi16_rm_128:
; X64:       # %bb.0:
; X64-NEXT:    vpackuswb (%rdi), %xmm0, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x67,0x07]
; X64-NEXT:    retq # encoding: [0xc3]
  %b = load <8 x i16>, <8 x i16>* %ptr_b
  %1 = call <16 x i8> @llvm.x86.sse2.packuswb.128(<8 x i16> %a, <8 x i16> %b)
  ret <16 x i8> %1
}

define <16 x i8> @test_mask_packus_epi16_rmk_128(<8 x i16> %a, <8 x i16>* %ptr_b, <16 x i8> %passThru, i16 %mask) {
; X86-LABEL: test_mask_packus_epi16_rmk_128:
; X86:       # %bb.0:
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT:    kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x08]
; X86-NEXT:    vpackuswb (%eax), %xmm0, %xmm1 {%k1} # encoding: [0x62,0xf1,0x7d,0x09,0x67,0x08]
; X86-NEXT:    vmovdqa %xmm1, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xc1]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_packus_epi16_rmk_128:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT:    vpackuswb (%rdi), %xmm0, %xmm1 {%k1} # encoding: [0x62,0xf1,0x7d,0x09,0x67,0x0f]
; X64-NEXT:    vmovdqa %xmm1, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xc1]
; X64-NEXT:    retq # encoding: [0xc3]
  %b = load <8 x i16>, <8 x i16>* %ptr_b
  %1 = call <16 x i8> @llvm.x86.sse2.packuswb.128(<8 x i16> %a, <8 x i16> %b)
  %2 = bitcast i16 %mask to <16 x i1>
  %3 = select <16 x i1> %2, <16 x i8> %1, <16 x i8> %passThru
  ret <16 x i8> %3
}

define <16 x i8> @test_mask_packus_epi16_rmkz_128(<8 x i16> %a, <8 x i16>* %ptr_b, i16 %mask) {
; X86-LABEL: test_mask_packus_epi16_rmkz_128:
; X86:       # %bb.0:
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT:    kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x08]
; X86-NEXT:    vpackuswb (%eax), %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf1,0x7d,0x89,0x67,0x00]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_packus_epi16_rmkz_128:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT:    vpackuswb (%rdi), %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf1,0x7d,0x89,0x67,0x07]
; X64-NEXT:    retq # encoding: [0xc3]
  %b = load <8 x i16>, <8 x i16>* %ptr_b
  %1 = call <16 x i8> @llvm.x86.sse2.packuswb.128(<8 x i16> %a, <8 x i16> %b)
  %2 = bitcast i16 %mask to <16 x i1>
  %3 = select <16 x i1> %2, <16 x i8> %1, <16 x i8> zeroinitializer
  ret <16 x i8> %3
}

declare <16 x i8> @llvm.x86.sse2.packuswb.128(<8 x i16>, <8 x i16>)

define <32 x i8> @test_mask_packus_epi16_rr_256(<16 x i16> %a, <16 x i16> %b) {
; CHECK-LABEL: test_mask_packus_epi16_rr_256:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vpackuswb %ymm1, %ymm0, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x67,0xc1]
; CHECK-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
  %1 = call <32 x i8> @llvm.x86.avx2.packuswb(<16 x i16> %a, <16 x i16> %b)
  ret <32 x i8> %1
}

define <32 x i8> @test_mask_packus_epi16_rrk_256(<16 x i16> %a, <16 x i16> %b, <32 x i8> %passThru, i32 %mask) {
; X86-LABEL: test_mask_packus_epi16_rrk_256:
; X86:       # %bb.0:
; X86-NEXT:    kmovd {{[0-9]+}}(%esp), %k1 # encoding: [0xc4,0xe1,0xf9,0x90,0x4c,0x24,0x04]
; X86-NEXT:    vpackuswb %ymm1, %ymm0, %ymm2 {%k1} # encoding: [0x62,0xf1,0x7d,0x29,0x67,0xd1]
; X86-NEXT:    vmovdqa %ymm2, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xc2]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_packus_epi16_rrk_256:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpackuswb %ymm1, %ymm0, %ymm2 {%k1} # encoding: [0x62,0xf1,0x7d,0x29,0x67,0xd1]
; X64-NEXT:    vmovdqa %ymm2, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xc2]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = call <32 x i8> @llvm.x86.avx2.packuswb(<16 x i16> %a, <16 x i16> %b)
  %2 = bitcast i32 %mask to <32 x i1>
  %3 = select <32 x i1> %2, <32 x i8> %1, <32 x i8> %passThru
  ret <32 x i8> %3
}

define <32 x i8> @test_mask_packus_epi16_rrkz_256(<16 x i16> %a, <16 x i16> %b, i32 %mask) {
; X86-LABEL: test_mask_packus_epi16_rrkz_256:
; X86:       # %bb.0:
; X86-NEXT:    kmovd {{[0-9]+}}(%esp), %k1 # encoding: [0xc4,0xe1,0xf9,0x90,0x4c,0x24,0x04]
; X86-NEXT:    vpackuswb %ymm1, %ymm0, %ymm0 {%k1} {z} # encoding: [0x62,0xf1,0x7d,0xa9,0x67,0xc1]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_packus_epi16_rrkz_256:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpackuswb %ymm1, %ymm0, %ymm0 {%k1} {z} # encoding: [0x62,0xf1,0x7d,0xa9,0x67,0xc1]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = call <32 x i8> @llvm.x86.avx2.packuswb(<16 x i16> %a, <16 x i16> %b)
  %2 = bitcast i32 %mask to <32 x i1>
  %3 = select <32 x i1> %2, <32 x i8> %1, <32 x i8> zeroinitializer
  ret <32 x i8> %3
}

define <32 x i8> @test_mask_packus_epi16_rm_256(<16 x i16> %a, <16 x i16>* %ptr_b) {
; X86-LABEL: test_mask_packus_epi16_rm_256:
; X86:       # %bb.0:
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT:    vpackuswb (%eax), %ymm0, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x67,0x00]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_packus_epi16_rm_256:
; X64:       # %bb.0:
; X64-NEXT:    vpackuswb (%rdi), %ymm0, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x67,0x07]
; X64-NEXT:    retq # encoding: [0xc3]
  %b = load <16 x i16>, <16 x i16>* %ptr_b
  %1 = call <32 x i8> @llvm.x86.avx2.packuswb(<16 x i16> %a, <16 x i16> %b)
  ret <32 x i8> %1
}

define <32 x i8> @test_mask_packus_epi16_rmk_256(<16 x i16> %a, <16 x i16>* %ptr_b, <32 x i8> %passThru, i32 %mask) {
; X86-LABEL: test_mask_packus_epi16_rmk_256:
; X86:       # %bb.0:
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT:    kmovd {{[0-9]+}}(%esp), %k1 # encoding: [0xc4,0xe1,0xf9,0x90,0x4c,0x24,0x08]
; X86-NEXT:    vpackuswb (%eax), %ymm0, %ymm1 {%k1} # encoding: [0x62,0xf1,0x7d,0x29,0x67,0x08]
; X86-NEXT:    vmovdqa %ymm1, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xc1]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_packus_epi16_rmk_256:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT:    vpackuswb (%rdi), %ymm0, %ymm1 {%k1} # encoding: [0x62,0xf1,0x7d,0x29,0x67,0x0f]
; X64-NEXT:    vmovdqa %ymm1, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xc1]
; X64-NEXT:    retq # encoding: [0xc3]
  %b = load <16 x i16>, <16 x i16>* %ptr_b
  %1 = call <32 x i8> @llvm.x86.avx2.packuswb(<16 x i16> %a, <16 x i16> %b)
  %2 = bitcast i32 %mask to <32 x i1>
  %3 = select <32 x i1> %2, <32 x i8> %1, <32 x i8> %passThru
  ret <32 x i8> %3
}

define <32 x i8> @test_mask_packus_epi16_rmkz_256(<16 x i16> %a, <16 x i16>* %ptr_b, i32 %mask) {
; X86-LABEL: test_mask_packus_epi16_rmkz_256:
; X86:       # %bb.0:
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT:    kmovd {{[0-9]+}}(%esp), %k1 # encoding: [0xc4,0xe1,0xf9,0x90,0x4c,0x24,0x08]
; X86-NEXT:    vpackuswb (%eax), %ymm0, %ymm0 {%k1} {z} # encoding: [0x62,0xf1,0x7d,0xa9,0x67,0x00]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_packus_epi16_rmkz_256:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT:    vpackuswb (%rdi), %ymm0, %ymm0 {%k1} {z} # encoding: [0x62,0xf1,0x7d,0xa9,0x67,0x07]
; X64-NEXT:    retq # encoding: [0xc3]
  %b = load <16 x i16>, <16 x i16>* %ptr_b
  %1 = call <32 x i8> @llvm.x86.avx2.packuswb(<16 x i16> %a, <16 x i16> %b)
  %2 = bitcast i32 %mask to <32 x i1>
  %3 = select <32 x i1> %2, <32 x i8> %1, <32 x i8> zeroinitializer
  ret <32 x i8> %3
}

declare <32 x i8> @llvm.x86.avx2.packuswb(<16 x i16>, <16 x i16>)

declare <8 x i16> @llvm.x86.sse2.padds.w(<8 x i16>, <8 x i16>) #0

define <8 x i16> @test_mask_adds_epi16_rrk_128(<8 x i16> %a, <8 x i16> %b, <8 x i16> %passThru, i8 %mask) {
; X86-LABEL: test_mask_adds_epi16_rrk_128:
; X86:       # %bb.0:
; X86-NEXT:    movzbl {{[0-9]+}}(%esp), %eax # encoding: [0x0f,0xb6,0x44,0x24,0x04]
; X86-NEXT:    kmovd %eax, %k1 # encoding: [0xc5,0xfb,0x92,0xc8]
; X86-NEXT:    vpaddsw %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf1,0x7d,0x09,0xed,0xd1]
; X86-NEXT:    vmovdqa %xmm2, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xc2]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_adds_epi16_rrk_128:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpaddsw %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf1,0x7d,0x09,0xed,0xd1]
; X64-NEXT:    vmovdqa %xmm2, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xc2]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = call <8 x i16> @llvm.x86.sse2.padds.w(<8 x i16> %a, <8 x i16> %b)
  %2 = bitcast i8 %mask to <8 x i1>
  %3 = select <8 x i1> %2, <8 x i16> %1, <8 x i16> %passThru
  ret <8 x i16> %3
}

define <8 x i16> @test_mask_adds_epi16_rrkz_128(<8 x i16> %a, <8 x i16> %b, i8 %mask) {
; X86-LABEL: test_mask_adds_epi16_rrkz_128:
; X86:       # %bb.0:
; X86-NEXT:    movzbl {{[0-9]+}}(%esp), %eax # encoding: [0x0f,0xb6,0x44,0x24,0x04]
; X86-NEXT:    kmovd %eax, %k1 # encoding: [0xc5,0xfb,0x92,0xc8]
; X86-NEXT:    vpaddsw %xmm1, %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf1,0x7d,0x89,0xed,0xc1]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_adds_epi16_rrkz_128:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpaddsw %xmm1, %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf1,0x7d,0x89,0xed,0xc1]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = call <8 x i16> @llvm.x86.sse2.padds.w(<8 x i16> %a, <8 x i16> %b)
  %2 = bitcast i8 %mask to <8 x i1>
  %3 = select <8 x i1> %2, <8 x i16> %1, <8 x i16> zeroinitializer
  ret <8 x i16> %3
}

define <8 x i16> @test_mask_adds_epi16_rmk_128(<8 x i16> %a, <8 x i16>* %ptr_b, <8 x i16> %passThru, i8 %mask) {
; X86-LABEL: test_mask_adds_epi16_rmk_128:
; X86:       # %bb.0:
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT:    movzbl {{[0-9]+}}(%esp), %ecx # encoding: [0x0f,0xb6,0x4c,0x24,0x08]
; X86-NEXT:    kmovd %ecx, %k1 # encoding: [0xc5,0xfb,0x92,0xc9]
; X86-NEXT:    vpaddsw (%eax), %xmm0, %xmm1 {%k1} # encoding: [0x62,0xf1,0x7d,0x09,0xed,0x08]
; X86-NEXT:    vmovdqa %xmm1, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xc1]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_adds_epi16_rmk_128:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT:    vpaddsw (%rdi), %xmm0, %xmm1 {%k1} # encoding: [0x62,0xf1,0x7d,0x09,0xed,0x0f]
; X64-NEXT:    vmovdqa %xmm1, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xc1]
; X64-NEXT:    retq # encoding: [0xc3]
  %b = load <8 x i16>, <8 x i16>* %ptr_b
  %1 = call <8 x i16> @llvm.x86.sse2.padds.w(<8 x i16> %a, <8 x i16> %b)
  %2 = bitcast i8 %mask to <8 x i1>
  %3 = select <8 x i1> %2, <8 x i16> %1, <8 x i16> %passThru
  ret <8 x i16> %3
}

define <8 x i16> @test_mask_adds_epi16_rmkz_128(<8 x i16> %a, <8 x i16>* %ptr_b, i8 %mask) {
; X86-LABEL: test_mask_adds_epi16_rmkz_128:
; X86:       # %bb.0:
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT:    movzbl {{[0-9]+}}(%esp), %ecx # encoding: [0x0f,0xb6,0x4c,0x24,0x08]
; X86-NEXT:    kmovd %ecx, %k1 # encoding: [0xc5,0xfb,0x92,0xc9]
; X86-NEXT:    vpaddsw (%eax), %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf1,0x7d,0x89,0xed,0x00]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_adds_epi16_rmkz_128:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT:    vpaddsw (%rdi), %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf1,0x7d,0x89,0xed,0x07]
; X64-NEXT:    retq # encoding: [0xc3]
  %b = load <8 x i16>, <8 x i16>* %ptr_b
  %1 = call <8 x i16> @llvm.x86.sse2.padds.w(<8 x i16> %a, <8 x i16> %b)
  %2 = bitcast i8 %mask to <8 x i1>
  %3 = select <8 x i1> %2, <8 x i16> %1, <8 x i16> zeroinitializer
  ret <8 x i16> %3
}

declare <16 x i16> @llvm.x86.avx2.padds.w(<16 x i16>, <16 x i16>) #0

define <16 x i16> @test_mask_adds_epi16_rrk_256(<16 x i16> %a, <16 x i16> %b, <16 x i16> %passThru, i16 %mask) {
; X86-LABEL: test_mask_adds_epi16_rrk_256:
; X86:       # %bb.0:
; X86-NEXT:    kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x04]
; X86-NEXT:    vpaddsw %ymm1, %ymm0, %ymm2 {%k1} # encoding: [0x62,0xf1,0x7d,0x29,0xed,0xd1]
; X86-NEXT:    vmovdqa %ymm2, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xc2]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_adds_epi16_rrk_256:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpaddsw %ymm1, %ymm0, %ymm2 {%k1} # encoding: [0x62,0xf1,0x7d,0x29,0xed,0xd1]
; X64-NEXT:    vmovdqa %ymm2, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xc2]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = call <16 x i16> @llvm.x86.avx2.padds.w(<16 x i16> %a, <16 x i16> %b)
  %2 = bitcast i16 %mask to <16 x i1>
  %3 = select <16 x i1> %2, <16 x i16> %1, <16 x i16> %passThru
  ret <16 x i16> %3
}

define <16 x i16> @test_mask_adds_epi16_rrkz_256(<16 x i16> %a, <16 x i16> %b, i16 %mask) {
; X86-LABEL: test_mask_adds_epi16_rrkz_256:
; X86:       # %bb.0:
; X86-NEXT:    kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x04]
; X86-NEXT:    vpaddsw %ymm1, %ymm0, %ymm0 {%k1} {z} # encoding: [0x62,0xf1,0x7d,0xa9,0xed,0xc1]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_adds_epi16_rrkz_256:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpaddsw %ymm1, %ymm0, %ymm0 {%k1} {z} # encoding: [0x62,0xf1,0x7d,0xa9,0xed,0xc1]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = call <16 x i16> @llvm.x86.avx2.padds.w(<16 x i16> %a, <16 x i16> %b)
  %2 = bitcast i16 %mask to <16 x i1>
  %3 = select <16 x i1> %2, <16 x i16> %1, <16 x i16> zeroinitializer
  ret <16 x i16> %3
}

define <16 x i16> @test_mask_adds_epi16_rmk_256(<16 x i16> %a, <16 x i16>* %ptr_b, <16 x i16> %passThru, i16 %mask) {
; X86-LABEL: test_mask_adds_epi16_rmk_256:
; X86:       # %bb.0:
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT:    kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x08]
; X86-NEXT:    vpaddsw (%eax), %ymm0, %ymm1 {%k1} # encoding: [0x62,0xf1,0x7d,0x29,0xed,0x08]
; X86-NEXT:    vmovdqa %ymm1, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xc1]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_adds_epi16_rmk_256:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT:    vpaddsw (%rdi), %ymm0, %ymm1 {%k1} # encoding: [0x62,0xf1,0x7d,0x29,0xed,0x0f]
; X64-NEXT:    vmovdqa %ymm1, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xc1]
; X64-NEXT:    retq # encoding: [0xc3]
  %b = load <16 x i16>, <16 x i16>* %ptr_b
  %1 = call <16 x i16> @llvm.x86.avx2.padds.w(<16 x i16> %a, <16 x i16> %b)
  %2 = bitcast i16 %mask to <16 x i1>
  %3 = select <16 x i1> %2, <16 x i16> %1, <16 x i16> %passThru
  ret <16 x i16> %3
}

define <16 x i16> @test_mask_adds_epi16_rmkz_256(<16 x i16> %a, <16 x i16>* %ptr_b, i16 %mask) {
; X86-LABEL: test_mask_adds_epi16_rmkz_256:
; X86:       # %bb.0:
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT:    kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x08]
; X86-NEXT:    vpaddsw (%eax), %ymm0, %ymm0 {%k1} {z} # encoding: [0x62,0xf1,0x7d,0xa9,0xed,0x00]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_adds_epi16_rmkz_256:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT:    vpaddsw (%rdi), %ymm0, %ymm0 {%k1} {z} # encoding: [0x62,0xf1,0x7d,0xa9,0xed,0x07]
; X64-NEXT:    retq # encoding: [0xc3]
  %b = load <16 x i16>, <16 x i16>* %ptr_b
  %1 = call <16 x i16> @llvm.x86.avx2.padds.w(<16 x i16> %a, <16 x i16> %b)
  %2 = bitcast i16 %mask to <16 x i1>
  %3 = select <16 x i1> %2, <16 x i16> %1, <16 x i16> zeroinitializer
  ret <16 x i16> %3
}

declare <8 x i16> @llvm.x86.sse2.psubs.w(<8 x i16>, <8 x i16>) #0

define <8 x i16> @test_mask_subs_epi16_rrk_128(<8 x i16> %a, <8 x i16> %b, <8 x i16> %passThru, i8 %mask) {
; X86-LABEL: test_mask_subs_epi16_rrk_128:
; X86:       # %bb.0:
; X86-NEXT:    movzbl {{[0-9]+}}(%esp), %eax # encoding: [0x0f,0xb6,0x44,0x24,0x04]
; X86-NEXT:    kmovd %eax, %k1 # encoding: [0xc5,0xfb,0x92,0xc8]
; X86-NEXT:    vpsubsw %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf1,0x7d,0x09,0xe9,0xd1]
; X86-NEXT:    vmovdqa %xmm2, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xc2]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_subs_epi16_rrk_128:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpsubsw %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf1,0x7d,0x09,0xe9,0xd1]
; X64-NEXT:    vmovdqa %xmm2, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xc2]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = call <8 x i16> @llvm.x86.sse2.psubs.w(<8 x i16> %a, <8 x i16> %b)
  %2 = bitcast i8 %mask to <8 x i1>
  %3 = select <8 x i1> %2, <8 x i16> %1, <8 x i16> %passThru
  ret <8 x i16> %3
}

define <8 x i16> @test_mask_subs_epi16_rrkz_128(<8 x i16> %a, <8 x i16> %b, i8 %mask) {
; X86-LABEL: test_mask_subs_epi16_rrkz_128:
; X86:       # %bb.0:
; X86-NEXT:    movzbl {{[0-9]+}}(%esp), %eax # encoding: [0x0f,0xb6,0x44,0x24,0x04]
; X86-NEXT:    kmovd %eax, %k1 # encoding: [0xc5,0xfb,0x92,0xc8]
; X86-NEXT:    vpsubsw %xmm1, %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf1,0x7d,0x89,0xe9,0xc1]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_subs_epi16_rrkz_128:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpsubsw %xmm1, %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf1,0x7d,0x89,0xe9,0xc1]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = call <8 x i16> @llvm.x86.sse2.psubs.w(<8 x i16> %a, <8 x i16> %b)
  %2 = bitcast i8 %mask to <8 x i1>
  %3 = select <8 x i1> %2, <8 x i16> %1, <8 x i16> zeroinitializer
  ret <8 x i16> %3
}

define <8 x i16> @test_mask_subs_epi16_rmk_128(<8 x i16> %a, <8 x i16>* %ptr_b, <8 x i16> %passThru, i8 %mask) {
; X86-LABEL: test_mask_subs_epi16_rmk_128:
; X86:       # %bb.0:
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT:    movzbl {{[0-9]+}}(%esp), %ecx # encoding: [0x0f,0xb6,0x4c,0x24,0x08]
; X86-NEXT:    kmovd %ecx, %k1 # encoding: [0xc5,0xfb,0x92,0xc9]
; X86-NEXT:    vpsubsw (%eax), %xmm0, %xmm1 {%k1} # encoding: [0x62,0xf1,0x7d,0x09,0xe9,0x08]
; X86-NEXT:    vmovdqa %xmm1, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xc1]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_subs_epi16_rmk_128:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT:    vpsubsw (%rdi), %xmm0, %xmm1 {%k1} # encoding: [0x62,0xf1,0x7d,0x09,0xe9,0x0f]
; X64-NEXT:    vmovdqa %xmm1, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xc1]
; X64-NEXT:    retq # encoding: [0xc3]
  %b = load <8 x i16>, <8 x i16>* %ptr_b
  %1 = call <8 x i16> @llvm.x86.sse2.psubs.w(<8 x i16> %a, <8 x i16> %b)
  %2 = bitcast i8 %mask to <8 x i1>
  %3 = select <8 x i1> %2, <8 x i16> %1, <8 x i16> %passThru
  ret <8 x i16> %3
}

define <8 x i16> @test_mask_subs_epi16_rmkz_128(<8 x i16> %a, <8 x i16>* %ptr_b, i8 %mask) {
; X86-LABEL: test_mask_subs_epi16_rmkz_128:
; X86:       # %bb.0:
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT:    movzbl {{[0-9]+}}(%esp), %ecx # encoding: [0x0f,0xb6,0x4c,0x24,0x08]
; X86-NEXT:    kmovd %ecx, %k1 # encoding: [0xc5,0xfb,0x92,0xc9]
; X86-NEXT:    vpsubsw (%eax), %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf1,0x7d,0x89,0xe9,0x00]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_subs_epi16_rmkz_128:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT:    vpsubsw (%rdi), %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf1,0x7d,0x89,0xe9,0x07]
; X64-NEXT:    retq # encoding: [0xc3]
  %b = load <8 x i16>, <8 x i16>* %ptr_b
  %1 = call <8 x i16> @llvm.x86.sse2.psubs.w(<8 x i16> %a, <8 x i16> %b)
  %2 = bitcast i8 %mask to <8 x i1>
  %3 = select <8 x i1> %2, <8 x i16> %1, <8 x i16> zeroinitializer
  ret <8 x i16> %3
}

declare <16 x i16> @llvm.x86.avx2.psubs.w(<16 x i16>, <16 x i16>) #0

define <16 x i16> @test_mask_subs_epi16_rrk_256(<16 x i16> %a, <16 x i16> %b, <16 x i16> %passThru, i16 %mask) {
; X86-LABEL: test_mask_subs_epi16_rrk_256:
; X86:       # %bb.0:
; X86-NEXT:    kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x04]
; X86-NEXT:    vpsubsw %ymm1, %ymm0, %ymm2 {%k1} # encoding: [0x62,0xf1,0x7d,0x29,0xe9,0xd1]
; X86-NEXT:    vmovdqa %ymm2, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xc2]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_subs_epi16_rrk_256:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpsubsw %ymm1, %ymm0, %ymm2 {%k1} # encoding: [0x62,0xf1,0x7d,0x29,0xe9,0xd1]
; X64-NEXT:    vmovdqa %ymm2, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xc2]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = call <16 x i16> @llvm.x86.avx2.psubs.w(<16 x i16> %a, <16 x i16> %b)
  %2 = bitcast i16 %mask to <16 x i1>
  %3 = select <16 x i1> %2, <16 x i16> %1, <16 x i16> %passThru
  ret <16 x i16> %3
}

define <16 x i16> @test_mask_subs_epi16_rrkz_256(<16 x i16> %a, <16 x i16> %b, i16 %mask) {
; X86-LABEL: test_mask_subs_epi16_rrkz_256:
; X86:       # %bb.0:
; X86-NEXT:    kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x04]
; X86-NEXT:    vpsubsw %ymm1, %ymm0, %ymm0 {%k1} {z} # encoding: [0x62,0xf1,0x7d,0xa9,0xe9,0xc1]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_subs_epi16_rrkz_256:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpsubsw %ymm1, %ymm0, %ymm0 {%k1} {z} # encoding: [0x62,0xf1,0x7d,0xa9,0xe9,0xc1]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = call <16 x i16> @llvm.x86.avx2.psubs.w(<16 x i16> %a, <16 x i16> %b)
  %2 = bitcast i16 %mask to <16 x i1>
  %3 = select <16 x i1> %2, <16 x i16> %1, <16 x i16> zeroinitializer
  ret <16 x i16> %3
}

define <16 x i16> @test_mask_subs_epi16_rmk_256(<16 x i16> %a, <16 x i16>* %ptr_b, <16 x i16> %passThru, i16 %mask) {
; X86-LABEL: test_mask_subs_epi16_rmk_256:
; X86:       # %bb.0:
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT:    kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x08]
; X86-NEXT:    vpsubsw (%eax), %ymm0, %ymm1 {%k1} # encoding: [0x62,0xf1,0x7d,0x29,0xe9,0x08]
; X86-NEXT:    vmovdqa %ymm1, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xc1]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_subs_epi16_rmk_256:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT:    vpsubsw (%rdi), %ymm0, %ymm1 {%k1} # encoding: [0x62,0xf1,0x7d,0x29,0xe9,0x0f]
; X64-NEXT:    vmovdqa %ymm1, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xc1]
; X64-NEXT:    retq # encoding: [0xc3]
  %b = load <16 x i16>, <16 x i16>* %ptr_b
  %1 = call <16 x i16> @llvm.x86.avx2.psubs.w(<16 x i16> %a, <16 x i16> %b)
  %2 = bitcast i16 %mask to <16 x i1>
  %3 = select <16 x i1> %2, <16 x i16> %1, <16 x i16> %passThru
  ret <16 x i16> %3
}

define <16 x i16> @test_mask_subs_epi16_rmkz_256(<16 x i16> %a, <16 x i16>* %ptr_b, i16 %mask) {
; X86-LABEL: test_mask_subs_epi16_rmkz_256:
; X86:       # %bb.0:
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT:    kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x08]
; X86-NEXT:    vpsubsw (%eax), %ymm0, %ymm0 {%k1} {z} # encoding: [0x62,0xf1,0x7d,0xa9,0xe9,0x00]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_subs_epi16_rmkz_256:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT:    vpsubsw (%rdi), %ymm0, %ymm0 {%k1} {z} # encoding: [0x62,0xf1,0x7d,0xa9,0xe9,0x07]
; X64-NEXT:    retq # encoding: [0xc3]
  %b = load <16 x i16>, <16 x i16>* %ptr_b
  %1 = call <16 x i16> @llvm.x86.avx2.psubs.w(<16 x i16> %a, <16 x i16> %b)
  %2 = bitcast i16 %mask to <16 x i1>
  %3 = select <16 x i1> %2, <16 x i16> %1, <16 x i16> zeroinitializer
  ret <16 x i16> %3
}

declare <16 x i8> @llvm.x86.sse2.padds.b(<16 x i8>, <16 x i8>) #0

define <16 x i8> @test_mask_adds_epi8_rrk_128(<16 x i8> %a, <16 x i8> %b, <16 x i8> %passThru, i16 %mask) {
; X86-LABEL: test_mask_adds_epi8_rrk_128:
; X86:       # %bb.0:
; X86-NEXT:    kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x04]
; X86-NEXT:    vpaddsb %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf1,0x7d,0x09,0xec,0xd1]
; X86-NEXT:    vmovdqa %xmm2, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xc2]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_adds_epi8_rrk_128:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpaddsb %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf1,0x7d,0x09,0xec,0xd1]
; X64-NEXT:    vmovdqa %xmm2, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xc2]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = call <16 x i8> @llvm.x86.sse2.padds.b(<16 x i8> %a, <16 x i8> %b)
  %2 = bitcast i16 %mask to <16 x i1>
  %3 = select <16 x i1> %2, <16 x i8> %1, <16 x i8> %passThru
  ret <16 x i8> %3
}

define <16 x i8> @test_mask_adds_epi8_rrkz_128(<16 x i8> %a, <16 x i8> %b, i16 %mask) {
; X86-LABEL: test_mask_adds_epi8_rrkz_128:
; X86:       # %bb.0:
; X86-NEXT:    kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x04]
; X86-NEXT:    vpaddsb %xmm1, %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf1,0x7d,0x89,0xec,0xc1]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_adds_epi8_rrkz_128:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpaddsb %xmm1, %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf1,0x7d,0x89,0xec,0xc1]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = call <16 x i8> @llvm.x86.sse2.padds.b(<16 x i8> %a, <16 x i8> %b)
  %2 = bitcast i16 %mask to <16 x i1>
  %3 = select <16 x i1> %2, <16 x i8> %1, <16 x i8> zeroinitializer
  ret <16 x i8> %3
}

define <16 x i8> @test_mask_adds_epi8_rm_128(<16 x i8> %a, <16 x i8>* %ptr_b) {
; X86-LABEL: test_mask_adds_epi8_rm_128:
; X86:       # %bb.0:
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT:    vpaddsb (%eax), %xmm0, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0xec,0x00]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_adds_epi8_rm_128:
; X64:       # %bb.0:
; X64-NEXT:    vpaddsb (%rdi), %xmm0, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0xec,0x07]
; X64-NEXT:    retq # encoding: [0xc3]
  %b = load <16 x i8>, <16 x i8>* %ptr_b
  %1 = call <16 x i8> @llvm.x86.sse2.padds.b(<16 x i8> %a, <16 x i8> %b)
  ret <16 x i8> %1
}

define <16 x i8> @test_mask_adds_epi8_rmk_128(<16 x i8> %a, <16 x i8>* %ptr_b, <16 x i8> %passThru, i16 %mask) {
; X86-LABEL: test_mask_adds_epi8_rmk_128:
; X86:       # %bb.0:
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT:    kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x08]
; X86-NEXT:    vpaddsb (%eax), %xmm0, %xmm1 {%k1} # encoding: [0x62,0xf1,0x7d,0x09,0xec,0x08]
; X86-NEXT:    vmovdqa %xmm1, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xc1]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_adds_epi8_rmk_128:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT:    vpaddsb (%rdi), %xmm0, %xmm1 {%k1} # encoding: [0x62,0xf1,0x7d,0x09,0xec,0x0f]
; X64-NEXT:    vmovdqa %xmm1, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xc1]
; X64-NEXT:    retq # encoding: [0xc3]
  %b = load <16 x i8>, <16 x i8>* %ptr_b
  %1 = call <16 x i8> @llvm.x86.sse2.padds.b(<16 x i8> %a, <16 x i8> %b)
  %2 = bitcast i16 %mask to <16 x i1>
  %3 = select <16 x i1> %2, <16 x i8> %1, <16 x i8> %passThru
  ret <16 x i8> %3
}

define <16 x i8> @test_mask_adds_epi8_rmkz_128(<16 x i8> %a, <16 x i8>* %ptr_b, i16 %mask) {
; X86-LABEL: test_mask_adds_epi8_rmkz_128:
; X86:       # %bb.0:
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT:    kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x08]
; X86-NEXT:    vpaddsb (%eax), %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf1,0x7d,0x89,0xec,0x00]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_adds_epi8_rmkz_128:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT:    vpaddsb (%rdi), %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf1,0x7d,0x89,0xec,0x07]
; X64-NEXT:    retq # encoding: [0xc3]
  %b = load <16 x i8>, <16 x i8>* %ptr_b
  %1 = call <16 x i8> @llvm.x86.sse2.padds.b(<16 x i8> %a, <16 x i8> %b)
  %2 = bitcast i16 %mask to <16 x i1>
  %3 = select <16 x i1> %2, <16 x i8> %1, <16 x i8> zeroinitializer
  ret <16 x i8> %3
}

declare <32 x i8> @llvm.x86.avx2.padds.b(<32 x i8>, <32 x i8>) #0

define <32 x i8> @test_mask_adds_epi8_rrk_256(<32 x i8> %a, <32 x i8> %b, <32 x i8> %passThru, i32 %mask) {
; X86-LABEL: test_mask_adds_epi8_rrk_256:
; X86:       # %bb.0:
; X86-NEXT:    kmovd {{[0-9]+}}(%esp), %k1 # encoding: [0xc4,0xe1,0xf9,0x90,0x4c,0x24,0x04]
; X86-NEXT:    vpaddsb %ymm1, %ymm0, %ymm2 {%k1} # encoding: [0x62,0xf1,0x7d,0x29,0xec,0xd1]
; X86-NEXT:    vmovdqa %ymm2, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xc2]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_adds_epi8_rrk_256:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpaddsb %ymm1, %ymm0, %ymm2 {%k1} # encoding: [0x62,0xf1,0x7d,0x29,0xec,0xd1]
; X64-NEXT:    vmovdqa %ymm2, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xc2]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = call <32 x i8> @llvm.x86.avx2.padds.b(<32 x i8> %a, <32 x i8> %b)
  %2 = bitcast i32 %mask to <32 x i1>
  %3 = select <32 x i1> %2, <32 x i8> %1, <32 x i8> %passThru
  ret <32 x i8> %3
}

define <32 x i8> @test_mask_adds_epi8_rrkz_256(<32 x i8> %a, <32 x i8> %b, i32 %mask) {
; X86-LABEL: test_mask_adds_epi8_rrkz_256:
; X86:       # %bb.0:
; X86-NEXT:    kmovd {{[0-9]+}}(%esp), %k1 # encoding: [0xc4,0xe1,0xf9,0x90,0x4c,0x24,0x04]
; X86-NEXT:    vpaddsb %ymm1, %ymm0, %ymm0 {%k1} {z} # encoding: [0x62,0xf1,0x7d,0xa9,0xec,0xc1]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_adds_epi8_rrkz_256:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpaddsb %ymm1, %ymm0, %ymm0 {%k1} {z} # encoding: [0x62,0xf1,0x7d,0xa9,0xec,0xc1]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = call <32 x i8> @llvm.x86.avx2.padds.b(<32 x i8> %a, <32 x i8> %b)
  %2 = bitcast i32 %mask to <32 x i1>
  %3 = select <32 x i1> %2, <32 x i8> %1, <32 x i8> zeroinitializer
  ret <32 x i8> %3
}

define <32 x i8> @test_mask_adds_epi8_rmk_256(<32 x i8> %a, <32 x i8>* %ptr_b, <32 x i8> %passThru, i32 %mask) {
; X86-LABEL: test_mask_adds_epi8_rmk_256:
; X86:       # %bb.0:
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT:    kmovd {{[0-9]+}}(%esp), %k1 # encoding: [0xc4,0xe1,0xf9,0x90,0x4c,0x24,0x08]
; X86-NEXT:    vpaddsb (%eax), %ymm0, %ymm1 {%k1} # encoding: [0x62,0xf1,0x7d,0x29,0xec,0x08]
; X86-NEXT:    vmovdqa %ymm1, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xc1]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_adds_epi8_rmk_256:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT:    vpaddsb (%rdi), %ymm0, %ymm1 {%k1} # encoding: [0x62,0xf1,0x7d,0x29,0xec,0x0f]
; X64-NEXT:    vmovdqa %ymm1, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xc1]
; X64-NEXT:    retq # encoding: [0xc3]
  %b = load <32 x i8>, <32 x i8>* %ptr_b
  %1 = call <32 x i8> @llvm.x86.avx2.padds.b(<32 x i8> %a, <32 x i8> %b)
  %2 = bitcast i32 %mask to <32 x i1>
  %3 = select <32 x i1> %2, <32 x i8> %1, <32 x i8> %passThru
  ret <32 x i8> %3
}

define <32 x i8> @test_mask_adds_epi8_rmkz_256(<32 x i8> %a, <32 x i8>* %ptr_b, i32 %mask) {
; X86-LABEL: test_mask_adds_epi8_rmkz_256:
; X86:       # %bb.0:
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT:    kmovd {{[0-9]+}}(%esp), %k1 # encoding: [0xc4,0xe1,0xf9,0x90,0x4c,0x24,0x08]
; X86-NEXT:    vpaddsb (%eax), %ymm0, %ymm0 {%k1} {z} # encoding: [0x62,0xf1,0x7d,0xa9,0xec,0x00]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_adds_epi8_rmkz_256:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT:    vpaddsb (%rdi), %ymm0, %ymm0 {%k1} {z} # encoding: [0x62,0xf1,0x7d,0xa9,0xec,0x07]
; X64-NEXT:    retq # encoding: [0xc3]
  %b = load <32 x i8>, <32 x i8>* %ptr_b
  %1 = call <32 x i8> @llvm.x86.avx2.padds.b(<32 x i8> %a, <32 x i8> %b)
  %2 = bitcast i32 %mask to <32 x i1>
  %3 = select <32 x i1> %2, <32 x i8> %1, <32 x i8> zeroinitializer
  ret <32 x i8> %3
}

declare <16 x i8> @llvm.x86.sse2.psubs.b(<16 x i8>, <16 x i8>) #0

define <16 x i8> @test_mask_subs_epi8_rrk_128(<16 x i8> %a, <16 x i8> %b, <16 x i8> %passThru, i16 %mask) {
; X86-LABEL: test_mask_subs_epi8_rrk_128:
; X86:       # %bb.0:
; X86-NEXT:    kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x04]
; X86-NEXT:    vpsubsb %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf1,0x7d,0x09,0xe8,0xd1]
; X86-NEXT:    vmovdqa %xmm2, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xc2]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_subs_epi8_rrk_128:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpsubsb %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf1,0x7d,0x09,0xe8,0xd1]
; X64-NEXT:    vmovdqa %xmm2, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xc2]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = call <16 x i8> @llvm.x86.sse2.psubs.b(<16 x i8> %a, <16 x i8> %b)
  %2 = bitcast i16 %mask to <16 x i1>
  %3 = select <16 x i1> %2, <16 x i8> %1, <16 x i8> %passThru
  ret <16 x i8> %3
}

define <16 x i8> @test_mask_subs_epi8_rrkz_128(<16 x i8> %a, <16 x i8> %b, i16 %mask) {
; X86-LABEL: test_mask_subs_epi8_rrkz_128:
; X86:       # %bb.0:
; X86-NEXT:    kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x04]
; X86-NEXT:    vpsubsb %xmm1, %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf1,0x7d,0x89,0xe8,0xc1]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_subs_epi8_rrkz_128:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpsubsb %xmm1, %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf1,0x7d,0x89,0xe8,0xc1]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = call <16 x i8> @llvm.x86.sse2.psubs.b(<16 x i8> %a, <16 x i8> %b)
  %2 = bitcast i16 %mask to <16 x i1>
  %3 = select <16 x i1> %2, <16 x i8> %1, <16 x i8> zeroinitializer
  ret <16 x i8> %3
}

define <16 x i8> @test_mask_subs_epi8_rmk_128(<16 x i8> %a, <16 x i8>* %ptr_b, <16 x i8> %passThru, i16 %mask) {
; X86-LABEL: test_mask_subs_epi8_rmk_128:
; X86:       # %bb.0:
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT:    kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x08]
; X86-NEXT:    vpsubsb (%eax), %xmm0, %xmm1 {%k1} # encoding: [0x62,0xf1,0x7d,0x09,0xe8,0x08]
; X86-NEXT:    vmovdqa %xmm1, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xc1]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_subs_epi8_rmk_128:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT:    vpsubsb (%rdi), %xmm0, %xmm1 {%k1} # encoding: [0x62,0xf1,0x7d,0x09,0xe8,0x0f]
; X64-NEXT:    vmovdqa %xmm1, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xc1]
; X64-NEXT:    retq # encoding: [0xc3]
  %b = load <16 x i8>, <16 x i8>* %ptr_b
  %1 = call <16 x i8> @llvm.x86.sse2.psubs.b(<16 x i8> %a, <16 x i8> %b)
  %2 = bitcast i16 %mask to <16 x i1>
  %3 = select <16 x i1> %2, <16 x i8> %1, <16 x i8> %passThru
  ret <16 x i8> %3
}

define <16 x i8> @test_mask_subs_epi8_rmkz_128(<16 x i8> %a, <16 x i8>* %ptr_b, i16 %mask) {
; X86-LABEL: test_mask_subs_epi8_rmkz_128:
; X86:       # %bb.0:
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT:    kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x08]
; X86-NEXT:    vpsubsb (%eax), %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf1,0x7d,0x89,0xe8,0x00]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_subs_epi8_rmkz_128:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT:    vpsubsb (%rdi), %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf1,0x7d,0x89,0xe8,0x07]
; X64-NEXT:    retq # encoding: [0xc3]
  %b = load <16 x i8>, <16 x i8>* %ptr_b
  %1 = call <16 x i8> @llvm.x86.sse2.psubs.b(<16 x i8> %a, <16 x i8> %b)
  %2 = bitcast i16 %mask to <16 x i1>
  %3 = select <16 x i1> %2, <16 x i8> %1, <16 x i8> zeroinitializer
  ret <16 x i8> %3
}

declare <32 x i8> @llvm.x86.avx2.psubs.b(<32 x i8>, <32 x i8>) #0

define <32 x i8> @test_mask_subs_epi8_rrk_256(<32 x i8> %a, <32 x i8> %b, <32 x i8> %passThru, i32 %mask) {
; X86-LABEL: test_mask_subs_epi8_rrk_256:
; X86:       # %bb.0:
; X86-NEXT:    kmovd {{[0-9]+}}(%esp), %k1 # encoding: [0xc4,0xe1,0xf9,0x90,0x4c,0x24,0x04]
; X86-NEXT:    vpsubsb %ymm1, %ymm0, %ymm2 {%k1} # encoding: [0x62,0xf1,0x7d,0x29,0xe8,0xd1]
; X86-NEXT:    vmovdqa %ymm2, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xc2]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_subs_epi8_rrk_256:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpsubsb %ymm1, %ymm0, %ymm2 {%k1} # encoding: [0x62,0xf1,0x7d,0x29,0xe8,0xd1]
; X64-NEXT:    vmovdqa %ymm2, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xc2]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = call <32 x i8> @llvm.x86.avx2.psubs.b(<32 x i8> %a, <32 x i8> %b)
  %2 = bitcast i32 %mask to <32 x i1>
  %3 = select <32 x i1> %2, <32 x i8> %1, <32 x i8> %passThru
  ret <32 x i8> %3
}

define <32 x i8> @test_mask_subs_epi8_rrkz_256(<32 x i8> %a, <32 x i8> %b, i32 %mask) {
; X86-LABEL: test_mask_subs_epi8_rrkz_256:
; X86:       # %bb.0:
; X86-NEXT:    kmovd {{[0-9]+}}(%esp), %k1 # encoding: [0xc4,0xe1,0xf9,0x90,0x4c,0x24,0x04]
; X86-NEXT:    vpsubsb %ymm1, %ymm0, %ymm0 {%k1} {z} # encoding: [0x62,0xf1,0x7d,0xa9,0xe8,0xc1]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_subs_epi8_rrkz_256:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpsubsb %ymm1, %ymm0, %ymm0 {%k1} {z} # encoding: [0x62,0xf1,0x7d,0xa9,0xe8,0xc1]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = call <32 x i8> @llvm.x86.avx2.psubs.b(<32 x i8> %a, <32 x i8> %b)
  %2 = bitcast i32 %mask to <32 x i1>
  %3 = select <32 x i1> %2, <32 x i8> %1, <32 x i8> zeroinitializer
  ret <32 x i8> %3
}

define <32 x i8> @test_mask_subs_epi8_rmk_256(<32 x i8> %a, <32 x i8>* %ptr_b, <32 x i8> %passThru, i32 %mask) {
; X86-LABEL: test_mask_subs_epi8_rmk_256:
; X86:       # %bb.0:
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT:    kmovd {{[0-9]+}}(%esp), %k1 # encoding: [0xc4,0xe1,0xf9,0x90,0x4c,0x24,0x08]
; X86-NEXT:    vpsubsb (%eax), %ymm0, %ymm1 {%k1} # encoding: [0x62,0xf1,0x7d,0x29,0xe8,0x08]
; X86-NEXT:    vmovdqa %ymm1, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xc1]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_subs_epi8_rmk_256:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT:    vpsubsb (%rdi), %ymm0, %ymm1 {%k1} # encoding: [0x62,0xf1,0x7d,0x29,0xe8,0x0f]
; X64-NEXT:    vmovdqa %ymm1, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xc1]
; X64-NEXT:    retq # encoding: [0xc3]
  %b = load <32 x i8>, <32 x i8>* %ptr_b
  %1 = call <32 x i8> @llvm.x86.avx2.psubs.b(<32 x i8> %a, <32 x i8> %b)
  %2 = bitcast i32 %mask to <32 x i1>
  %3 = select <32 x i1> %2, <32 x i8> %1, <32 x i8> %passThru
  ret <32 x i8> %3
}

define <32 x i8> @test_mask_subs_epi8_rmkz_256(<32 x i8> %a, <32 x i8>* %ptr_b, i32 %mask) {
; X86-LABEL: test_mask_subs_epi8_rmkz_256:
; X86:       # %bb.0:
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT:    kmovd {{[0-9]+}}(%esp), %k1 # encoding: [0xc4,0xe1,0xf9,0x90,0x4c,0x24,0x08]
; X86-NEXT:    vpsubsb (%eax), %ymm0, %ymm0 {%k1} {z} # encoding: [0x62,0xf1,0x7d,0xa9,0xe8,0x00]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_subs_epi8_rmkz_256:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT:    vpsubsb (%rdi), %ymm0, %ymm0 {%k1} {z} # encoding: [0x62,0xf1,0x7d,0xa9,0xe8,0x07]
; X64-NEXT:    retq # encoding: [0xc3]
  %b = load <32 x i8>, <32 x i8>* %ptr_b
  %1 = call <32 x i8> @llvm.x86.avx2.psubs.b(<32 x i8> %a, <32 x i8> %b)
  %2 = bitcast i32 %mask to <32 x i1>
  %3 = select <32 x i1> %2, <32 x i8> %1, <32 x i8> zeroinitializer
  ret <32 x i8> %3
}

define <8 x i16>@test_int_x86_avx512_mask_vpermt2var_hi_128(<8 x i16> %x0, <8 x i16> %x1, <8 x i16> %x2, i8 %x3) {
; X86-LABEL: test_int_x86_avx512_mask_vpermt2var_hi_128:
; X86:       # %bb.0:
; X86-NEXT:    vmovdqa %xmm1, %xmm3 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xd9]
; X86-NEXT:    vpermt2w %xmm2, %xmm0, %xmm3 # encoding: [0x62,0xf2,0xfd,0x08,0x7d,0xda]
; X86-NEXT:    movzbl {{[0-9]+}}(%esp), %eax # encoding: [0x0f,0xb6,0x44,0x24,0x04]
; X86-NEXT:    kmovd %eax, %k1 # encoding: [0xc5,0xfb,0x92,0xc8]
; X86-NEXT:    vpermt2w %xmm2, %xmm0, %xmm1 {%k1} # encoding: [0x62,0xf2,0xfd,0x09,0x7d,0xca]
; X86-NEXT:    vpaddw %xmm3, %xmm1, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf1,0xfd,0xc3]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_vpermt2var_hi_128:
; X64:       # %bb.0:
; X64-NEXT:    vmovdqa %xmm1, %xmm3 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xd9]
; X64-NEXT:    vpermt2w %xmm2, %xmm0, %xmm3 # encoding: [0x62,0xf2,0xfd,0x08,0x7d,0xda]
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpermt2w %xmm2, %xmm0, %xmm1 {%k1} # encoding: [0x62,0xf2,0xfd,0x09,0x7d,0xca]
; X64-NEXT:    vpaddw %xmm3, %xmm1, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf1,0xfd,0xc3]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = call <8 x i16> @llvm.x86.avx512.vpermi2var.hi.128(<8 x i16> %x1, <8 x i16> %x0, <8 x i16> %x2)
  %2 = bitcast i8 %x3 to <8 x i1>
  %3 = select <8 x i1> %2, <8 x i16> %1, <8 x i16> %x1
  %4 = call <8 x i16> @llvm.x86.avx512.vpermi2var.hi.128(<8 x i16> %x1, <8 x i16> %x0, <8 x i16> %x2)
  %res2 = add <8 x i16> %3, %4
  ret <8 x i16> %res2
}

define <8 x i16>@test_int_x86_avx512_maskz_vpermt2var_hi_128(<8 x i16> %x0, <8 x i16> %x1, <8 x i16> %x2, i8 %x3) {
; X86-LABEL: test_int_x86_avx512_maskz_vpermt2var_hi_128:
; X86:       # %bb.0:
; X86-NEXT:    vmovdqa %xmm1, %xmm3 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xd9]
; X86-NEXT:    vpermt2w %xmm2, %xmm0, %xmm3 # encoding: [0x62,0xf2,0xfd,0x08,0x7d,0xda]
; X86-NEXT:    movzbl {{[0-9]+}}(%esp), %eax # encoding: [0x0f,0xb6,0x44,0x24,0x04]
; X86-NEXT:    kmovd %eax, %k1 # encoding: [0xc5,0xfb,0x92,0xc8]
; X86-NEXT:    vpermt2w %xmm2, %xmm0, %xmm1 {%k1} {z} # encoding: [0x62,0xf2,0xfd,0x89,0x7d,0xca]
; X86-NEXT:    vpaddw %xmm3, %xmm1, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf1,0xfd,0xc3]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_maskz_vpermt2var_hi_128:
; X64:       # %bb.0:
; X64-NEXT:    vmovdqa %xmm1, %xmm3 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xd9]
; X64-NEXT:    vpermt2w %xmm2, %xmm0, %xmm3 # encoding: [0x62,0xf2,0xfd,0x08,0x7d,0xda]
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpermt2w %xmm2, %xmm0, %xmm1 {%k1} {z} # encoding: [0x62,0xf2,0xfd,0x89,0x7d,0xca]
; X64-NEXT:    vpaddw %xmm3, %xmm1, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf1,0xfd,0xc3]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = call <8 x i16> @llvm.x86.avx512.vpermi2var.hi.128(<8 x i16> %x1, <8 x i16> %x0, <8 x i16> %x2)
  %2 = bitcast i8 %x3 to <8 x i1>
  %3 = select <8 x i1> %2, <8 x i16> %1, <8 x i16> zeroinitializer
  %4 = call <8 x i16> @llvm.x86.avx512.vpermi2var.hi.128(<8 x i16> %x1, <8 x i16> %x0, <8 x i16> %x2)
  %res2 = add <8 x i16> %3, %4
  ret <8 x i16> %res2
}

define <16 x i16>@test_int_x86_avx512_mask_vpermt2var_hi_256(<16 x i16> %x0, <16 x i16> %x1, <16 x i16> %x2, i16 %x3) {
; X86-LABEL: test_int_x86_avx512_mask_vpermt2var_hi_256:
; X86:       # %bb.0:
; X86-NEXT:    vmovdqa %ymm1, %ymm3 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xd9]
; X86-NEXT:    vpermt2w %ymm2, %ymm0, %ymm3 # encoding: [0x62,0xf2,0xfd,0x28,0x7d,0xda]
; X86-NEXT:    kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x04]
; X86-NEXT:    vpermt2w %ymm2, %ymm0, %ymm1 {%k1} # encoding: [0x62,0xf2,0xfd,0x29,0x7d,0xca]
; X86-NEXT:    vpaddw %ymm3, %ymm1, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xf5,0xfd,0xc3]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_vpermt2var_hi_256:
; X64:       # %bb.0:
; X64-NEXT:    vmovdqa %ymm1, %ymm3 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xd9]
; X64-NEXT:    vpermt2w %ymm2, %ymm0, %ymm3 # encoding: [0x62,0xf2,0xfd,0x28,0x7d,0xda]
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpermt2w %ymm2, %ymm0, %ymm1 {%k1} # encoding: [0x62,0xf2,0xfd,0x29,0x7d,0xca]
; X64-NEXT:    vpaddw %ymm3, %ymm1, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xf5,0xfd,0xc3]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = call <16 x i16> @llvm.x86.avx512.vpermi2var.hi.256(<16 x i16> %x1, <16 x i16> %x0, <16 x i16> %x2)
  %2 = bitcast i16 %x3 to <16 x i1>
  %3 = select <16 x i1> %2, <16 x i16> %1, <16 x i16> %x1
  %4 = call <16 x i16> @llvm.x86.avx512.vpermi2var.hi.256(<16 x i16> %x1, <16 x i16> %x0, <16 x i16> %x2)
  %res2 = add <16 x i16> %3, %4
  ret <16 x i16> %res2
}

define <16 x i16>@test_int_x86_avx512_maskz_vpermt2var_hi_256(<16 x i16> %x0, <16 x i16> %x1, <16 x i16> %x2, i16 %x3) {
; X86-LABEL: test_int_x86_avx512_maskz_vpermt2var_hi_256:
; X86:       # %bb.0:
; X86-NEXT:    vmovdqa %ymm1, %ymm3 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xd9]
; X86-NEXT:    vpermt2w %ymm2, %ymm0, %ymm3 # encoding: [0x62,0xf2,0xfd,0x28,0x7d,0xda]
; X86-NEXT:    kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x04]
; X86-NEXT:    vpermt2w %ymm2, %ymm0, %ymm1 {%k1} {z} # encoding: [0x62,0xf2,0xfd,0xa9,0x7d,0xca]
; X86-NEXT:    vpaddw %ymm3, %ymm1, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xf5,0xfd,0xc3]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_maskz_vpermt2var_hi_256:
; X64:       # %bb.0:
; X64-NEXT:    vmovdqa %ymm1, %ymm3 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xd9]
; X64-NEXT:    vpermt2w %ymm2, %ymm0, %ymm3 # encoding: [0x62,0xf2,0xfd,0x28,0x7d,0xda]
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpermt2w %ymm2, %ymm0, %ymm1 {%k1} {z} # encoding: [0x62,0xf2,0xfd,0xa9,0x7d,0xca]
; X64-NEXT:    vpaddw %ymm3, %ymm1, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xf5,0xfd,0xc3]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = call <16 x i16> @llvm.x86.avx512.vpermi2var.hi.256(<16 x i16> %x1, <16 x i16> %x0, <16 x i16> %x2)
  %2 = bitcast i16 %x3 to <16 x i1>
  %3 = select <16 x i1> %2, <16 x i16> %1, <16 x i16> zeroinitializer
  %4 = call <16 x i16> @llvm.x86.avx512.vpermi2var.hi.256(<16 x i16> %x1, <16 x i16> %x0, <16 x i16> %x2)
  %res2 = add <16 x i16> %3, %4
  ret <16 x i16> %res2
}

declare <8 x i16> @llvm.x86.avx512.vpermi2var.hi.128(<8 x i16>, <8 x i16>, <8 x i16>)

define <8 x i16>@test_int_x86_avx512_mask_vpermi2var_hi_128(<8 x i16> %x0, <8 x i16> %x1, <8 x i16> %x2, i8 %x3) {
; X86-LABEL: test_int_x86_avx512_mask_vpermi2var_hi_128:
; X86:       # %bb.0:
; X86-NEXT:    vmovdqa %xmm0, %xmm3 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xd8]
; X86-NEXT:    vpermt2w %xmm2, %xmm1, %xmm3 # encoding: [0x62,0xf2,0xf5,0x08,0x7d,0xda]
; X86-NEXT:    movzbl {{[0-9]+}}(%esp), %eax # encoding: [0x0f,0xb6,0x44,0x24,0x04]
; X86-NEXT:    kmovd %eax, %k1 # encoding: [0xc5,0xfb,0x92,0xc8]
; X86-NEXT:    vpermi2w %xmm2, %xmm0, %xmm1 {%k1} # encoding: [0x62,0xf2,0xfd,0x09,0x75,0xca]
; X86-NEXT:    vpaddw %xmm3, %xmm1, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf1,0xfd,0xc3]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_vpermi2var_hi_128:
; X64:       # %bb.0:
; X64-NEXT:    vmovdqa %xmm0, %xmm3 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xd8]
; X64-NEXT:    vpermt2w %xmm2, %xmm1, %xmm3 # encoding: [0x62,0xf2,0xf5,0x08,0x7d,0xda]
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpermi2w %xmm2, %xmm0, %xmm1 {%k1} # encoding: [0x62,0xf2,0xfd,0x09,0x75,0xca]
; X64-NEXT:    vpaddw %xmm3, %xmm1, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf1,0xfd,0xc3]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = call <8 x i16> @llvm.x86.avx512.vpermi2var.hi.128(<8 x i16> %x0, <8 x i16> %x1, <8 x i16> %x2)
  %2 = bitcast i8 %x3 to <8 x i1>
  %3 = select <8 x i1> %2, <8 x i16> %1, <8 x i16> %x1
  %4 = call <8 x i16> @llvm.x86.avx512.vpermi2var.hi.128(<8 x i16> %x0, <8 x i16> %x1, <8 x i16> %x2)
  %res2 = add <8 x i16> %3, %4
  ret <8 x i16> %res2
}

declare <16 x i16> @llvm.x86.avx512.vpermi2var.hi.256(<16 x i16>, <16 x i16>, <16 x i16>)

define <16 x i16>@test_int_x86_avx512_mask_vpermi2var_hi_256(<16 x i16> %x0, <16 x i16> %x1, <16 x i16> %x2, i16 %x3) {
; X86-LABEL: test_int_x86_avx512_mask_vpermi2var_hi_256:
; X86:       # %bb.0:
; X86-NEXT:    vmovdqa %ymm0, %ymm3 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xd8]
; X86-NEXT:    vpermt2w %ymm2, %ymm1, %ymm3 # encoding: [0x62,0xf2,0xf5,0x28,0x7d,0xda]
; X86-NEXT:    kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x04]
; X86-NEXT:    vpermi2w %ymm2, %ymm0, %ymm1 {%k1} # encoding: [0x62,0xf2,0xfd,0x29,0x75,0xca]
; X86-NEXT:    vpaddw %ymm3, %ymm1, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xf5,0xfd,0xc3]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_vpermi2var_hi_256:
; X64:       # %bb.0:
; X64-NEXT:    vmovdqa %ymm0, %ymm3 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xd8]
; X64-NEXT:    vpermt2w %ymm2, %ymm1, %ymm3 # encoding: [0x62,0xf2,0xf5,0x28,0x7d,0xda]
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpermi2w %ymm2, %ymm0, %ymm1 {%k1} # encoding: [0x62,0xf2,0xfd,0x29,0x75,0xca]
; X64-NEXT:    vpaddw %ymm3, %ymm1, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xf5,0xfd,0xc3]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = call <16 x i16> @llvm.x86.avx512.vpermi2var.hi.256(<16 x i16> %x0, <16 x i16> %x1, <16 x i16> %x2)
  %2 = bitcast i16 %x3 to <16 x i1>
  %3 = select <16 x i1> %2, <16 x i16> %1, <16 x i16> %x1
  %4 = call <16 x i16> @llvm.x86.avx512.vpermi2var.hi.256(<16 x i16> %x0, <16 x i16> %x1, <16 x i16> %x2)
  %res2 = add <16 x i16> %3, %4
  ret <16 x i16> %res2
}

declare <8 x i16> @llvm.x86.sse2.pmulhu.w(<8 x i16>, <8 x i16>)

define <8 x i16> @test_int_x86_avx512_mask_pmulhu_w_128(<8 x i16> %x0, <8 x i16> %x1, <8 x i16> %x2, i8 %x3) {
; X86-LABEL: test_int_x86_avx512_mask_pmulhu_w_128:
; X86:       # %bb.0:
; X86-NEXT:    vpmulhuw %xmm1, %xmm0, %xmm3 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0xe4,0xd9]
; X86-NEXT:    movzbl {{[0-9]+}}(%esp), %eax # encoding: [0x0f,0xb6,0x44,0x24,0x04]
; X86-NEXT:    kmovd %eax, %k1 # encoding: [0xc5,0xfb,0x92,0xc8]
; X86-NEXT:    vpmulhuw %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf1,0x7d,0x09,0xe4,0xd1]
; X86-NEXT:    vpaddw %xmm3, %xmm2, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe9,0xfd,0xc3]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_pmulhu_w_128:
; X64:       # %bb.0:
; X64-NEXT:    vpmulhuw %xmm1, %xmm0, %xmm3 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0xe4,0xd9]
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpmulhuw %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf1,0x7d,0x09,0xe4,0xd1]
; X64-NEXT:    vpaddw %xmm3, %xmm2, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe9,0xfd,0xc3]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = call <8 x i16> @llvm.x86.sse2.pmulhu.w(<8 x i16> %x0, <8 x i16> %x1)
  %2 = bitcast i8 %x3 to <8 x i1>
  %3 = select <8 x i1> %2, <8 x i16> %1, <8 x i16> %x2
  %4 = call <8 x i16> @llvm.x86.sse2.pmulhu.w(<8 x i16> %x0, <8 x i16> %x1)
  %res2 = add <8 x i16> %3, %4
  ret <8 x i16> %res2
}

declare <16 x i16> @llvm.x86.avx2.pmulhu.w(<16 x i16>, <16 x i16>)

define <16 x i16> @test_int_x86_avx512_mask_pmulhu_w_256(<16 x i16> %x0, <16 x i16> %x1, <16 x i16> %x2, i16 %x3) {
; X86-LABEL: test_int_x86_avx512_mask_pmulhu_w_256:
; X86:       # %bb.0:
; X86-NEXT:    vpmulhuw %ymm1, %ymm0, %ymm3 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0xe4,0xd9]
; X86-NEXT:    kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x04]
; X86-NEXT:    vpmulhuw %ymm1, %ymm0, %ymm2 {%k1} # encoding: [0x62,0xf1,0x7d,0x29,0xe4,0xd1]
; X86-NEXT:    vpaddw %ymm3, %ymm2, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xed,0xfd,0xc3]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_pmulhu_w_256:
; X64:       # %bb.0:
; X64-NEXT:    vpmulhuw %ymm1, %ymm0, %ymm3 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0xe4,0xd9]
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpmulhuw %ymm1, %ymm0, %ymm2 {%k1} # encoding: [0x62,0xf1,0x7d,0x29,0xe4,0xd1]
; X64-NEXT:    vpaddw %ymm3, %ymm2, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xed,0xfd,0xc3]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = call <16 x i16> @llvm.x86.avx2.pmulhu.w(<16 x i16> %x0, <16 x i16> %x1)
  %2 = bitcast i16 %x3 to <16 x i1>
  %3 = select <16 x i1> %2, <16 x i16> %1, <16 x i16> %x2
  %4 = call <16 x i16> @llvm.x86.avx2.pmulhu.w(<16 x i16> %x0, <16 x i16> %x1)
  %res2 = add <16 x i16> %3, %4
  ret <16 x i16> %res2
}

declare <8 x i16> @llvm.x86.sse2.pmulh.w(<8 x i16>, <8 x i16>)

define <8 x i16> @test_int_x86_avx512_mask_pmulh_w_128(<8 x i16> %x0, <8 x i16> %x1, <8 x i16> %x2, i8 %x3) {
; X86-LABEL: test_int_x86_avx512_mask_pmulh_w_128:
; X86:       # %bb.0:
; X86-NEXT:    vpmulhw %xmm1, %xmm0, %xmm3 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0xe5,0xd9]
; X86-NEXT:    movzbl {{[0-9]+}}(%esp), %eax # encoding: [0x0f,0xb6,0x44,0x24,0x04]
; X86-NEXT:    kmovd %eax, %k1 # encoding: [0xc5,0xfb,0x92,0xc8]
; X86-NEXT:    vpmulhw %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf1,0x7d,0x09,0xe5,0xd1]
; X86-NEXT:    vpaddw %xmm3, %xmm2, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe9,0xfd,0xc3]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_pmulh_w_128:
; X64:       # %bb.0:
; X64-NEXT:    vpmulhw %xmm1, %xmm0, %xmm3 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0xe5,0xd9]
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpmulhw %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf1,0x7d,0x09,0xe5,0xd1]
; X64-NEXT:    vpaddw %xmm3, %xmm2, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe9,0xfd,0xc3]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = call <8 x i16> @llvm.x86.sse2.pmulh.w(<8 x i16> %x0, <8 x i16> %x1)
  %2 = bitcast i8 %x3 to <8 x i1>
  %3 = select <8 x i1> %2, <8 x i16> %1, <8 x i16> %x2
  %4 = call <8 x i16> @llvm.x86.sse2.pmulh.w(<8 x i16> %x0, <8 x i16> %x1)
  %res2 = add <8 x i16> %3, %4
  ret <8 x i16> %res2
}

declare <16 x i16> @llvm.x86.avx2.pmulh.w(<16 x i16>, <16 x i16>)

define <16 x i16> @test_int_x86_avx512_mask_pmulh_w_256(<16 x i16> %x0, <16 x i16> %x1, <16 x i16> %x2, i16 %x3) {
; X86-LABEL: test_int_x86_avx512_mask_pmulh_w_256:
; X86:       # %bb.0:
; X86-NEXT:    vpmulhw %ymm1, %ymm0, %ymm3 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0xe5,0xd9]
; X86-NEXT:    kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x04]
; X86-NEXT:    vpmulhw %ymm1, %ymm0, %ymm2 {%k1} # encoding: [0x62,0xf1,0x7d,0x29,0xe5,0xd1]
; X86-NEXT:    vpaddw %ymm3, %ymm2, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xed,0xfd,0xc3]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_pmulh_w_256:
; X64:       # %bb.0:
; X64-NEXT:    vpmulhw %ymm1, %ymm0, %ymm3 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0xe5,0xd9]
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpmulhw %ymm1, %ymm0, %ymm2 {%k1} # encoding: [0x62,0xf1,0x7d,0x29,0xe5,0xd1]
; X64-NEXT:    vpaddw %ymm3, %ymm2, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xed,0xfd,0xc3]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = call <16 x i16> @llvm.x86.avx2.pmulh.w(<16 x i16> %x0, <16 x i16> %x1)
  %2 = bitcast i16 %x3 to <16 x i1>
  %3 = select <16 x i1> %2, <16 x i16> %1, <16 x i16> %x2
  %4 = call <16 x i16> @llvm.x86.avx2.pmulh.w(<16 x i16> %x0, <16 x i16> %x1)
  %res2 = add <16 x i16> %3, %4
  ret <16 x i16> %res2
}

declare <8 x i16> @llvm.x86.ssse3.pmul.hr.sw.128(<8 x i16>, <8 x i16>)

define <8 x i16> @test_int_x86_avx512_mask_pmulhr_sw_128(<8 x i16> %x0, <8 x i16> %x1, <8 x i16> %x2, i8 %x3) {
; X86-LABEL: test_int_x86_avx512_mask_pmulhr_sw_128:
; X86:       # %bb.0:
; X86-NEXT:    vpmulhrsw %xmm1, %xmm0, %xmm3 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0x79,0x0b,0xd9]
; X86-NEXT:    movzbl {{[0-9]+}}(%esp), %eax # encoding: [0x0f,0xb6,0x44,0x24,0x04]
; X86-NEXT:    kmovd %eax, %k1 # encoding: [0xc5,0xfb,0x92,0xc8]
; X86-NEXT:    vpmulhrsw %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf2,0x7d,0x09,0x0b,0xd1]
; X86-NEXT:    vpaddw %xmm3, %xmm2, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe9,0xfd,0xc3]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_pmulhr_sw_128:
; X64:       # %bb.0:
; X64-NEXT:    vpmulhrsw %xmm1, %xmm0, %xmm3 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0x79,0x0b,0xd9]
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpmulhrsw %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf2,0x7d,0x09,0x0b,0xd1]
; X64-NEXT:    vpaddw %xmm3, %xmm2, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe9,0xfd,0xc3]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = call <8 x i16> @llvm.x86.ssse3.pmul.hr.sw.128(<8 x i16> %x0, <8 x i16> %x1)
  %2 = bitcast i8 %x3 to <8 x i1>
  %3 = select <8 x i1> %2, <8 x i16> %1, <8 x i16> %x2
  %4 = call <8 x i16> @llvm.x86.ssse3.pmul.hr.sw.128(<8 x i16> %x0, <8 x i16> %x1)
  %res2 = add <8 x i16> %3, %4
  ret <8 x i16> %res2
}

declare <16 x i16> @llvm.x86.avx2.pmul.hr.sw(<16 x i16>, <16 x i16>)

define <16 x i16> @test_int_x86_avx512_mask_pmulhr_sw_256(<16 x i16> %x0, <16 x i16> %x1, <16 x i16> %x2, i16 %x3) {
; X86-LABEL: test_int_x86_avx512_mask_pmulhr_sw_256:
; X86:       # %bb.0:
; X86-NEXT:    vpmulhrsw %ymm1, %ymm0, %ymm3 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0x7d,0x0b,0xd9]
; X86-NEXT:    kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x04]
; X86-NEXT:    vpmulhrsw %ymm1, %ymm0, %ymm2 {%k1} # encoding: [0x62,0xf2,0x7d,0x29,0x0b,0xd1]
; X86-NEXT:    vpaddw %ymm3, %ymm2, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xed,0xfd,0xc3]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_pmulhr_sw_256:
; X64:       # %bb.0:
; X64-NEXT:    vpmulhrsw %ymm1, %ymm0, %ymm3 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0x7d,0x0b,0xd9]
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpmulhrsw %ymm1, %ymm0, %ymm2 {%k1} # encoding: [0x62,0xf2,0x7d,0x29,0x0b,0xd1]
; X64-NEXT:    vpaddw %ymm3, %ymm2, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xed,0xfd,0xc3]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = call <16 x i16> @llvm.x86.avx2.pmul.hr.sw(<16 x i16> %x0, <16 x i16> %x1)
  %2 = bitcast i16 %x3 to <16 x i1>
  %3 = select <16 x i1> %2, <16 x i16> %1, <16 x i16> %x2
  %4 = call <16 x i16> @llvm.x86.avx2.pmul.hr.sw(<16 x i16> %x0, <16 x i16> %x1)
  %res2 = add <16 x i16> %3, %4
  ret <16 x i16> %res2
}

declare <16 x i8> @llvm.x86.avx512.mask.pmov.wb.128(<8 x i16>, <16 x i8>, i8)

define <16 x i8>@test_int_x86_avx512_mask_pmov_wb_128(<8 x i16> %x0, <16 x i8> %x1, i8 %x2) {
; X86-LABEL: test_int_x86_avx512_mask_pmov_wb_128:
; X86:       # %bb.0:
; X86-NEXT:    kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x04]
; X86-NEXT:    vpmovwb %xmm0, %xmm2 {%k1} {z} # encoding: [0x62,0xf2,0x7e,0x89,0x30,0xc2]
; X86-NEXT:    vpmovwb %xmm0, %xmm1 {%k1} # encoding: [0x62,0xf2,0x7e,0x09,0x30,0xc1]
; X86-NEXT:    vpaddb %xmm2, %xmm1, %xmm1 # EVEX TO VEX Compression encoding: [0xc5,0xf1,0xfc,0xca]
; X86-NEXT:    vpmovwb %xmm0, %xmm0 # encoding: [0x62,0xf2,0x7e,0x08,0x30,0xc0]
; X86-NEXT:    vpaddb %xmm1, %xmm0, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0xfc,0xc1]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_pmov_wb_128:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpmovwb %xmm0, %xmm2 {%k1} {z} # encoding: [0x62,0xf2,0x7e,0x89,0x30,0xc2]
; X64-NEXT:    vpmovwb %xmm0, %xmm1 {%k1} # encoding: [0x62,0xf2,0x7e,0x09,0x30,0xc1]
; X64-NEXT:    vpaddb %xmm2, %xmm1, %xmm1 # EVEX TO VEX Compression encoding: [0xc5,0xf1,0xfc,0xca]
; X64-NEXT:    vpmovwb %xmm0, %xmm0 # encoding: [0x62,0xf2,0x7e,0x08,0x30,0xc0]
; X64-NEXT:    vpaddb %xmm1, %xmm0, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0xfc,0xc1]
; X64-NEXT:    retq # encoding: [0xc3]
    %res0 = call <16 x i8> @llvm.x86.avx512.mask.pmov.wb.128(<8 x i16> %x0, <16 x i8> %x1, i8 -1)
    %res1 = call <16 x i8> @llvm.x86.avx512.mask.pmov.wb.128(<8 x i16> %x0, <16 x i8> %x1, i8 %x2)
    %res2 = call <16 x i8> @llvm.x86.avx512.mask.pmov.wb.128(<8 x i16> %x0, <16 x i8> zeroinitializer, i8 %x2)
    %res3 = add <16 x i8> %res0, %res1
    %res4 = add <16 x i8> %res3, %res2
    ret <16 x i8> %res4
}

declare void @llvm.x86.avx512.mask.pmov.wb.mem.128(i8* %ptr, <8 x i16>, i8)

define void @test_int_x86_avx512_mask_pmov_wb_mem_128(i8* %ptr, <8 x i16> %x1, i8 %x2) {
; X86-LABEL: test_int_x86_avx512_mask_pmov_wb_mem_128:
; X86:       # %bb.0:
; X86-NEXT:    movzbl {{[0-9]+}}(%esp), %eax # encoding: [0x0f,0xb6,0x44,0x24,0x08]
; X86-NEXT:    kmovd %eax, %k1 # encoding: [0xc5,0xfb,0x92,0xc8]
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT:    vpmovwb %xmm0, (%eax) # encoding: [0x62,0xf2,0x7e,0x08,0x30,0x00]
; X86-NEXT:    vpmovwb %xmm0, (%eax) {%k1} # encoding: [0x62,0xf2,0x7e,0x09,0x30,0x00]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_pmov_wb_mem_128:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT:    vpmovwb %xmm0, (%rdi) # encoding: [0x62,0xf2,0x7e,0x08,0x30,0x07]
; X64-NEXT:    vpmovwb %xmm0, (%rdi) {%k1} # encoding: [0x62,0xf2,0x7e,0x09,0x30,0x07]
; X64-NEXT:    retq # encoding: [0xc3]
    call void @llvm.x86.avx512.mask.pmov.wb.mem.128(i8* %ptr, <8 x i16> %x1, i8 -1)
    call void @llvm.x86.avx512.mask.pmov.wb.mem.128(i8* %ptr, <8 x i16> %x1, i8 %x2)
    ret void
}

declare <16 x i8> @llvm.x86.avx512.mask.pmovs.wb.128(<8 x i16>, <16 x i8>, i8)

define <16 x i8>@test_int_x86_avx512_mask_pmovs_wb_128(<8 x i16> %x0, <16 x i8> %x1, i8 %x2) {
; X86-LABEL: test_int_x86_avx512_mask_pmovs_wb_128:
; X86:       # %bb.0:
; X86-NEXT:    kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x04]
; X86-NEXT:    vpmovswb %xmm0, %xmm2 {%k1} {z} # encoding: [0x62,0xf2,0x7e,0x89,0x20,0xc2]
; X86-NEXT:    vpmovswb %xmm0, %xmm1 {%k1} # encoding: [0x62,0xf2,0x7e,0x09,0x20,0xc1]
; X86-NEXT:    vpaddb %xmm2, %xmm1, %xmm1 # EVEX TO VEX Compression encoding: [0xc5,0xf1,0xfc,0xca]
; X86-NEXT:    vpmovswb %xmm0, %xmm0 # encoding: [0x62,0xf2,0x7e,0x08,0x20,0xc0]
; X86-NEXT:    vpaddb %xmm1, %xmm0, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0xfc,0xc1]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_pmovs_wb_128:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpmovswb %xmm0, %xmm2 {%k1} {z} # encoding: [0x62,0xf2,0x7e,0x89,0x20,0xc2]
; X64-NEXT:    vpmovswb %xmm0, %xmm1 {%k1} # encoding: [0x62,0xf2,0x7e,0x09,0x20,0xc1]
; X64-NEXT:    vpaddb %xmm2, %xmm1, %xmm1 # EVEX TO VEX Compression encoding: [0xc5,0xf1,0xfc,0xca]
; X64-NEXT:    vpmovswb %xmm0, %xmm0 # encoding: [0x62,0xf2,0x7e,0x08,0x20,0xc0]
; X64-NEXT:    vpaddb %xmm1, %xmm0, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0xfc,0xc1]
; X64-NEXT:    retq # encoding: [0xc3]
    %res0 = call <16 x i8> @llvm.x86.avx512.mask.pmovs.wb.128(<8 x i16> %x0, <16 x i8> %x1, i8 -1)
    %res1 = call <16 x i8> @llvm.x86.avx512.mask.pmovs.wb.128(<8 x i16> %x0, <16 x i8> %x1, i8 %x2)
    %res2 = call <16 x i8> @llvm.x86.avx512.mask.pmovs.wb.128(<8 x i16> %x0, <16 x i8> zeroinitializer, i8 %x2)
    %res3 = add <16 x i8> %res0, %res1
    %res4 = add <16 x i8> %res3, %res2
    ret <16 x i8> %res4
}

declare void @llvm.x86.avx512.mask.pmovs.wb.mem.128(i8* %ptr, <8 x i16>, i8)

define void @test_int_x86_avx512_mask_pmovs_wb_mem_128(i8* %ptr, <8 x i16> %x1, i8 %x2) {
; X86-LABEL: test_int_x86_avx512_mask_pmovs_wb_mem_128:
; X86:       # %bb.0:
; X86-NEXT:    movzbl {{[0-9]+}}(%esp), %eax # encoding: [0x0f,0xb6,0x44,0x24,0x08]
; X86-NEXT:    kmovd %eax, %k1 # encoding: [0xc5,0xfb,0x92,0xc8]
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT:    vpmovswb %xmm0, (%eax) # encoding: [0x62,0xf2,0x7e,0x08,0x20,0x00]
; X86-NEXT:    vpmovswb %xmm0, (%eax) {%k1} # encoding: [0x62,0xf2,0x7e,0x09,0x20,0x00]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_pmovs_wb_mem_128:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT:    vpmovswb %xmm0, (%rdi) # encoding: [0x62,0xf2,0x7e,0x08,0x20,0x07]
; X64-NEXT:    vpmovswb %xmm0, (%rdi) {%k1} # encoding: [0x62,0xf2,0x7e,0x09,0x20,0x07]
; X64-NEXT:    retq # encoding: [0xc3]
    call void @llvm.x86.avx512.mask.pmovs.wb.mem.128(i8* %ptr, <8 x i16> %x1, i8 -1)
    call void @llvm.x86.avx512.mask.pmovs.wb.mem.128(i8* %ptr, <8 x i16> %x1, i8 %x2)
    ret void
}

declare <16 x i8> @llvm.x86.avx512.mask.pmovus.wb.128(<8 x i16>, <16 x i8>, i8)

define <16 x i8>@test_int_x86_avx512_mask_pmovus_wb_128(<8 x i16> %x0, <16 x i8> %x1, i8 %x2) {
; X86-LABEL: test_int_x86_avx512_mask_pmovus_wb_128:
; X86:       # %bb.0:
; X86-NEXT:    kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x04]
; X86-NEXT:    vpmovuswb %xmm0, %xmm2 {%k1} {z} # encoding: [0x62,0xf2,0x7e,0x89,0x10,0xc2]
; X86-NEXT:    vpmovuswb %xmm0, %xmm1 {%k1} # encoding: [0x62,0xf2,0x7e,0x09,0x10,0xc1]
; X86-NEXT:    vpaddb %xmm2, %xmm1, %xmm1 # EVEX TO VEX Compression encoding: [0xc5,0xf1,0xfc,0xca]
; X86-NEXT:    vpmovuswb %xmm0, %xmm0 # encoding: [0x62,0xf2,0x7e,0x08,0x10,0xc0]
; X86-NEXT:    vpaddb %xmm1, %xmm0, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0xfc,0xc1]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_pmovus_wb_128:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpmovuswb %xmm0, %xmm2 {%k1} {z} # encoding: [0x62,0xf2,0x7e,0x89,0x10,0xc2]
; X64-NEXT:    vpmovuswb %xmm0, %xmm1 {%k1} # encoding: [0x62,0xf2,0x7e,0x09,0x10,0xc1]
; X64-NEXT:    vpaddb %xmm2, %xmm1, %xmm1 # EVEX TO VEX Compression encoding: [0xc5,0xf1,0xfc,0xca]
; X64-NEXT:    vpmovuswb %xmm0, %xmm0 # encoding: [0x62,0xf2,0x7e,0x08,0x10,0xc0]
; X64-NEXT:    vpaddb %xmm1, %xmm0, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0xfc,0xc1]
; X64-NEXT:    retq # encoding: [0xc3]
    %res0 = call <16 x i8> @llvm.x86.avx512.mask.pmovus.wb.128(<8 x i16> %x0, <16 x i8> %x1, i8 -1)
    %res1 = call <16 x i8> @llvm.x86.avx512.mask.pmovus.wb.128(<8 x i16> %x0, <16 x i8> %x1, i8 %x2)
    %res2 = call <16 x i8> @llvm.x86.avx512.mask.pmovus.wb.128(<8 x i16> %x0, <16 x i8> zeroinitializer, i8 %x2)
    %res3 = add <16 x i8> %res0, %res1
    %res4 = add <16 x i8> %res3, %res2
    ret <16 x i8> %res4
}

declare void @llvm.x86.avx512.mask.pmovus.wb.mem.128(i8* %ptr, <8 x i16>, i8)

define void @test_int_x86_avx512_mask_pmovus_wb_mem_128(i8* %ptr, <8 x i16> %x1, i8 %x2) {
; X86-LABEL: test_int_x86_avx512_mask_pmovus_wb_mem_128:
; X86:       # %bb.0:
; X86-NEXT:    movzbl {{[0-9]+}}(%esp), %eax # encoding: [0x0f,0xb6,0x44,0x24,0x08]
; X86-NEXT:    kmovd %eax, %k1 # encoding: [0xc5,0xfb,0x92,0xc8]
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT:    vpmovuswb %xmm0, (%eax) # encoding: [0x62,0xf2,0x7e,0x08,0x10,0x00]
; X86-NEXT:    vpmovuswb %xmm0, (%eax) {%k1} # encoding: [0x62,0xf2,0x7e,0x09,0x10,0x00]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_pmovus_wb_mem_128:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT:    vpmovuswb %xmm0, (%rdi) # encoding: [0x62,0xf2,0x7e,0x08,0x10,0x07]
; X64-NEXT:    vpmovuswb %xmm0, (%rdi) {%k1} # encoding: [0x62,0xf2,0x7e,0x09,0x10,0x07]
; X64-NEXT:    retq # encoding: [0xc3]
    call void @llvm.x86.avx512.mask.pmovus.wb.mem.128(i8* %ptr, <8 x i16> %x1, i8 -1)
    call void @llvm.x86.avx512.mask.pmovus.wb.mem.128(i8* %ptr, <8 x i16> %x1, i8 %x2)
    ret void
}

declare <16 x i8> @llvm.x86.avx512.mask.pmov.wb.256(<16 x i16>, <16 x i8>, i16)

define <16 x i8>@test_int_x86_avx512_mask_pmov_wb_256(<16 x i16> %x0, <16 x i8> %x1, i16 %x2) {
; X86-LABEL: test_int_x86_avx512_mask_pmov_wb_256:
; X86:       # %bb.0:
; X86-NEXT:    kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x04]
; X86-NEXT:    vpmovwb %ymm0, %xmm1 {%k1} # encoding: [0x62,0xf2,0x7e,0x29,0x30,0xc1]
; X86-NEXT:    vpmovwb %ymm0, %xmm2 {%k1} {z} # encoding: [0x62,0xf2,0x7e,0xa9,0x30,0xc2]
; X86-NEXT:    vpaddb %xmm2, %xmm1, %xmm1 # EVEX TO VEX Compression encoding: [0xc5,0xf1,0xfc,0xca]
; X86-NEXT:    vpmovwb %ymm0, %xmm0 # encoding: [0x62,0xf2,0x7e,0x28,0x30,0xc0]
; X86-NEXT:    vpaddb %xmm1, %xmm0, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0xfc,0xc1]
; X86-NEXT:    vzeroupper # encoding: [0xc5,0xf8,0x77]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_pmov_wb_256:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpmovwb %ymm0, %xmm2 {%k1} {z} # encoding: [0x62,0xf2,0x7e,0xa9,0x30,0xc2]
; X64-NEXT:    vpmovwb %ymm0, %xmm1 {%k1} # encoding: [0x62,0xf2,0x7e,0x29,0x30,0xc1]
; X64-NEXT:    vpaddb %xmm2, %xmm1, %xmm1 # EVEX TO VEX Compression encoding: [0xc5,0xf1,0xfc,0xca]
; X64-NEXT:    vpmovwb %ymm0, %xmm0 # encoding: [0x62,0xf2,0x7e,0x28,0x30,0xc0]
; X64-NEXT:    vpaddb %xmm1, %xmm0, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0xfc,0xc1]
; X64-NEXT:    vzeroupper # encoding: [0xc5,0xf8,0x77]
; X64-NEXT:    retq # encoding: [0xc3]
    %res0 = call <16 x i8> @llvm.x86.avx512.mask.pmov.wb.256(<16 x i16> %x0, <16 x i8> %x1, i16 -1)
    %res1 = call <16 x i8> @llvm.x86.avx512.mask.pmov.wb.256(<16 x i16> %x0, <16 x i8> %x1, i16 %x2)
    %res2 = call <16 x i8> @llvm.x86.avx512.mask.pmov.wb.256(<16 x i16> %x0, <16 x i8> zeroinitializer, i16 %x2)
    %res3 = add <16 x i8> %res0, %res1
    %res4 = add <16 x i8> %res3, %res2
    ret <16 x i8> %res4
}

declare void @llvm.x86.avx512.mask.pmov.wb.mem.256(i8* %ptr, <16 x i16>, i16)

define void @test_int_x86_avx512_mask_pmov_wb_mem_256(i8* %ptr, <16 x i16> %x1, i16 %x2) {
; X86-LABEL: test_int_x86_avx512_mask_pmov_wb_mem_256:
; X86:       # %bb.0:
; X86-NEXT:    kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x08]
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT:    vpmovwb %ymm0, (%eax) # encoding: [0x62,0xf2,0x7e,0x28,0x30,0x00]
; X86-NEXT:    vpmovwb %ymm0, (%eax) {%k1} # encoding: [0x62,0xf2,0x7e,0x29,0x30,0x00]
; X86-NEXT:    vzeroupper # encoding: [0xc5,0xf8,0x77]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_pmov_wb_mem_256:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT:    vpmovwb %ymm0, (%rdi) # encoding: [0x62,0xf2,0x7e,0x28,0x30,0x07]
; X64-NEXT:    vpmovwb %ymm0, (%rdi) {%k1} # encoding: [0x62,0xf2,0x7e,0x29,0x30,0x07]
; X64-NEXT:    vzeroupper # encoding: [0xc5,0xf8,0x77]
; X64-NEXT:    retq # encoding: [0xc3]
    call void @llvm.x86.avx512.mask.pmov.wb.mem.256(i8* %ptr, <16 x i16> %x1, i16 -1)
    call void @llvm.x86.avx512.mask.pmov.wb.mem.256(i8* %ptr, <16 x i16> %x1, i16 %x2)
    ret void
}

declare <16 x i8> @llvm.x86.avx512.mask.pmovs.wb.256(<16 x i16>, <16 x i8>, i16)

define <16 x i8>@test_int_x86_avx512_mask_pmovs_wb_256(<16 x i16> %x0, <16 x i8> %x1, i16 %x2) {
; X86-LABEL: test_int_x86_avx512_mask_pmovs_wb_256:
; X86:       # %bb.0:
; X86-NEXT:    kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x04]
; X86-NEXT:    vpmovswb %ymm0, %xmm1 {%k1} # encoding: [0x62,0xf2,0x7e,0x29,0x20,0xc1]
; X86-NEXT:    vpmovswb %ymm0, %xmm2 {%k1} {z} # encoding: [0x62,0xf2,0x7e,0xa9,0x20,0xc2]
; X86-NEXT:    vpaddb %xmm2, %xmm1, %xmm1 # EVEX TO VEX Compression encoding: [0xc5,0xf1,0xfc,0xca]
; X86-NEXT:    vpmovswb %ymm0, %xmm0 # encoding: [0x62,0xf2,0x7e,0x28,0x20,0xc0]
; X86-NEXT:    vpaddb %xmm1, %xmm0, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0xfc,0xc1]
; X86-NEXT:    vzeroupper # encoding: [0xc5,0xf8,0x77]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_pmovs_wb_256:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpmovswb %ymm0, %xmm2 {%k1} {z} # encoding: [0x62,0xf2,0x7e,0xa9,0x20,0xc2]
; X64-NEXT:    vpmovswb %ymm0, %xmm1 {%k1} # encoding: [0x62,0xf2,0x7e,0x29,0x20,0xc1]
; X64-NEXT:    vpaddb %xmm2, %xmm1, %xmm1 # EVEX TO VEX Compression encoding: [0xc5,0xf1,0xfc,0xca]
; X64-NEXT:    vpmovswb %ymm0, %xmm0 # encoding: [0x62,0xf2,0x7e,0x28,0x20,0xc0]
; X64-NEXT:    vpaddb %xmm1, %xmm0, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0xfc,0xc1]
; X64-NEXT:    vzeroupper # encoding: [0xc5,0xf8,0x77]
; X64-NEXT:    retq # encoding: [0xc3]
    %res0 = call <16 x i8> @llvm.x86.avx512.mask.pmovs.wb.256(<16 x i16> %x0, <16 x i8> %x1, i16 -1)
    %res1 = call <16 x i8> @llvm.x86.avx512.mask.pmovs.wb.256(<16 x i16> %x0, <16 x i8> %x1, i16 %x2)
    %res2 = call <16 x i8> @llvm.x86.avx512.mask.pmovs.wb.256(<16 x i16> %x0, <16 x i8> zeroinitializer, i16 %x2)
    %res3 = add <16 x i8> %res0, %res1
    %res4 = add <16 x i8> %res3, %res2
    ret <16 x i8> %res4
}

declare void @llvm.x86.avx512.mask.pmovs.wb.mem.256(i8* %ptr, <16 x i16>, i16)

define void @test_int_x86_avx512_mask_pmovs_wb_mem_256(i8* %ptr, <16 x i16> %x1, i16 %x2) {
; X86-LABEL: test_int_x86_avx512_mask_pmovs_wb_mem_256:
; X86:       # %bb.0:
; X86-NEXT:    kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x08]
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT:    vpmovswb %ymm0, (%eax) # encoding: [0x62,0xf2,0x7e,0x28,0x20,0x00]
; X86-NEXT:    vpmovswb %ymm0, (%eax) {%k1} # encoding: [0x62,0xf2,0x7e,0x29,0x20,0x00]
; X86-NEXT:    vzeroupper # encoding: [0xc5,0xf8,0x77]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_pmovs_wb_mem_256:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT:    vpmovswb %ymm0, (%rdi) # encoding: [0x62,0xf2,0x7e,0x28,0x20,0x07]
; X64-NEXT:    vpmovswb %ymm0, (%rdi) {%k1} # encoding: [0x62,0xf2,0x7e,0x29,0x20,0x07]
; X64-NEXT:    vzeroupper # encoding: [0xc5,0xf8,0x77]
; X64-NEXT:    retq # encoding: [0xc3]
    call void @llvm.x86.avx512.mask.pmovs.wb.mem.256(i8* %ptr, <16 x i16> %x1, i16 -1)
    call void @llvm.x86.avx512.mask.pmovs.wb.mem.256(i8* %ptr, <16 x i16> %x1, i16 %x2)
    ret void
}

declare <16 x i8> @llvm.x86.avx512.mask.pmovus.wb.256(<16 x i16>, <16 x i8>, i16)

define <16 x i8>@test_int_x86_avx512_mask_pmovus_wb_256(<16 x i16> %x0, <16 x i8> %x1, i16 %x2) {
; X86-LABEL: test_int_x86_avx512_mask_pmovus_wb_256:
; X86:       # %bb.0:
; X86-NEXT:    kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x04]
; X86-NEXT:    vpmovuswb %ymm0, %xmm1 {%k1} # encoding: [0x62,0xf2,0x7e,0x29,0x10,0xc1]
; X86-NEXT:    vpmovuswb %ymm0, %xmm2 {%k1} {z} # encoding: [0x62,0xf2,0x7e,0xa9,0x10,0xc2]
; X86-NEXT:    vpaddb %xmm2, %xmm1, %xmm1 # EVEX TO VEX Compression encoding: [0xc5,0xf1,0xfc,0xca]
; X86-NEXT:    vpmovuswb %ymm0, %xmm0 # encoding: [0x62,0xf2,0x7e,0x28,0x10,0xc0]
; X86-NEXT:    vpaddb %xmm1, %xmm0, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0xfc,0xc1]
; X86-NEXT:    vzeroupper # encoding: [0xc5,0xf8,0x77]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_pmovus_wb_256:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpmovuswb %ymm0, %xmm2 {%k1} {z} # encoding: [0x62,0xf2,0x7e,0xa9,0x10,0xc2]
; X64-NEXT:    vpmovuswb %ymm0, %xmm1 {%k1} # encoding: [0x62,0xf2,0x7e,0x29,0x10,0xc1]
; X64-NEXT:    vpaddb %xmm2, %xmm1, %xmm1 # EVEX TO VEX Compression encoding: [0xc5,0xf1,0xfc,0xca]
; X64-NEXT:    vpmovuswb %ymm0, %xmm0 # encoding: [0x62,0xf2,0x7e,0x28,0x10,0xc0]
; X64-NEXT:    vpaddb %xmm1, %xmm0, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0xfc,0xc1]
; X64-NEXT:    vzeroupper # encoding: [0xc5,0xf8,0x77]
; X64-NEXT:    retq # encoding: [0xc3]
    %res0 = call <16 x i8> @llvm.x86.avx512.mask.pmovus.wb.256(<16 x i16> %x0, <16 x i8> %x1, i16 -1)
    %res1 = call <16 x i8> @llvm.x86.avx512.mask.pmovus.wb.256(<16 x i16> %x0, <16 x i8> %x1, i16 %x2)
    %res2 = call <16 x i8> @llvm.x86.avx512.mask.pmovus.wb.256(<16 x i16> %x0, <16 x i8> zeroinitializer, i16 %x2)
    %res3 = add <16 x i8> %res0, %res1
    %res4 = add <16 x i8> %res3, %res2
    ret <16 x i8> %res4
}

declare void @llvm.x86.avx512.mask.pmovus.wb.mem.256(i8* %ptr, <16 x i16>, i16)

define void @test_int_x86_avx512_mask_pmovus_wb_mem_256(i8* %ptr, <16 x i16> %x1, i16 %x2) {
; X86-LABEL: test_int_x86_avx512_mask_pmovus_wb_mem_256:
; X86:       # %bb.0:
; X86-NEXT:    kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x08]
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT:    vpmovuswb %ymm0, (%eax) # encoding: [0x62,0xf2,0x7e,0x28,0x10,0x00]
; X86-NEXT:    vpmovuswb %ymm0, (%eax) {%k1} # encoding: [0x62,0xf2,0x7e,0x29,0x10,0x00]
; X86-NEXT:    vzeroupper # encoding: [0xc5,0xf8,0x77]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_pmovus_wb_mem_256:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT:    vpmovuswb %ymm0, (%rdi) # encoding: [0x62,0xf2,0x7e,0x28,0x10,0x07]
; X64-NEXT:    vpmovuswb %ymm0, (%rdi) {%k1} # encoding: [0x62,0xf2,0x7e,0x29,0x10,0x07]
; X64-NEXT:    vzeroupper # encoding: [0xc5,0xf8,0x77]
; X64-NEXT:    retq # encoding: [0xc3]
    call void @llvm.x86.avx512.mask.pmovus.wb.mem.256(i8* %ptr, <16 x i16> %x1, i16 -1)
    call void @llvm.x86.avx512.mask.pmovus.wb.mem.256(i8* %ptr, <16 x i16> %x1, i16 %x2)
    ret void
}

declare <4 x i32> @llvm.x86.sse2.pmadd.wd(<8 x i16>, <8 x i16>)

define <4 x i32> @test_int_x86_avx512_mask_pmaddw_d_128(<8 x i16> %x0, <8 x i16> %x1, <4 x i32> %x2, i8 %x3) {
; X86-LABEL: test_int_x86_avx512_mask_pmaddw_d_128:
; X86:       # %bb.0:
; X86-NEXT:    vpmaddwd %xmm1, %xmm0, %xmm3 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0xf5,0xd9]
; X86-NEXT:    movzbl {{[0-9]+}}(%esp), %eax # encoding: [0x0f,0xb6,0x44,0x24,0x04]
; X86-NEXT:    kmovd %eax, %k1 # encoding: [0xc5,0xfb,0x92,0xc8]
; X86-NEXT:    vpmaddwd %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf1,0x7d,0x09,0xf5,0xd1]
; X86-NEXT:    vpaddd %xmm3, %xmm2, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe9,0xfe,0xc3]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_pmaddw_d_128:
; X64:       # %bb.0:
; X64-NEXT:    vpmaddwd %xmm1, %xmm0, %xmm3 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0xf5,0xd9]
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpmaddwd %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf1,0x7d,0x09,0xf5,0xd1]
; X64-NEXT:    vpaddd %xmm3, %xmm2, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe9,0xfe,0xc3]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = call <4 x i32> @llvm.x86.sse2.pmadd.wd(<8 x i16> %x0, <8 x i16> %x1)
  %2 = bitcast i8 %x3 to <8 x i1>
  %extract = shufflevector <8 x i1> %2, <8 x i1> %2, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
  %3 = select <4 x i1> %extract, <4 x i32> %1, <4 x i32> %x2
  %4 = call <4 x i32> @llvm.x86.sse2.pmadd.wd(<8 x i16> %x0, <8 x i16> %x1)
  %res2 = add <4 x i32> %3, %4
  ret <4 x i32> %res2
}

declare <8 x i32> @llvm.x86.avx2.pmadd.wd(<16 x i16>, <16 x i16>)

define <8 x i32> @test_int_x86_avx512_mask_pmaddw_d_256(<16 x i16> %x0, <16 x i16> %x1, <8 x i32> %x2, i8 %x3) {
; X86-LABEL: test_int_x86_avx512_mask_pmaddw_d_256:
; X86:       # %bb.0:
; X86-NEXT:    vpmaddwd %ymm1, %ymm0, %ymm3 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0xf5,0xd9]
; X86-NEXT:    movzbl {{[0-9]+}}(%esp), %eax # encoding: [0x0f,0xb6,0x44,0x24,0x04]
; X86-NEXT:    kmovd %eax, %k1 # encoding: [0xc5,0xfb,0x92,0xc8]
; X86-NEXT:    vpmaddwd %ymm1, %ymm0, %ymm2 {%k1} # encoding: [0x62,0xf1,0x7d,0x29,0xf5,0xd1]
; X86-NEXT:    vpaddd %ymm3, %ymm2, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xed,0xfe,0xc3]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_pmaddw_d_256:
; X64:       # %bb.0:
; X64-NEXT:    vpmaddwd %ymm1, %ymm0, %ymm3 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0xf5,0xd9]
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpmaddwd %ymm1, %ymm0, %ymm2 {%k1} # encoding: [0x62,0xf1,0x7d,0x29,0xf5,0xd1]
; X64-NEXT:    vpaddd %ymm3, %ymm2, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xed,0xfe,0xc3]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = call <8 x i32> @llvm.x86.avx2.pmadd.wd(<16 x i16> %x0, <16 x i16> %x1)
  %2 = bitcast i8 %x3 to <8 x i1>
  %3 = select <8 x i1> %2, <8 x i32> %1, <8 x i32> %x2
  %4 = call <8 x i32> @llvm.x86.avx2.pmadd.wd(<16 x i16> %x0, <16 x i16> %x1)
  %res2 = add <8 x i32> %3, %4
  ret <8 x i32> %res2
}

declare <8 x i16> @llvm.x86.ssse3.pmadd.ub.sw.128(<16 x i8>, <16 x i8>)

define <8 x i16> @test_int_x86_avx512_mask_pmaddubs_w_128(<16 x i8> %x0, <16 x i8> %x1, <8 x i16> %x2, i8 %x3) {
; X86-LABEL: test_int_x86_avx512_mask_pmaddubs_w_128:
; X86:       # %bb.0:
; X86-NEXT:    vpmaddubsw %xmm1, %xmm0, %xmm3 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0x79,0x04,0xd9]
; X86-NEXT:    movzbl {{[0-9]+}}(%esp), %eax # encoding: [0x0f,0xb6,0x44,0x24,0x04]
; X86-NEXT:    kmovd %eax, %k1 # encoding: [0xc5,0xfb,0x92,0xc8]
; X86-NEXT:    vpmaddubsw %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf2,0x7d,0x09,0x04,0xd1]
; X86-NEXT:    vpaddw %xmm3, %xmm2, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe9,0xfd,0xc3]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_pmaddubs_w_128:
; X64:       # %bb.0:
; X64-NEXT:    vpmaddubsw %xmm1, %xmm0, %xmm3 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0x79,0x04,0xd9]
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpmaddubsw %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf2,0x7d,0x09,0x04,0xd1]
; X64-NEXT:    vpaddw %xmm3, %xmm2, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe9,0xfd,0xc3]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = call <8 x i16> @llvm.x86.ssse3.pmadd.ub.sw.128(<16 x i8> %x0, <16 x i8> %x1)
  %2 = bitcast i8 %x3 to <8 x i1>
  %3 = select <8 x i1> %2, <8 x i16> %1, <8 x i16> %x2
  %4 = call <8 x i16> @llvm.x86.ssse3.pmadd.ub.sw.128(<16 x i8> %x0, <16 x i8> %x1)
  %res2 = add <8 x i16> %3, %4
  ret <8 x i16> %res2
}

declare <16 x i16> @llvm.x86.avx2.pmadd.ub.sw(<32 x i8>, <32 x i8>)

define <16 x i16> @test_int_x86_avx512_mask_pmaddubs_w_256(<32 x i8> %x0, <32 x i8> %x1, <16 x i16> %x2, i16 %x3) {
; X86-LABEL: test_int_x86_avx512_mask_pmaddubs_w_256:
; X86:       # %bb.0:
; X86-NEXT:    vpmaddubsw %ymm1, %ymm0, %ymm3 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0x7d,0x04,0xd9]
; X86-NEXT:    kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x04]
; X86-NEXT:    vpmaddubsw %ymm1, %ymm0, %ymm2 {%k1} # encoding: [0x62,0xf2,0x7d,0x29,0x04,0xd1]
; X86-NEXT:    vpaddw %ymm3, %ymm2, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xed,0xfd,0xc3]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_pmaddubs_w_256:
; X64:       # %bb.0:
; X64-NEXT:    vpmaddubsw %ymm1, %ymm0, %ymm3 # EVEX TO VEX Compression encoding: [0xc4,0xe2,0x7d,0x04,0xd9]
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpmaddubsw %ymm1, %ymm0, %ymm2 {%k1} # encoding: [0x62,0xf2,0x7d,0x29,0x04,0xd1]
; X64-NEXT:    vpaddw %ymm3, %ymm2, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xed,0xfd,0xc3]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = call <16 x i16> @llvm.x86.avx2.pmadd.ub.sw(<32 x i8> %x0, <32 x i8> %x1)
  %2 = bitcast i16 %x3 to <16 x i1>
  %3 = select <16 x i1> %2, <16 x i16> %1, <16 x i16> %x2
  %4 = call <16 x i16> @llvm.x86.avx2.pmadd.ub.sw(<32 x i8> %x0, <32 x i8> %x1)
  %res2 = add <16 x i16> %3, %4
  ret <16 x i16> %res2
}

declare <8 x i16> @llvm.x86.avx512.dbpsadbw.128(<16 x i8>, <16 x i8>, i32)

define <8 x i16>@test_int_x86_avx512_mask_dbpsadbw_128(<16 x i8> %x0, <16 x i8> %x1, <8 x i16> %x3, i8 %x4) {
; X86-LABEL: test_int_x86_avx512_mask_dbpsadbw_128:
; X86:       # %bb.0:
; X86-NEXT:    vdbpsadbw $2, %xmm1, %xmm0, %xmm3 # encoding: [0x62,0xf3,0x7d,0x08,0x42,0xd9,0x02]
; X86-NEXT:    movzbl {{[0-9]+}}(%esp), %eax # encoding: [0x0f,0xb6,0x44,0x24,0x04]
; X86-NEXT:    kmovd %eax, %k1 # encoding: [0xc5,0xfb,0x92,0xc8]
; X86-NEXT:    vdbpsadbw $2, %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf3,0x7d,0x09,0x42,0xd1,0x02]
; X86-NEXT:    vdbpsadbw $2, %xmm1, %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf3,0x7d,0x89,0x42,0xc1,0x02]
; X86-NEXT:    vpaddw %xmm3, %xmm0, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0xfd,0xc3]
; X86-NEXT:    vpaddw %xmm0, %xmm2, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe9,0xfd,0xc0]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_dbpsadbw_128:
; X64:       # %bb.0:
; X64-NEXT:    vdbpsadbw $2, %xmm1, %xmm0, %xmm3 # encoding: [0x62,0xf3,0x7d,0x08,0x42,0xd9,0x02]
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vdbpsadbw $2, %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf3,0x7d,0x09,0x42,0xd1,0x02]
; X64-NEXT:    vdbpsadbw $2, %xmm1, %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf3,0x7d,0x89,0x42,0xc1,0x02]
; X64-NEXT:    vpaddw %xmm3, %xmm0, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0xfd,0xc3]
; X64-NEXT:    vpaddw %xmm0, %xmm2, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe9,0xfd,0xc0]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = call <8 x i16> @llvm.x86.avx512.dbpsadbw.128(<16 x i8> %x0, <16 x i8> %x1, i32 2)
  %2 = bitcast i8 %x4 to <8 x i1>
  %3 = select <8 x i1> %2, <8 x i16> %1, <8 x i16> %x3
  %4 = call <8 x i16> @llvm.x86.avx512.dbpsadbw.128(<16 x i8> %x0, <16 x i8> %x1, i32 2)
  %5 = bitcast i8 %x4 to <8 x i1>
  %6 = select <8 x i1> %5, <8 x i16> %4, <8 x i16> zeroinitializer
  %7 = call <8 x i16> @llvm.x86.avx512.dbpsadbw.128(<16 x i8> %x0, <16 x i8> %x1, i32 2)
  %res3 = add <8 x i16> %3, %6
  %res4 = add <8 x i16> %7, %res3
  ret <8 x i16> %res4
}

declare <16 x i16> @llvm.x86.avx512.dbpsadbw.256(<32 x i8>, <32 x i8>, i32)

define <16 x i16>@test_int_x86_avx512_mask_dbpsadbw_256(<32 x i8> %x0, <32 x i8> %x1, <16 x i16> %x3, i16 %x4) {
; X86-LABEL: test_int_x86_avx512_mask_dbpsadbw_256:
; X86:       # %bb.0:
; X86-NEXT:    vdbpsadbw $2, %ymm1, %ymm0, %ymm3 # encoding: [0x62,0xf3,0x7d,0x28,0x42,0xd9,0x02]
; X86-NEXT:    kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x04]
; X86-NEXT:    vdbpsadbw $2, %ymm1, %ymm0, %ymm2 {%k1} # encoding: [0x62,0xf3,0x7d,0x29,0x42,0xd1,0x02]
; X86-NEXT:    vdbpsadbw $2, %ymm1, %ymm0, %ymm0 {%k1} {z} # encoding: [0x62,0xf3,0x7d,0xa9,0x42,0xc1,0x02]
; X86-NEXT:    vpaddw %ymm3, %ymm0, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0xfd,0xc3]
; X86-NEXT:    vpaddw %ymm0, %ymm2, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xed,0xfd,0xc0]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_dbpsadbw_256:
; X64:       # %bb.0:
; X64-NEXT:    vdbpsadbw $2, %ymm1, %ymm0, %ymm3 # encoding: [0x62,0xf3,0x7d,0x28,0x42,0xd9,0x02]
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vdbpsadbw $2, %ymm1, %ymm0, %ymm2 {%k1} # encoding: [0x62,0xf3,0x7d,0x29,0x42,0xd1,0x02]
; X64-NEXT:    vdbpsadbw $2, %ymm1, %ymm0, %ymm0 {%k1} {z} # encoding: [0x62,0xf3,0x7d,0xa9,0x42,0xc1,0x02]
; X64-NEXT:    vpaddw %ymm3, %ymm0, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0xfd,0xc3]
; X64-NEXT:    vpaddw %ymm0, %ymm2, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xed,0xfd,0xc0]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = call <16 x i16> @llvm.x86.avx512.dbpsadbw.256(<32 x i8> %x0, <32 x i8> %x1, i32 2)
  %2 = bitcast i16 %x4 to <16 x i1>
  %3 = select <16 x i1> %2, <16 x i16> %1, <16 x i16> %x3
  %4 = call <16 x i16> @llvm.x86.avx512.dbpsadbw.256(<32 x i8> %x0, <32 x i8> %x1, i32 2)
  %5 = bitcast i16 %x4 to <16 x i1>
  %6 = select <16 x i1> %5, <16 x i16> %4, <16 x i16> zeroinitializer
  %7 = call <16 x i16> @llvm.x86.avx512.dbpsadbw.256(<32 x i8> %x0, <32 x i8> %x1, i32 2)
  %res3 = add <16 x i16> %3, %6
  %res4 = add <16 x i16> %res3, %7
  ret <16 x i16> %res4
}

declare <16 x i16> @llvm.x86.avx512.mask.psrlv16.hi(<16 x i16>, <16 x i16>, <16 x i16>, i16)

define <16 x i16>@test_int_x86_avx512_mask_psrlv16_hi(<16 x i16> %x0, <16 x i16> %x1, <16 x i16> %x2, i16 %x3) {
; X86-LABEL: test_int_x86_avx512_mask_psrlv16_hi:
; X86:       # %bb.0:
; X86-NEXT:    vpsrlvw %ymm1, %ymm0, %ymm3 # encoding: [0x62,0xf2,0xfd,0x28,0x10,0xd9]
; X86-NEXT:    kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x04]
; X86-NEXT:    vpsrlvw %ymm1, %ymm0, %ymm2 {%k1} # encoding: [0x62,0xf2,0xfd,0x29,0x10,0xd1]
; X86-NEXT:    vpsrlvw %ymm1, %ymm0, %ymm0 {%k1} {z} # encoding: [0x62,0xf2,0xfd,0xa9,0x10,0xc1]
; X86-NEXT:    vpaddw %ymm3, %ymm0, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0xfd,0xc3]
; X86-NEXT:    vpaddw %ymm0, %ymm2, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xed,0xfd,0xc0]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_psrlv16_hi:
; X64:       # %bb.0:
; X64-NEXT:    vpsrlvw %ymm1, %ymm0, %ymm3 # encoding: [0x62,0xf2,0xfd,0x28,0x10,0xd9]
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpsrlvw %ymm1, %ymm0, %ymm2 {%k1} # encoding: [0x62,0xf2,0xfd,0x29,0x10,0xd1]
; X64-NEXT:    vpsrlvw %ymm1, %ymm0, %ymm0 {%k1} {z} # encoding: [0x62,0xf2,0xfd,0xa9,0x10,0xc1]
; X64-NEXT:    vpaddw %ymm3, %ymm0, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0xfd,0xc3]
; X64-NEXT:    vpaddw %ymm0, %ymm2, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xed,0xfd,0xc0]
; X64-NEXT:    retq # encoding: [0xc3]
  %res = call <16 x i16> @llvm.x86.avx512.mask.psrlv16.hi(<16 x i16> %x0, <16 x i16> %x1, <16 x i16> %x2, i16 %x3)
  %res1 = call <16 x i16> @llvm.x86.avx512.mask.psrlv16.hi(<16 x i16> %x0, <16 x i16> %x1, <16 x i16> zeroinitializer, i16 %x3)
  %res2 = call <16 x i16> @llvm.x86.avx512.mask.psrlv16.hi(<16 x i16> %x0, <16 x i16> %x1, <16 x i16> %x2, i16 -1)
  %res3 = add <16 x i16> %res, %res1
  %res4 = add <16 x i16> %res3, %res2
  ret <16 x i16> %res4
}

declare <8 x i16> @llvm.x86.avx512.mask.psrlv8.hi(<8 x i16>, <8 x i16>, <8 x i16>, i8)

define <8 x i16>@test_int_x86_avx512_mask_psrlv8_hi(<8 x i16> %x0, <8 x i16> %x1, <8 x i16> %x2, i8 %x3) {
; X86-LABEL: test_int_x86_avx512_mask_psrlv8_hi:
; X86:       # %bb.0:
; X86-NEXT:    vpsrlvw %xmm1, %xmm0, %xmm3 # encoding: [0x62,0xf2,0xfd,0x08,0x10,0xd9]
; X86-NEXT:    movzbl {{[0-9]+}}(%esp), %eax # encoding: [0x0f,0xb6,0x44,0x24,0x04]
; X86-NEXT:    kmovd %eax, %k1 # encoding: [0xc5,0xfb,0x92,0xc8]
; X86-NEXT:    vpsrlvw %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf2,0xfd,0x09,0x10,0xd1]
; X86-NEXT:    vpsrlvw %xmm1, %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf2,0xfd,0x89,0x10,0xc1]
; X86-NEXT:    vpaddw %xmm3, %xmm0, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0xfd,0xc3]
; X86-NEXT:    vpaddw %xmm0, %xmm2, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe9,0xfd,0xc0]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_psrlv8_hi:
; X64:       # %bb.0:
; X64-NEXT:    vpsrlvw %xmm1, %xmm0, %xmm3 # encoding: [0x62,0xf2,0xfd,0x08,0x10,0xd9]
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpsrlvw %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf2,0xfd,0x09,0x10,0xd1]
; X64-NEXT:    vpsrlvw %xmm1, %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf2,0xfd,0x89,0x10,0xc1]
; X64-NEXT:    vpaddw %xmm3, %xmm0, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0xfd,0xc3]
; X64-NEXT:    vpaddw %xmm0, %xmm2, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe9,0xfd,0xc0]
; X64-NEXT:    retq # encoding: [0xc3]
  %res = call <8 x i16> @llvm.x86.avx512.mask.psrlv8.hi(<8 x i16> %x0, <8 x i16> %x1, <8 x i16> %x2, i8 %x3)
  %res1 = call <8 x i16> @llvm.x86.avx512.mask.psrlv8.hi(<8 x i16> %x0, <8 x i16> %x1, <8 x i16> zeroinitializer, i8 %x3)
  %res2 = call <8 x i16> @llvm.x86.avx512.mask.psrlv8.hi(<8 x i16> %x0, <8 x i16> %x1, <8 x i16> %x2, i8 -1)
  %res3 = add <8 x i16> %res, %res1
  %res4 = add <8 x i16> %res3, %res2
  ret <8 x i16> %res4
}

declare <16 x i16> @llvm.x86.avx512.mask.psrav16.hi(<16 x i16>, <16 x i16>, <16 x i16>, i16)

define <16 x i16>@test_int_x86_avx512_mask_psrav16_hi(<16 x i16> %x0, <16 x i16> %x1, <16 x i16> %x2, i16 %x3) {
; X86-LABEL: test_int_x86_avx512_mask_psrav16_hi:
; X86:       # %bb.0:
; X86-NEXT:    vpsravw %ymm1, %ymm0, %ymm3 # encoding: [0x62,0xf2,0xfd,0x28,0x11,0xd9]
; X86-NEXT:    kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x04]
; X86-NEXT:    vpsravw %ymm1, %ymm0, %ymm2 {%k1} # encoding: [0x62,0xf2,0xfd,0x29,0x11,0xd1]
; X86-NEXT:    vpsravw %ymm1, %ymm0, %ymm0 {%k1} {z} # encoding: [0x62,0xf2,0xfd,0xa9,0x11,0xc1]
; X86-NEXT:    vpaddw %ymm3, %ymm0, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0xfd,0xc3]
; X86-NEXT:    vpaddw %ymm0, %ymm2, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xed,0xfd,0xc0]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_psrav16_hi:
; X64:       # %bb.0:
; X64-NEXT:    vpsravw %ymm1, %ymm0, %ymm3 # encoding: [0x62,0xf2,0xfd,0x28,0x11,0xd9]
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpsravw %ymm1, %ymm0, %ymm2 {%k1} # encoding: [0x62,0xf2,0xfd,0x29,0x11,0xd1]
; X64-NEXT:    vpsravw %ymm1, %ymm0, %ymm0 {%k1} {z} # encoding: [0x62,0xf2,0xfd,0xa9,0x11,0xc1]
; X64-NEXT:    vpaddw %ymm3, %ymm0, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0xfd,0xc3]
; X64-NEXT:    vpaddw %ymm0, %ymm2, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xed,0xfd,0xc0]
; X64-NEXT:    retq # encoding: [0xc3]
  %res = call <16 x i16> @llvm.x86.avx512.mask.psrav16.hi(<16 x i16> %x0, <16 x i16> %x1, <16 x i16> %x2, i16 %x3)
  %res1 = call <16 x i16> @llvm.x86.avx512.mask.psrav16.hi(<16 x i16> %x0, <16 x i16> %x1, <16 x i16> zeroinitializer, i16 %x3)
  %res2 = call <16 x i16> @llvm.x86.avx512.mask.psrav16.hi(<16 x i16> %x0, <16 x i16> %x1, <16 x i16> %x2, i16 -1)
  %res3 = add <16 x i16> %res, %res1
  %res4 = add <16 x i16> %res3, %res2
  ret <16 x i16> %res4
}

declare <8 x i16> @llvm.x86.avx512.mask.psrav8.hi(<8 x i16>, <8 x i16>, <8 x i16>, i8)

define <8 x i16>@test_int_x86_avx512_mask_psrav8_hi(<8 x i16> %x0, <8 x i16> %x1, <8 x i16> %x2, i8 %x3) {
; X86-LABEL: test_int_x86_avx512_mask_psrav8_hi:
; X86:       # %bb.0:
; X86-NEXT:    vpsravw %xmm1, %xmm0, %xmm3 # encoding: [0x62,0xf2,0xfd,0x08,0x11,0xd9]
; X86-NEXT:    movzbl {{[0-9]+}}(%esp), %eax # encoding: [0x0f,0xb6,0x44,0x24,0x04]
; X86-NEXT:    kmovd %eax, %k1 # encoding: [0xc5,0xfb,0x92,0xc8]
; X86-NEXT:    vpsravw %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf2,0xfd,0x09,0x11,0xd1]
; X86-NEXT:    vpsravw %xmm1, %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf2,0xfd,0x89,0x11,0xc1]
; X86-NEXT:    vpaddw %xmm3, %xmm0, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0xfd,0xc3]
; X86-NEXT:    vpaddw %xmm0, %xmm2, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe9,0xfd,0xc0]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_psrav8_hi:
; X64:       # %bb.0:
; X64-NEXT:    vpsravw %xmm1, %xmm0, %xmm3 # encoding: [0x62,0xf2,0xfd,0x08,0x11,0xd9]
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpsravw %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf2,0xfd,0x09,0x11,0xd1]
; X64-NEXT:    vpsravw %xmm1, %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf2,0xfd,0x89,0x11,0xc1]
; X64-NEXT:    vpaddw %xmm3, %xmm0, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0xfd,0xc3]
; X64-NEXT:    vpaddw %xmm0, %xmm2, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe9,0xfd,0xc0]
; X64-NEXT:    retq # encoding: [0xc3]
  %res = call <8 x i16> @llvm.x86.avx512.mask.psrav8.hi(<8 x i16> %x0, <8 x i16> %x1, <8 x i16> %x2, i8 %x3)
  %res1 = call <8 x i16> @llvm.x86.avx512.mask.psrav8.hi(<8 x i16> %x0, <8 x i16> %x1, <8 x i16> zeroinitializer, i8 %x3)
  %res2 = call <8 x i16> @llvm.x86.avx512.mask.psrav8.hi(<8 x i16> %x0, <8 x i16> %x1, <8 x i16> %x2, i8 -1)
  %res3 = add <8 x i16> %res, %res1
  %res4 = add <8 x i16> %res3, %res2
  ret <8 x i16> %res4
}

declare <16 x i16> @llvm.x86.avx512.mask.psllv16.hi(<16 x i16>, <16 x i16>, <16 x i16>, i16)

define <16 x i16>@test_int_x86_avx512_mask_psllv16_hi(<16 x i16> %x0, <16 x i16> %x1, <16 x i16> %x2, i16 %x3) {
; X86-LABEL: test_int_x86_avx512_mask_psllv16_hi:
; X86:       # %bb.0:
; X86-NEXT:    vpsllvw %ymm1, %ymm0, %ymm3 # encoding: [0x62,0xf2,0xfd,0x28,0x12,0xd9]
; X86-NEXT:    kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x04]
; X86-NEXT:    vpsllvw %ymm1, %ymm0, %ymm2 {%k1} # encoding: [0x62,0xf2,0xfd,0x29,0x12,0xd1]
; X86-NEXT:    vpsllvw %ymm1, %ymm0, %ymm0 {%k1} {z} # encoding: [0x62,0xf2,0xfd,0xa9,0x12,0xc1]
; X86-NEXT:    vpaddw %ymm3, %ymm0, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0xfd,0xc3]
; X86-NEXT:    vpaddw %ymm0, %ymm2, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xed,0xfd,0xc0]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_psllv16_hi:
; X64:       # %bb.0:
; X64-NEXT:    vpsllvw %ymm1, %ymm0, %ymm3 # encoding: [0x62,0xf2,0xfd,0x28,0x12,0xd9]
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpsllvw %ymm1, %ymm0, %ymm2 {%k1} # encoding: [0x62,0xf2,0xfd,0x29,0x12,0xd1]
; X64-NEXT:    vpsllvw %ymm1, %ymm0, %ymm0 {%k1} {z} # encoding: [0x62,0xf2,0xfd,0xa9,0x12,0xc1]
; X64-NEXT:    vpaddw %ymm3, %ymm0, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0xfd,0xc3]
; X64-NEXT:    vpaddw %ymm0, %ymm2, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xed,0xfd,0xc0]
; X64-NEXT:    retq # encoding: [0xc3]
  %res = call <16 x i16> @llvm.x86.avx512.mask.psllv16.hi(<16 x i16> %x0, <16 x i16> %x1, <16 x i16> %x2, i16 %x3)
  %res1 = call <16 x i16> @llvm.x86.avx512.mask.psllv16.hi(<16 x i16> %x0, <16 x i16> %x1, <16 x i16> zeroinitializer, i16 %x3)
  %res2 = call <16 x i16> @llvm.x86.avx512.mask.psllv16.hi(<16 x i16> %x0, <16 x i16> %x1, <16 x i16> %x2, i16 -1)
  %res3 = add <16 x i16> %res, %res1
  %res4 = add <16 x i16> %res3, %res2
  ret <16 x i16> %res4
}

declare <8 x i16> @llvm.x86.avx512.mask.psllv8.hi(<8 x i16>, <8 x i16>, <8 x i16>, i8)

define <8 x i16>@test_int_x86_avx512_mask_psllv8_hi(<8 x i16> %x0, <8 x i16> %x1, <8 x i16> %x2, i8 %x3) {
; X86-LABEL: test_int_x86_avx512_mask_psllv8_hi:
; X86:       # %bb.0:
; X86-NEXT:    vpsllvw %xmm1, %xmm0, %xmm3 # encoding: [0x62,0xf2,0xfd,0x08,0x12,0xd9]
; X86-NEXT:    movzbl {{[0-9]+}}(%esp), %eax # encoding: [0x0f,0xb6,0x44,0x24,0x04]
; X86-NEXT:    kmovd %eax, %k1 # encoding: [0xc5,0xfb,0x92,0xc8]
; X86-NEXT:    vpsllvw %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf2,0xfd,0x09,0x12,0xd1]
; X86-NEXT:    vpsllvw %xmm1, %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf2,0xfd,0x89,0x12,0xc1]
; X86-NEXT:    vpaddw %xmm3, %xmm0, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0xfd,0xc3]
; X86-NEXT:    vpaddw %xmm0, %xmm2, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe9,0xfd,0xc0]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_psllv8_hi:
; X64:       # %bb.0:
; X64-NEXT:    vpsllvw %xmm1, %xmm0, %xmm3 # encoding: [0x62,0xf2,0xfd,0x08,0x12,0xd9]
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpsllvw %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf2,0xfd,0x09,0x12,0xd1]
; X64-NEXT:    vpsllvw %xmm1, %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf2,0xfd,0x89,0x12,0xc1]
; X64-NEXT:    vpaddw %xmm3, %xmm0, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0xfd,0xc3]
; X64-NEXT:    vpaddw %xmm0, %xmm2, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe9,0xfd,0xc0]
; X64-NEXT:    retq # encoding: [0xc3]
  %res = call <8 x i16> @llvm.x86.avx512.mask.psllv8.hi(<8 x i16> %x0, <8 x i16> %x1, <8 x i16> %x2, i8 %x3)
  %res1 = call <8 x i16> @llvm.x86.avx512.mask.psllv8.hi(<8 x i16> %x0, <8 x i16> %x1, <8 x i16> zeroinitializer, i8 %x3)
  %res2 = call <8 x i16> @llvm.x86.avx512.mask.psllv8.hi(<8 x i16> %x0, <8 x i16> %x1, <8 x i16> %x2, i8 -1)
  %res3 = add <8 x i16> %res, %res1
  %res4 = add <8 x i16> %res3, %res2
  ret <8 x i16> %res4
}

declare <8 x i16> @llvm.x86.avx512.permvar.hi.128(<8 x i16>, <8 x i16>)

define <8 x i16>@test_int_x86_avx512_mask_permvar_hi_128(<8 x i16> %x0, <8 x i16> %x1, <8 x i16> %x2, i8 %x3) {
; X86-LABEL: test_int_x86_avx512_mask_permvar_hi_128:
; X86:       # %bb.0:
; X86-NEXT:    vpermw %xmm0, %xmm1, %xmm3 # encoding: [0x62,0xf2,0xf5,0x08,0x8d,0xd8]
; X86-NEXT:    movzbl {{[0-9]+}}(%esp), %eax # encoding: [0x0f,0xb6,0x44,0x24,0x04]
; X86-NEXT:    kmovd %eax, %k1 # encoding: [0xc5,0xfb,0x92,0xc8]
; X86-NEXT:    vpermw %xmm0, %xmm1, %xmm2 {%k1} # encoding: [0x62,0xf2,0xf5,0x09,0x8d,0xd0]
; X86-NEXT:    vpermw %xmm0, %xmm1, %xmm0 {%k1} {z} # encoding: [0x62,0xf2,0xf5,0x89,0x8d,0xc0]
; X86-NEXT:    vpaddw %xmm3, %xmm0, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0xfd,0xc3]
; X86-NEXT:    vpaddw %xmm0, %xmm2, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe9,0xfd,0xc0]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_permvar_hi_128:
; X64:       # %bb.0:
; X64-NEXT:    vpermw %xmm0, %xmm1, %xmm3 # encoding: [0x62,0xf2,0xf5,0x08,0x8d,0xd8]
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpermw %xmm0, %xmm1, %xmm2 {%k1} # encoding: [0x62,0xf2,0xf5,0x09,0x8d,0xd0]
; X64-NEXT:    vpermw %xmm0, %xmm1, %xmm0 {%k1} {z} # encoding: [0x62,0xf2,0xf5,0x89,0x8d,0xc0]
; X64-NEXT:    vpaddw %xmm3, %xmm0, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0xfd,0xc3]
; X64-NEXT:    vpaddw %xmm0, %xmm2, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe9,0xfd,0xc0]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = call <8 x i16> @llvm.x86.avx512.permvar.hi.128(<8 x i16> %x0, <8 x i16> %x1)
  %2 = bitcast i8 %x3 to <8 x i1>
  %3 = select <8 x i1> %2, <8 x i16> %1, <8 x i16> %x2
  %4 = call <8 x i16> @llvm.x86.avx512.permvar.hi.128(<8 x i16> %x0, <8 x i16> %x1)
  %5 = bitcast i8 %x3 to <8 x i1>
  %6 = select <8 x i1> %5, <8 x i16> %4, <8 x i16> zeroinitializer
  %7 = call <8 x i16> @llvm.x86.avx512.permvar.hi.128(<8 x i16> %x0, <8 x i16> %x1)
  %res3 = add <8 x i16> %3, %6
  %res4 = add <8 x i16> %res3, %7
  ret <8 x i16> %res4
}

declare <16 x i16> @llvm.x86.avx512.permvar.hi.256(<16 x i16>, <16 x i16>)

define <16 x i16>@test_int_x86_avx512_mask_permvar_hi_256(<16 x i16> %x0, <16 x i16> %x1, <16 x i16> %x2, i16 %x3) {
; X86-LABEL: test_int_x86_avx512_mask_permvar_hi_256:
; X86:       # %bb.0:
; X86-NEXT:    vpermw %ymm0, %ymm1, %ymm3 # encoding: [0x62,0xf2,0xf5,0x28,0x8d,0xd8]
; X86-NEXT:    kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x04]
; X86-NEXT:    vpermw %ymm0, %ymm1, %ymm2 {%k1} # encoding: [0x62,0xf2,0xf5,0x29,0x8d,0xd0]
; X86-NEXT:    vpermw %ymm0, %ymm1, %ymm0 {%k1} {z} # encoding: [0x62,0xf2,0xf5,0xa9,0x8d,0xc0]
; X86-NEXT:    vpaddw %ymm3, %ymm0, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0xfd,0xc3]
; X86-NEXT:    vpaddw %ymm0, %ymm2, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xed,0xfd,0xc0]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_permvar_hi_256:
; X64:       # %bb.0:
; X64-NEXT:    vpermw %ymm0, %ymm1, %ymm3 # encoding: [0x62,0xf2,0xf5,0x28,0x8d,0xd8]
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpermw %ymm0, %ymm1, %ymm2 {%k1} # encoding: [0x62,0xf2,0xf5,0x29,0x8d,0xd0]
; X64-NEXT:    vpermw %ymm0, %ymm1, %ymm0 {%k1} {z} # encoding: [0x62,0xf2,0xf5,0xa9,0x8d,0xc0]
; X64-NEXT:    vpaddw %ymm3, %ymm0, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0xfd,0xc3]
; X64-NEXT:    vpaddw %ymm0, %ymm2, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xed,0xfd,0xc0]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = call <16 x i16> @llvm.x86.avx512.permvar.hi.256(<16 x i16> %x0, <16 x i16> %x1)
  %2 = bitcast i16 %x3 to <16 x i1>
  %3 = select <16 x i1> %2, <16 x i16> %1, <16 x i16> %x2
  %4 = call <16 x i16> @llvm.x86.avx512.permvar.hi.256(<16 x i16> %x0, <16 x i16> %x1)
  %5 = bitcast i16 %x3 to <16 x i1>
  %6 = select <16 x i1> %5, <16 x i16> %4, <16 x i16> zeroinitializer
  %7 = call <16 x i16> @llvm.x86.avx512.permvar.hi.256(<16 x i16> %x0, <16 x i16> %x1)
  %res3 = add <16 x i16> %3, %6
  %res4 = add <16 x i16> %res3, %7
  ret <16 x i16> %res4
}