llvm/test/CodeGen/X86/perm.avx2-false-deps.ll

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

define <8 x i32> @permd(<8 x i32> %a0, <8 x i32> %a1) {
; ENABLE-ADL-LABEL: permd:
; ENABLE-ADL:       # %bb.0:
; ENABLE-ADL-NEXT:    vmovups %ymm1, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
; ENABLE-ADL-NEXT:    vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
; ENABLE-ADL-NEXT:    #APP
; ENABLE-ADL-NEXT:    nop
; ENABLE-ADL-NEXT:    #NO_APP
; ENABLE-ADL-NEXT:    vmovdqu {{[-0-9]+}}(%r{{[sb]}}p), %ymm1 # 32-byte Reload
; ENABLE-ADL-NEXT:    vmovdqu {{[-0-9]+}}(%r{{[sb]}}p), %ymm2 # 32-byte Reload
; ENABLE-ADL-NEXT:    vxorps %xmm0, %xmm0, %xmm0
; ENABLE-ADL-NEXT:    vpermd %ymm2, %ymm1, %ymm0
; ENABLE-ADL-NEXT:    vpaddd %ymm1, %ymm2, %ymm1
; ENABLE-ADL-NEXT:    vpaddd %ymm1, %ymm0, %ymm0
; ENABLE-ADL-NEXT:    retq
;
; ENABLE-SPR-LABEL: permd:
; ENABLE-SPR:       # %bb.0:
; ENABLE-SPR-NEXT:    vmovdqa64 %ymm1, %ymm16
; ENABLE-SPR-NEXT:    vmovdqa64 %ymm0, %ymm17
; ENABLE-SPR-NEXT:    #APP
; ENABLE-SPR-NEXT:    nop
; ENABLE-SPR-NEXT:    #NO_APP
; ENABLE-SPR-NEXT:    vxorps %xmm0, %xmm0, %xmm0
; ENABLE-SPR-NEXT:    vpermd %ymm17, %ymm16, %ymm0
; ENABLE-SPR-NEXT:    vpaddd %ymm16, %ymm17, %ymm1
; ENABLE-SPR-NEXT:    vpaddd %ymm1, %ymm0, %ymm0
; ENABLE-SPR-NEXT:    retq
;
; DISABLE-ADL-LABEL: permd:
; DISABLE-ADL:       # %bb.0:
; DISABLE-ADL-NEXT:    vmovups %ymm1, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
; DISABLE-ADL-NEXT:    vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
; DISABLE-ADL-NEXT:    #APP
; DISABLE-ADL-NEXT:    nop
; DISABLE-ADL-NEXT:    #NO_APP
; DISABLE-ADL-NEXT:    vmovdqu {{[-0-9]+}}(%r{{[sb]}}p), %ymm1 # 32-byte Reload
; DISABLE-ADL-NEXT:    vmovdqu {{[-0-9]+}}(%r{{[sb]}}p), %ymm2 # 32-byte Reload
; DISABLE-ADL-NEXT:    vpermd %ymm2, %ymm1, %ymm0
; DISABLE-ADL-NEXT:    vpaddd %ymm1, %ymm2, %ymm1
; DISABLE-ADL-NEXT:    vpaddd %ymm1, %ymm0, %ymm0
; DISABLE-ADL-NEXT:    retq
;
; DISABLE-SPR-LABEL: permd:
; DISABLE-SPR:       # %bb.0:
; DISABLE-SPR-NEXT:    vmovdqa64 %ymm1, %ymm16
; DISABLE-SPR-NEXT:    vmovdqa64 %ymm0, %ymm17
; DISABLE-SPR-NEXT:    #APP
; DISABLE-SPR-NEXT:    nop
; DISABLE-SPR-NEXT:    #NO_APP
; DISABLE-SPR-NEXT:    vpermd %ymm17, %ymm16, %ymm0
; DISABLE-SPR-NEXT:    vpaddd %ymm16, %ymm17, %ymm1
; DISABLE-SPR-NEXT:    vpaddd %ymm1, %ymm0, %ymm0
; DISABLE-SPR-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},~{flags}"()
  %2 = call <8 x i32> @llvm.x86.avx2.permd(<8 x i32> %a0, <8 x i32> %a1)
  %3 = add <8 x i32> %a0, %a1
  %res = add <8 x i32> %2, %3
  ret <8 x i32> %res
}

define <8 x i32> @permd_mem(ptr %p0, <8 x i32> %a1) {
; ENABLE-ADL-LABEL: permd_mem:
; ENABLE-ADL:       # %bb.0:
; ENABLE-ADL-NEXT:    vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
; ENABLE-ADL-NEXT:    #APP
; ENABLE-ADL-NEXT:    nop
; ENABLE-ADL-NEXT:    #NO_APP
; ENABLE-ADL-NEXT:    vmovdqu {{[-0-9]+}}(%r{{[sb]}}p), %ymm1 # 32-byte Reload
; ENABLE-ADL-NEXT:    vxorps %xmm0, %xmm0, %xmm0
; ENABLE-ADL-NEXT:    vpermd (%rdi), %ymm1, %ymm0
; ENABLE-ADL-NEXT:    vpaddd %ymm1, %ymm0, %ymm0
; ENABLE-ADL-NEXT:    retq
;
; ENABLE-SPR-LABEL: permd_mem:
; ENABLE-SPR:       # %bb.0:
; ENABLE-SPR-NEXT:    vmovdqa64 %ymm0, %ymm16
; ENABLE-SPR-NEXT:    #APP
; ENABLE-SPR-NEXT:    nop
; ENABLE-SPR-NEXT:    #NO_APP
; ENABLE-SPR-NEXT:    vxorps %xmm0, %xmm0, %xmm0
; ENABLE-SPR-NEXT:    vpermd (%rdi), %ymm16, %ymm0
; ENABLE-SPR-NEXT:    vpaddd %ymm16, %ymm0, %ymm0
; ENABLE-SPR-NEXT:    retq
;
; DISABLE-ADL-LABEL: permd_mem:
; DISABLE-ADL:       # %bb.0:
; DISABLE-ADL-NEXT:    vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
; DISABLE-ADL-NEXT:    #APP
; DISABLE-ADL-NEXT:    nop
; DISABLE-ADL-NEXT:    #NO_APP
; DISABLE-ADL-NEXT:    vmovdqu {{[-0-9]+}}(%r{{[sb]}}p), %ymm1 # 32-byte Reload
; DISABLE-ADL-NEXT:    vpermd (%rdi), %ymm1, %ymm0
; DISABLE-ADL-NEXT:    vpaddd %ymm1, %ymm0, %ymm0
; DISABLE-ADL-NEXT:    retq
;
; DISABLE-SPR-LABEL: permd_mem:
; DISABLE-SPR:       # %bb.0:
; DISABLE-SPR-NEXT:    vmovdqa64 %ymm0, %ymm16
; DISABLE-SPR-NEXT:    #APP
; DISABLE-SPR-NEXT:    nop
; DISABLE-SPR-NEXT:    #NO_APP
; DISABLE-SPR-NEXT:    vpermd (%rdi), %ymm16, %ymm0
; DISABLE-SPR-NEXT:    vpaddd %ymm16, %ymm0, %ymm0
; DISABLE-SPR-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},~{flags}"()
  %a0 = load <8 x i32>, ptr %p0, align 64
  %2 = call <8 x i32> @llvm.x86.avx2.permd(<8 x i32> %a0, <8 x i32> %a1)
  %res = add <8 x i32> %2, %a1
  ret <8 x i32> %res
}

declare <8 x i32> @llvm.x86.avx2.permd(<8 x i32>, <8 x i32>) nounwind readonly

define <4 x i64> @permq(<4 x i64> %a0) {
; ENABLE-LABEL: permq:
; 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:
; 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},~{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_mem(ptr %p0) {
; ENABLE-LABEL: permq_mem:
; ENABLE:       # %bb.0:
; ENABLE-NEXT:    #APP
; ENABLE-NEXT:    nop
; ENABLE-NEXT:    #NO_APP
; ENABLE-NEXT:    vxorps %xmm0, %xmm0, %xmm0
; ENABLE-NEXT:    vpermpd {{.*#+}} ymm0 = mem[1,2,1,0]
; ENABLE-NEXT:    retq
;
; DISABLE-LABEL: permq_mem:
; DISABLE:       # %bb.0:
; DISABLE-NEXT:    #APP
; DISABLE-NEXT:    nop
; DISABLE-NEXT:    #NO_APP
; DISABLE-NEXT:    vpermpd {{.*#+}} ymm0 = mem[1,2,1,0]
; 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},~{flags}"()
  %a0 = load <4 x i64>, ptr %p0, align 64
  %2 = shufflevector <4 x i64> %a0, <4 x i64> undef, <4 x i32> <i32 1, i32 2, i32 1, i32 0>
  ret <4 x i64> %2
}

define <8 x float> @permps(<8 x float> %a0, <8 x i32> %a1) {
; ENABLE-ADL-LABEL: permps:
; ENABLE-ADL:       # %bb.0:
; ENABLE-ADL-NEXT:    vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
; ENABLE-ADL-NEXT:    #APP
; ENABLE-ADL-NEXT:    nop
; ENABLE-ADL-NEXT:    #NO_APP
; ENABLE-ADL-NEXT:    vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm2 # 32-byte Reload
; ENABLE-ADL-NEXT:    vxorps %xmm1, %xmm1, %xmm1
; ENABLE-ADL-NEXT:    vpermps %ymm2, %ymm0, %ymm1
; ENABLE-ADL-NEXT:    vcvtdq2ps %ymm0, %ymm0
; ENABLE-ADL-NEXT:    vaddps %ymm2, %ymm0, %ymm0
; ENABLE-ADL-NEXT:    vaddps %ymm0, %ymm1, %ymm0
; ENABLE-ADL-NEXT:    retq
;
; ENABLE-SPR-LABEL: permps:
; ENABLE-SPR:       # %bb.0:
; ENABLE-SPR-NEXT:    vmovaps %ymm0, %ymm16
; ENABLE-SPR-NEXT:    #APP
; ENABLE-SPR-NEXT:    nop
; ENABLE-SPR-NEXT:    #NO_APP
; ENABLE-SPR-NEXT:    vxorps %xmm1, %xmm1, %xmm1
; ENABLE-SPR-NEXT:    vpermps %ymm16, %ymm0, %ymm1
; ENABLE-SPR-NEXT:    vcvtdq2ps %ymm0, %ymm0
; ENABLE-SPR-NEXT:    vaddps %ymm16, %ymm0, %ymm0
; ENABLE-SPR-NEXT:    vaddps %ymm0, %ymm1, %ymm0
; ENABLE-SPR-NEXT:    retq
;
; DISABLE-ADL-LABEL: permps:
; DISABLE-ADL:       # %bb.0:
; DISABLE-ADL-NEXT:    vmovups %ymm0, {{[-0-9]+}}(%r{{[sb]}}p) # 32-byte Spill
; DISABLE-ADL-NEXT:    #APP
; DISABLE-ADL-NEXT:    nop
; DISABLE-ADL-NEXT:    #NO_APP
; DISABLE-ADL-NEXT:    vmovups {{[-0-9]+}}(%r{{[sb]}}p), %ymm2 # 32-byte Reload
; DISABLE-ADL-NEXT:    vpermps %ymm2, %ymm0, %ymm1
; DISABLE-ADL-NEXT:    vcvtdq2ps %ymm0, %ymm0
; DISABLE-ADL-NEXT:    vaddps %ymm2, %ymm0, %ymm0
; DISABLE-ADL-NEXT:    vaddps %ymm0, %ymm1, %ymm0
; DISABLE-ADL-NEXT:    retq
;
; DISABLE-SPR-LABEL: permps:
; DISABLE-SPR:       # %bb.0:
; DISABLE-SPR-NEXT:    vmovaps %ymm0, %ymm16
; DISABLE-SPR-NEXT:    #APP
; DISABLE-SPR-NEXT:    nop
; DISABLE-SPR-NEXT:    #NO_APP
; DISABLE-SPR-NEXT:    vpermps %ymm16, %ymm0, %ymm1
; DISABLE-SPR-NEXT:    vcvtdq2ps %ymm0, %ymm0
; DISABLE-SPR-NEXT:    vaddps %ymm16, %ymm0, %ymm0
; DISABLE-SPR-NEXT:    vaddps %ymm0, %ymm1, %ymm0
; DISABLE-SPR-NEXT:    retq
  %1 = tail call <8 x i32> asm sideeffect "nop", "=x,~{xmm1},~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{flags}"()
  %2 = call <8 x float> @llvm.x86.avx2.permps(<8 x float> %a0, <8 x i32> %1)
  %t = sitofp <8 x i32> %1 to <8 x float>
  %3 = fadd <8 x float> %t, %a0
  %res = fadd <8 x float> %2, %3
  ret <8 x float> %res
}

define <8 x float> @permps_mem(ptr %p0, <8 x i32> %a1) {
; ENABLE-LABEL: permps_mem:
; ENABLE:       # %bb.0:
; ENABLE-NEXT:    #APP
; ENABLE-NEXT:    nop
; ENABLE-NEXT:    #NO_APP
; ENABLE-NEXT:    vxorps %xmm1, %xmm1, %xmm1
; ENABLE-NEXT:    vpermps (%rdi), %ymm0, %ymm1
; ENABLE-NEXT:    vcvtdq2ps %ymm0, %ymm0
; ENABLE-NEXT:    vaddps %ymm0, %ymm1, %ymm0
; ENABLE-NEXT:    retq
;
; DISABLE-LABEL: permps_mem:
; DISABLE:       # %bb.0:
; DISABLE-NEXT:    #APP
; DISABLE-NEXT:    nop
; DISABLE-NEXT:    #NO_APP
; DISABLE-NEXT:    vpermps (%rdi), %ymm0, %ymm1
; DISABLE-NEXT:    vcvtdq2ps %ymm0, %ymm0
; DISABLE-NEXT:    vaddps %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},~{flags}"()
  %a0 = load <8 x float>, ptr %p0, align 64
  %2 = call <8 x float> @llvm.x86.avx2.permps(<8 x float> %a0, <8 x i32> %a1)
  %t = sitofp <8 x i32> %a1 to <8 x float>
  %res = fadd <8 x float> %2, %t
  ret <8 x float> %res
}

declare <8 x float> @llvm.x86.avx2.permps(<8 x float>, <8 x i32>) nounwind readonly

define <4 x double> @permpd(<4 x double> %a0) {
; ENABLE-LABEL: permpd:
; 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:
; 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},~{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_mem(ptr %p0) {
; ENABLE-LABEL: permpd_mem:
; ENABLE:       # %bb.0:
; ENABLE-NEXT:    #APP
; ENABLE-NEXT:    nop
; ENABLE-NEXT:    #NO_APP
; ENABLE-NEXT:    vxorps %xmm0, %xmm0, %xmm0
; ENABLE-NEXT:    vpermpd {{.*#+}} ymm0 = mem[1,2,1,0]
; ENABLE-NEXT:    retq
;
; DISABLE-LABEL: permpd_mem:
; DISABLE:       # %bb.0:
; DISABLE-NEXT:    #APP
; DISABLE-NEXT:    nop
; DISABLE-NEXT:    #NO_APP
; DISABLE-NEXT:    vpermpd {{.*#+}} ymm0 = mem[1,2,1,0]
; 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},~{flags}"()
  %a0 = load <4 x double>, ptr %p0, align 64
  %2 = shufflevector <4 x double> %a0, <4 x double> undef, <4 x i32> <i32 1, i32 2, i32 1, i32 0>
  ret <4 x double> %2
}