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

declare <2 x i64> @llvm.x86.avx512.vpmadd52h.uq.128(<2 x i64>, <2 x i64>, <2 x i64>)
declare <4 x i64> @llvm.x86.avx512.vpmadd52h.uq.256(<4 x i64>, <4 x i64>, <4 x i64>)
declare <2 x i64> @llvm.x86.avx512.vpmadd52l.uq.128(<2 x i64>, <2 x i64>, <2 x i64>)
declare <4 x i64> @llvm.x86.avx512.vpmadd52l.uq.256(<4 x i64>, <4 x i64>, <4 x i64>)

define <2 x i64> @stack_fold_vpmadd52huq(<2 x i64> %a0, <2 x i64> %a1, <2 x i64> %a2) {
; CHECK-LABEL: stack_fold_vpmadd52huq:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vmovaps %xmm2, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; CHECK-NEXT:    #APP
; CHECK-NEXT:    nop
; CHECK-NEXT:    #NO_APP
; CHECK-NEXT:    {vex} vpmadd52huq {{[-0-9]+}}(%r{{[sb]}}p), %xmm1, %xmm0 # 16-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},~{flags}"()
  %2 = call <2 x i64> @llvm.x86.avx512.vpmadd52h.uq.128(<2 x i64> %a0, <2 x i64> %a1, <2 x i64> %a2)
  ret <2 x i64> %2
}

define <2 x i64> @stack_fold_vpmadd52huq_commuted(<2 x i64> %a0, <2 x i64> %a1, <2 x i64> %a2) {
; CHECK-LABEL: stack_fold_vpmadd52huq_commuted:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vmovaps %xmm2, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; CHECK-NEXT:    #APP
; CHECK-NEXT:    nop
; CHECK-NEXT:    #NO_APP
; CHECK-NEXT:    {vex} vpmadd52huq {{[-0-9]+}}(%r{{[sb]}}p), %xmm1, %xmm0 # 16-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},~{flags}"()
  %2 = call <2 x i64> @llvm.x86.avx512.vpmadd52h.uq.128(<2 x i64> %a0, <2 x i64> %a2, <2 x i64> %a1)
  ret <2 x i64> %2
}

define <4 x i64> @stack_fold_vpmadd52huq_256(<4 x i64> %a0, <4 x i64> %a1, <4 x i64> %a2) {
; CHECK-LABEL: stack_fold_vpmadd52huq_256:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vmovups %ymm2, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
; CHECK-NEXT:    #APP
; CHECK-NEXT:    nop
; CHECK-NEXT:    #NO_APP
; CHECK-NEXT:    {vex} vpmadd52huq {{[-0-9]+}}(%r{{[sb]}}p), %ymm1, %ymm0 # 32-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},~{flags}"()
  %2 = call <4 x i64> @llvm.x86.avx512.vpmadd52h.uq.256(<4 x i64> %a0, <4 x i64> %a1, <4 x i64> %a2)
  ret <4 x i64> %2
}

define <4 x i64> @stack_fold_vpmadd52huq_256_commuted(<4 x i64> %a0, <4 x i64> %a1, <4 x i64> %a2) {
; CHECK-LABEL: stack_fold_vpmadd52huq_256_commuted:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vmovups %ymm2, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
; CHECK-NEXT:    #APP
; CHECK-NEXT:    nop
; CHECK-NEXT:    #NO_APP
; CHECK-NEXT:    {vex} vpmadd52huq {{[-0-9]+}}(%r{{[sb]}}p), %ymm1, %ymm0 # 32-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},~{flags}"()
  %2 = call <4 x i64> @llvm.x86.avx512.vpmadd52h.uq.256(<4 x i64> %a0, <4 x i64> %a2, <4 x i64> %a1)
  ret <4 x i64> %2
}

define <2 x i64> @stack_fold_vpmadd52luq(<2 x i64> %a0, <2 x i64> %a1, <2 x i64> %a2) {
; CHECK-LABEL: stack_fold_vpmadd52luq:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vmovaps %xmm2, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; CHECK-NEXT:    #APP
; CHECK-NEXT:    nop
; CHECK-NEXT:    #NO_APP
; CHECK-NEXT:    {vex} vpmadd52luq {{[-0-9]+}}(%r{{[sb]}}p), %xmm1, %xmm0 # 16-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},~{flags}"()
  %2 = call <2 x i64> @llvm.x86.avx512.vpmadd52l.uq.128(<2 x i64> %a0, <2 x i64> %a1, <2 x i64> %a2)
  ret <2 x i64> %2
}

define <2 x i64> @stack_fold_vpmadd52luq_commuted(<2 x i64> %a0, <2 x i64> %a1, <2 x i64> %a2) {
; CHECK-LABEL: stack_fold_vpmadd52luq_commuted:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vmovaps %xmm2, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; CHECK-NEXT:    #APP
; CHECK-NEXT:    nop
; CHECK-NEXT:    #NO_APP
; CHECK-NEXT:    {vex} vpmadd52luq {{[-0-9]+}}(%r{{[sb]}}p), %xmm1, %xmm0 # 16-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},~{flags}"()
  %2 = call <2 x i64> @llvm.x86.avx512.vpmadd52l.uq.128(<2 x i64> %a0, <2 x i64> %a2, <2 x i64> %a1)
  ret <2 x i64> %2
}

define <4 x i64> @stack_fold_vpmadd52luq_256(<4 x i64> %a0, <4 x i64> %a1, <4 x i64> %a2) {
; CHECK-LABEL: stack_fold_vpmadd52luq_256:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vmovups %ymm2, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
; CHECK-NEXT:    #APP
; CHECK-NEXT:    nop
; CHECK-NEXT:    #NO_APP
; CHECK-NEXT:    {vex} vpmadd52luq {{[-0-9]+}}(%r{{[sb]}}p), %ymm1, %ymm0 # 32-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},~{flags}"()
  %2 = call <4 x i64> @llvm.x86.avx512.vpmadd52l.uq.256(<4 x i64> %a0, <4 x i64> %a1, <4 x i64> %a2)
  ret <4 x i64> %2
}

define <4 x i64> @stack_fold_vpmadd52luq_256_commuted(<4 x i64> %a0, <4 x i64> %a1, <4 x i64> %a2) {
; CHECK-LABEL: stack_fold_vpmadd52luq_256_commuted:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vmovups %ymm2, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
; CHECK-NEXT:    #APP
; CHECK-NEXT:    nop
; CHECK-NEXT:    #NO_APP
; CHECK-NEXT:    {vex} vpmadd52luq {{[-0-9]+}}(%r{{[sb]}}p), %ymm1, %ymm0 # 32-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},~{flags}"()
  %2 = call <4 x i64> @llvm.x86.avx512.vpmadd52l.uq.256(<4 x i64> %a0, <4 x i64> %a2, <4 x i64> %a1)
  ret <4 x i64> %2
}