; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -verify-machineinstrs -mcpu=sapphirerapids -mattr=+false-deps-perm -mtriple=x86_64-unknown-unknown < %s | FileCheck %s --check-prefixes=ENABLE
; RUN: llc -verify-machineinstrs -mcpu=sapphirerapids -mattr=-false-deps-perm -mtriple=x86_64-unknown-unknown < %s | FileCheck %s --check-prefixes=DISABLE

define <4 x i64> @permq_ri_256(<4 x i64> %a0) {
; ENABLE-LABEL: permq_ri_256:
; ENABLE:       # %bb.0:
; ENABLE-NEXT:    #APP
; ENABLE-NEXT:    nop
; ENABLE-NEXT:    #NO_APP
; ENABLE-NEXT:    vxorps %xmm1, %xmm1, %xmm1
; ENABLE-NEXT:    vpermq {{.*#+}} ymm1 = ymm0[1,2,1,0]
; ENABLE-NEXT:    vpaddq %ymm0, %ymm1, %ymm0
; ENABLE-NEXT:    retq
;
; DISABLE-LABEL: permq_ri_256:
; DISABLE:       # %bb.0:
; DISABLE-NEXT:    #APP
; DISABLE-NEXT:    nop
; DISABLE-NEXT:    #NO_APP
; DISABLE-NEXT:    vpermq {{.*#+}} ymm1 = ymm0[1,2,1,0]
; DISABLE-NEXT:    vpaddq %ymm0, %ymm1, %ymm0
; DISABLE-NEXT:    retq
  %1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"()
  %2 = shufflevector <4 x i64> %a0, <4 x i64> undef, <4 x i32> <i32 1, i32 2, i32 1, i32 0>
  %res = add <4 x i64> %2, %a0
  ret <4 x i64> %res
}

define <4 x i64> @permq_rr_256(<4 x i64> %a0, <4 x i64> %idx) {
; ENABLE-LABEL: permq_rr_256:
; ENABLE:       # %bb.0:
; ENABLE-NEXT:    vmovups %ymm1, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
; ENABLE-NEXT:    #APP
; ENABLE-NEXT:    nop
; ENABLE-NEXT:    #NO_APP
; ENABLE-NEXT:    vmovdqu {{[-0-9]+}}(%r{{[sb]}}p), %ymm2 # 32-byte Reload
; ENABLE-NEXT:    vxorps %xmm1, %xmm1, %xmm1
; ENABLE-NEXT:    vpermq %ymm0, %ymm2, %ymm1
; ENABLE-NEXT:    vpaddq %ymm2, %ymm0, %ymm0
; ENABLE-NEXT:    vpaddq %ymm1, %ymm0, %ymm0
; ENABLE-NEXT:    retq
;
; DISABLE-LABEL: permq_rr_256:
; DISABLE:       # %bb.0:
; DISABLE-NEXT:    vmovups %ymm1, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
; DISABLE-NEXT:    #APP
; DISABLE-NEXT:    nop
; DISABLE-NEXT:    #NO_APP
; DISABLE-NEXT:    vmovdqu {{[-0-9]+}}(%r{{[sb]}}p), %ymm2 # 32-byte Reload
; DISABLE-NEXT:    vpermq %ymm0, %ymm2, %ymm1
; DISABLE-NEXT:    vpaddq %ymm2, %ymm0, %ymm0
; DISABLE-NEXT:    vpaddq %ymm1, %ymm0, %ymm0
; DISABLE-NEXT:    retq
  %1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"()
  %2 = call <4 x i64> @llvm.x86.avx512.permvar.di.256(<4 x i64> %a0, <4 x i64> %idx)
  %t = add <4 x i64> %a0, %idx
  %res = add <4 x i64> %t, %2
  ret <4 x i64> %res
}

define <4 x i64> @permq_rm_256(ptr %p0, <4 x i64> %idx) {
; ENABLE-LABEL: permq_rm_256:
; ENABLE:       # %bb.0:
; ENABLE-NEXT:    #APP
; ENABLE-NEXT:    nop
; ENABLE-NEXT:    #NO_APP
; ENABLE-NEXT:    vxorps %xmm1, %xmm1, %xmm1
; ENABLE-NEXT:    vpermq (%rdi), %ymm0, %ymm1
; ENABLE-NEXT:    vpaddq %ymm1, %ymm0, %ymm0
; ENABLE-NEXT:    retq
;
; DISABLE-LABEL: permq_rm_256:
; DISABLE:       # %bb.0:
; DISABLE-NEXT:    #APP
; DISABLE-NEXT:    nop
; DISABLE-NEXT:    #NO_APP
; DISABLE-NEXT:    vpermq (%rdi), %ymm0, %ymm1
; DISABLE-NEXT:    vpaddq %ymm1, %ymm0, %ymm0
; DISABLE-NEXT:    retq
  %1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"()
  %a0 = load <4 x i64>, ptr %p0, align 64
  %2 = call <4 x i64> @llvm.x86.avx512.permvar.di.256(<4 x i64> %a0, <4 x i64> %idx)
  %res = add <4 x i64> %idx, %2
  ret <4 x i64> %res
}

define <4 x i64> @permq_mi_256(ptr %p0) {
; ENABLE-LABEL: permq_mi_256:
; ENABLE:       # %bb.0:
; ENABLE-NEXT:    #APP
; ENABLE-NEXT:    nop
; ENABLE-NEXT:    #NO_APP
; ENABLE-NEXT:    vxorps %xmm0, %xmm0, %xmm0
; ENABLE-NEXT:    vpermpd {{.*#+}} ymm0 = mem[3,2,2,0]
; ENABLE-NEXT:    retq
;
; DISABLE-LABEL: permq_mi_256:
; DISABLE:       # %bb.0:
; DISABLE-NEXT:    #APP
; DISABLE-NEXT:    nop
; DISABLE-NEXT:    #NO_APP
; DISABLE-NEXT:    vpermpd {{.*#+}} ymm0 = mem[3,2,2,0]
; DISABLE-NEXT:    retq
  %1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm1},~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"()
  %a0 = load <4 x i64>, ptr %p0, align 64
  %2 = shufflevector <4 x i64> %a0, <4 x i64> undef, <4 x i32> <i32 3, i32 2, i32 2, i32 0>
  ret <4 x i64> %2
}

define <4 x i64> @permq_broadcast_256(ptr %p0, <4 x i64> %idx) {
; ENABLE-LABEL: permq_broadcast_256:
; ENABLE:       # %bb.0:
; ENABLE-NEXT:    vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
; ENABLE-NEXT:    #APP
; ENABLE-NEXT:    nop
; ENABLE-NEXT:    #NO_APP
; ENABLE-NEXT:    vmovdqu {{[-0-9]+}}(%r{{[sb]}}p), %ymm1 # 32-byte Reload
; ENABLE-NEXT:    vxorps %xmm0, %xmm0, %xmm0
; ENABLE-NEXT:    vpermq (%rdi){1to4}, %ymm1, %ymm0
; ENABLE-NEXT:    vpaddq %ymm1, %ymm0, %ymm0
; ENABLE-NEXT:    retq
;
; DISABLE-LABEL: permq_broadcast_256:
; DISABLE:       # %bb.0:
; DISABLE-NEXT:    vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
; DISABLE-NEXT:    #APP
; DISABLE-NEXT:    nop
; DISABLE-NEXT:    #NO_APP
; DISABLE-NEXT:    vmovdqu {{[-0-9]+}}(%r{{[sb]}}p), %ymm1 # 32-byte Reload
; DISABLE-NEXT:    vpermq (%rdi){1to4}, %ymm1, %ymm0
; DISABLE-NEXT:    vpaddq %ymm1, %ymm0, %ymm0
; DISABLE-NEXT:    retq
  %1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm1},~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"()
  %v0 = load i64, ptr %p0, align 4
  %t0 = insertelement <4 x i64> undef, i64 %v0, i64 0
  %a0 = shufflevector <4 x i64> %t0, <4 x i64> undef, <4 x i32> zeroinitializer
  %2 = call <4 x i64> @llvm.x86.avx512.permvar.di.256(<4 x i64> %a0, <4 x i64> %idx)
  %res = add <4 x i64> %2, %idx
  ret <4 x i64> %res
}

define <4 x i64> @permq_maskz_256(<4 x i64> %a0, <4 x i64> %idx, ptr %mask) {
; ENABLE-LABEL: permq_maskz_256:
; ENABLE:       # %bb.0:
; ENABLE-NEXT:    #APP
; ENABLE-NEXT:    nop
; ENABLE-NEXT:    #NO_APP
; ENABLE-NEXT:    vxorps %xmm2, %xmm2, %xmm2
; ENABLE-NEXT:    vpermq %ymm0, %ymm1, %ymm2
; ENABLE-NEXT:    kmovb (%rdi), %k1
; ENABLE-NEXT:    vpaddq %ymm1, %ymm0, %ymm0
; ENABLE-NEXT:    vpaddq %ymm2, %ymm0, %ymm0 {%k1}
; ENABLE-NEXT:    retq
;
; DISABLE-LABEL: permq_maskz_256:
; DISABLE:       # %bb.0:
; DISABLE-NEXT:    #APP
; DISABLE-NEXT:    nop
; DISABLE-NEXT:    #NO_APP
; DISABLE-NEXT:    vpermq %ymm0, %ymm1, %ymm2
; DISABLE-NEXT:    kmovb (%rdi), %k1
; DISABLE-NEXT:    vpaddq %ymm1, %ymm0, %ymm0
; DISABLE-NEXT:    vpaddq %ymm2, %ymm0, %ymm0 {%k1}
; DISABLE-NEXT:    retq
  %1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"()
  %2 = load i8, ptr %mask
  %3 = call <4 x i64> @llvm.x86.avx512.mask.permvar.di.256(<4 x i64> %a0, <4 x i64> %idx, <4 x i64> zeroinitializer, i8 %2)
  %t = add <4 x i64> %a0, %idx
  %res = add <4 x i64> %3, %t
  ret <4 x i64> %res
}

declare <4 x i64> @llvm.x86.avx512.permvar.di.256(<4 x i64>, <4 x i64>)
declare <4 x i64> @llvm.x86.avx512.mask.permvar.di.256(<4 x i64>, <4 x i64>, <4 x i64>, i8)

define <8 x i64> @permq_rr_512(<8 x i64> %a0, <8 x i64> %idx) {
; ENABLE-LABEL: permq_rr_512:
; ENABLE:       # %bb.0:
; ENABLE-NEXT:    vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
; ENABLE-NEXT:    #APP
; ENABLE-NEXT:    nop
; ENABLE-NEXT:    #NO_APP
; ENABLE-NEXT:    vmovdqu64 {{[-0-9]+}}(%r{{[sb]}}p), %zmm2 # 64-byte Reload
; ENABLE-NEXT:    vpxor %xmm1, %xmm1, %xmm1
; ENABLE-NEXT:    vpermq %zmm0, %zmm2, %zmm1
; ENABLE-NEXT:    vpaddq %zmm2, %zmm0, %zmm0
; ENABLE-NEXT:    vpaddq %zmm1, %zmm0, %zmm0
; ENABLE-NEXT:    retq
;
; DISABLE-LABEL: permq_rr_512:
; DISABLE:       # %bb.0:
; DISABLE-NEXT:    vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
; DISABLE-NEXT:    #APP
; DISABLE-NEXT:    nop
; DISABLE-NEXT:    #NO_APP
; DISABLE-NEXT:    vmovdqu64 {{[-0-9]+}}(%r{{[sb]}}p), %zmm2 # 64-byte Reload
; DISABLE-NEXT:    vpermq %zmm0, %zmm2, %zmm1
; DISABLE-NEXT:    vpaddq %zmm2, %zmm0, %zmm0
; DISABLE-NEXT:    vpaddq %zmm1, %zmm0, %zmm0
; DISABLE-NEXT:    retq
  %1 = tail call <8 x i64> asm sideeffect "nop", "=x,~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"()
  %2 = call <8 x i64> @llvm.x86.avx512.permvar.di.512(<8 x i64> %a0, <8 x i64> %idx)
  %t = add <8 x i64> %a0, %idx
  %res = add <8 x i64> %t, %2
  ret <8 x i64> %res
}

define <8 x i64> @permq_rm_512(ptr %p0, <8 x i64> %idx) {
; ENABLE-LABEL: permq_rm_512:
; ENABLE:       # %bb.0:
; ENABLE-NEXT:    #APP
; ENABLE-NEXT:    nop
; ENABLE-NEXT:    #NO_APP
; ENABLE-NEXT:    vpxor %xmm1, %xmm1, %xmm1
; ENABLE-NEXT:    vpermq (%rdi), %zmm0, %zmm1
; ENABLE-NEXT:    vpaddq %zmm1, %zmm0, %zmm0
; ENABLE-NEXT:    retq
;
; DISABLE-LABEL: permq_rm_512:
; DISABLE:       # %bb.0:
; DISABLE-NEXT:    #APP
; DISABLE-NEXT:    nop
; DISABLE-NEXT:    #NO_APP
; DISABLE-NEXT:    vpermq (%rdi), %zmm0, %zmm1
; DISABLE-NEXT:    vpaddq %zmm1, %zmm0, %zmm0
; DISABLE-NEXT:    retq
  %1 = tail call <8 x i64> asm sideeffect "nop", "=x,~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"()
  %a0 = load <8 x i64>, ptr %p0, align 64
  %2 = call <8 x i64> @llvm.x86.avx512.permvar.di.512(<8 x i64> %a0, <8 x i64> %idx)
  %res = add <8 x i64> %idx, %2
  ret <8 x i64> %res
}

define <8 x i64> @permq_broadcast_512(ptr %p0, <8 x i64> %idx) {
; ENABLE-LABEL: permq_broadcast_512:
; ENABLE:       # %bb.0:
; ENABLE-NEXT:    vmovups %zmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
; ENABLE-NEXT:    #APP
; ENABLE-NEXT:    nop
; ENABLE-NEXT:    #NO_APP
; ENABLE-NEXT:    vmovdqu64 {{[-0-9]+}}(%r{{[sb]}}p), %zmm1 # 64-byte Reload
; ENABLE-NEXT:    vpxor %xmm0, %xmm0, %xmm0
; ENABLE-NEXT:    vpermq (%rdi){1to8}, %zmm1, %zmm0
; ENABLE-NEXT:    vpaddq %zmm1, %zmm0, %zmm0
; ENABLE-NEXT:    retq
;
; DISABLE-LABEL: permq_broadcast_512:
; DISABLE:       # %bb.0:
; DISABLE-NEXT:    vmovups %zmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
; DISABLE-NEXT:    #APP
; DISABLE-NEXT:    nop
; DISABLE-NEXT:    #NO_APP
; DISABLE-NEXT:    vmovdqu64 {{[-0-9]+}}(%r{{[sb]}}p), %zmm1 # 64-byte Reload
; DISABLE-NEXT:    vpermq (%rdi){1to8}, %zmm1, %zmm0
; DISABLE-NEXT:    vpaddq %zmm1, %zmm0, %zmm0
; DISABLE-NEXT:    retq
  %1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm1},~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"()
  %v0 = load i64, ptr %p0, align 4
  %t0 = insertelement <8 x i64> undef, i64 %v0, i64 0
  %a0 = shufflevector <8 x i64> %t0, <8 x i64> undef, <8 x i32> zeroinitializer
  %2 = call <8 x i64> @llvm.x86.avx512.permvar.di.512(<8 x i64> %a0, <8 x i64> %idx)
  %res = add <8 x i64> %2, %idx
  ret <8 x i64> %res
}

define <8 x i64> @permq_maskz_512(<8 x i64> %a0, <8 x i64> %idx, ptr %mask) {
; ENABLE-LABEL: permq_maskz_512:
; ENABLE:       # %bb.0:
; ENABLE-NEXT:    #APP
; ENABLE-NEXT:    nop
; ENABLE-NEXT:    #NO_APP
; ENABLE-NEXT:    vpxor %xmm2, %xmm2, %xmm2
; ENABLE-NEXT:    vpermq %zmm0, %zmm1, %zmm2
; ENABLE-NEXT:    kmovb (%rdi), %k1
; ENABLE-NEXT:    vpaddq %zmm1, %zmm0, %zmm0
; ENABLE-NEXT:    vpaddq %zmm2, %zmm0, %zmm0 {%k1}
; ENABLE-NEXT:    retq
;
; DISABLE-LABEL: permq_maskz_512:
; DISABLE:       # %bb.0:
; DISABLE-NEXT:    #APP
; DISABLE-NEXT:    nop
; DISABLE-NEXT:    #NO_APP
; DISABLE-NEXT:    vpermq %zmm0, %zmm1, %zmm2
; DISABLE-NEXT:    kmovb (%rdi), %k1
; DISABLE-NEXT:    vpaddq %zmm1, %zmm0, %zmm0
; DISABLE-NEXT:    vpaddq %zmm2, %zmm0, %zmm0 {%k1}
; DISABLE-NEXT:    retq
  %1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"()
  %2 = load i8, ptr %mask
  %3 = call <8 x i64> @llvm.x86.avx512.mask.permvar.di.512(<8 x i64> %a0, <8 x i64> %idx, <8 x i64> zeroinitializer, i8 %2)
  %t = add <8 x i64> %a0, %idx
  %res = add <8 x i64> %3, %t
  ret <8 x i64> %res
}

declare <8 x i64> @llvm.x86.avx512.permvar.di.512(<8 x i64>, <8 x i64>)
declare <8 x i64> @llvm.x86.avx512.mask.permvar.di.512(<8 x i64>, <8 x i64>, <8 x i64>, i8)

define <8 x i32> @permd_rr_256(<8 x i32> %a0, <8 x i32> %idx) {
; ENABLE-LABEL: permd_rr_256:
; ENABLE:       # %bb.0:
; ENABLE-NEXT:    vmovups %ymm1, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
; ENABLE-NEXT:    #APP
; ENABLE-NEXT:    nop
; ENABLE-NEXT:    #NO_APP
; ENABLE-NEXT:    vmovdqu {{[-0-9]+}}(%r{{[sb]}}p), %ymm2 # 32-byte Reload
; ENABLE-NEXT:    vxorps %xmm1, %xmm1, %xmm1
; ENABLE-NEXT:    vpermd %ymm0, %ymm2, %ymm1
; ENABLE-NEXT:    vpaddd %ymm2, %ymm0, %ymm0
; ENABLE-NEXT:    vpaddd %ymm1, %ymm0, %ymm0
; ENABLE-NEXT:    retq
;
; DISABLE-LABEL: permd_rr_256:
; DISABLE:       # %bb.0:
; DISABLE-NEXT:    vmovups %ymm1, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
; DISABLE-NEXT:    #APP
; DISABLE-NEXT:    nop
; DISABLE-NEXT:    #NO_APP
; DISABLE-NEXT:    vmovdqu {{[-0-9]+}}(%r{{[sb]}}p), %ymm2 # 32-byte Reload
; DISABLE-NEXT:    vpermd %ymm0, %ymm2, %ymm1
; DISABLE-NEXT:    vpaddd %ymm2, %ymm0, %ymm0
; DISABLE-NEXT:    vpaddd %ymm1, %ymm0, %ymm0
; DISABLE-NEXT:    retq
  %1 = tail call <8 x i64> asm sideeffect "nop", "=x,~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"()
  %2 = call <8 x i32> @llvm.x86.avx512.mask.permvar.si.256(<8 x i32> %a0, <8 x i32> %idx, <8 x i32> undef, i8 -1)
  %t = add <8 x i32> %a0, %idx
  %res = add <8 x i32> %t, %2
  ret <8 x i32> %res
}

define <8 x i32> @permd_rm_256(ptr %p0, <8 x i32> %idx) {
; ENABLE-LABEL: permd_rm_256:
; ENABLE:       # %bb.0:
; ENABLE-NEXT:    #APP
; ENABLE-NEXT:    nop
; ENABLE-NEXT:    #NO_APP
; ENABLE-NEXT:    vxorps %xmm1, %xmm1, %xmm1
; ENABLE-NEXT:    vpermd (%rdi), %ymm0, %ymm1
; ENABLE-NEXT:    vpaddd %ymm1, %ymm0, %ymm0
; ENABLE-NEXT:    retq
;
; DISABLE-LABEL: permd_rm_256:
; DISABLE:       # %bb.0:
; DISABLE-NEXT:    #APP
; DISABLE-NEXT:    nop
; DISABLE-NEXT:    #NO_APP
; DISABLE-NEXT:    vpermd (%rdi), %ymm0, %ymm1
; DISABLE-NEXT:    vpaddd %ymm1, %ymm0, %ymm0
; DISABLE-NEXT:    retq
  %1 = tail call <8 x i64> asm sideeffect "nop", "=x,~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"()
  %a0 = load <8 x i32>, ptr %p0, align 64
  %2 = call <8 x i32> @llvm.x86.avx512.mask.permvar.si.256(<8 x i32> %a0, <8 x i32> %idx, <8 x i32> undef, i8 -1)
  %res = add <8 x i32> %idx, %2
  ret <8 x i32> %res
}

define <8 x i32> @permd_broadcast_256(ptr %p0, <8 x i32> %idx) {
; ENABLE-LABEL: permd_broadcast_256:
; ENABLE:       # %bb.0:
; ENABLE-NEXT:    vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
; ENABLE-NEXT:    #APP
; ENABLE-NEXT:    nop
; ENABLE-NEXT:    #NO_APP
; ENABLE-NEXT:    vmovdqu {{[-0-9]+}}(%r{{[sb]}}p), %ymm1 # 32-byte Reload
; ENABLE-NEXT:    vxorps %xmm0, %xmm0, %xmm0
; ENABLE-NEXT:    vpermd (%rdi){1to8}, %ymm1, %ymm0
; ENABLE-NEXT:    vpaddd %ymm1, %ymm0, %ymm0
; ENABLE-NEXT:    retq
;
; DISABLE-LABEL: permd_broadcast_256:
; DISABLE:       # %bb.0:
; DISABLE-NEXT:    vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
; DISABLE-NEXT:    #APP
; DISABLE-NEXT:    nop
; DISABLE-NEXT:    #NO_APP
; DISABLE-NEXT:    vmovdqu {{[-0-9]+}}(%r{{[sb]}}p), %ymm1 # 32-byte Reload
; DISABLE-NEXT:    vpermd (%rdi){1to8}, %ymm1, %ymm0
; DISABLE-NEXT:    vpaddd %ymm1, %ymm0, %ymm0
; DISABLE-NEXT:    retq
  %1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm1},~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"()
  %v0 = load i32, ptr %p0, align 4
  %t0 = insertelement <8 x i32> undef, i32 %v0, i32 0
  %a0 = shufflevector <8 x i32> %t0, <8 x i32> undef, <8 x i32> zeroinitializer
  %2 = call <8 x i32> @llvm.x86.avx512.mask.permvar.si.256(<8 x i32> %a0, <8 x i32> %idx, <8 x i32> zeroinitializer, i8 -1)
  %res = add <8 x i32> %2, %idx
  ret <8 x i32> %res
}

define <8 x i32> @permd_maskz_256(<8 x i32> %a0, <8 x i32> %idx, ptr %mask) {
; ENABLE-LABEL: permd_maskz_256:
; ENABLE:       # %bb.0:
; ENABLE-NEXT:    #APP
; ENABLE-NEXT:    nop
; ENABLE-NEXT:    #NO_APP
; ENABLE-NEXT:    vxorps %xmm2, %xmm2, %xmm2
; ENABLE-NEXT:    vpermd %ymm0, %ymm1, %ymm2
; ENABLE-NEXT:    kmovb (%rdi), %k1
; ENABLE-NEXT:    vpaddd %ymm1, %ymm0, %ymm0
; ENABLE-NEXT:    vpaddd %ymm2, %ymm0, %ymm0 {%k1}
; ENABLE-NEXT:    retq
;
; DISABLE-LABEL: permd_maskz_256:
; DISABLE:       # %bb.0:
; DISABLE-NEXT:    #APP
; DISABLE-NEXT:    nop
; DISABLE-NEXT:    #NO_APP
; DISABLE-NEXT:    vpermd %ymm0, %ymm1, %ymm2
; DISABLE-NEXT:    kmovb (%rdi), %k1
; DISABLE-NEXT:    vpaddd %ymm1, %ymm0, %ymm0
; DISABLE-NEXT:    vpaddd %ymm2, %ymm0, %ymm0 {%k1}
; DISABLE-NEXT:    retq
  %1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"()
  %2 = load i8, ptr %mask
  %3 = call <8 x i32> @llvm.x86.avx512.mask.permvar.si.256(<8 x i32> %a0, <8 x i32> %idx, <8 x i32> zeroinitializer, i8 %2)
  %t = add <8 x i32> %a0, %idx
  %res = add <8 x i32> %3, %t
  ret <8 x i32> %res
}

declare <8 x i32> @llvm.x86.avx512.mask.permvar.si.256(<8 x i32>, <8 x i32>, <8 x i32>, i8)

define <16 x i32> @permd_rr_512(<16 x i32> %a0, <16 x i32> %idx) {
; ENABLE-LABEL: permd_rr_512:
; ENABLE:       # %bb.0:
; ENABLE-NEXT:    vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
; ENABLE-NEXT:    #APP
; ENABLE-NEXT:    nop
; ENABLE-NEXT:    #NO_APP
; ENABLE-NEXT:    vmovdqu64 {{[-0-9]+}}(%r{{[sb]}}p), %zmm2 # 64-byte Reload
; ENABLE-NEXT:    vpxor %xmm1, %xmm1, %xmm1
; ENABLE-NEXT:    vpermd %zmm0, %zmm2, %zmm1
; ENABLE-NEXT:    vpaddd %zmm2, %zmm0, %zmm0
; ENABLE-NEXT:    vpaddd %zmm1, %zmm0, %zmm0
; ENABLE-NEXT:    retq
;
; DISABLE-LABEL: permd_rr_512:
; DISABLE:       # %bb.0:
; DISABLE-NEXT:    vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
; DISABLE-NEXT:    #APP
; DISABLE-NEXT:    nop
; DISABLE-NEXT:    #NO_APP
; DISABLE-NEXT:    vmovdqu64 {{[-0-9]+}}(%r{{[sb]}}p), %zmm2 # 64-byte Reload
; DISABLE-NEXT:    vpermd %zmm0, %zmm2, %zmm1
; DISABLE-NEXT:    vpaddd %zmm2, %zmm0, %zmm0
; DISABLE-NEXT:    vpaddd %zmm1, %zmm0, %zmm0
; DISABLE-NEXT:    retq
  %1 = tail call <8 x i64> asm sideeffect "nop", "=x,~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"()
  %2 = call <16 x i32> @llvm.x86.avx512.mask.permvar.si.512(<16 x i32> %a0, <16 x i32> %idx, <16 x i32> undef, i16 -1)
  %t = add <16 x i32> %a0, %idx
  %res = add <16 x i32> %t, %2
  ret <16 x i32> %res
}

define <16 x i32> @permd_rm_512(ptr %p0, <16 x i32> %idx) {
; ENABLE-LABEL: permd_rm_512:
; ENABLE:       # %bb.0:
; ENABLE-NEXT:    #APP
; ENABLE-NEXT:    nop
; ENABLE-NEXT:    #NO_APP
; ENABLE-NEXT:    vpxor %xmm1, %xmm1, %xmm1
; ENABLE-NEXT:    vpermd (%rdi), %zmm0, %zmm1
; ENABLE-NEXT:    vpaddd %zmm1, %zmm0, %zmm0
; ENABLE-NEXT:    retq
;
; DISABLE-LABEL: permd_rm_512:
; DISABLE:       # %bb.0:
; DISABLE-NEXT:    #APP
; DISABLE-NEXT:    nop
; DISABLE-NEXT:    #NO_APP
; DISABLE-NEXT:    vpermd (%rdi), %zmm0, %zmm1
; DISABLE-NEXT:    vpaddd %zmm1, %zmm0, %zmm0
; DISABLE-NEXT:    retq
  %1 = tail call <8 x i64> asm sideeffect "nop", "=x,~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"()
  %a0 = load <16 x i32>, ptr %p0, align 64
  %2 = call <16 x i32> @llvm.x86.avx512.mask.permvar.si.512(<16 x i32> %a0, <16 x i32> %idx, <16 x i32> undef, i16 -1)
  %res = add <16 x i32> %idx, %2
  ret <16 x i32> %res
}

define <16 x i32> @permd_broadcast_512(ptr %p0, <16 x i32> %idx) {
; ENABLE-LABEL: permd_broadcast_512:
; ENABLE:       # %bb.0:
; ENABLE-NEXT:    vmovups %zmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
; ENABLE-NEXT:    #APP
; ENABLE-NEXT:    nop
; ENABLE-NEXT:    #NO_APP
; ENABLE-NEXT:    vmovdqu64 {{[-0-9]+}}(%r{{[sb]}}p), %zmm1 # 64-byte Reload
; ENABLE-NEXT:    vpxor %xmm0, %xmm0, %xmm0
; ENABLE-NEXT:    vpermd (%rdi){1to16}, %zmm1, %zmm0
; ENABLE-NEXT:    vpaddd %zmm1, %zmm0, %zmm0
; ENABLE-NEXT:    retq
;
; DISABLE-LABEL: permd_broadcast_512:
; DISABLE:       # %bb.0:
; DISABLE-NEXT:    vmovups %zmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
; DISABLE-NEXT:    #APP
; DISABLE-NEXT:    nop
; DISABLE-NEXT:    #NO_APP
; DISABLE-NEXT:    vmovdqu64 {{[-0-9]+}}(%r{{[sb]}}p), %zmm1 # 64-byte Reload
; DISABLE-NEXT:    vpermd (%rdi){1to16}, %zmm1, %zmm0
; DISABLE-NEXT:    vpaddd %zmm1, %zmm0, %zmm0
; DISABLE-NEXT:    retq
  %1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm1},~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"()
  %v0 = load i32, ptr %p0, align 4
  %t0 = insertelement <16 x i32> undef, i32 %v0, i32 0
  %a0 = shufflevector <16 x i32> %t0, <16 x i32> undef, <16 x i32> zeroinitializer
  %2 = call <16 x i32> @llvm.x86.avx512.mask.permvar.si.512(<16 x i32> %a0, <16 x i32> %idx, <16 x i32> undef, i16 -1)
  %res = add <16 x i32> %2, %idx
  ret <16 x i32> %res
}

define <16 x i32> @permd_maskz_512(<16 x i32> %a0, <16 x i32> %idx, ptr %mask) {
; ENABLE-LABEL: permd_maskz_512:
; ENABLE:       # %bb.0:
; ENABLE-NEXT:    #APP
; ENABLE-NEXT:    nop
; ENABLE-NEXT:    #NO_APP
; ENABLE-NEXT:    vpxor %xmm2, %xmm2, %xmm2
; ENABLE-NEXT:    vpermd %zmm0, %zmm1, %zmm2
; ENABLE-NEXT:    kmovw (%rdi), %k1
; ENABLE-NEXT:    vpaddd %zmm1, %zmm0, %zmm0
; ENABLE-NEXT:    vpaddd %zmm2, %zmm0, %zmm0 {%k1}
; ENABLE-NEXT:    retq
;
; DISABLE-LABEL: permd_maskz_512:
; DISABLE:       # %bb.0:
; DISABLE-NEXT:    #APP
; DISABLE-NEXT:    nop
; DISABLE-NEXT:    #NO_APP
; DISABLE-NEXT:    vpermd %zmm0, %zmm1, %zmm2
; DISABLE-NEXT:    kmovw (%rdi), %k1
; DISABLE-NEXT:    vpaddd %zmm1, %zmm0, %zmm0
; DISABLE-NEXT:    vpaddd %zmm2, %zmm0, %zmm0 {%k1}
; DISABLE-NEXT:    retq
  %1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"()
  %2 = load i16, ptr %mask
  %3 = call <16 x i32> @llvm.x86.avx512.mask.permvar.si.512(<16 x i32> %a0, <16 x i32> %idx, <16 x i32> zeroinitializer, i16 %2)
  %t = add <16 x i32> %a0, %idx
  %res = add <16 x i32> %3, %t
  ret <16 x i32> %res
}

declare <16 x i32> @llvm.x86.avx512.mask.permvar.si.512(<16 x i32>, <16 x i32>, <16 x i32>, i16)

define <4 x double> @permpd_ri_256(<4 x double> %a0) {
; ENABLE-LABEL: permpd_ri_256:
; ENABLE:       # %bb.0:
; ENABLE-NEXT:    #APP
; ENABLE-NEXT:    nop
; ENABLE-NEXT:    #NO_APP
; ENABLE-NEXT:    vxorps %xmm1, %xmm1, %xmm1
; ENABLE-NEXT:    vpermpd {{.*#+}} ymm1 = ymm0[1,2,1,0]
; ENABLE-NEXT:    vaddpd %ymm0, %ymm1, %ymm0
; ENABLE-NEXT:    retq
;
; DISABLE-LABEL: permpd_ri_256:
; DISABLE:       # %bb.0:
; DISABLE-NEXT:    #APP
; DISABLE-NEXT:    nop
; DISABLE-NEXT:    #NO_APP
; DISABLE-NEXT:    vpermpd {{.*#+}} ymm1 = ymm0[1,2,1,0]
; DISABLE-NEXT:    vaddpd %ymm0, %ymm1, %ymm0
; DISABLE-NEXT:    retq
  %1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"()
  %2 = shufflevector <4 x double> %a0, <4 x double> undef, <4 x i32> <i32 1, i32 2, i32 1, i32 0>
  %res = fadd <4 x double> %2, %a0
  ret <4 x double> %res
}

define <4 x double> @permpd_rr_256(<4 x double> %a0, <4 x i64> %idx) {
; ENABLE-LABEL: permpd_rr_256:
; ENABLE:       # %bb.0:
; ENABLE-NEXT:    vmovups %ymm1, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
; ENABLE-NEXT:    #APP
; ENABLE-NEXT:    nop
; ENABLE-NEXT:    #NO_APP
; ENABLE-NEXT:    vmovapd %ymm0, %ymm2
; ENABLE-NEXT:    vmovupd {{[-0-9]+}}(%r{{[sb]}}p), %ymm0 # 32-byte Reload
; ENABLE-NEXT:    vxorps %xmm1, %xmm1, %xmm1
; ENABLE-NEXT:    vpermpd %ymm2, %ymm0, %ymm1
; ENABLE-NEXT:    vcvtqq2pd %ymm0, %ymm0
; ENABLE-NEXT:    vaddpd %ymm0, %ymm2, %ymm0
; ENABLE-NEXT:    vaddpd %ymm0, %ymm1, %ymm0
; ENABLE-NEXT:    retq
;
; DISABLE-LABEL: permpd_rr_256:
; DISABLE:       # %bb.0:
; DISABLE-NEXT:    vmovups %ymm1, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
; DISABLE-NEXT:    #APP
; DISABLE-NEXT:    nop
; DISABLE-NEXT:    #NO_APP
; DISABLE-NEXT:    vmovapd %ymm0, %ymm2
; DISABLE-NEXT:    vmovupd {{[-0-9]+}}(%r{{[sb]}}p), %ymm0 # 32-byte Reload
; DISABLE-NEXT:    vpermpd %ymm2, %ymm0, %ymm1
; DISABLE-NEXT:    vcvtqq2pd %ymm0, %ymm0
; DISABLE-NEXT:    vaddpd %ymm0, %ymm2, %ymm0
; DISABLE-NEXT:    vaddpd %ymm0, %ymm1, %ymm0
; DISABLE-NEXT:    retq
  %1 = tail call <4 x double> asm sideeffect "nop", "=x,~{xmm1},~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"()
  %2 = call <4 x double> @llvm.x86.avx512.permvar.df.256(<4 x double> %1, <4 x i64> %idx)
  %a1 = sitofp <4 x i64> %idx to <4 x double>
  %t = fadd <4 x double> %1, %a1
  %res = fadd <4 x double> %2, %t
  ret <4 x double> %res
}

define <4 x double> @permpd_rm_256(ptr %p0, <4 x i64> %idx) {
; ENABLE-LABEL: permpd_rm_256:
; ENABLE:       # %bb.0:
; ENABLE-NEXT:    vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
; ENABLE-NEXT:    #APP
; ENABLE-NEXT:    nop
; ENABLE-NEXT:    #NO_APP
; ENABLE-NEXT:    vmovupd {{[-0-9]+}}(%r{{[sb]}}p), %ymm1 # 32-byte Reload
; ENABLE-NEXT:    vxorps %xmm0, %xmm0, %xmm0
; ENABLE-NEXT:    vpermpd (%rdi), %ymm1, %ymm0
; ENABLE-NEXT:    vcvtqq2pd %ymm1, %ymm1
; ENABLE-NEXT:    vaddpd %ymm1, %ymm0, %ymm0
; ENABLE-NEXT:    retq
;
; DISABLE-LABEL: permpd_rm_256:
; DISABLE:       # %bb.0:
; DISABLE-NEXT:    vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
; DISABLE-NEXT:    #APP
; DISABLE-NEXT:    nop
; DISABLE-NEXT:    #NO_APP
; DISABLE-NEXT:    vmovupd {{[-0-9]+}}(%r{{[sb]}}p), %ymm1 # 32-byte Reload
; DISABLE-NEXT:    vpermpd (%rdi), %ymm1, %ymm0
; DISABLE-NEXT:    vcvtqq2pd %ymm1, %ymm1
; DISABLE-NEXT:    vaddpd %ymm1, %ymm0, %ymm0
; DISABLE-NEXT:    retq
  %1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm1},~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"()
  %a0 = load <4 x double>, ptr %p0, align 64
  %2 = call <4 x double> @llvm.x86.avx512.permvar.df.256(<4 x double> %a0, <4 x i64> %idx)
  %a1 = sitofp <4 x i64> %idx to <4 x double>
  %res = fadd <4 x double> %2, %a1
  ret <4 x double> %res
}

define <4 x double> @permpd_mi_256(ptr %p0) {
; ENABLE-LABEL: permpd_mi_256:
; ENABLE:       # %bb.0:
; ENABLE-NEXT:    #APP
; ENABLE-NEXT:    nop
; ENABLE-NEXT:    #NO_APP
; ENABLE-NEXT:    vxorps %xmm0, %xmm0, %xmm0
; ENABLE-NEXT:    vpermpd {{.*#+}} ymm0 = mem[3,2,2,0]
; ENABLE-NEXT:    retq
;
; DISABLE-LABEL: permpd_mi_256:
; DISABLE:       # %bb.0:
; DISABLE-NEXT:    #APP
; DISABLE-NEXT:    nop
; DISABLE-NEXT:    #NO_APP
; DISABLE-NEXT:    vpermpd {{.*#+}} ymm0 = mem[3,2,2,0]
; DISABLE-NEXT:    retq
  %1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm1},~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"()
  %a0 = load <4 x double>, ptr %p0, align 64
  %2 = shufflevector <4 x double> %a0, <4 x double> undef, <4 x i32> <i32 3, i32 2, i32 2, i32 0>
  ret <4 x double> %2
}

define <4 x double> @permpd_broadcast_256(ptr %p0, <4 x i64> %idx) {
; ENABLE-LABEL: permpd_broadcast_256:
; ENABLE:       # %bb.0:
; ENABLE-NEXT:    vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
; ENABLE-NEXT:    #APP
; ENABLE-NEXT:    nop
; ENABLE-NEXT:    #NO_APP
; ENABLE-NEXT:    vmovupd {{[-0-9]+}}(%r{{[sb]}}p), %ymm1 # 32-byte Reload
; ENABLE-NEXT:    vxorps %xmm0, %xmm0, %xmm0
; ENABLE-NEXT:    vpermpd (%rdi){1to4}, %ymm1, %ymm0
; ENABLE-NEXT:    vcvtqq2pd %ymm1, %ymm1
; ENABLE-NEXT:    vaddpd %ymm1, %ymm0, %ymm0
; ENABLE-NEXT:    retq
;
; DISABLE-LABEL: permpd_broadcast_256:
; DISABLE:       # %bb.0:
; DISABLE-NEXT:    vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
; DISABLE-NEXT:    #APP
; DISABLE-NEXT:    nop
; DISABLE-NEXT:    #NO_APP
; DISABLE-NEXT:    vmovupd {{[-0-9]+}}(%r{{[sb]}}p), %ymm1 # 32-byte Reload
; DISABLE-NEXT:    vpermpd (%rdi){1to4}, %ymm1, %ymm0
; DISABLE-NEXT:    vcvtqq2pd %ymm1, %ymm1
; DISABLE-NEXT:    vaddpd %ymm1, %ymm0, %ymm0
; DISABLE-NEXT:    retq
  %1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm1},~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"()
  %v0 = load double, ptr %p0, align 4
  %t0 = insertelement <4 x double> undef, double %v0, i64 0
  %a0 = shufflevector <4 x double> %t0, <4 x double> undef, <4 x i32> zeroinitializer
  %2 = call <4 x double> @llvm.x86.avx512.permvar.df.256(<4 x double> %a0, <4 x i64> %idx)
  %a1 = sitofp <4 x i64> %idx to <4 x double>
  %res = fadd <4 x double> %2, %a1
  ret <4 x double> %res
}

define <4 x double> @permpd_maskz_256(<4 x double> %a0, <4 x i64> %idx, ptr %mask) {
; ENABLE-LABEL: permpd_maskz_256:
; ENABLE:       # %bb.0:
; ENABLE-NEXT:    #APP
; ENABLE-NEXT:    nop
; ENABLE-NEXT:    #NO_APP
; ENABLE-NEXT:    kmovb (%rdi), %k1
; ENABLE-NEXT:    vxorps %xmm2, %xmm2, %xmm2
; ENABLE-NEXT:    vpermpd %ymm0, %ymm1, %ymm2 {%k1} {z}
; ENABLE-NEXT:    vcvtqq2pd %ymm1, %ymm1
; ENABLE-NEXT:    vaddpd %ymm1, %ymm0, %ymm0
; ENABLE-NEXT:    vaddpd %ymm0, %ymm2, %ymm0
; ENABLE-NEXT:    retq
;
; DISABLE-LABEL: permpd_maskz_256:
; DISABLE:       # %bb.0:
; DISABLE-NEXT:    #APP
; DISABLE-NEXT:    nop
; DISABLE-NEXT:    #NO_APP
; DISABLE-NEXT:    kmovb (%rdi), %k1
; DISABLE-NEXT:    vpermpd %ymm0, %ymm1, %ymm2 {%k1} {z}
; DISABLE-NEXT:    vcvtqq2pd %ymm1, %ymm1
; DISABLE-NEXT:    vaddpd %ymm1, %ymm0, %ymm0
; DISABLE-NEXT:    vaddpd %ymm0, %ymm2, %ymm0
; DISABLE-NEXT:    retq
  %1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"()
  %2 = load i8, ptr %mask
  %3 = call <4 x double> @llvm.x86.avx512.mask.permvar.df.256(<4 x double> %a0, <4 x i64> %idx, <4 x double> zeroinitializer, i8 %2)
  %a1 = sitofp <4 x i64> %idx to <4 x double>
  %t = fadd <4 x double> %a0, %a1
  %res = fadd <4 x double> %3, %t
  ret <4 x double> %res
}

declare <4 x double> @llvm.x86.avx512.permvar.df.256(<4 x double>, <4 x i64>)
declare <4 x double> @llvm.x86.avx512.mask.permvar.df.256(<4 x double>, <4 x i64>, <4 x double>, i8)

define <8 x double> @permpd_rr_512(<8 x double> %a0, <8 x i64> %idx) {
; ENABLE-LABEL: permpd_rr_512:
; ENABLE:       # %bb.0:
; ENABLE-NEXT:    vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
; ENABLE-NEXT:    #APP
; ENABLE-NEXT:    nop
; ENABLE-NEXT:    #NO_APP
; ENABLE-NEXT:    vmovapd %zmm0, %zmm2
; ENABLE-NEXT:    vmovupd {{[-0-9]+}}(%r{{[sb]}}p), %zmm0 # 64-byte Reload
; ENABLE-NEXT:    vpxor %xmm1, %xmm1, %xmm1
; ENABLE-NEXT:    vpermpd %zmm2, %zmm0, %zmm1
; ENABLE-NEXT:    vcvtqq2pd %zmm0, %zmm0
; ENABLE-NEXT:    vaddpd %zmm0, %zmm2, %zmm0
; ENABLE-NEXT:    vaddpd %zmm0, %zmm1, %zmm0
; ENABLE-NEXT:    retq
;
; DISABLE-LABEL: permpd_rr_512:
; DISABLE:       # %bb.0:
; DISABLE-NEXT:    vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
; DISABLE-NEXT:    #APP
; DISABLE-NEXT:    nop
; DISABLE-NEXT:    #NO_APP
; DISABLE-NEXT:    vmovapd %zmm0, %zmm2
; DISABLE-NEXT:    vmovupd {{[-0-9]+}}(%r{{[sb]}}p), %zmm0 # 64-byte Reload
; DISABLE-NEXT:    vpermpd %zmm2, %zmm0, %zmm1
; DISABLE-NEXT:    vcvtqq2pd %zmm0, %zmm0
; DISABLE-NEXT:    vaddpd %zmm0, %zmm2, %zmm0
; DISABLE-NEXT:    vaddpd %zmm0, %zmm1, %zmm0
; DISABLE-NEXT:    retq
  %1 = tail call <8 x double> asm sideeffect "nop", "=x,~{xmm1},~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"()
  %2 = call <8 x double> @llvm.x86.avx512.permvar.df.512(<8 x double> %1, <8 x i64> %idx)
  %a1 = sitofp <8 x i64> %idx to <8 x double>
  %t = fadd <8 x double> %1, %a1
  %res = fadd <8 x double> %2, %t
  ret <8 x double> %res
}

define <8 x double> @permpd_rm_512(ptr %p0, <8 x i64> %idx) {
; ENABLE-LABEL: permpd_rm_512:
; ENABLE:       # %bb.0:
; ENABLE-NEXT:    vmovups %zmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
; ENABLE-NEXT:    #APP
; ENABLE-NEXT:    nop
; ENABLE-NEXT:    #NO_APP
; ENABLE-NEXT:    vmovupd {{[-0-9]+}}(%r{{[sb]}}p), %zmm1 # 64-byte Reload
; ENABLE-NEXT:    vpxor %xmm0, %xmm0, %xmm0
; ENABLE-NEXT:    vpermpd (%rdi), %zmm1, %zmm0
; ENABLE-NEXT:    vcvtqq2pd %zmm1, %zmm1
; ENABLE-NEXT:    vaddpd %zmm1, %zmm0, %zmm0
; ENABLE-NEXT:    retq
;
; DISABLE-LABEL: permpd_rm_512:
; DISABLE:       # %bb.0:
; DISABLE-NEXT:    vmovups %zmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
; DISABLE-NEXT:    #APP
; DISABLE-NEXT:    nop
; DISABLE-NEXT:    #NO_APP
; DISABLE-NEXT:    vmovupd {{[-0-9]+}}(%r{{[sb]}}p), %zmm1 # 64-byte Reload
; DISABLE-NEXT:    vpermpd (%rdi), %zmm1, %zmm0
; DISABLE-NEXT:    vcvtqq2pd %zmm1, %zmm1
; DISABLE-NEXT:    vaddpd %zmm1, %zmm0, %zmm0
; DISABLE-NEXT:    retq
  %1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm1},~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"()
  %a0 = load <8 x double>, ptr %p0, align 64
  %2 = call <8 x double> @llvm.x86.avx512.permvar.df.512(<8 x double> %a0, <8 x i64> %idx)
  %a1 = sitofp <8 x i64> %idx to <8 x double>
  %res = fadd <8 x double> %2, %a1
  ret <8 x double> %res
}

define <8 x double> @permpd_broadcast_512(ptr %p0, <8 x i64> %idx) {
; ENABLE-LABEL: permpd_broadcast_512:
; ENABLE:       # %bb.0:
; ENABLE-NEXT:    vmovups %zmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
; ENABLE-NEXT:    #APP
; ENABLE-NEXT:    nop
; ENABLE-NEXT:    #NO_APP
; ENABLE-NEXT:    vmovupd {{[-0-9]+}}(%r{{[sb]}}p), %zmm1 # 64-byte Reload
; ENABLE-NEXT:    vpxor %xmm0, %xmm0, %xmm0
; ENABLE-NEXT:    vpermpd (%rdi){1to8}, %zmm1, %zmm0
; ENABLE-NEXT:    vcvtqq2pd %zmm1, %zmm1
; ENABLE-NEXT:    vaddpd %zmm1, %zmm0, %zmm0
; ENABLE-NEXT:    retq
;
; DISABLE-LABEL: permpd_broadcast_512:
; DISABLE:       # %bb.0:
; DISABLE-NEXT:    vmovups %zmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
; DISABLE-NEXT:    #APP
; DISABLE-NEXT:    nop
; DISABLE-NEXT:    #NO_APP
; DISABLE-NEXT:    vmovupd {{[-0-9]+}}(%r{{[sb]}}p), %zmm1 # 64-byte Reload
; DISABLE-NEXT:    vpermpd (%rdi){1to8}, %zmm1, %zmm0
; DISABLE-NEXT:    vcvtqq2pd %zmm1, %zmm1
; DISABLE-NEXT:    vaddpd %zmm1, %zmm0, %zmm0
; DISABLE-NEXT:    retq
  %1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm1},~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"()
  %v0 = load double, ptr %p0, align 4
  %t0 = insertelement <8 x double> undef, double %v0, i64 0
  %a0 = shufflevector <8 x double> %t0, <8 x double> undef, <8 x i32> zeroinitializer
  %2 = call <8 x double> @llvm.x86.avx512.permvar.df.512(<8 x double> %a0, <8 x i64> %idx)
  %a1 = sitofp <8 x i64> %idx to <8 x double>
  %res = fadd <8 x double> %2, %a1
  ret <8 x double> %res
}

define <8 x double> @permpd_maskz_512(<8 x double> %a0, <8 x i64> %idx, ptr %mask) {
; ENABLE-LABEL: permpd_maskz_512:
; ENABLE:       # %bb.0:
; ENABLE-NEXT:    #APP
; ENABLE-NEXT:    nop
; ENABLE-NEXT:    #NO_APP
; ENABLE-NEXT:    kmovb (%rdi), %k1
; ENABLE-NEXT:    vpxor %xmm2, %xmm2, %xmm2
; ENABLE-NEXT:    vpermpd %zmm0, %zmm1, %zmm2 {%k1} {z}
; ENABLE-NEXT:    vcvtqq2pd %zmm1, %zmm1
; ENABLE-NEXT:    vaddpd %zmm1, %zmm0, %zmm0
; ENABLE-NEXT:    vaddpd %zmm0, %zmm2, %zmm0
; ENABLE-NEXT:    retq
;
; DISABLE-LABEL: permpd_maskz_512:
; DISABLE:       # %bb.0:
; DISABLE-NEXT:    #APP
; DISABLE-NEXT:    nop
; DISABLE-NEXT:    #NO_APP
; DISABLE-NEXT:    kmovb (%rdi), %k1
; DISABLE-NEXT:    vpermpd %zmm0, %zmm1, %zmm2 {%k1} {z}
; DISABLE-NEXT:    vcvtqq2pd %zmm1, %zmm1
; DISABLE-NEXT:    vaddpd %zmm1, %zmm0, %zmm0
; DISABLE-NEXT:    vaddpd %zmm0, %zmm2, %zmm0
; DISABLE-NEXT:    retq
  %1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"()
  %2 = load i8, ptr %mask
  %3 = call <8 x double> @llvm.x86.avx512.mask.permvar.df.512(<8 x double> %a0, <8 x i64> %idx, <8 x double> zeroinitializer, i8 %2)
  %a1 = sitofp <8 x i64> %idx to <8 x double>
  %t = fadd <8 x double> %a0, %a1
  %res = fadd <8 x double> %3, %t
  ret <8 x double> %res
}

declare <8 x double> @llvm.x86.avx512.permvar.df.512(<8 x double>, <8 x i64>)
declare <8 x double> @llvm.x86.avx512.mask.permvar.df.512(<8 x double>, <8 x i64>, <8 x double>, i8)


define <8 x float> @permps_rr_256(<8 x float> %a0, <8 x i32> %idx) {
; ENABLE-LABEL: permps_rr_256:
; ENABLE:       # %bb.0:
; ENABLE-NEXT:    vmovups %ymm1, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
; ENABLE-NEXT:    #APP
; ENABLE-NEXT:    nop
; ENABLE-NEXT:    #NO_APP
; ENABLE-NEXT:    vmovaps %ymm0, %ymm2
; ENABLE-NEXT:    vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm0 # 32-byte Reload
; ENABLE-NEXT:    vxorps %xmm1, %xmm1, %xmm1
; ENABLE-NEXT:    vpermps %ymm2, %ymm0, %ymm1
; ENABLE-NEXT:    vcvtdq2ps %ymm0, %ymm0
; ENABLE-NEXT:    vaddps %ymm0, %ymm2, %ymm0
; ENABLE-NEXT:    vaddps %ymm0, %ymm1, %ymm0
; ENABLE-NEXT:    retq
;
; DISABLE-LABEL: permps_rr_256:
; DISABLE:       # %bb.0:
; DISABLE-NEXT:    vmovups %ymm1, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
; DISABLE-NEXT:    #APP
; DISABLE-NEXT:    nop
; DISABLE-NEXT:    #NO_APP
; DISABLE-NEXT:    vmovaps %ymm0, %ymm2
; DISABLE-NEXT:    vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm0 # 32-byte Reload
; DISABLE-NEXT:    vpermps %ymm2, %ymm0, %ymm1
; DISABLE-NEXT:    vcvtdq2ps %ymm0, %ymm0
; DISABLE-NEXT:    vaddps %ymm0, %ymm2, %ymm0
; DISABLE-NEXT:    vaddps %ymm0, %ymm1, %ymm0
; DISABLE-NEXT:    retq
  %1 = tail call <8 x float> asm sideeffect "nop", "=x,~{xmm1},~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"()
  %2 = call <8 x float> @llvm.x86.avx512.mask.permvar.sf.256(<8 x float> %1, <8 x i32> %idx, <8 x float> zeroinitializer, i8 -1)
  %a1 = sitofp <8 x i32> %idx to <8 x float>
  %t = fadd <8 x float> %1, %a1
  %res = fadd <8 x float> %2, %t
  ret <8 x float> %res
}

define <8 x float> @permps_rm_256(ptr %p0, <8 x i32> %idx) {
; ENABLE-LABEL: permps_rm_256:
; ENABLE:       # %bb.0:
; ENABLE-NEXT:    vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
; ENABLE-NEXT:    #APP
; ENABLE-NEXT:    nop
; ENABLE-NEXT:    #NO_APP
; ENABLE-NEXT:    vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm1 # 32-byte Reload
; ENABLE-NEXT:    vxorps %xmm0, %xmm0, %xmm0
; ENABLE-NEXT:    vpermps (%rdi), %ymm1, %ymm0
; ENABLE-NEXT:    vcvtdq2ps %ymm1, %ymm1
; ENABLE-NEXT:    vaddps %ymm1, %ymm0, %ymm0
; ENABLE-NEXT:    retq
;
; DISABLE-LABEL: permps_rm_256:
; DISABLE:       # %bb.0:
; DISABLE-NEXT:    vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
; DISABLE-NEXT:    #APP
; DISABLE-NEXT:    nop
; DISABLE-NEXT:    #NO_APP
; DISABLE-NEXT:    vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm1 # 32-byte Reload
; DISABLE-NEXT:    vpermps (%rdi), %ymm1, %ymm0
; DISABLE-NEXT:    vcvtdq2ps %ymm1, %ymm1
; DISABLE-NEXT:    vaddps %ymm1, %ymm0, %ymm0
; DISABLE-NEXT:    retq
  %1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm1},~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"()
  %a0 = load <8 x float>, ptr %p0, align 64
  %2 = call <8 x float> @llvm.x86.avx512.mask.permvar.sf.256(<8 x float> %a0, <8 x i32> %idx, <8 x float> zeroinitializer, i8 -1)
  %a1 = sitofp <8 x i32> %idx to <8 x float>
  %res = fadd <8 x float> %2, %a1
  ret <8 x float> %res
}

define <8 x float> @permps_broadcast_256(ptr %p0, <8 x i32> %idx) {
; ENABLE-LABEL: permps_broadcast_256:
; ENABLE:       # %bb.0:
; ENABLE-NEXT:    vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
; ENABLE-NEXT:    #APP
; ENABLE-NEXT:    nop
; ENABLE-NEXT:    #NO_APP
; ENABLE-NEXT:    vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm1 # 32-byte Reload
; ENABLE-NEXT:    vxorps %xmm0, %xmm0, %xmm0
; ENABLE-NEXT:    vpermps (%rdi){1to8}, %ymm1, %ymm0
; ENABLE-NEXT:    vcvtdq2ps %ymm1, %ymm1
; ENABLE-NEXT:    vaddps %ymm1, %ymm0, %ymm0
; ENABLE-NEXT:    retq
;
; DISABLE-LABEL: permps_broadcast_256:
; DISABLE:       # %bb.0:
; DISABLE-NEXT:    vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
; DISABLE-NEXT:    #APP
; DISABLE-NEXT:    nop
; DISABLE-NEXT:    #NO_APP
; DISABLE-NEXT:    vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm1 # 32-byte Reload
; DISABLE-NEXT:    vpermps (%rdi){1to8}, %ymm1, %ymm0
; DISABLE-NEXT:    vcvtdq2ps %ymm1, %ymm1
; DISABLE-NEXT:    vaddps %ymm1, %ymm0, %ymm0
; DISABLE-NEXT:    retq
  %1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm1},~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"()
  %v0 = load float, ptr %p0, align 4
  %t0 = insertelement <8 x float> undef, float %v0, i32 0
  %a0 = shufflevector <8 x float> %t0, <8 x float> undef, <8 x i32> zeroinitializer
  %2 = call <8 x float> @llvm.x86.avx512.mask.permvar.sf.256(<8 x float> %a0, <8 x i32> %idx, <8 x float> zeroinitializer, i8 -1)
  %a1 = sitofp <8 x i32> %idx to <8 x float>
  %res = fadd <8 x float> %2, %a1
  ret <8 x float> %res
}

define <8 x float> @permps_maskz_256(<8 x float> %a0, <8 x i32> %idx, ptr %mask) {
; ENABLE-LABEL: permps_maskz_256:
; ENABLE:       # %bb.0:
; ENABLE-NEXT:    #APP
; ENABLE-NEXT:    nop
; ENABLE-NEXT:    #NO_APP
; ENABLE-NEXT:    kmovb (%rdi), %k1
; ENABLE-NEXT:    vxorps %xmm2, %xmm2, %xmm2
; ENABLE-NEXT:    vpermps %ymm0, %ymm1, %ymm2 {%k1} {z}
; ENABLE-NEXT:    vcvtdq2ps %ymm1, %ymm1
; ENABLE-NEXT:    vaddps %ymm1, %ymm0, %ymm0
; ENABLE-NEXT:    vaddps %ymm0, %ymm2, %ymm0
; ENABLE-NEXT:    retq
;
; DISABLE-LABEL: permps_maskz_256:
; DISABLE:       # %bb.0:
; DISABLE-NEXT:    #APP
; DISABLE-NEXT:    nop
; DISABLE-NEXT:    #NO_APP
; DISABLE-NEXT:    kmovb (%rdi), %k1
; DISABLE-NEXT:    vpermps %ymm0, %ymm1, %ymm2 {%k1} {z}
; DISABLE-NEXT:    vcvtdq2ps %ymm1, %ymm1
; DISABLE-NEXT:    vaddps %ymm1, %ymm0, %ymm0
; DISABLE-NEXT:    vaddps %ymm0, %ymm2, %ymm0
; DISABLE-NEXT:    retq
  %1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"()
  %2 = load i8, ptr %mask
  %3 = call <8 x float> @llvm.x86.avx512.mask.permvar.sf.256(<8 x float> %a0, <8 x i32> %idx, <8 x float> zeroinitializer, i8 %2)
  %a1 = sitofp <8 x i32> %idx to <8 x float>
  %t = fadd <8 x float> %a0, %a1
  %res = fadd <8 x float> %3, %t
  ret <8 x float> %res
}

declare <8 x float> @llvm.x86.avx512.mask.permvar.sf.256(<8 x float>, <8 x i32>, <8 x float>, i8)

define <16 x float> @permps_rr_512(<16 x float> %a0, <16 x i32> %idx) {
; ENABLE-LABEL: permps_rr_512:
; ENABLE:       # %bb.0:
; ENABLE-NEXT:    vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
; ENABLE-NEXT:    #APP
; ENABLE-NEXT:    nop
; ENABLE-NEXT:    #NO_APP
; ENABLE-NEXT:    vmovaps %zmm0, %zmm2
; ENABLE-NEXT:    vmovups {{[-0-9]+}}(%r{{[sb]}}p), %zmm0 # 64-byte Reload
; ENABLE-NEXT:    vpxor %xmm1, %xmm1, %xmm1
; ENABLE-NEXT:    vpermps %zmm2, %zmm0, %zmm1
; ENABLE-NEXT:    vcvtdq2ps %zmm0, %zmm0
; ENABLE-NEXT:    vaddps %zmm0, %zmm2, %zmm0
; ENABLE-NEXT:    vaddps %zmm0, %zmm1, %zmm0
; ENABLE-NEXT:    retq
;
; DISABLE-LABEL: permps_rr_512:
; DISABLE:       # %bb.0:
; DISABLE-NEXT:    vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
; DISABLE-NEXT:    #APP
; DISABLE-NEXT:    nop
; DISABLE-NEXT:    #NO_APP
; DISABLE-NEXT:    vmovaps %zmm0, %zmm2
; DISABLE-NEXT:    vmovups {{[-0-9]+}}(%r{{[sb]}}p), %zmm0 # 64-byte Reload
; DISABLE-NEXT:    vpermps %zmm2, %zmm0, %zmm1
; DISABLE-NEXT:    vcvtdq2ps %zmm0, %zmm0
; DISABLE-NEXT:    vaddps %zmm0, %zmm2, %zmm0
; DISABLE-NEXT:    vaddps %zmm0, %zmm1, %zmm0
; DISABLE-NEXT:    retq
  %1 = tail call <16 x float> asm sideeffect "nop", "=x,~{xmm1},~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"()
  %2 = call <16 x float> @llvm.x86.avx512.permvar.sf.512(<16 x float> %1, <16 x i32> %idx)
  %a1 = sitofp <16 x i32> %idx to <16 x float>
  %t = fadd <16 x float> %1, %a1
  %res = fadd <16 x float> %2, %t
  ret <16 x float> %res
}

define <16 x float> @permps_rm_512(ptr %p0, <16 x i32> %idx) {
; ENABLE-LABEL: permps_rm_512:
; ENABLE:       # %bb.0:
; ENABLE-NEXT:    vmovups %zmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
; ENABLE-NEXT:    #APP
; ENABLE-NEXT:    nop
; ENABLE-NEXT:    #NO_APP
; ENABLE-NEXT:    vmovups {{[-0-9]+}}(%r{{[sb]}}p), %zmm1 # 64-byte Reload
; ENABLE-NEXT:    vpxor %xmm0, %xmm0, %xmm0
; ENABLE-NEXT:    vpermps (%rdi), %zmm1, %zmm0
; ENABLE-NEXT:    vcvtdq2ps %zmm1, %zmm1
; ENABLE-NEXT:    vaddps %zmm1, %zmm0, %zmm0
; ENABLE-NEXT:    retq
;
; DISABLE-LABEL: permps_rm_512:
; DISABLE:       # %bb.0:
; DISABLE-NEXT:    vmovups %zmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
; DISABLE-NEXT:    #APP
; DISABLE-NEXT:    nop
; DISABLE-NEXT:    #NO_APP
; DISABLE-NEXT:    vmovups {{[-0-9]+}}(%r{{[sb]}}p), %zmm1 # 64-byte Reload
; DISABLE-NEXT:    vpermps (%rdi), %zmm1, %zmm0
; DISABLE-NEXT:    vcvtdq2ps %zmm1, %zmm1
; DISABLE-NEXT:    vaddps %zmm1, %zmm0, %zmm0
; DISABLE-NEXT:    retq
  %1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm1},~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"()
  %a0 = load <16 x float>, ptr %p0, align 64
  %2 = call <16 x float> @llvm.x86.avx512.permvar.sf.512(<16 x float> %a0, <16 x i32> %idx)
  %a1 = sitofp <16 x i32> %idx to <16 x float>
  %res = fadd <16 x float> %2, %a1
  ret <16 x float> %res
}

define <16 x float> @permps_broadcast_512(ptr %p0, <16 x i32> %idx) {
; ENABLE-LABEL: permps_broadcast_512:
; ENABLE:       # %bb.0:
; ENABLE-NEXT:    vmovups %zmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
; ENABLE-NEXT:    #APP
; ENABLE-NEXT:    nop
; ENABLE-NEXT:    #NO_APP
; ENABLE-NEXT:    vmovups {{[-0-9]+}}(%r{{[sb]}}p), %zmm1 # 64-byte Reload
; ENABLE-NEXT:    vpxor %xmm0, %xmm0, %xmm0
; ENABLE-NEXT:    vpermps (%rdi){1to16}, %zmm1, %zmm0
; ENABLE-NEXT:    vcvtdq2ps %zmm1, %zmm1
; ENABLE-NEXT:    vaddps %zmm1, %zmm0, %zmm0
; ENABLE-NEXT:    retq
;
; DISABLE-LABEL: permps_broadcast_512:
; DISABLE:       # %bb.0:
; DISABLE-NEXT:    vmovups %zmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
; DISABLE-NEXT:    #APP
; DISABLE-NEXT:    nop
; DISABLE-NEXT:    #NO_APP
; DISABLE-NEXT:    vmovups {{[-0-9]+}}(%r{{[sb]}}p), %zmm1 # 64-byte Reload
; DISABLE-NEXT:    vpermps (%rdi){1to16}, %zmm1, %zmm0
; DISABLE-NEXT:    vcvtdq2ps %zmm1, %zmm1
; DISABLE-NEXT:    vaddps %zmm1, %zmm0, %zmm0
; DISABLE-NEXT:    retq
  %1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm1},~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"()
  %v0 = load float, ptr %p0, align 4
  %t0 = insertelement <16 x float> undef, float %v0, i32 0
  %a0 = shufflevector <16 x float> %t0, <16 x float> undef, <16 x i32> zeroinitializer
  %2 = call <16 x float> @llvm.x86.avx512.permvar.sf.512(<16 x float> %a0, <16 x i32> %idx)
  %a1 = sitofp <16 x i32> %idx to <16 x float>
  %res = fadd <16 x float> %2, %a1
  ret <16 x float> %res
}

define <16 x float> @permps_maskz_512(<16 x float> %a0, <16 x i32> %idx, ptr %mask) {
; ENABLE-LABEL: permps_maskz_512:
; ENABLE:       # %bb.0:
; ENABLE-NEXT:    #APP
; ENABLE-NEXT:    nop
; ENABLE-NEXT:    #NO_APP
; ENABLE-NEXT:    kmovw (%rdi), %k1
; ENABLE-NEXT:    vpxor %xmm2, %xmm2, %xmm2
; ENABLE-NEXT:    vpermps %zmm0, %zmm1, %zmm2 {%k1} {z}
; ENABLE-NEXT:    vcvtdq2ps %zmm1, %zmm1
; ENABLE-NEXT:    vaddps %zmm1, %zmm0, %zmm0
; ENABLE-NEXT:    vaddps %zmm0, %zmm2, %zmm0
; ENABLE-NEXT:    retq
;
; DISABLE-LABEL: permps_maskz_512:
; DISABLE:       # %bb.0:
; DISABLE-NEXT:    #APP
; DISABLE-NEXT:    nop
; DISABLE-NEXT:    #NO_APP
; DISABLE-NEXT:    kmovw (%rdi), %k1
; DISABLE-NEXT:    vpermps %zmm0, %zmm1, %zmm2 {%k1} {z}
; DISABLE-NEXT:    vcvtdq2ps %zmm1, %zmm1
; DISABLE-NEXT:    vaddps %zmm1, %zmm0, %zmm0
; DISABLE-NEXT:    vaddps %zmm0, %zmm2, %zmm0
; DISABLE-NEXT:    retq
  %1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{xmm16},~{xmm17},~{xmm18},~{xmm19},~{xmm20},~{xmm21},~{xmm22},~{xmm23},~{xmm24},~{xmm25},~{xmm26},~{xmm27},~{xmm28},~{xmm29},~{xmm30},~{xmm31},~{flags}"()
  %2 = load i16, ptr %mask
  %3 = call <16 x float> @llvm.x86.avx512.mask.permvar.sf.512(<16 x float> %a0, <16 x i32> %idx, <16 x float> zeroinitializer, i16 %2)
  %a1 = sitofp <16 x i32> %idx to <16 x float>
  %t = fadd <16 x float> %a0, %a1
  %res = fadd <16 x float> %3, %t
  ret <16 x float> %res
}

declare <16 x float> @llvm.x86.avx512.permvar.sf.512(<16 x float>, <16 x i32>)
declare <16 x float> @llvm.x86.avx512.mask.permvar.sf.512(<16 x float>, <16 x i32>, <16 x float>, i16)