; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -O3 -disable-peephole -mtriple=x86_64-unknown-unknown -mattr=+avx512ifma,+avx512vl < %s | FileCheck %s

declare <8 x i64> @llvm.x86.avx512.vpmadd52h.uq.512(<8 x i64>, <8 x i64>, <8 x i64>)
declare <8 x i64> @llvm.x86.avx512.vpmadd52l.uq.512(<8 x i64>, <8 x i64>, <8 x i64>)

define <8 x i64> @stack_fold_vpmadd52huq(<8 x i64> %a0, <8 x i64> %a1, <8 x i64> %a2) {
; CHECK-LABEL: stack_fold_vpmadd52huq:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vmovups %zmm2, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
; CHECK-NEXT:    #APP
; CHECK-NEXT:    nop
; CHECK-NEXT:    #NO_APP
; CHECK-NEXT:    vpmadd52huq {{[-0-9]+}}(%r{{[sb]}}p), %zmm1, %zmm0 # 64-byte Folded Reload
; CHECK-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 = call <8 x i64> @llvm.x86.avx512.vpmadd52h.uq.512(<8 x i64> %a0, <8 x i64> %a1, <8 x i64> %a2)
  ret <8 x i64> %2
}

define <8 x i64> @stack_fold_vpmadd52huq_commuted(<8 x i64> %a0, <8 x i64> %a1, <8 x i64> %a2) {
; CHECK-LABEL: stack_fold_vpmadd52huq_commuted:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vmovups %zmm2, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
; CHECK-NEXT:    #APP
; CHECK-NEXT:    nop
; CHECK-NEXT:    #NO_APP
; CHECK-NEXT:    vpmadd52huq {{[-0-9]+}}(%r{{[sb]}}p), %zmm1, %zmm0 # 64-byte Folded Reload
; CHECK-NEXT:    retq
  %1 = tail call <8 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 = call <8 x i64> @llvm.x86.avx512.vpmadd52h.uq.512(<8 x i64> %a0, <8 x i64> %a2, <8 x i64> %a1)
  ret <8 x i64> %2
}

define <8 x i64> @stack_fold_vpmadd52huq_mask(ptr %a0, <8 x i64> %a1, <8 x i64> %a2, i8 %mask) {
; CHECK-LABEL: stack_fold_vpmadd52huq_mask:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
; CHECK-NEXT:    #APP
; CHECK-NEXT:    nop
; CHECK-NEXT:    #NO_APP
; CHECK-NEXT:    vmovdqa64 (%rdi), %zmm2
; CHECK-NEXT:    kmovw %esi, %k1
; CHECK-NEXT:    vpmadd52huq {{[-0-9]+}}(%r{{[sb]}}p), %zmm0, %zmm2 {%k1} # 64-byte Folded Reload
; CHECK-NEXT:    vmovdqa64 %zmm2, %zmm0
; CHECK-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 = load <8 x i64>, ptr %a0
  %3 = call <8 x i64> @llvm.x86.avx512.vpmadd52h.uq.512(<8 x i64> %2, <8 x i64> %a1, <8 x i64> %a2)
  %4 = bitcast i8 %mask to <8 x i1>
  %5 = select <8 x i1> %4, <8 x i64> %3, <8 x i64> %2
  ret <8 x i64> %5
}

define <8 x i64> @stack_fold_vpmadd52huq_mask_commuted(ptr %a0, <8 x i64> %a1, <8 x i64> %a2, i8 %mask) {
; CHECK-LABEL: stack_fold_vpmadd52huq_mask_commuted:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
; CHECK-NEXT:    #APP
; CHECK-NEXT:    nop
; CHECK-NEXT:    #NO_APP
; CHECK-NEXT:    vmovdqa64 (%rdi), %zmm2
; CHECK-NEXT:    kmovw %esi, %k1
; CHECK-NEXT:    vpmadd52huq {{[-0-9]+}}(%r{{[sb]}}p), %zmm0, %zmm2 {%k1} # 64-byte Folded Reload
; CHECK-NEXT:    vmovdqa64 %zmm2, %zmm0
; CHECK-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 = load <8 x i64>, ptr %a0
  %3 = call <8 x i64> @llvm.x86.avx512.vpmadd52h.uq.512(<8 x i64> %2, <8 x i64> %a2, <8 x i64> %a1)
  %4 = bitcast i8 %mask to <8 x i1>
  %5 = select <8 x i1> %4, <8 x i64> %3, <8 x i64> %2
  ret <8 x i64> %5
}

define <8 x i64> @stack_fold_vpmadd52huq_maskz(<8 x i64> %a0, <8 x i64> %a1, <8 x i64> %a2, ptr %mask) {
; CHECK-LABEL: stack_fold_vpmadd52huq_maskz:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vmovups %zmm2, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
; CHECK-NEXT:    #APP
; CHECK-NEXT:    nop
; CHECK-NEXT:    #NO_APP
; CHECK-NEXT:    movzbl (%rdi), %eax
; CHECK-NEXT:    kmovw %eax, %k1
; CHECK-NEXT:    vpmadd52huq {{[-0-9]+}}(%r{{[sb]}}p), %zmm1, %zmm0 {%k1} {z} # 64-byte Folded Reload
; CHECK-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 = call <8 x i64> @llvm.x86.avx512.vpmadd52h.uq.512(<8 x i64> %a0, <8 x i64> %a1, <8 x i64> %a2)
  %3 = load i8, ptr %mask
  %4 = bitcast i8 %3 to <8 x i1>
  %5 = select <8 x i1> %4, <8 x i64> %2, <8 x i64> zeroinitializer
  ret <8 x i64> %5
}

define <8 x i64> @stack_fold_vpmadd52huq_maskz_commuted(<8 x i64> %a0, <8 x i64> %a1, <8 x i64> %a2, ptr %mask) {
; CHECK-LABEL: stack_fold_vpmadd52huq_maskz_commuted:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vmovups %zmm2, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
; CHECK-NEXT:    #APP
; CHECK-NEXT:    nop
; CHECK-NEXT:    #NO_APP
; CHECK-NEXT:    movzbl (%rdi), %eax
; CHECK-NEXT:    kmovw %eax, %k1
; CHECK-NEXT:    vpmadd52huq {{[-0-9]+}}(%r{{[sb]}}p), %zmm1, %zmm0 {%k1} {z} # 64-byte Folded Reload
; CHECK-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 = call <8 x i64> @llvm.x86.avx512.vpmadd52h.uq.512(<8 x i64> %a0, <8 x i64> %a2, <8 x i64> %a1)
  %3 = load i8, ptr %mask
  %4 = bitcast i8 %3 to <8 x i1>
  %5 = select <8 x i1> %4, <8 x i64> %2, <8 x i64> zeroinitializer
  ret <8 x i64> %5
}

define <8 x i64> @stack_fold_vpmadd52luq(<8 x i64> %a0, <8 x i64> %a1, <8 x i64> %a2) {
; CHECK-LABEL: stack_fold_vpmadd52luq:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vmovups %zmm2, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
; CHECK-NEXT:    #APP
; CHECK-NEXT:    nop
; CHECK-NEXT:    #NO_APP
; CHECK-NEXT:    vpmadd52luq {{[-0-9]+}}(%r{{[sb]}}p), %zmm1, %zmm0 # 64-byte Folded Reload
; CHECK-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 = call <8 x i64> @llvm.x86.avx512.vpmadd52l.uq.512(<8 x i64> %a0, <8 x i64> %a1, <8 x i64> %a2)
  ret <8 x i64> %2
}

define <8 x i64> @stack_fold_vpmadd52luq_commuted(<8 x i64> %a0, <8 x i64> %a1, <8 x i64> %a2) {
; CHECK-LABEL: stack_fold_vpmadd52luq_commuted:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vmovups %zmm2, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
; CHECK-NEXT:    #APP
; CHECK-NEXT:    nop
; CHECK-NEXT:    #NO_APP
; CHECK-NEXT:    vpmadd52luq {{[-0-9]+}}(%r{{[sb]}}p), %zmm1, %zmm0 # 64-byte Folded Reload
; CHECK-NEXT:    retq
  %1 = tail call <8 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 = call <8 x i64> @llvm.x86.avx512.vpmadd52l.uq.512(<8 x i64> %a0, <8 x i64> %a2, <8 x i64> %a1)
  ret <8 x i64> %2
}

define <8 x i64> @stack_fold_vpmadd52luq_mask(ptr %a0, <8 x i64> %a1, <8 x i64> %a2, i8 %mask) {
; CHECK-LABEL: stack_fold_vpmadd52luq_mask:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
; CHECK-NEXT:    #APP
; CHECK-NEXT:    nop
; CHECK-NEXT:    #NO_APP
; CHECK-NEXT:    vmovdqa64 (%rdi), %zmm2
; CHECK-NEXT:    kmovw %esi, %k1
; CHECK-NEXT:    vpmadd52luq {{[-0-9]+}}(%r{{[sb]}}p), %zmm0, %zmm2 {%k1} # 64-byte Folded Reload
; CHECK-NEXT:    vmovdqa64 %zmm2, %zmm0
; CHECK-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 = load <8 x i64>, ptr %a0
  %3 = call <8 x i64> @llvm.x86.avx512.vpmadd52l.uq.512(<8 x i64> %2, <8 x i64> %a1, <8 x i64> %a2)
  %4 = bitcast i8 %mask to <8 x i1>
  %5 = select <8 x i1> %4, <8 x i64> %3, <8 x i64> %2
  ret <8 x i64> %5
}

define <8 x i64> @stack_fold_vpmadd52luq_mask_commuted(ptr %a0, <8 x i64> %a1, <8 x i64> %a2, i8 %mask) {
; CHECK-LABEL: stack_fold_vpmadd52luq_mask_commuted:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vmovups %zmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
; CHECK-NEXT:    #APP
; CHECK-NEXT:    nop
; CHECK-NEXT:    #NO_APP
; CHECK-NEXT:    vmovdqa64 (%rdi), %zmm2
; CHECK-NEXT:    kmovw %esi, %k1
; CHECK-NEXT:    vpmadd52luq {{[-0-9]+}}(%r{{[sb]}}p), %zmm0, %zmm2 {%k1} # 64-byte Folded Reload
; CHECK-NEXT:    vmovdqa64 %zmm2, %zmm0
; CHECK-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 = load <8 x i64>, ptr %a0
  %3 = call <8 x i64> @llvm.x86.avx512.vpmadd52l.uq.512(<8 x i64> %2, <8 x i64> %a2, <8 x i64> %a1)
  %4 = bitcast i8 %mask to <8 x i1>
  %5 = select <8 x i1> %4, <8 x i64> %3, <8 x i64> %2
  ret <8 x i64> %5
}

define <8 x i64> @stack_fold_vpmadd52luq_maskz(<8 x i64> %a0, <8 x i64> %a1, <8 x i64> %a2, ptr %mask) {
; CHECK-LABEL: stack_fold_vpmadd52luq_maskz:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vmovups %zmm2, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
; CHECK-NEXT:    #APP
; CHECK-NEXT:    nop
; CHECK-NEXT:    #NO_APP
; CHECK-NEXT:    movzbl (%rdi), %eax
; CHECK-NEXT:    kmovw %eax, %k1
; CHECK-NEXT:    vpmadd52luq {{[-0-9]+}}(%r{{[sb]}}p), %zmm1, %zmm0 {%k1} {z} # 64-byte Folded Reload
; CHECK-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 = call <8 x i64> @llvm.x86.avx512.vpmadd52l.uq.512(<8 x i64> %a0, <8 x i64> %a1, <8 x i64> %a2)
  %3 = load i8, ptr %mask
  %4 = bitcast i8 %3 to <8 x i1>
  %5 = select <8 x i1> %4, <8 x i64> %2, <8 x i64> zeroinitializer
  ret <8 x i64> %5
}

define <8 x i64> @stack_fold_vpmadd52luq_maskz_commuted(<8 x i64> %a0, <8 x i64> %a1, <8 x i64> %a2, ptr %mask) {
; CHECK-LABEL: stack_fold_vpmadd52luq_maskz_commuted:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vmovups %zmm2, {{[-0-9]+}}(%r{{[sb]}}p) # 64-byte Spill
; CHECK-NEXT:    #APP
; CHECK-NEXT:    nop
; CHECK-NEXT:    #NO_APP
; CHECK-NEXT:    movzbl (%rdi), %eax
; CHECK-NEXT:    kmovw %eax, %k1
; CHECK-NEXT:    vpmadd52luq {{[-0-9]+}}(%r{{[sb]}}p), %zmm1, %zmm0 {%k1} {z} # 64-byte Folded Reload
; CHECK-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 = call <8 x i64> @llvm.x86.avx512.vpmadd52l.uq.512(<8 x i64> %a0, <8 x i64> %a2, <8 x i64> %a1)
  %3 = load i8, ptr %mask
  %4 = bitcast i8 %3 to <8 x i1>
  %5 = select <8 x i1> %4, <8 x i64> %2, <8 x i64> zeroinitializer
  ret <8 x i64> %5
}