test/CodeGen/X86/avx512vbmi2vl-intrinsics.ll

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=+avx512vbmi2,+avx512vl --show-mc-encoding | FileCheck %s --check-prefixes=CHECK,X86
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512vbmi2,+avx512vl --show-mc-encoding | FileCheck %s --check-prefixes=CHECK,X64

define <8 x i16> @test_mask_expand_load_w_128(i8* %addr, <8 x i16> %data, i8 %mask) {
; X86-LABEL: test_mask_expand_load_w_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:    vpexpandw (%eax), %xmm0 {%k1} # encoding: [0x62,0xf2,0xfd,0x09,0x62,0x00]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_expand_load_w_128:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT:    vpexpandw (%rdi), %xmm0 {%k1} # encoding: [0x62,0xf2,0xfd,0x09,0x62,0x07]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = bitcast i8* %addr to i16*
  %2 = bitcast i8 %mask to <8 x i1>
  %3 = call <8 x i16> @llvm.masked.expandload.v8i16(i16* %1, <8 x i1> %2, <8 x i16> %data)
  ret <8 x i16> %3
}

define <8 x i16> @test_maskz_expand_load_w_128(i8* %addr, i8 %mask) {
; X86-LABEL: test_maskz_expand_load_w_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:    vpexpandw (%eax), %xmm0 {%k1} {z} # encoding: [0x62,0xf2,0xfd,0x89,0x62,0x00]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_maskz_expand_load_w_128:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT:    vpexpandw (%rdi), %xmm0 {%k1} {z} # encoding: [0x62,0xf2,0xfd,0x89,0x62,0x07]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = bitcast i8* %addr to i16*
  %2 = bitcast i8 %mask to <8 x i1>
  %3 = call <8 x i16> @llvm.masked.expandload.v8i16(i16* %1, <8 x i1> %2, <8 x i16> zeroinitializer)
  ret <8 x i16> %3
}

define <8 x i16> @test_expand_load_w_128(i8* %addr, <8 x i16> %data) {
; X86-LABEL: test_expand_load_w_128:
; X86:       # %bb.0:
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT:    kxnorw %k0, %k0, %k1 # encoding: [0xc5,0xfc,0x46,0xc8]
; X86-NEXT:    vpexpandw (%eax), %xmm0 {%k1} # encoding: [0x62,0xf2,0xfd,0x09,0x62,0x00]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_expand_load_w_128:
; X64:       # %bb.0:
; X64-NEXT:    kxnorw %k0, %k0, %k1 # encoding: [0xc5,0xfc,0x46,0xc8]
; X64-NEXT:    vpexpandw (%rdi), %xmm0 {%k1} # encoding: [0x62,0xf2,0xfd,0x09,0x62,0x07]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = bitcast i8* %addr to i16*
  %2 = call <8 x i16> @llvm.masked.expandload.v8i16(i16* %1, <8 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <8 x i16> %data)
  ret <8 x i16> %2
}

define <8 x i16> @test_expand_w_128(<8 x i16> %data) {
; CHECK-LABEL: test_expand_w_128:
; CHECK:       # %bb.0:
; CHECK-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
  %1 = call <8 x i16> @llvm.x86.avx512.mask.expand.v8i16(<8 x i16> %data, <8 x i16> undef, <8 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>)
  ret <8 x i16> %1
}

define <8 x i16> @test_mask_expand_w_128(<8 x i16> %data, <8 x i16> %passthru, i8 %mask) {
; X86-LABEL: test_mask_expand_w_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:    vpexpandw %xmm0, %xmm1 {%k1} # encoding: [0x62,0xf2,0xfd,0x09,0x62,0xc8]
; X86-NEXT:    vmovdqa %xmm1, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xc1]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_expand_w_128:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpexpandw %xmm0, %xmm1 {%k1} # encoding: [0x62,0xf2,0xfd,0x09,0x62,0xc8]
; X64-NEXT:    vmovdqa %xmm1, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xc1]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = bitcast i8 %mask to <8 x i1>
  %2 = call <8 x i16> @llvm.x86.avx512.mask.expand.v8i16(<8 x i16> %data, <8 x i16> %passthru, <8 x i1> %1)
  ret <8 x i16> %2
}

define <8 x i16> @test_maskz_expand_w_128(<8 x i16> %data, i8 %mask) {
; X86-LABEL: test_maskz_expand_w_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:    vpexpandw %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf2,0xfd,0x89,0x62,0xc0]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_maskz_expand_w_128:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpexpandw %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf2,0xfd,0x89,0x62,0xc0]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = bitcast i8 %mask to <8 x i1>
  %2 = call <8 x i16> @llvm.x86.avx512.mask.expand.v8i16(<8 x i16> %data, <8 x i16> zeroinitializer, <8 x i1> %1)
  ret <8 x i16> %2
}

define <16 x i8> @test_mask_expand_load_b_128(i8* %addr, <16 x i8> %data, i16 %mask) {
; X86-LABEL: test_mask_expand_load_b_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:    vpexpandb (%eax), %xmm0 {%k1} # encoding: [0x62,0xf2,0x7d,0x09,0x62,0x00]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_expand_load_b_128:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT:    vpexpandb (%rdi), %xmm0 {%k1} # encoding: [0x62,0xf2,0x7d,0x09,0x62,0x07]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = bitcast i16 %mask to <16 x i1>
  %2 = call <16 x i8> @llvm.masked.expandload.v16i8(i8* %addr, <16 x i1> %1, <16 x i8> %data)
  ret <16 x i8> %2
}

define <16 x i8> @test_maskz_expand_load_b_128(i8* %addr, i16 %mask) {
; X86-LABEL: test_maskz_expand_load_b_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:    vpexpandb (%eax), %xmm0 {%k1} {z} # encoding: [0x62,0xf2,0x7d,0x89,0x62,0x00]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_maskz_expand_load_b_128:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT:    vpexpandb (%rdi), %xmm0 {%k1} {z} # encoding: [0x62,0xf2,0x7d,0x89,0x62,0x07]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = bitcast i16 %mask to <16 x i1>
  %2 = call <16 x i8> @llvm.masked.expandload.v16i8(i8* %addr, <16 x i1> %1, <16 x i8> zeroinitializer)
  ret <16 x i8> %2
}

define <16 x i8> @test_expand_load_b_128(i8* %addr, <16 x i8> %data) {
; X86-LABEL: test_expand_load_b_128:
; X86:       # %bb.0:
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT:    kxnorw %k0, %k0, %k1 # encoding: [0xc5,0xfc,0x46,0xc8]
; X86-NEXT:    vpexpandb (%eax), %xmm0 {%k1} # encoding: [0x62,0xf2,0x7d,0x09,0x62,0x00]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_expand_load_b_128:
; X64:       # %bb.0:
; X64-NEXT:    kxnorw %k0, %k0, %k1 # encoding: [0xc5,0xfc,0x46,0xc8]
; X64-NEXT:    vpexpandb (%rdi), %xmm0 {%k1} # encoding: [0x62,0xf2,0x7d,0x09,0x62,0x07]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = call <16 x i8> @llvm.masked.expandload.v16i8(i8* %addr, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x i8> %data)
  ret <16 x i8> %1
}

define <16 x i8> @test_expand_b_128(<16 x i8> %data) {
; CHECK-LABEL: test_expand_b_128:
; CHECK:       # %bb.0:
; CHECK-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
  %1 = call <16 x i8> @llvm.x86.avx512.mask.expand.v16i8(<16 x i8> %data, <16 x i8> undef, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>)
  ret <16 x i8> %1
}

define <16 x i8> @test_mask_expand_b_128(<16 x i8> %data, <16 x i8> %passthru, i16 %mask) {
; X86-LABEL: test_mask_expand_b_128:
; X86:       # %bb.0:
; X86-NEXT:    kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x04]
; X86-NEXT:    vpexpandb %xmm0, %xmm1 {%k1} # encoding: [0x62,0xf2,0x7d,0x09,0x62,0xc8]
; X86-NEXT:    vmovdqa %xmm1, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xc1]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_expand_b_128:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpexpandb %xmm0, %xmm1 {%k1} # encoding: [0x62,0xf2,0x7d,0x09,0x62,0xc8]
; X64-NEXT:    vmovdqa %xmm1, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xc1]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = bitcast i16 %mask to <16 x i1>
  %2 = call <16 x i8> @llvm.x86.avx512.mask.expand.v16i8(<16 x i8> %data, <16 x i8> %passthru, <16 x i1> %1)
  ret <16 x i8> %2
}

define <16 x i8> @test_maskz_expand_b_128(<16 x i8> %data, i16 %mask) {
; X86-LABEL: test_maskz_expand_b_128:
; X86:       # %bb.0:
; X86-NEXT:    kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x04]
; X86-NEXT:    vpexpandb %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf2,0x7d,0x89,0x62,0xc0]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_maskz_expand_b_128:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpexpandb %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf2,0x7d,0x89,0x62,0xc0]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = bitcast i16 %mask to <16 x i1>
  %2 = call <16 x i8> @llvm.x86.avx512.mask.expand.v16i8(<16 x i8> %data, <16 x i8> zeroinitializer, <16 x i1> %1)
  ret <16 x i8> %2
}

define void @test_mask_compress_store_w_128(i8* %addr, <8 x i16> %data, i8 %mask) {
; X86-LABEL: test_mask_compress_store_w_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:    vpcompressw %xmm0, (%eax) {%k1} # encoding: [0x62,0xf2,0xfd,0x09,0x63,0x00]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_compress_store_w_128:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT:    vpcompressw %xmm0, (%rdi) {%k1} # encoding: [0x62,0xf2,0xfd,0x09,0x63,0x07]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = bitcast i8* %addr to i16*
  %2 = bitcast i8 %mask to <8 x i1>
  call void @llvm.masked.compressstore.v8i16(<8 x i16> %data, i16* %1, <8 x i1> %2)
  ret void
}

define void @test_compress_store_w_128(i8* %addr, <8 x i16> %data) {
; X86-LABEL: test_compress_store_w_128:
; X86:       # %bb.0:
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT:    kxnorw %k0, %k0, %k1 # encoding: [0xc5,0xfc,0x46,0xc8]
; X86-NEXT:    vpcompressw %xmm0, (%eax) {%k1} # encoding: [0x62,0xf2,0xfd,0x09,0x63,0x00]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_compress_store_w_128:
; X64:       # %bb.0:
; X64-NEXT:    kxnorw %k0, %k0, %k1 # encoding: [0xc5,0xfc,0x46,0xc8]
; X64-NEXT:    vpcompressw %xmm0, (%rdi) {%k1} # encoding: [0x62,0xf2,0xfd,0x09,0x63,0x07]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = bitcast i8* %addr to i16*
  call void @llvm.masked.compressstore.v8i16(<8 x i16> %data, i16* %1, <8 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>)
  ret void
}

define <8 x i16> @test_mask_compress_w_128(<8 x i16> %data, <8 x i16> %passthru, i8 %mask) {
; X86-LABEL: test_mask_compress_w_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:    vpcompressw %xmm0, %xmm1 {%k1} # encoding: [0x62,0xf2,0xfd,0x09,0x63,0xc1]
; X86-NEXT:    vmovdqa %xmm1, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xc1]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_compress_w_128:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpcompressw %xmm0, %xmm1 {%k1} # encoding: [0x62,0xf2,0xfd,0x09,0x63,0xc1]
; X64-NEXT:    vmovdqa %xmm1, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xc1]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = bitcast i8 %mask to <8 x i1>
  %2 = call <8 x i16> @llvm.x86.avx512.mask.compress.v8i16(<8 x i16> %data, <8 x i16> %passthru, <8 x i1> %1)
  ret <8 x i16> %2
}

define <8 x i16> @test_maskz_compress_w_128(<8 x i16> %data, i8 %mask) {
; X86-LABEL: test_maskz_compress_w_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:    vpcompressw %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf2,0xfd,0x89,0x63,0xc0]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_maskz_compress_w_128:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpcompressw %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf2,0xfd,0x89,0x63,0xc0]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = bitcast i8 %mask to <8 x i1>
  %2 = call <8 x i16> @llvm.x86.avx512.mask.compress.v8i16(<8 x i16> %data, <8 x i16> zeroinitializer, <8 x i1> %1)
  ret <8 x i16> %2
}

define <8 x i16> @test_compress_w_128(<8 x i16> %data) {
; CHECK-LABEL: test_compress_w_128:
; CHECK:       # %bb.0:
; CHECK-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
  %1 = call <8 x i16> @llvm.x86.avx512.mask.compress.v8i16(<8 x i16> %data, <8 x i16> undef, <8 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>)
  ret <8 x i16> %1
}

define void @test_mask_compress_store_b_128(i8* %addr, <16 x i8> %data, i16 %mask) {
; X86-LABEL: test_mask_compress_store_b_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:    vpcompressb %xmm0, (%eax) {%k1} # encoding: [0x62,0xf2,0x7d,0x09,0x63,0x00]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_compress_store_b_128:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT:    vpcompressb %xmm0, (%rdi) {%k1} # encoding: [0x62,0xf2,0x7d,0x09,0x63,0x07]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = bitcast i16 %mask to <16 x i1>
  call void @llvm.masked.compressstore.v16i8(<16 x i8> %data, i8* %addr, <16 x i1> %1)
  ret void
}

define void @test_compress_store_b_128(i8* %addr, <16 x i8> %data) {
; X86-LABEL: test_compress_store_b_128:
; X86:       # %bb.0:
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT:    kxnorw %k0, %k0, %k1 # encoding: [0xc5,0xfc,0x46,0xc8]
; X86-NEXT:    vpcompressb %xmm0, (%eax) {%k1} # encoding: [0x62,0xf2,0x7d,0x09,0x63,0x00]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_compress_store_b_128:
; X64:       # %bb.0:
; X64-NEXT:    kxnorw %k0, %k0, %k1 # encoding: [0xc5,0xfc,0x46,0xc8]
; X64-NEXT:    vpcompressb %xmm0, (%rdi) {%k1} # encoding: [0x62,0xf2,0x7d,0x09,0x63,0x07]
; X64-NEXT:    retq # encoding: [0xc3]
  call void @llvm.masked.compressstore.v16i8(<16 x i8> %data, i8* %addr, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>)
  ret void
}

define <16 x i8> @test_mask_compress_b_128(<16 x i8> %data, <16 x i8> %passthru, i16 %mask) {
; X86-LABEL: test_mask_compress_b_128:
; X86:       # %bb.0:
; X86-NEXT:    kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x04]
; X86-NEXT:    vpcompressb %xmm0, %xmm1 {%k1} # encoding: [0x62,0xf2,0x7d,0x09,0x63,0xc1]
; X86-NEXT:    vmovdqa %xmm1, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xc1]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_compress_b_128:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpcompressb %xmm0, %xmm1 {%k1} # encoding: [0x62,0xf2,0x7d,0x09,0x63,0xc1]
; X64-NEXT:    vmovdqa %xmm1, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xc1]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = bitcast i16 %mask to <16 x i1>
  %2 = call <16 x i8> @llvm.x86.avx512.mask.compress.v16i8(<16 x i8> %data, <16 x i8> %passthru, <16 x i1> %1)
  ret <16 x i8> %2
}

define <16 x i8> @test_maskz_compress_b_128(<16 x i8> %data, i16 %mask) {
; X86-LABEL: test_maskz_compress_b_128:
; X86:       # %bb.0:
; X86-NEXT:    kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x04]
; X86-NEXT:    vpcompressb %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf2,0x7d,0x89,0x63,0xc0]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_maskz_compress_b_128:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpcompressb %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf2,0x7d,0x89,0x63,0xc0]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = bitcast i16 %mask to <16 x i1>
  %2 = call <16 x i8> @llvm.x86.avx512.mask.compress.v16i8(<16 x i8> %data, <16 x i8> zeroinitializer, <16 x i1> %1)
  ret <16 x i8> %2
}

define <16 x i8> @test_compress_b_128(<16 x i8> %data) {
; CHECK-LABEL: test_compress_b_128:
; CHECK:       # %bb.0:
; CHECK-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
  %1 = call <16 x i8> @llvm.x86.avx512.mask.compress.v16i8(<16 x i8> %data, <16 x i8> undef, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>)
  ret <16 x i8> %1
}

define <16 x i16> @test_mask_expand_load_w_256(i8* %addr, <16 x i16> %data, i16 %mask) {
; X86-LABEL: test_mask_expand_load_w_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:    vpexpandw (%eax), %ymm0 {%k1} # encoding: [0x62,0xf2,0xfd,0x29,0x62,0x00]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_expand_load_w_256:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT:    vpexpandw (%rdi), %ymm0 {%k1} # encoding: [0x62,0xf2,0xfd,0x29,0x62,0x07]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = bitcast i8* %addr to i16*
  %2 = bitcast i16 %mask to <16 x i1>
  %3 = call <16 x i16> @llvm.masked.expandload.v16i16(i16* %1, <16 x i1> %2, <16 x i16> %data)
  ret <16 x i16> %3
}

define <16 x i16> @test_maskz_expand_load_w_256(i8* %addr, i16 %mask) {
; X86-LABEL: test_maskz_expand_load_w_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:    vpexpandw (%eax), %ymm0 {%k1} {z} # encoding: [0x62,0xf2,0xfd,0xa9,0x62,0x00]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_maskz_expand_load_w_256:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT:    vpexpandw (%rdi), %ymm0 {%k1} {z} # encoding: [0x62,0xf2,0xfd,0xa9,0x62,0x07]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = bitcast i8* %addr to i16*
  %2 = bitcast i16 %mask to <16 x i1>
  %3 = call <16 x i16> @llvm.masked.expandload.v16i16(i16* %1, <16 x i1> %2, <16 x i16> zeroinitializer)
  ret <16 x i16> %3
}

define <16 x i16> @test_expand_load_w_256(i8* %addr, <16 x i16> %data) {
; X86-LABEL: test_expand_load_w_256:
; X86:       # %bb.0:
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT:    kxnorw %k0, %k0, %k1 # encoding: [0xc5,0xfc,0x46,0xc8]
; X86-NEXT:    vpexpandw (%eax), %ymm0 {%k1} # encoding: [0x62,0xf2,0xfd,0x29,0x62,0x00]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_expand_load_w_256:
; X64:       # %bb.0:
; X64-NEXT:    kxnorw %k0, %k0, %k1 # encoding: [0xc5,0xfc,0x46,0xc8]
; X64-NEXT:    vpexpandw (%rdi), %ymm0 {%k1} # encoding: [0x62,0xf2,0xfd,0x29,0x62,0x07]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = bitcast i8* %addr to i16*
  %2 = call <16 x i16> @llvm.masked.expandload.v16i16(i16* %1, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <16 x i16> %data)
  ret <16 x i16> %2
}

define <16 x i16> @test_expand_w_256(<16 x i16> %data) {
; CHECK-LABEL: test_expand_w_256:
; CHECK:       # %bb.0:
; CHECK-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
  %1 = call <16 x i16> @llvm.x86.avx512.mask.expand.v16i16(<16 x i16> %data, <16 x i16> undef, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>)
  ret <16 x i16> %1
}

define <16 x i16> @test_mask_expand_w_256(<16 x i16> %data, <16 x i16> %passthru, i16 %mask) {
; X86-LABEL: test_mask_expand_w_256:
; X86:       # %bb.0:
; X86-NEXT:    kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x04]
; X86-NEXT:    vpexpandw %ymm0, %ymm1 {%k1} # encoding: [0x62,0xf2,0xfd,0x29,0x62,0xc8]
; X86-NEXT:    vmovdqa %ymm1, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xc1]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_expand_w_256:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpexpandw %ymm0, %ymm1 {%k1} # encoding: [0x62,0xf2,0xfd,0x29,0x62,0xc8]
; X64-NEXT:    vmovdqa %ymm1, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xc1]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = bitcast i16 %mask to <16 x i1>
  %2 = call <16 x i16> @llvm.x86.avx512.mask.expand.v16i16(<16 x i16> %data, <16 x i16> %passthru, <16 x i1> %1)
  ret <16 x i16> %2
}

define <16 x i16> @test_maskz_expand_w_256(<16 x i16> %data, i16 %mask) {
; X86-LABEL: test_maskz_expand_w_256:
; X86:       # %bb.0:
; X86-NEXT:    kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x04]
; X86-NEXT:    vpexpandw %ymm0, %ymm0 {%k1} {z} # encoding: [0x62,0xf2,0xfd,0xa9,0x62,0xc0]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_maskz_expand_w_256:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpexpandw %ymm0, %ymm0 {%k1} {z} # encoding: [0x62,0xf2,0xfd,0xa9,0x62,0xc0]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = bitcast i16 %mask to <16 x i1>
  %2 = call <16 x i16> @llvm.x86.avx512.mask.expand.v16i16(<16 x i16> %data, <16 x i16> zeroinitializer, <16 x i1> %1)
  ret <16 x i16> %2
}

define <32 x i8> @test_mask_expand_load_b_256(i8* %addr, <32 x i8> %data, i32 %mask) {
; X86-LABEL: test_mask_expand_load_b_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:    vpexpandb (%eax), %ymm0 {%k1} # encoding: [0x62,0xf2,0x7d,0x29,0x62,0x00]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_expand_load_b_256:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT:    vpexpandb (%rdi), %ymm0 {%k1} # encoding: [0x62,0xf2,0x7d,0x29,0x62,0x07]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = bitcast i32 %mask to <32 x i1>
  %2 = call <32 x i8> @llvm.masked.expandload.v32i8(i8* %addr, <32 x i1> %1, <32 x i8> %data)
  ret <32 x i8> %2
}

define <32 x i8> @test_maskz_expand_load_b_256(i8* %addr, i32 %mask) {
; X86-LABEL: test_maskz_expand_load_b_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:    vpexpandb (%eax), %ymm0 {%k1} {z} # encoding: [0x62,0xf2,0x7d,0xa9,0x62,0x00]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_maskz_expand_load_b_256:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT:    vpexpandb (%rdi), %ymm0 {%k1} {z} # encoding: [0x62,0xf2,0x7d,0xa9,0x62,0x07]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = bitcast i32 %mask to <32 x i1>
  %2 = call <32 x i8> @llvm.masked.expandload.v32i8(i8* %addr, <32 x i1> %1, <32 x i8> zeroinitializer)
  ret <32 x i8> %2
}

define <32 x i8> @test_expand_load_b_256(i8* %addr, <32 x i8> %data) {
; X86-LABEL: test_expand_load_b_256:
; X86:       # %bb.0:
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT:    kxnord %k0, %k0, %k1 # encoding: [0xc4,0xe1,0xfd,0x46,0xc8]
; X86-NEXT:    vpexpandb (%eax), %ymm0 {%k1} # encoding: [0x62,0xf2,0x7d,0x29,0x62,0x00]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_expand_load_b_256:
; X64:       # %bb.0:
; X64-NEXT:    kxnord %k0, %k0, %k1 # encoding: [0xc4,0xe1,0xfd,0x46,0xc8]
; X64-NEXT:    vpexpandb (%rdi), %ymm0 {%k1} # encoding: [0x62,0xf2,0x7d,0x29,0x62,0x07]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = call <32 x i8> @llvm.masked.expandload.v32i8(i8* %addr, <32 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <32 x i8> %data)
  ret <32 x i8> %1
}

define <32 x i8> @test_expand_b_256(<32 x i8> %data) {
; CHECK-LABEL: test_expand_b_256:
; CHECK:       # %bb.0:
; CHECK-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
  %1 = call <32 x i8> @llvm.x86.avx512.mask.expand.v32i8(<32 x i8> %data, <32 x i8> undef, <32 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>)
  ret <32 x i8> %1
}

define <32 x i8> @test_mask_expand_b_256(<32 x i8> %data, <32 x i8> %passthru, i32 %mask) {
; X86-LABEL: test_mask_expand_b_256:
; X86:       # %bb.0:
; X86-NEXT:    kmovd {{[0-9]+}}(%esp), %k1 # encoding: [0xc4,0xe1,0xf9,0x90,0x4c,0x24,0x04]
; X86-NEXT:    vpexpandb %ymm0, %ymm1 {%k1} # encoding: [0x62,0xf2,0x7d,0x29,0x62,0xc8]
; X86-NEXT:    vmovdqa %ymm1, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xc1]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_expand_b_256:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpexpandb %ymm0, %ymm1 {%k1} # encoding: [0x62,0xf2,0x7d,0x29,0x62,0xc8]
; X64-NEXT:    vmovdqa %ymm1, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xc1]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = bitcast i32 %mask to <32 x i1>
  %2 = call <32 x i8> @llvm.x86.avx512.mask.expand.v32i8(<32 x i8> %data, <32 x i8> %passthru, <32 x i1> %1)
  ret <32 x i8> %2
}

define <32 x i8> @test_maskz_expand_b_256(<32 x i8> %data, i32 %mask) {
; X86-LABEL: test_maskz_expand_b_256:
; X86:       # %bb.0:
; X86-NEXT:    kmovd {{[0-9]+}}(%esp), %k1 # encoding: [0xc4,0xe1,0xf9,0x90,0x4c,0x24,0x04]
; X86-NEXT:    vpexpandb %ymm0, %ymm0 {%k1} {z} # encoding: [0x62,0xf2,0x7d,0xa9,0x62,0xc0]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_maskz_expand_b_256:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpexpandb %ymm0, %ymm0 {%k1} {z} # encoding: [0x62,0xf2,0x7d,0xa9,0x62,0xc0]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = bitcast i32 %mask to <32 x i1>
  %2 = call <32 x i8> @llvm.x86.avx512.mask.expand.v32i8(<32 x i8> %data, <32 x i8> zeroinitializer, <32 x i1> %1)
  ret <32 x i8> %2
}

define void @test_mask_compress_store_w_256(i8* %addr, <16 x i16> %data, i16 %mask) {
; X86-LABEL: test_mask_compress_store_w_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:    vpcompressw %ymm0, (%eax) {%k1} # encoding: [0x62,0xf2,0xfd,0x29,0x63,0x00]
; X86-NEXT:    vzeroupper # encoding: [0xc5,0xf8,0x77]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_compress_store_w_256:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT:    vpcompressw %ymm0, (%rdi) {%k1} # encoding: [0x62,0xf2,0xfd,0x29,0x63,0x07]
; X64-NEXT:    vzeroupper # encoding: [0xc5,0xf8,0x77]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = bitcast i8* %addr to i16*
  %2 = bitcast i16 %mask to <16 x i1>
  call void @llvm.masked.compressstore.v16i16(<16 x i16> %data, i16* %1, <16 x i1> %2)
  ret void
}

define void @test_compress_store_w_256(i8* %addr, <16 x i16> %data) {
; X86-LABEL: test_compress_store_w_256:
; X86:       # %bb.0:
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT:    kxnorw %k0, %k0, %k1 # encoding: [0xc5,0xfc,0x46,0xc8]
; X86-NEXT:    vpcompressw %ymm0, (%eax) {%k1} # encoding: [0x62,0xf2,0xfd,0x29,0x63,0x00]
; X86-NEXT:    vzeroupper # encoding: [0xc5,0xf8,0x77]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_compress_store_w_256:
; X64:       # %bb.0:
; X64-NEXT:    kxnorw %k0, %k0, %k1 # encoding: [0xc5,0xfc,0x46,0xc8]
; X64-NEXT:    vpcompressw %ymm0, (%rdi) {%k1} # encoding: [0x62,0xf2,0xfd,0x29,0x63,0x07]
; X64-NEXT:    vzeroupper # encoding: [0xc5,0xf8,0x77]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = bitcast i8* %addr to i16*
  call void @llvm.masked.compressstore.v16i16(<16 x i16> %data, i16* %1, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>)
  ret void
}

define <16 x i16> @test_mask_compress_w_256(<16 x i16> %data, <16 x i16> %passthru, i16 %mask) {
; X86-LABEL: test_mask_compress_w_256:
; X86:       # %bb.0:
; X86-NEXT:    kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x04]
; X86-NEXT:    vpcompressw %ymm0, %ymm1 {%k1} # encoding: [0x62,0xf2,0xfd,0x29,0x63,0xc1]
; X86-NEXT:    vmovdqa %ymm1, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xc1]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_compress_w_256:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpcompressw %ymm0, %ymm1 {%k1} # encoding: [0x62,0xf2,0xfd,0x29,0x63,0xc1]
; X64-NEXT:    vmovdqa %ymm1, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xc1]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = bitcast i16 %mask to <16 x i1>
  %2 = call <16 x i16> @llvm.x86.avx512.mask.compress.v16i16(<16 x i16> %data, <16 x i16> %passthru, <16 x i1> %1)
  ret <16 x i16> %2
}

define <16 x i16> @test_maskz_compress_w_256(<16 x i16> %data, i16 %mask) {
; X86-LABEL: test_maskz_compress_w_256:
; X86:       # %bb.0:
; X86-NEXT:    kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x04]
; X86-NEXT:    vpcompressw %ymm0, %ymm0 {%k1} {z} # encoding: [0x62,0xf2,0xfd,0xa9,0x63,0xc0]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_maskz_compress_w_256:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpcompressw %ymm0, %ymm0 {%k1} {z} # encoding: [0x62,0xf2,0xfd,0xa9,0x63,0xc0]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = bitcast i16 %mask to <16 x i1>
  %2 = call <16 x i16> @llvm.x86.avx512.mask.compress.v16i16(<16 x i16> %data, <16 x i16> zeroinitializer, <16 x i1> %1)
  ret <16 x i16> %2
}

define <16 x i16> @test_compress_w_256(<16 x i16> %data) {
; CHECK-LABEL: test_compress_w_256:
; CHECK:       # %bb.0:
; CHECK-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
  %1 = call <16 x i16> @llvm.x86.avx512.mask.compress.v16i16(<16 x i16> %data, <16 x i16> undef, <16 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>)
  ret <16 x i16> %1
}

define void @test_mask_compress_store_b_256(i8* %addr, <32 x i8> %data, i32 %mask) {
; X86-LABEL: test_mask_compress_store_b_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:    vpcompressb %ymm0, (%eax) {%k1} # encoding: [0x62,0xf2,0x7d,0x29,0x63,0x00]
; X86-NEXT:    vzeroupper # encoding: [0xc5,0xf8,0x77]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_compress_store_b_256:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT:    vpcompressb %ymm0, (%rdi) {%k1} # encoding: [0x62,0xf2,0x7d,0x29,0x63,0x07]
; X64-NEXT:    vzeroupper # encoding: [0xc5,0xf8,0x77]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = bitcast i32 %mask to <32 x i1>
  call void @llvm.masked.compressstore.v32i8(<32 x i8> %data, i8* %addr, <32 x i1> %1)
  ret void
}

define void @test_compress_store_b_256(i8* %addr, <32 x i8> %data) {
; X86-LABEL: test_compress_store_b_256:
; X86:       # %bb.0:
; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax # encoding: [0x8b,0x44,0x24,0x04]
; X86-NEXT:    kxnord %k0, %k0, %k1 # encoding: [0xc4,0xe1,0xfd,0x46,0xc8]
; X86-NEXT:    vpcompressb %ymm0, (%eax) {%k1} # encoding: [0x62,0xf2,0x7d,0x29,0x63,0x00]
; X86-NEXT:    vzeroupper # encoding: [0xc5,0xf8,0x77]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_compress_store_b_256:
; X64:       # %bb.0:
; X64-NEXT:    kxnord %k0, %k0, %k1 # encoding: [0xc4,0xe1,0xfd,0x46,0xc8]
; X64-NEXT:    vpcompressb %ymm0, (%rdi) {%k1} # encoding: [0x62,0xf2,0x7d,0x29,0x63,0x07]
; X64-NEXT:    vzeroupper # encoding: [0xc5,0xf8,0x77]
; X64-NEXT:    retq # encoding: [0xc3]
  call void @llvm.masked.compressstore.v32i8(<32 x i8> %data, i8* %addr, <32 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>)
  ret void
}

define <32 x i8> @test_mask_compress_b_256(<32 x i8> %data, <32 x i8> %passthru, i32 %mask) {
; X86-LABEL: test_mask_compress_b_256:
; X86:       # %bb.0:
; X86-NEXT:    kmovd {{[0-9]+}}(%esp), %k1 # encoding: [0xc4,0xe1,0xf9,0x90,0x4c,0x24,0x04]
; X86-NEXT:    vpcompressb %ymm0, %ymm1 {%k1} # encoding: [0x62,0xf2,0x7d,0x29,0x63,0xc1]
; X86-NEXT:    vmovdqa %ymm1, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xc1]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_mask_compress_b_256:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpcompressb %ymm0, %ymm1 {%k1} # encoding: [0x62,0xf2,0x7d,0x29,0x63,0xc1]
; X64-NEXT:    vmovdqa %ymm1, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xc1]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = bitcast i32 %mask to <32 x i1>
  %2 = call <32 x i8> @llvm.x86.avx512.mask.compress.v32i8(<32 x i8> %data, <32 x i8> %passthru, <32 x i1> %1)
  ret <32 x i8> %2
}

define <32 x i8> @test_maskz_compress_b_256(<32 x i8> %data, i32 %mask) {
; X86-LABEL: test_maskz_compress_b_256:
; X86:       # %bb.0:
; X86-NEXT:    kmovd {{[0-9]+}}(%esp), %k1 # encoding: [0xc4,0xe1,0xf9,0x90,0x4c,0x24,0x04]
; X86-NEXT:    vpcompressb %ymm0, %ymm0 {%k1} {z} # encoding: [0x62,0xf2,0x7d,0xa9,0x63,0xc0]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_maskz_compress_b_256:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpcompressb %ymm0, %ymm0 {%k1} {z} # encoding: [0x62,0xf2,0x7d,0xa9,0x63,0xc0]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = bitcast i32 %mask to <32 x i1>
  %2 = call <32 x i8> @llvm.x86.avx512.mask.compress.v32i8(<32 x i8> %data, <32 x i8> zeroinitializer, <32 x i1> %1)
  ret <32 x i8> %2
}

define <32 x i8> @test_compress_b_256(<32 x i8> %data) {
; CHECK-LABEL: test_compress_b_256:
; CHECK:       # %bb.0:
; CHECK-NEXT:    ret{{[l|q]}} # encoding: [0xc3]
  %1 = call <32 x i8> @llvm.x86.avx512.mask.compress.v32i8(<32 x i8> %data, <32 x i8> undef, <32 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>)
  ret <32 x i8> %1
}

define <4 x i32> @test_int_x86_avx512_mask_vpshld_d_128(<4 x i32> %x0, <4 x i32> %x1,<4 x i32> %x3, i8 %x4) {
; X86-LABEL: test_int_x86_avx512_mask_vpshld_d_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:    vpshldd $22, %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf3,0x7d,0x09,0x71,0xd1,0x16]
; X86-NEXT:    vpshldd $23, %xmm1, %xmm0, %xmm3 # encoding: [0x62,0xf3,0x7d,0x08,0x71,0xd9,0x17]
; X86-NEXT:    vpshldd $24, %xmm1, %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf3,0x7d,0x89,0x71,0xc1,0x18]
; X86-NEXT:    vpaddd %xmm0, %xmm3, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe1,0xfe,0xc0]
; X86-NEXT:    vpaddd %xmm0, %xmm2, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe9,0xfe,0xc0]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_vpshld_d_128:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpshldd $22, %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf3,0x7d,0x09,0x71,0xd1,0x16]
; X64-NEXT:    vpshldd $23, %xmm1, %xmm0, %xmm3 # encoding: [0x62,0xf3,0x7d,0x08,0x71,0xd9,0x17]
; X64-NEXT:    vpshldd $24, %xmm1, %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf3,0x7d,0x89,0x71,0xc1,0x18]
; X64-NEXT:    vpaddd %xmm0, %xmm3, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe1,0xfe,0xc0]
; X64-NEXT:    vpaddd %xmm0, %xmm2, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe9,0xfe,0xc0]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = call <4 x i32> @llvm.fshl.v4i32(<4 x i32> %x0, <4 x i32> %x1, <4 x i32> <i32 22, i32 22, i32 22, i32 22>)
  %2 = bitcast i8 %x4 to <8 x i1>
  %extract1 = 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> %extract1, <4 x i32> %1, <4 x i32> %x3
  %4 = call <4 x i32> @llvm.fshl.v4i32(<4 x i32> %x0, <4 x i32> %x1, <4 x i32> <i32 23, i32 23, i32 23, i32 23>)
  %5 = call <4 x i32> @llvm.fshl.v4i32(<4 x i32> %x0, <4 x i32> %x1, <4 x i32> <i32 24, i32 24, i32 24, i32 24>)
  %6 = bitcast i8 %x4 to <8 x i1>
  %extract = shufflevector <8 x i1> %6, <8 x i1> %6, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
  %7 = select <4 x i1> %extract, <4 x i32> %5, <4 x i32> zeroinitializer
  %res3 = add <4 x i32> %3, %4
  %res4 = add <4 x i32> %res3, %7
  ret <4 x i32> %res4
}

define <8 x i32> @test_int_x86_avx512_mask_vpshld_d_256(<8 x i32> %x0, <8 x i32> %x1, <8 x i32> %x3, i8 %x4) {
; X86-LABEL: test_int_x86_avx512_mask_vpshld_d_256:
; 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:    vpshldd $22, %ymm1, %ymm0, %ymm2 {%k1} # encoding: [0x62,0xf3,0x7d,0x29,0x71,0xd1,0x16]
; X86-NEXT:    vpshldd $23, %ymm1, %ymm0, %ymm0 # encoding: [0x62,0xf3,0x7d,0x28,0x71,0xc1,0x17]
; X86-NEXT:    vpaddd %ymm0, %ymm2, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xed,0xfe,0xc0]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_vpshld_d_256:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpshldd $22, %ymm1, %ymm0, %ymm2 {%k1} # encoding: [0x62,0xf3,0x7d,0x29,0x71,0xd1,0x16]
; X64-NEXT:    vpshldd $23, %ymm1, %ymm0, %ymm0 # encoding: [0x62,0xf3,0x7d,0x28,0x71,0xc1,0x17]
; X64-NEXT:    vpaddd %ymm0, %ymm2, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xed,0xfe,0xc0]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = call <8 x i32> @llvm.fshl.v8i32(<8 x i32> %x0, <8 x i32> %x1, <8 x i32> <i32 22, i32 22, i32 22, i32 22, i32 22, i32 22, i32 22, i32 22>)
  %2 = bitcast i8 %x4 to <8 x i1>
  %3 = select <8 x i1> %2, <8 x i32> %1, <8 x i32> %x3
  %4 = call <8 x i32> @llvm.fshl.v8i32(<8 x i32> %x0, <8 x i32> %x1, <8 x i32> <i32 23, i32 23, i32 23, i32 23, i32 23, i32 23, i32 23, i32 23>)
  %res2 = add <8 x i32> %3, %4
  ret <8 x i32> %res2
}

define <2 x i64> @test_int_x86_avx512_mask_vpshld_q_128(<2 x i64> %x0, <2 x i64> %x1, <2 x i64> %x3, i8 %x4) {
; X86-LABEL: test_int_x86_avx512_mask_vpshld_q_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:    vpshldq $22, %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf3,0xfd,0x09,0x71,0xd1,0x16]
; X86-NEXT:    vpshldq $23, %xmm1, %xmm0, %xmm0 # encoding: [0x62,0xf3,0xfd,0x08,0x71,0xc1,0x17]
; X86-NEXT:    vpaddq %xmm0, %xmm2, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe9,0xd4,0xc0]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_vpshld_q_128:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpshldq $22, %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf3,0xfd,0x09,0x71,0xd1,0x16]
; X64-NEXT:    vpshldq $23, %xmm1, %xmm0, %xmm0 # encoding: [0x62,0xf3,0xfd,0x08,0x71,0xc1,0x17]
; X64-NEXT:    vpaddq %xmm0, %xmm2, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe9,0xd4,0xc0]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = call <2 x i64> @llvm.fshl.v2i64(<2 x i64> %x0, <2 x i64> %x1, <2 x i64> <i64 22, i64 22>)
  %2 = bitcast i8 %x4 to <8 x i1>
  %extract = shufflevector <8 x i1> %2, <8 x i1> %2, <2 x i32> <i32 0, i32 1>
  %3 = select <2 x i1> %extract, <2 x i64> %1, <2 x i64> %x3
  %4 = call <2 x i64> @llvm.fshl.v2i64(<2 x i64> %x0, <2 x i64> %x1, <2 x i64> <i64 23, i64 23>)
  %res2 = add <2 x i64> %3, %4
  ret <2 x i64> %res2
}

define <4 x i64> @test_int_x86_avx512_mask_vpshld_q_256(<4 x i64> %x0, <4 x i64> %x1, <4 x i64> %x3, i8 %x4) {
; X86-LABEL: test_int_x86_avx512_mask_vpshld_q_256:
; 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:    vpshldq $22, %ymm1, %ymm0, %ymm2 {%k1} # encoding: [0x62,0xf3,0xfd,0x29,0x71,0xd1,0x16]
; X86-NEXT:    vpshldq $23, %ymm1, %ymm0, %ymm0 # encoding: [0x62,0xf3,0xfd,0x28,0x71,0xc1,0x17]
; X86-NEXT:    vpaddq %ymm0, %ymm2, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xed,0xd4,0xc0]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_vpshld_q_256:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpshldq $22, %ymm1, %ymm0, %ymm2 {%k1} # encoding: [0x62,0xf3,0xfd,0x29,0x71,0xd1,0x16]
; X64-NEXT:    vpshldq $23, %ymm1, %ymm0, %ymm0 # encoding: [0x62,0xf3,0xfd,0x28,0x71,0xc1,0x17]
; X64-NEXT:    vpaddq %ymm0, %ymm2, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xed,0xd4,0xc0]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = call <4 x i64> @llvm.fshl.v4i64(<4 x i64> %x0, <4 x i64> %x1, <4 x i64> <i64 22, i64 22, i64 22, i64 22>)
  %2 = bitcast i8 %x4 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 i64> %1, <4 x i64> %x3
  %4 = call <4 x i64> @llvm.fshl.v4i64(<4 x i64> %x0, <4 x i64> %x1, <4 x i64> <i64 23, i64 23, i64 23, i64 23>)
  %res2 = add <4 x i64> %3, %4
  ret <4 x i64> %res2
}

define <8 x i16> @test_int_x86_avx512_mask_vpshld_w_128(<8 x i16> %x0, <8 x i16> %x1, <8 x i16> %x3, i8 %x4) {
; X86-LABEL: test_int_x86_avx512_mask_vpshld_w_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:    vpshldw $6, %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf3,0xfd,0x09,0x70,0xd1,0x06]
; X86-NEXT:    vpshldw $7, %xmm1, %xmm0, %xmm0 # encoding: [0x62,0xf3,0xfd,0x08,0x70,0xc1,0x07]
; 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_vpshld_w_128:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpshldw $6, %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf3,0xfd,0x09,0x70,0xd1,0x06]
; X64-NEXT:    vpshldw $7, %xmm1, %xmm0, %xmm0 # encoding: [0x62,0xf3,0xfd,0x08,0x70,0xc1,0x07]
; 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.fshl.v8i16(<8 x i16> %x0, <8 x i16> %x1, <8 x i16> <i16 6, i16 6, i16 6, i16 6, i16 6, i16 6, i16 6, i16 6>)
  %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.fshl.v8i16(<8 x i16> %x0, <8 x i16> %x1, <8 x i16> <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>)
  %res2 = add <8 x i16> %3, %4
  ret <8 x i16> %res2
}

define <16 x i16> @test_int_x86_avx512_mask_vpshld_w_256(<16 x i16> %x0, <16 x i16> %x1, <16 x i16> %x3, i16 %x4) {
; X86-LABEL: test_int_x86_avx512_mask_vpshld_w_256:
; X86:       # %bb.0:
; X86-NEXT:    kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x04]
; X86-NEXT:    vpshldw $6, %ymm1, %ymm0, %ymm2 {%k1} # encoding: [0x62,0xf3,0xfd,0x29,0x70,0xd1,0x06]
; X86-NEXT:    vpshldw $7, %ymm1, %ymm0, %ymm0 # encoding: [0x62,0xf3,0xfd,0x28,0x70,0xc1,0x07]
; 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_vpshld_w_256:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpshldw $6, %ymm1, %ymm0, %ymm2 {%k1} # encoding: [0x62,0xf3,0xfd,0x29,0x70,0xd1,0x06]
; X64-NEXT:    vpshldw $7, %ymm1, %ymm0, %ymm0 # encoding: [0x62,0xf3,0xfd,0x28,0x70,0xc1,0x07]
; 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.fshl.v16i16(<16 x i16> %x0, <16 x i16> %x1, <16 x i16> <i16 6, i16 6, i16 6, i16 6, i16 6, i16 6, i16 6, i16 6, i16 6, i16 6, i16 6, i16 6, i16 6, i16 6, i16 6, i16 6>)
  %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.fshl.v16i16(<16 x i16> %x0, <16 x i16> %x1, <16 x i16> <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>)
  %res2 = add <16 x i16> %3, %4
  ret <16 x i16> %res2
}

define <4 x i32> @test_int_x86_avx512_mask_vpshrd_d_128(<4 x i32> %x0, <4 x i32> %x1,<4 x i32> %x3, i8 %x4) {
; X86-LABEL: test_int_x86_avx512_mask_vpshrd_d_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:    vpshrdd $22, %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf3,0x7d,0x09,0x73,0xd1,0x16]
; X86-NEXT:    vpshrdd $23, %xmm1, %xmm0, %xmm3 # encoding: [0x62,0xf3,0x7d,0x08,0x73,0xd9,0x17]
; X86-NEXT:    vpshrdd $24, %xmm1, %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf3,0x7d,0x89,0x73,0xc1,0x18]
; X86-NEXT:    vpaddd %xmm0, %xmm3, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe1,0xfe,0xc0]
; X86-NEXT:    vpaddd %xmm0, %xmm2, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe9,0xfe,0xc0]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_vpshrd_d_128:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpshrdd $22, %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf3,0x7d,0x09,0x73,0xd1,0x16]
; X64-NEXT:    vpshrdd $23, %xmm1, %xmm0, %xmm3 # encoding: [0x62,0xf3,0x7d,0x08,0x73,0xd9,0x17]
; X64-NEXT:    vpshrdd $24, %xmm1, %xmm0, %xmm0 {%k1} {z} # encoding: [0x62,0xf3,0x7d,0x89,0x73,0xc1,0x18]
; X64-NEXT:    vpaddd %xmm0, %xmm3, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe1,0xfe,0xc0]
; X64-NEXT:    vpaddd %xmm0, %xmm2, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe9,0xfe,0xc0]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = call <4 x i32> @llvm.fshr.v4i32(<4 x i32> %x1, <4 x i32> %x0, <4 x i32> <i32 22, i32 22, i32 22, i32 22>)
  %2 = bitcast i8 %x4 to <8 x i1>
  %extract1 = 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> %extract1, <4 x i32> %1, <4 x i32> %x3
  %4 = call <4 x i32> @llvm.fshr.v4i32(<4 x i32> %x1, <4 x i32> %x0, <4 x i32> <i32 23, i32 23, i32 23, i32 23>)
  %5 = call <4 x i32> @llvm.fshr.v4i32(<4 x i32> %x1, <4 x i32> %x0, <4 x i32> <i32 24, i32 24, i32 24, i32 24>)
  %6 = bitcast i8 %x4 to <8 x i1>
  %extract = shufflevector <8 x i1> %6, <8 x i1> %6, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
  %7 = select <4 x i1> %extract, <4 x i32> %5, <4 x i32> zeroinitializer
  %res3 = add <4 x i32> %3, %4
  %res4 = add <4 x i32> %res3, %7
  ret <4 x i32> %res4
}

define <8 x i32> @test_int_x86_avx512_mask_vpshrd_d_256(<8 x i32> %x0, <8 x i32> %x1, <8 x i32> %x3, i8 %x4) {
; X86-LABEL: test_int_x86_avx512_mask_vpshrd_d_256:
; 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:    vpshrdd $22, %ymm1, %ymm0, %ymm2 {%k1} # encoding: [0x62,0xf3,0x7d,0x29,0x73,0xd1,0x16]
; X86-NEXT:    vpshrdd $23, %ymm1, %ymm0, %ymm0 # encoding: [0x62,0xf3,0x7d,0x28,0x73,0xc1,0x17]
; X86-NEXT:    vpaddd %ymm0, %ymm2, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xed,0xfe,0xc0]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_vpshrd_d_256:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpshrdd $22, %ymm1, %ymm0, %ymm2 {%k1} # encoding: [0x62,0xf3,0x7d,0x29,0x73,0xd1,0x16]
; X64-NEXT:    vpshrdd $23, %ymm1, %ymm0, %ymm0 # encoding: [0x62,0xf3,0x7d,0x28,0x73,0xc1,0x17]
; X64-NEXT:    vpaddd %ymm0, %ymm2, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xed,0xfe,0xc0]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = call <8 x i32> @llvm.fshr.v8i32(<8 x i32> %x1, <8 x i32> %x0, <8 x i32> <i32 22, i32 22, i32 22, i32 22, i32 22, i32 22, i32 22, i32 22>)
  %2 = bitcast i8 %x4 to <8 x i1>
  %3 = select <8 x i1> %2, <8 x i32> %1, <8 x i32> %x3
  %4 = call <8 x i32> @llvm.fshr.v8i32(<8 x i32> %x1, <8 x i32> %x0, <8 x i32> <i32 23, i32 23, i32 23, i32 23, i32 23, i32 23, i32 23, i32 23>)
  %res2 = add <8 x i32> %3, %4
  ret <8 x i32> %res2
}

define <2 x i64> @test_int_x86_avx512_mask_vpshrd_q_128(<2 x i64> %x0, <2 x i64> %x1, <2 x i64> %x3, i8 %x4) {
; X86-LABEL: test_int_x86_avx512_mask_vpshrd_q_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:    vpshrdq $22, %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf3,0xfd,0x09,0x73,0xd1,0x16]
; X86-NEXT:    vpshrdq $23, %xmm1, %xmm0, %xmm0 # encoding: [0x62,0xf3,0xfd,0x08,0x73,0xc1,0x17]
; X86-NEXT:    vpaddq %xmm0, %xmm2, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe9,0xd4,0xc0]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_vpshrd_q_128:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpshrdq $22, %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf3,0xfd,0x09,0x73,0xd1,0x16]
; X64-NEXT:    vpshrdq $23, %xmm1, %xmm0, %xmm0 # encoding: [0x62,0xf3,0xfd,0x08,0x73,0xc1,0x17]
; X64-NEXT:    vpaddq %xmm0, %xmm2, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe9,0xd4,0xc0]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = call <2 x i64> @llvm.fshr.v2i64(<2 x i64> %x1, <2 x i64> %x0, <2 x i64> <i64 22, i64 22>)
  %2 = bitcast i8 %x4 to <8 x i1>
  %extract = shufflevector <8 x i1> %2, <8 x i1> %2, <2 x i32> <i32 0, i32 1>
  %3 = select <2 x i1> %extract, <2 x i64> %1, <2 x i64> %x3
  %4 = call <2 x i64> @llvm.fshr.v2i64(<2 x i64> %x1, <2 x i64> %x0, <2 x i64> <i64 23, i64 23>)
  %res2 = add <2 x i64> %3, %4
  ret <2 x i64> %res2
}

define <4 x i64> @test_int_x86_avx512_mask_vpshrd_q_256(<4 x i64> %x0, <4 x i64> %x1, <4 x i64> %x3, i8 %x4) {
; X86-LABEL: test_int_x86_avx512_mask_vpshrd_q_256:
; 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:    vpshrdq $22, %ymm1, %ymm0, %ymm2 {%k1} # encoding: [0x62,0xf3,0xfd,0x29,0x73,0xd1,0x16]
; X86-NEXT:    vpshrdq $23, %ymm1, %ymm0, %ymm0 # encoding: [0x62,0xf3,0xfd,0x28,0x73,0xc1,0x17]
; X86-NEXT:    vpaddq %ymm0, %ymm2, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xed,0xd4,0xc0]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_vpshrd_q_256:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpshrdq $22, %ymm1, %ymm0, %ymm2 {%k1} # encoding: [0x62,0xf3,0xfd,0x29,0x73,0xd1,0x16]
; X64-NEXT:    vpshrdq $23, %ymm1, %ymm0, %ymm0 # encoding: [0x62,0xf3,0xfd,0x28,0x73,0xc1,0x17]
; X64-NEXT:    vpaddq %ymm0, %ymm2, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xed,0xd4,0xc0]
; X64-NEXT:    retq # encoding: [0xc3]
  %1 = call <4 x i64> @llvm.fshr.v4i64(<4 x i64> %x1, <4 x i64> %x0, <4 x i64> <i64 22, i64 22, i64 22, i64 22>)
  %2 = bitcast i8 %x4 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 i64> %1, <4 x i64> %x3
  %4 = call <4 x i64> @llvm.fshr.v4i64(<4 x i64> %x1, <4 x i64> %x0, <4 x i64> <i64 23, i64 23, i64 23, i64 23>)
  %res2 = add <4 x i64> %3, %4
  ret <4 x i64> %res2
}

define <8 x i16> @test_int_x86_avx512_mask_vpshrd_w_128(<8 x i16> %x0, <8 x i16> %x1, <8 x i16> %x3, i8 %x4) {
; X86-LABEL: test_int_x86_avx512_mask_vpshrd_w_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:    vpshrdw $6, %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf3,0xfd,0x09,0x72,0xd1,0x06]
; X86-NEXT:    vpshrdw $7, %xmm1, %xmm0, %xmm0 # encoding: [0x62,0xf3,0xfd,0x08,0x72,0xc1,0x07]
; 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_vpshrd_w_128:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpshrdw $6, %xmm1, %xmm0, %xmm2 {%k1} # encoding: [0x62,0xf3,0xfd,0x09,0x72,0xd1,0x06]
; X64-NEXT:    vpshrdw $7, %xmm1, %xmm0, %xmm0 # encoding: [0x62,0xf3,0xfd,0x08,0x72,0xc1,0x07]
; 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.fshr.v8i16(<8 x i16> %x1, <8 x i16> %x0, <8 x i16> <i16 6, i16 6, i16 6, i16 6, i16 6, i16 6, i16 6, i16 6>)
  %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.fshr.v8i16(<8 x i16> %x1, <8 x i16> %x0, <8 x i16> <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>)
  %res2 = add <8 x i16> %3, %4
  ret <8 x i16> %res2
}

define <16 x i16> @test_int_x86_avx512_mask_vpshrd_w_256(<16 x i16> %x0, <16 x i16> %x1, <16 x i16> %x3, i16 %x4) {
; X86-LABEL: test_int_x86_avx512_mask_vpshrd_w_256:
; X86:       # %bb.0:
; X86-NEXT:    kmovw {{[0-9]+}}(%esp), %k1 # encoding: [0xc5,0xf8,0x90,0x4c,0x24,0x04]
; X86-NEXT:    vpshrdw $6, %ymm1, %ymm0, %ymm2 {%k1} # encoding: [0x62,0xf3,0xfd,0x29,0x72,0xd1,0x06]
; X86-NEXT:    vpshrdw $7, %ymm1, %ymm0, %ymm0 # encoding: [0x62,0xf3,0xfd,0x28,0x72,0xc1,0x07]
; 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_vpshrd_w_256:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %edi, %k1 # encoding: [0xc5,0xfb,0x92,0xcf]
; X64-NEXT:    vpshrdw $6, %ymm1, %ymm0, %ymm2 {%k1} # encoding: [0x62,0xf3,0xfd,0x29,0x72,0xd1,0x06]
; X64-NEXT:    vpshrdw $7, %ymm1, %ymm0, %ymm0 # encoding: [0x62,0xf3,0xfd,0x28,0x72,0xc1,0x07]
; 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.fshr.v16i16(<16 x i16> %x1, <16 x i16> %x0, <16 x i16> <i16 6, i16 6, i16 6, i16 6, i16 6, i16 6, i16 6, i16 6, i16 6, i16 6, i16 6, i16 6, i16 6, i16 6, i16 6, i16 6>)
  %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.fshr.v16i16(<16 x i16> %x1, <16 x i16> %x0, <16 x i16> <i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7, i16 7>)
  %res2 = add <16 x i16> %3, %4
  ret <16 x i16> %res2
}

define <8 x i32> @test_int_x86_avx512_mask_vpshrdv_d_256(<8 x i32> %x0, <8 x i32> %x1, <8 x i32>* %x2p, <8 x i32> %x4, i8 %x3) {
; X86-LABEL: test_int_x86_avx512_mask_vpshrdv_d_256:
; 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:    vmovdqa %ymm0, %ymm3 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xd8]
; X86-NEXT:    vpshrdvd (%eax), %ymm1, %ymm3 {%k1} # encoding: [0x62,0xf2,0x75,0x29,0x73,0x18]
; X86-NEXT:    vpshrdvd %ymm2, %ymm1, %ymm0 {%k1} {z} # encoding: [0x62,0xf2,0x75,0xa9,0x73,0xc2]
; X86-NEXT:    vpaddd %ymm0, %ymm3, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xe5,0xfe,0xc0]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_vpshrdv_d_256:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT:    vmovdqa %ymm0, %ymm3 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xd8]
; X64-NEXT:    vpshrdvd (%rdi), %ymm1, %ymm3 {%k1} # encoding: [0x62,0xf2,0x75,0x29,0x73,0x1f]
; X64-NEXT:    vpshrdvd %ymm2, %ymm1, %ymm0 {%k1} {z} # encoding: [0x62,0xf2,0x75,0xa9,0x73,0xc2]
; X64-NEXT:    vpaddd %ymm0, %ymm3, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xe5,0xfe,0xc0]
; X64-NEXT:    retq # encoding: [0xc3]
  %x2 = load <8 x i32>, <8 x i32>* %x2p
  %1 = call <8 x i32> @llvm.fshr.v8i32(<8 x i32> %x1, <8 x i32> %x0, <8 x i32> %x2)
  %2 = bitcast i8 %x3 to <8 x i1>
  %3 = select <8 x i1> %2, <8 x i32> %1, <8 x i32> %x0
  %4 = call <8 x i32> @llvm.fshr.v8i32(<8 x i32> %x1, <8 x i32> %x0, <8 x i32> %x4)
  %5 = bitcast i8 %x3 to <8 x i1>
  %6 = select <8 x i1> %5, <8 x i32> %4, <8 x i32> zeroinitializer
  %res3 = add <8 x i32> %3, %6
  ret <8 x i32> %res3
}

define <4 x i32> @test_int_x86_avx512_mask_vpshrdv_d_128(<4 x i32> %x0, <4 x i32> %x1, <4 x i32>* %x2p, <4 x i32> %x4, i8 %x3) {
; X86-LABEL: test_int_x86_avx512_mask_vpshrdv_d_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:    vmovdqa %xmm0, %xmm3 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xd8]
; X86-NEXT:    vpshrdvd (%eax), %xmm1, %xmm3 {%k1} # encoding: [0x62,0xf2,0x75,0x09,0x73,0x18]
; X86-NEXT:    vpshrdvd %xmm2, %xmm1, %xmm0 {%k1} {z} # encoding: [0x62,0xf2,0x75,0x89,0x73,0xc2]
; X86-NEXT:    vpaddd %xmm0, %xmm3, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe1,0xfe,0xc0]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_vpshrdv_d_128:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT:    vmovdqa %xmm0, %xmm3 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xd8]
; X64-NEXT:    vpshrdvd (%rdi), %xmm1, %xmm3 {%k1} # encoding: [0x62,0xf2,0x75,0x09,0x73,0x1f]
; X64-NEXT:    vpshrdvd %xmm2, %xmm1, %xmm0 {%k1} {z} # encoding: [0x62,0xf2,0x75,0x89,0x73,0xc2]
; X64-NEXT:    vpaddd %xmm0, %xmm3, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe1,0xfe,0xc0]
; X64-NEXT:    retq # encoding: [0xc3]
  %x2 = load <4 x i32>, <4 x i32>* %x2p
  %1 = call <4 x i32> @llvm.fshr.v4i32(<4 x i32> %x1, <4 x i32> %x0, <4 x i32> %x2)
  %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> %x0
  %4 = call <4 x i32> @llvm.fshr.v4i32(<4 x i32> %x1, <4 x i32> %x0, <4 x i32> %x4)
  %5 = bitcast i8 %x3 to <8 x i1>
  %extract1 = shufflevector <8 x i1> %5, <8 x i1> %5, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
  %6 = select <4 x i1> %extract1, <4 x i32> %4, <4 x i32> zeroinitializer
  %res3 = add <4 x i32> %3, %6
  ret <4 x i32> %res3
}

define <4 x i64> @test_int_x86_avx512_mask_vpshrdv_q_256(<4 x i64> %x0, <4 x i64> %x1, <4 x i64>* %x2p, <4 x i64> %x4, i8 %x3) {
; X86-LABEL: test_int_x86_avx512_mask_vpshrdv_q_256:
; 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:    vmovdqa %ymm0, %ymm3 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xd8]
; X86-NEXT:    vpshrdvq (%eax), %ymm1, %ymm3 {%k1} # encoding: [0x62,0xf2,0xf5,0x29,0x73,0x18]
; X86-NEXT:    vpshrdvq %ymm2, %ymm1, %ymm0 {%k1} {z} # encoding: [0x62,0xf2,0xf5,0xa9,0x73,0xc2]
; X86-NEXT:    vpaddq %ymm0, %ymm3, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xe5,0xd4,0xc0]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_vpshrdv_q_256:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT:    vmovdqa %ymm0, %ymm3 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xd8]
; X64-NEXT:    vpshrdvq (%rdi), %ymm1, %ymm3 {%k1} # encoding: [0x62,0xf2,0xf5,0x29,0x73,0x1f]
; X64-NEXT:    vpshrdvq %ymm2, %ymm1, %ymm0 {%k1} {z} # encoding: [0x62,0xf2,0xf5,0xa9,0x73,0xc2]
; X64-NEXT:    vpaddq %ymm0, %ymm3, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xe5,0xd4,0xc0]
; X64-NEXT:    retq # encoding: [0xc3]
  %x2 = load <4 x i64>, <4 x i64>* %x2p
  %1 = call <4 x i64> @llvm.fshr.v4i64(<4 x i64> %x1, <4 x i64> %x0, <4 x i64> %x2)
  %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 i64> %1, <4 x i64> %x0
  %4 = call <4 x i64> @llvm.fshr.v4i64(<4 x i64> %x1, <4 x i64> %x0, <4 x i64> %x4)
  %5 = bitcast i8 %x3 to <8 x i1>
  %extract1 = shufflevector <8 x i1> %5, <8 x i1> %5, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
  %6 = select <4 x i1> %extract1, <4 x i64> %4, <4 x i64> zeroinitializer
  %res3 = add <4 x i64> %3, %6
  ret <4 x i64> %res3
}

define <2 x i64> @test_int_x86_avx512_mask_vpshrdv_q_128(<2 x i64> %x0, <2 x i64> %x1, <2 x i64>* %x2p, <2 x i64> %x4, i8 %x3) {
; X86-LABEL: test_int_x86_avx512_mask_vpshrdv_q_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:    vmovdqa %xmm0, %xmm3 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xd8]
; X86-NEXT:    vpshrdvq (%eax), %xmm1, %xmm3 {%k1} # encoding: [0x62,0xf2,0xf5,0x09,0x73,0x18]
; X86-NEXT:    vpshrdvq %xmm2, %xmm1, %xmm0 {%k1} {z} # encoding: [0x62,0xf2,0xf5,0x89,0x73,0xc2]
; X86-NEXT:    vpaddq %xmm0, %xmm3, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe1,0xd4,0xc0]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_vpshrdv_q_128:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT:    vmovdqa %xmm0, %xmm3 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xd8]
; X64-NEXT:    vpshrdvq (%rdi), %xmm1, %xmm3 {%k1} # encoding: [0x62,0xf2,0xf5,0x09,0x73,0x1f]
; X64-NEXT:    vpshrdvq %xmm2, %xmm1, %xmm0 {%k1} {z} # encoding: [0x62,0xf2,0xf5,0x89,0x73,0xc2]
; X64-NEXT:    vpaddq %xmm0, %xmm3, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe1,0xd4,0xc0]
; X64-NEXT:    retq # encoding: [0xc3]
  %x2 = load <2 x i64>, <2 x i64>* %x2p
  %1 = call <2 x i64> @llvm.fshr.v2i64(<2 x i64> %x1, <2 x i64> %x0, <2 x i64> %x2)
  %2 = bitcast i8 %x3 to <8 x i1>
  %extract = shufflevector <8 x i1> %2, <8 x i1> %2, <2 x i32> <i32 0, i32 1>
  %3 = select <2 x i1> %extract, <2 x i64> %1, <2 x i64> %x0
  %4 = call <2 x i64> @llvm.fshr.v2i64(<2 x i64> %x1, <2 x i64> %x0, <2 x i64> %x4)
  %5 = bitcast i8 %x3 to <8 x i1>
  %extract1 = shufflevector <8 x i1> %5, <8 x i1> %5, <2 x i32> <i32 0, i32 1>
  %6 = select <2 x i1> %extract1, <2 x i64> %4, <2 x i64> zeroinitializer
  %res3 = add <2 x i64> %3, %6
  ret <2 x i64> %res3
}

define <16 x i16> @test_int_x86_avx512_mask_vpshrdv_w_256(<16 x i16> %x0, <16 x i16> %x1, <16 x i16>* %x2p, <16 x i16> %x4, i16 %x3) {
; X86-LABEL: test_int_x86_avx512_mask_vpshrdv_w_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:    vmovdqa %ymm0, %ymm3 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xd8]
; X86-NEXT:    vpshrdvw (%eax), %ymm1, %ymm3 {%k1} # encoding: [0x62,0xf2,0xf5,0x29,0x72,0x18]
; X86-NEXT:    vpshrdvw %ymm2, %ymm1, %ymm0 # encoding: [0x62,0xf2,0xf5,0x28,0x72,0xc2]
; X86-NEXT:    vpaddw %ymm0, %ymm3, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xe5,0xfd,0xc0]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_vpshrdv_w_256:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT:    vmovdqa %ymm0, %ymm3 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xd8]
; X64-NEXT:    vpshrdvw (%rdi), %ymm1, %ymm3 {%k1} # encoding: [0x62,0xf2,0xf5,0x29,0x72,0x1f]
; X64-NEXT:    vpshrdvw %ymm2, %ymm1, %ymm0 # encoding: [0x62,0xf2,0xf5,0x28,0x72,0xc2]
; X64-NEXT:    vpaddw %ymm0, %ymm3, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xe5,0xfd,0xc0]
; X64-NEXT:    retq # encoding: [0xc3]
  %x2 = load <16 x i16>, <16 x i16>* %x2p
  %1 = call <16 x i16> @llvm.fshr.v16i16(<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> %x0
  %4 = call <16 x i16> @llvm.fshr.v16i16(<16 x i16> %x1, <16 x i16> %x0, <16 x i16> %x4)
  %5 = bitcast i16 %x3 to <16 x i1>
  %6 = select <16 x i1> %5, <16 x i16> %4, <16 x i16> zeroinitializer
  %res3 = add <16 x i16> %3, %4
  ret <16 x i16> %res3
}

define <8 x i16> @test_int_x86_avx512_mask_vpshrdv_w_128(<8 x i16> %x0, <8 x i16> %x1, <8 x i16>* %x2p, <8 x i16> %x4, i8 %x3) {
; X86-LABEL: test_int_x86_avx512_mask_vpshrdv_w_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:    vmovdqa %xmm0, %xmm3 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xd8]
; X86-NEXT:    vpshrdvw (%eax), %xmm1, %xmm3 {%k1} # encoding: [0x62,0xf2,0xf5,0x09,0x72,0x18]
; X86-NEXT:    vpshrdvw %xmm2, %xmm1, %xmm0 {%k1} {z} # encoding: [0x62,0xf2,0xf5,0x89,0x72,0xc2]
; X86-NEXT:    vpaddw %xmm0, %xmm3, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe1,0xfd,0xc0]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_vpshrdv_w_128:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT:    vmovdqa %xmm0, %xmm3 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xd8]
; X64-NEXT:    vpshrdvw (%rdi), %xmm1, %xmm3 {%k1} # encoding: [0x62,0xf2,0xf5,0x09,0x72,0x1f]
; X64-NEXT:    vpshrdvw %xmm2, %xmm1, %xmm0 {%k1} {z} # encoding: [0x62,0xf2,0xf5,0x89,0x72,0xc2]
; X64-NEXT:    vpaddw %xmm0, %xmm3, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe1,0xfd,0xc0]
; X64-NEXT:    retq # encoding: [0xc3]
  %x2 = load <8 x i16>, <8 x i16>* %x2p
  %1 = call <8 x i16> @llvm.fshr.v8i16(<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> %x0
  %4 = call <8 x i16> @llvm.fshr.v8i16(<8 x i16> %x1, <8 x i16> %x0, <8 x i16> %x4)
  %5 = bitcast i8 %x3 to <8 x i1>
  %6 = select <8 x i1> %5, <8 x i16> %4, <8 x i16> zeroinitializer
  %res3 = add <8 x i16> %3, %6
  ret <8 x i16> %res3
}

define <8 x i32> @test_int_x86_avx512_mask_vpshldv_d_256(<8 x i32> %x0, <8 x i32> %x1, <8 x i32>* %x2p, <8 x i32> %x4, i8 %x3) {
; X86-LABEL: test_int_x86_avx512_mask_vpshldv_d_256:
; 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:    vmovdqa %ymm0, %ymm3 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xd8]
; X86-NEXT:    vpshldvd (%eax), %ymm1, %ymm3 {%k1} # encoding: [0x62,0xf2,0x75,0x29,0x71,0x18]
; X86-NEXT:    vpshldvd %ymm2, %ymm1, %ymm0 {%k1} {z} # encoding: [0x62,0xf2,0x75,0xa9,0x71,0xc2]
; X86-NEXT:    vpaddd %ymm0, %ymm3, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xe5,0xfe,0xc0]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_vpshldv_d_256:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT:    vmovdqa %ymm0, %ymm3 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xd8]
; X64-NEXT:    vpshldvd (%rdi), %ymm1, %ymm3 {%k1} # encoding: [0x62,0xf2,0x75,0x29,0x71,0x1f]
; X64-NEXT:    vpshldvd %ymm2, %ymm1, %ymm0 {%k1} {z} # encoding: [0x62,0xf2,0x75,0xa9,0x71,0xc2]
; X64-NEXT:    vpaddd %ymm0, %ymm3, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xe5,0xfe,0xc0]
; X64-NEXT:    retq # encoding: [0xc3]
  %x2 = load <8 x i32>, <8 x i32>* %x2p
  %1 = call <8 x i32> @llvm.fshl.v8i32(<8 x i32> %x0, <8 x i32> %x1, <8 x i32> %x2)
  %2 = bitcast i8 %x3 to <8 x i1>
  %3 = select <8 x i1> %2, <8 x i32> %1, <8 x i32> %x0
  %4 = call <8 x i32> @llvm.fshl.v8i32(<8 x i32> %x0, <8 x i32> %x1, <8 x i32> %x4)
  %5 = bitcast i8 %x3 to <8 x i1>
  %6 = select <8 x i1> %5, <8 x i32> %4, <8 x i32> zeroinitializer
  %res3 = add <8 x i32> %3, %6
  ret <8 x i32> %res3
}

define <4 x i32> @test_int_x86_avx512_mask_vpshldv_d_128(<4 x i32> %x0, <4 x i32> %x1, <4 x i32>* %x2p, <4 x i32> %x4, i8 %x3) {
; X86-LABEL: test_int_x86_avx512_mask_vpshldv_d_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:    vmovdqa %xmm0, %xmm3 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xd8]
; X86-NEXT:    vpshldvd (%eax), %xmm1, %xmm3 {%k1} # encoding: [0x62,0xf2,0x75,0x09,0x71,0x18]
; X86-NEXT:    vpshldvd %xmm2, %xmm1, %xmm0 {%k1} {z} # encoding: [0x62,0xf2,0x75,0x89,0x71,0xc2]
; X86-NEXT:    vpaddd %xmm0, %xmm3, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe1,0xfe,0xc0]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_vpshldv_d_128:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT:    vmovdqa %xmm0, %xmm3 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xd8]
; X64-NEXT:    vpshldvd (%rdi), %xmm1, %xmm3 {%k1} # encoding: [0x62,0xf2,0x75,0x09,0x71,0x1f]
; X64-NEXT:    vpshldvd %xmm2, %xmm1, %xmm0 {%k1} {z} # encoding: [0x62,0xf2,0x75,0x89,0x71,0xc2]
; X64-NEXT:    vpaddd %xmm0, %xmm3, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe1,0xfe,0xc0]
; X64-NEXT:    retq # encoding: [0xc3]
  %x2 = load <4 x i32>, <4 x i32>* %x2p
  %1 = call <4 x i32> @llvm.fshl.v4i32(<4 x i32> %x0, <4 x i32> %x1, <4 x i32> %x2)
  %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> %x0
  %4 = call <4 x i32> @llvm.fshl.v4i32(<4 x i32> %x0, <4 x i32> %x1, <4 x i32> %x4)
  %5 = bitcast i8 %x3 to <8 x i1>
  %extract1 = shufflevector <8 x i1> %5, <8 x i1> %5, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
  %6 = select <4 x i1> %extract1, <4 x i32> %4, <4 x i32> zeroinitializer
  %res3 = add <4 x i32> %3, %6
  ret <4 x i32> %res3
}

define <4 x i64> @test_int_x86_avx512_mask_vpshldv_q_256(<4 x i64> %x0, <4 x i64> %x1, <4 x i64>* %x2p, <4 x i64> %x4, i8 %x3) {
; X86-LABEL: test_int_x86_avx512_mask_vpshldv_q_256:
; 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:    vmovdqa %ymm0, %ymm3 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xd8]
; X86-NEXT:    vpshldvq (%eax), %ymm1, %ymm3 {%k1} # encoding: [0x62,0xf2,0xf5,0x29,0x71,0x18]
; X86-NEXT:    vpshldvq %ymm2, %ymm1, %ymm0 {%k1} {z} # encoding: [0x62,0xf2,0xf5,0xa9,0x71,0xc2]
; X86-NEXT:    vpaddq %ymm0, %ymm3, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xe5,0xd4,0xc0]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_vpshldv_q_256:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT:    vmovdqa %ymm0, %ymm3 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xd8]
; X64-NEXT:    vpshldvq (%rdi), %ymm1, %ymm3 {%k1} # encoding: [0x62,0xf2,0xf5,0x29,0x71,0x1f]
; X64-NEXT:    vpshldvq %ymm2, %ymm1, %ymm0 {%k1} {z} # encoding: [0x62,0xf2,0xf5,0xa9,0x71,0xc2]
; X64-NEXT:    vpaddq %ymm0, %ymm3, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xe5,0xd4,0xc0]
; X64-NEXT:    retq # encoding: [0xc3]
  %x2 = load <4 x i64>, <4 x i64>* %x2p
  %1 = call <4 x i64> @llvm.fshl.v4i64(<4 x i64> %x0, <4 x i64> %x1, <4 x i64> %x2)
  %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 i64> %1, <4 x i64> %x0
  %4 = call <4 x i64> @llvm.fshl.v4i64(<4 x i64> %x0, <4 x i64> %x1, <4 x i64> %x4)
  %5 = bitcast i8 %x3 to <8 x i1>
  %extract1 = shufflevector <8 x i1> %5, <8 x i1> %5, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
  %6 = select <4 x i1> %extract1, <4 x i64> %4, <4 x i64> zeroinitializer
  %res3 = add <4 x i64> %3, %6
  ret <4 x i64> %res3
}

define <2 x i64> @test_int_x86_avx512_mask_vpshldv_q_128(<2 x i64> %x0, <2 x i64> %x1, <2 x i64>* %x2p, <2 x i64> %x4, i8 %x3) {
; X86-LABEL: test_int_x86_avx512_mask_vpshldv_q_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:    vmovdqa %xmm0, %xmm3 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xd8]
; X86-NEXT:    vpshldvq (%eax), %xmm1, %xmm3 {%k1} # encoding: [0x62,0xf2,0xf5,0x09,0x71,0x18]
; X86-NEXT:    vpshldvq %xmm2, %xmm1, %xmm0 {%k1} {z} # encoding: [0x62,0xf2,0xf5,0x89,0x71,0xc2]
; X86-NEXT:    vpaddq %xmm0, %xmm3, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe1,0xd4,0xc0]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_vpshldv_q_128:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT:    vmovdqa %xmm0, %xmm3 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xd8]
; X64-NEXT:    vpshldvq (%rdi), %xmm1, %xmm3 {%k1} # encoding: [0x62,0xf2,0xf5,0x09,0x71,0x1f]
; X64-NEXT:    vpshldvq %xmm2, %xmm1, %xmm0 {%k1} {z} # encoding: [0x62,0xf2,0xf5,0x89,0x71,0xc2]
; X64-NEXT:    vpaddq %xmm0, %xmm3, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe1,0xd4,0xc0]
; X64-NEXT:    retq # encoding: [0xc3]
  %x2 = load <2 x i64>, <2 x i64>* %x2p
  %1 = call <2 x i64> @llvm.fshl.v2i64(<2 x i64> %x0, <2 x i64> %x1, <2 x i64> %x2)
  %2 = bitcast i8 %x3 to <8 x i1>
  %extract = shufflevector <8 x i1> %2, <8 x i1> %2, <2 x i32> <i32 0, i32 1>
  %3 = select <2 x i1> %extract, <2 x i64> %1, <2 x i64> %x0
  %4 = call <2 x i64> @llvm.fshl.v2i64(<2 x i64> %x0, <2 x i64> %x1, <2 x i64> %x4)
  %5 = bitcast i8 %x3 to <8 x i1>
  %extract1 = shufflevector <8 x i1> %5, <8 x i1> %5, <2 x i32> <i32 0, i32 1>
  %6 = select <2 x i1> %extract1, <2 x i64> %4, <2 x i64> zeroinitializer
  %res3 = add <2 x i64> %3, %6
  ret <2 x i64> %res3
}

define <16 x i16> @test_int_x86_avx512_mask_vpshldv_w_256(<16 x i16> %x0, <16 x i16> %x1, <16 x i16>* %x2p, <16 x i16> %x4, i16 %x3) {
; X86-LABEL: test_int_x86_avx512_mask_vpshldv_w_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:    vmovdqa %ymm0, %ymm3 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xd8]
; X86-NEXT:    vpshldvw (%eax), %ymm1, %ymm3 {%k1} # encoding: [0x62,0xf2,0xf5,0x29,0x70,0x18]
; X86-NEXT:    vpshldvw %ymm2, %ymm1, %ymm0 {%k1} {z} # encoding: [0x62,0xf2,0xf5,0xa9,0x70,0xc2]
; X86-NEXT:    vpaddw %ymm0, %ymm3, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xe5,0xfd,0xc0]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_vpshldv_w_256:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT:    vmovdqa %ymm0, %ymm3 # EVEX TO VEX Compression encoding: [0xc5,0xfd,0x6f,0xd8]
; X64-NEXT:    vpshldvw (%rdi), %ymm1, %ymm3 {%k1} # encoding: [0x62,0xf2,0xf5,0x29,0x70,0x1f]
; X64-NEXT:    vpshldvw %ymm2, %ymm1, %ymm0 {%k1} {z} # encoding: [0x62,0xf2,0xf5,0xa9,0x70,0xc2]
; X64-NEXT:    vpaddw %ymm0, %ymm3, %ymm0 # EVEX TO VEX Compression encoding: [0xc5,0xe5,0xfd,0xc0]
; X64-NEXT:    retq # encoding: [0xc3]
  %x2 = load <16 x i16>, <16 x i16>* %x2p
  %1 = call <16 x i16> @llvm.fshl.v16i16(<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> %x0
  %4 = call <16 x i16> @llvm.fshl.v16i16(<16 x i16> %x0, <16 x i16> %x1, <16 x i16> %x4)
  %5 = bitcast i16 %x3 to <16 x i1>
  %6 = select <16 x i1> %5, <16 x i16> %4, <16 x i16> zeroinitializer
  %res3 = add <16 x i16> %3, %6
  ret <16 x i16> %res3
}

define <8 x i16> @test_int_x86_avx512_mask_vpshldv_w_128(<8 x i16> %x0, <8 x i16> %x1, <8 x i16>* %x2p, <8 x i16> %x4, i8 %x3) {
; X86-LABEL: test_int_x86_avx512_mask_vpshldv_w_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:    vmovdqa %xmm0, %xmm3 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xd8]
; X86-NEXT:    vpshldvw (%eax), %xmm1, %xmm3 {%k1} # encoding: [0x62,0xf2,0xf5,0x09,0x70,0x18]
; X86-NEXT:    vpshldvw %xmm2, %xmm1, %xmm0 # encoding: [0x62,0xf2,0xf5,0x08,0x70,0xc2]
; X86-NEXT:    vpaddw %xmm0, %xmm3, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe1,0xfd,0xc0]
; X86-NEXT:    retl # encoding: [0xc3]
;
; X64-LABEL: test_int_x86_avx512_mask_vpshldv_w_128:
; X64:       # %bb.0:
; X64-NEXT:    kmovd %esi, %k1 # encoding: [0xc5,0xfb,0x92,0xce]
; X64-NEXT:    vmovdqa %xmm0, %xmm3 # EVEX TO VEX Compression encoding: [0xc5,0xf9,0x6f,0xd8]
; X64-NEXT:    vpshldvw (%rdi), %xmm1, %xmm3 {%k1} # encoding: [0x62,0xf2,0xf5,0x09,0x70,0x1f]
; X64-NEXT:    vpshldvw %xmm2, %xmm1, %xmm0 # encoding: [0x62,0xf2,0xf5,0x08,0x70,0xc2]
; X64-NEXT:    vpaddw %xmm0, %xmm3, %xmm0 # EVEX TO VEX Compression encoding: [0xc5,0xe1,0xfd,0xc0]
; X64-NEXT:    retq # encoding: [0xc3]
  %x2 = load <8 x i16>, <8 x i16>* %x2p
  %1 = call <8 x i16> @llvm.fshl.v8i16(<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> %x0
  %4 = call <8 x i16> @llvm.fshl.v8i16(<8 x i16> %x0, <8 x i16> %x1, <8 x i16> %x4)
  %5 = bitcast i8 %x3 to <8 x i1>
  %6 = select <8 x i1> %5, <8 x i16> %4, <8 x i16> zeroinitializer
  %res3 = add <8 x i16> %3, %4
  ret <8 x i16> %res3
}

declare <4 x i32> @llvm.fshl.v4i32(<4 x i32>, <4 x i32>, <4 x i32>)
declare <8 x i32> @llvm.fshl.v8i32(<8 x i32>, <8 x i32>, <8 x i32>)
declare <2 x i64> @llvm.fshl.v2i64(<2 x i64>, <2 x i64>, <2 x i64>)
declare <4 x i64> @llvm.fshl.v4i64(<4 x i64>, <4 x i64>, <4 x i64>)
declare <8 x i16> @llvm.fshl.v8i16(<8 x i16>, <8 x i16>, <8 x i16>)
declare <16 x i16> @llvm.fshl.v16i16(<16 x i16>, <16 x i16>, <16 x i16>)
declare <4 x i32> @llvm.fshr.v4i32(<4 x i32>, <4 x i32>, <4 x i32>)
declare <8 x i32> @llvm.fshr.v8i32(<8 x i32>, <8 x i32>, <8 x i32>)
declare <2 x i64> @llvm.fshr.v2i64(<2 x i64>, <2 x i64>, <2 x i64>)
declare <4 x i64> @llvm.fshr.v4i64(<4 x i64>, <4 x i64>, <4 x i64>)
declare <8 x i16> @llvm.fshr.v8i16(<8 x i16>, <8 x i16>, <8 x i16>)
declare <16 x i16> @llvm.fshr.v16i16(<16 x i16>, <16 x i16>, <16 x i16>)
declare <8 x i16> @llvm.masked.expandload.v8i16(i16*, <8 x i1>, <8 x i16>)
declare <16 x i8> @llvm.masked.expandload.v16i8(i8*, <16 x i1>, <16 x i8>)
declare void @llvm.masked.compressstore.v8i16(<8 x i16>, i16*, <8 x i1>)
declare void @llvm.masked.compressstore.v16i8(<16 x i8>, i8*, <16 x i1>)
declare <16 x i16> @llvm.masked.expandload.v16i16(i16*, <16 x i1>, <16 x i16>)
declare <32 x i8> @llvm.masked.expandload.v32i8(i8*, <32 x i1>, <32 x i8>)
declare void @llvm.masked.compressstore.v16i16(<16 x i16>, i16*, <16 x i1>)
declare void @llvm.masked.compressstore.v32i8(<32 x i8>, i8*, <32 x i1>)
declare <8 x i16> @llvm.x86.avx512.mask.expand.v8i16(<8 x i16>, <8 x i16>, <8 x i1>)
declare <16 x i8> @llvm.x86.avx512.mask.expand.v16i8(<16 x i8>, <16 x i8>, <16 x i1>)
declare <8 x i16> @llvm.x86.avx512.mask.compress.v8i16(<8 x i16>, <8 x i16>, <8 x i1>)
declare <16 x i8> @llvm.x86.avx512.mask.compress.v16i8(<16 x i8>, <16 x i8>, <16 x i1>)
declare <16 x i16> @llvm.x86.avx512.mask.expand.v16i16(<16 x i16>, <16 x i16>, <16 x i1>)
declare <32 x i8> @llvm.x86.avx512.mask.expand.v32i8(<32 x i8>, <32 x i8>, <32 x i1>)
declare <16 x i16> @llvm.x86.avx512.mask.compress.v16i16(<16 x i16>, <16 x i16>, <16 x i1>)
declare <32 x i8> @llvm.x86.avx512.mask.compress.v32i8(<32 x i8>, <32 x i8>, <32 x i1>)