test/CodeGen/X86/avx512fp16-fminimum-fmaximum.ll

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -verify-machineinstrs -mtriple=x86_64-unknown-unknown -mattr=+avx512fp16 | FileCheck %s

declare half @llvm.minimum.f16(half, half)
declare half @llvm.maximum.f16(half, half)
declare <8 x half> @llvm.minimum.v8f16(<8 x half>, <8 x half>)
declare <8 x half> @llvm.maximum.v8f16(<8 x half>, <8 x half>)

define half @test_fminimum(half %x, half %y) {
; CHECK-LABEL: test_fminimum:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vmovw %xmm0, %eax
; CHECK-NEXT:    testw %ax, %ax
; CHECK-NEXT:    sets %al
; CHECK-NEXT:    kmovd %eax, %k1
; CHECK-NEXT:    vmovaps %xmm1, %xmm2
; CHECK-NEXT:    vmovsh %xmm0, %xmm0, %xmm2 {%k1}
; CHECK-NEXT:    vmovsh %xmm1, %xmm0, %xmm0 {%k1}
; CHECK-NEXT:    vminsh %xmm2, %xmm0, %xmm1
; CHECK-NEXT:    vcmpunordsh %xmm0, %xmm0, %k1
; CHECK-NEXT:    vmovsh %xmm0, %xmm0, %xmm1 {%k1}
; CHECK-NEXT:    vmovaps %xmm1, %xmm0
; CHECK-NEXT:    retq
  %z = call half @llvm.minimum.f16(half %x, half %y)
  ret half %z
}

define <8 x half> @test_fminimum_scalarize(<8 x half> %x, <8 x half> %y) "no-nans-fp-math"="true" "no-signed-zeros-fp-math"="true" {
; CHECK-LABEL: test_fminimum_scalarize:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vpsrldq {{.*#+}} xmm2 = xmm1[14,15],zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero
; CHECK-NEXT:    vpsrldq {{.*#+}} xmm3 = xmm0[14,15],zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero
; CHECK-NEXT:    vminsh %xmm2, %xmm3, %xmm2
; CHECK-NEXT:    vshufps {{.*#+}} xmm3 = xmm1[3,3,3,3]
; CHECK-NEXT:    vshufps {{.*#+}} xmm4 = xmm0[3,3,3,3]
; CHECK-NEXT:    vminsh %xmm3, %xmm4, %xmm3
; CHECK-NEXT:    vpunpcklwd {{.*#+}} xmm2 = xmm3[0],xmm2[0],xmm3[1],xmm2[1],xmm3[2],xmm2[2],xmm3[3],xmm2[3]
; CHECK-NEXT:    vpsrldq {{.*#+}} xmm3 = xmm1[10,11,12,13,14,15],zero,zero,zero,zero,zero,zero,zero,zero,zero,zero
; CHECK-NEXT:    vpsrldq {{.*#+}} xmm4 = xmm0[10,11,12,13,14,15],zero,zero,zero,zero,zero,zero,zero,zero,zero,zero
; CHECK-NEXT:    vminsh %xmm3, %xmm4, %xmm3
; CHECK-NEXT:    vshufpd {{.*#+}} xmm4 = xmm1[1,0]
; CHECK-NEXT:    vshufpd {{.*#+}} xmm5 = xmm0[1,0]
; CHECK-NEXT:    vminsh %xmm4, %xmm5, %xmm4
; CHECK-NEXT:    vpunpcklwd {{.*#+}} xmm3 = xmm4[0],xmm3[0],xmm4[1],xmm3[1],xmm4[2],xmm3[2],xmm4[3],xmm3[3]
; CHECK-NEXT:    vpunpckldq {{.*#+}} xmm2 = xmm3[0],xmm2[0],xmm3[1],xmm2[1]
; CHECK-NEXT:    vpsrlq $48, %xmm1, %xmm3
; CHECK-NEXT:    vpsrlq $48, %xmm0, %xmm4
; CHECK-NEXT:    vminsh %xmm3, %xmm4, %xmm3
; CHECK-NEXT:    vmovshdup {{.*#+}} xmm4 = xmm1[1,1,3,3]
; CHECK-NEXT:    vmovshdup {{.*#+}} xmm5 = xmm0[1,1,3,3]
; CHECK-NEXT:    vminsh %xmm4, %xmm5, %xmm4
; CHECK-NEXT:    vpunpcklwd {{.*#+}} xmm3 = xmm4[0],xmm3[0],xmm4[1],xmm3[1],xmm4[2],xmm3[2],xmm4[3],xmm3[3]
; CHECK-NEXT:    vminsh %xmm1, %xmm0, %xmm4
; CHECK-NEXT:    vpsrld $16, %xmm1, %xmm1
; CHECK-NEXT:    vpsrld $16, %xmm0, %xmm0
; CHECK-NEXT:    vminsh %xmm1, %xmm0, %xmm0
; CHECK-NEXT:    vpunpcklwd {{.*#+}} xmm0 = xmm4[0],xmm0[0],xmm4[1],xmm0[1],xmm4[2],xmm0[2],xmm4[3],xmm0[3]
; CHECK-NEXT:    vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm3[0],xmm0[1],xmm3[1]
; CHECK-NEXT:    vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm2[0]
; CHECK-NEXT:    retq
  %r = call <8 x half> @llvm.minimum.v8f16(<8 x half> %x, <8 x half> %y)
  ret <8 x half> %r
}

define half @test_fminimum_nnan(half %x, half %y) "no-nans-fp-math"="true" {
; CHECK-LABEL: test_fminimum_nnan:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vfpclasssh $5, %xmm1, %k1
; CHECK-NEXT:    vmovaps %xmm0, %xmm2
; CHECK-NEXT:    vmovsh %xmm1, %xmm0, %xmm2 {%k1}
; CHECK-NEXT:    vmovsh %xmm0, %xmm0, %xmm1 {%k1}
; CHECK-NEXT:    vminsh %xmm2, %xmm1, %xmm0
; CHECK-NEXT:    retq
  %1 = tail call half @llvm.minimum.f16(half %x, half %y)
  ret half %1
}

define half @test_fminimum_zero(half %x, half %y) {
; CHECK-LABEL: test_fminimum_zero:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vcmpunordsh %xmm1, %xmm1, %k1
; CHECK-NEXT:    vminsh {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm1, %xmm0
; CHECK-NEXT:    vmovsh %xmm1, %xmm0, %xmm0 {%k1}
; CHECK-NEXT:    retq
  %1 = tail call half @llvm.minimum.f16(half -0.0, half %y)
  ret half %1
}

define half @test_fminimum_nsz(half %x, half %y) {
; CHECK-LABEL: test_fminimum_nsz:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vminsh %xmm1, %xmm0, %xmm1
; CHECK-NEXT:    vcmpunordsh %xmm0, %xmm0, %k1
; CHECK-NEXT:    vmovsh %xmm0, %xmm0, %xmm1 {%k1}
; CHECK-NEXT:    vmovaps %xmm1, %xmm0
; CHECK-NEXT:    retq
  %1 = tail call nsz half @llvm.minimum.f16(half %x, half %y)
  ret half %1
}

define half @test_fminimum_combine_cmps(half %x, half %y) {
; CHECK-LABEL: test_fminimum_combine_cmps:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vdivsh %xmm0, %xmm1, %xmm1
; CHECK-NEXT:    vfpclasssh $5, %xmm0, %k1
; CHECK-NEXT:    vmovaps %xmm1, %xmm2
; CHECK-NEXT:    vmovsh %xmm0, %xmm0, %xmm2 {%k1}
; CHECK-NEXT:    vmovsh %xmm1, %xmm0, %xmm0 {%k1}
; CHECK-NEXT:    vminsh %xmm2, %xmm0, %xmm0
; CHECK-NEXT:    retq
  %1 = fdiv nnan half %y, %x
  %2 = tail call half @llvm.minimum.f16(half %x, half %1)
  ret half %2
}

define half @test_fmaximum(half %x, half %y) {
; CHECK-LABEL: test_fmaximum:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vmovw %xmm0, %eax
; CHECK-NEXT:    testw %ax, %ax
; CHECK-NEXT:    sets %al
; CHECK-NEXT:    kmovd %eax, %k1
; CHECK-NEXT:    vmovaps %xmm0, %xmm2
; CHECK-NEXT:    vmovsh %xmm1, %xmm0, %xmm2 {%k1}
; CHECK-NEXT:    vmovsh %xmm0, %xmm0, %xmm1 {%k1}
; CHECK-NEXT:    vmaxsh %xmm2, %xmm1, %xmm0
; CHECK-NEXT:    vcmpunordsh %xmm1, %xmm1, %k1
; CHECK-NEXT:    vmovsh %xmm1, %xmm0, %xmm0 {%k1}
; CHECK-NEXT:    retq
  %r = call half @llvm.maximum.f16(half %x, half %y)
  ret half %r
}

define <8 x half> @test_fmaximum_scalarize(<8 x half> %x, <8 x half> %y) "no-nans-fp-math"="true" "no-signed-zeros-fp-math"="true" {
; CHECK-LABEL: test_fmaximum_scalarize:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vpsrldq {{.*#+}} xmm2 = xmm1[14,15],zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero
; CHECK-NEXT:    vpsrldq {{.*#+}} xmm3 = xmm0[14,15],zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero
; CHECK-NEXT:    vmaxsh %xmm2, %xmm3, %xmm2
; CHECK-NEXT:    vshufps {{.*#+}} xmm3 = xmm1[3,3,3,3]
; CHECK-NEXT:    vshufps {{.*#+}} xmm4 = xmm0[3,3,3,3]
; CHECK-NEXT:    vmaxsh %xmm3, %xmm4, %xmm3
; CHECK-NEXT:    vpunpcklwd {{.*#+}} xmm2 = xmm3[0],xmm2[0],xmm3[1],xmm2[1],xmm3[2],xmm2[2],xmm3[3],xmm2[3]
; CHECK-NEXT:    vpsrldq {{.*#+}} xmm3 = xmm1[10,11,12,13,14,15],zero,zero,zero,zero,zero,zero,zero,zero,zero,zero
; CHECK-NEXT:    vpsrldq {{.*#+}} xmm4 = xmm0[10,11,12,13,14,15],zero,zero,zero,zero,zero,zero,zero,zero,zero,zero
; CHECK-NEXT:    vmaxsh %xmm3, %xmm4, %xmm3
; CHECK-NEXT:    vshufpd {{.*#+}} xmm4 = xmm1[1,0]
; CHECK-NEXT:    vshufpd {{.*#+}} xmm5 = xmm0[1,0]
; CHECK-NEXT:    vmaxsh %xmm4, %xmm5, %xmm4
; CHECK-NEXT:    vpunpcklwd {{.*#+}} xmm3 = xmm4[0],xmm3[0],xmm4[1],xmm3[1],xmm4[2],xmm3[2],xmm4[3],xmm3[3]
; CHECK-NEXT:    vpunpckldq {{.*#+}} xmm2 = xmm3[0],xmm2[0],xmm3[1],xmm2[1]
; CHECK-NEXT:    vpsrlq $48, %xmm1, %xmm3
; CHECK-NEXT:    vpsrlq $48, %xmm0, %xmm4
; CHECK-NEXT:    vmaxsh %xmm3, %xmm4, %xmm3
; CHECK-NEXT:    vmovshdup {{.*#+}} xmm4 = xmm1[1,1,3,3]
; CHECK-NEXT:    vmovshdup {{.*#+}} xmm5 = xmm0[1,1,3,3]
; CHECK-NEXT:    vmaxsh %xmm4, %xmm5, %xmm4
; CHECK-NEXT:    vpunpcklwd {{.*#+}} xmm3 = xmm4[0],xmm3[0],xmm4[1],xmm3[1],xmm4[2],xmm3[2],xmm4[3],xmm3[3]
; CHECK-NEXT:    vmaxsh %xmm1, %xmm0, %xmm4
; CHECK-NEXT:    vpsrld $16, %xmm1, %xmm1
; CHECK-NEXT:    vpsrld $16, %xmm0, %xmm0
; CHECK-NEXT:    vmaxsh %xmm1, %xmm0, %xmm0
; CHECK-NEXT:    vpunpcklwd {{.*#+}} xmm0 = xmm4[0],xmm0[0],xmm4[1],xmm0[1],xmm4[2],xmm0[2],xmm4[3],xmm0[3]
; CHECK-NEXT:    vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm3[0],xmm0[1],xmm3[1]
; CHECK-NEXT:    vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm2[0]
; CHECK-NEXT:    retq
  %r = call <8 x half> @llvm.maximum.v8f16(<8 x half> %x, <8 x half> %y)
  ret <8 x half> %r
}

define half @test_fmaximum_nnan(half %x, half %y) {
; CHECK-LABEL: test_fmaximum_nnan:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vaddsh %xmm1, %xmm0, %xmm2
; CHECK-NEXT:    vsubsh %xmm1, %xmm0, %xmm0
; CHECK-NEXT:    vfpclasssh $3, %xmm0, %k1
; CHECK-NEXT:    vmovaps %xmm2, %xmm1
; CHECK-NEXT:    vmovsh %xmm0, %xmm0, %xmm1 {%k1}
; CHECK-NEXT:    vmovsh %xmm2, %xmm0, %xmm0 {%k1}
; CHECK-NEXT:    vmaxsh %xmm1, %xmm0, %xmm0
; CHECK-NEXT:    retq
  %1 = fadd nnan half %x, %y
  %2 = fsub nnan half %x, %y
  %3 = tail call half @llvm.maximum.f16(half %1, half %2)
  ret half %3
}

define half @test_fmaximum_zero(half %x, half %y) {
; CHECK-LABEL: test_fmaximum_zero:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vxorps %xmm0, %xmm0, %xmm0
; CHECK-NEXT:    vmaxsh %xmm0, %xmm1, %xmm0
; CHECK-NEXT:    vcmpunordsh %xmm1, %xmm1, %k1
; CHECK-NEXT:    vmovsh %xmm1, %xmm0, %xmm0 {%k1}
; CHECK-NEXT:    retq
  %1 = tail call half @llvm.maximum.f16(half 0.0, half %y)
  ret half %1
}

define half @test_fmaximum_nsz(half %x, half %y) "no-signed-zeros-fp-math"="true" {
; CHECK-LABEL: test_fmaximum_nsz:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vmaxsh %xmm1, %xmm0, %xmm1
; CHECK-NEXT:    vcmpunordsh %xmm0, %xmm0, %k1
; CHECK-NEXT:    vmovsh %xmm0, %xmm0, %xmm1 {%k1}
; CHECK-NEXT:    vmovaps %xmm1, %xmm0
; CHECK-NEXT:    retq
  %1 = tail call half @llvm.maximum.f16(half %x, half %y)
  ret half %1
}

define half @test_fmaximum_combine_cmps(half %x, half %y) {
; CHECK-LABEL: test_fmaximum_combine_cmps:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vdivsh %xmm0, %xmm1, %xmm1
; CHECK-NEXT:    vfpclasssh $3, %xmm0, %k1
; CHECK-NEXT:    vmovaps %xmm1, %xmm2
; CHECK-NEXT:    vmovsh %xmm0, %xmm0, %xmm2 {%k1}
; CHECK-NEXT:    vmovsh %xmm1, %xmm0, %xmm0 {%k1}
; CHECK-NEXT:    vmaxsh %xmm2, %xmm0, %xmm0
; CHECK-NEXT:    retq
  %1 = fdiv nnan half %y, %x
  %2 = tail call half @llvm.maximum.f16(half %x, half %1)
  ret half %2
}