llvm/test/CodeGen/AArch64/vector-fcopysign.ll

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple aarch64-apple-darwin | FileCheck --check-prefixes=CHECK,NOFP16 %s
; RUN: llc < %s -mtriple aarch64-apple-darwin -mattr=+v8.2a,+fullfp16 | FileCheck --check-prefixes=CHECK,FP16 %s

target datalayout = "e-m:o-i64:64-i128:128-n32:64-S128"

;============ v1f32

; WidenVecRes same
define <1 x float> @test_copysign_v1f32_v1f32(<1 x float> %a, <1 x float> %b) #0 {
; CHECK-LABEL: test_copysign_v1f32_v1f32:
; CHECK:       ; %bb.0:
; CHECK-NEXT:    mvni.2s v2, #128, lsl #24
; CHECK-NEXT:    bif.8b v0, v1, v2
; CHECK-NEXT:    ret
  %r = call <1 x float> @llvm.copysign.v1f32(<1 x float> %a, <1 x float> %b)
  ret <1 x float> %r
}

; WidenVecRes mismatched
define <1 x float> @test_copysign_v1f32_v1f64(<1 x float> %a, <1 x double> %b) #0 {
; CHECK-LABEL: test_copysign_v1f32_v1f64:
; CHECK:       ; %bb.0:
; CHECK-NEXT:    ; kill: def $d1 killed $d1 def $q1
; CHECK-NEXT:    mvni.2s v2, #128, lsl #24
; CHECK-NEXT:    fcvtn v1.2s, v1.2d
; CHECK-NEXT:    bif.8b v0, v1, v2
; CHECK-NEXT:    ret
  %tmp0 = fptrunc <1 x double> %b to <1 x float>
  %r = call <1 x float> @llvm.copysign.v1f32(<1 x float> %a, <1 x float> %tmp0)
  ret <1 x float> %r
}

declare <1 x float> @llvm.copysign.v1f32(<1 x float> %a, <1 x float> %b) #0

;============ v1f64

; WidenVecOp #1
define <1 x double> @test_copysign_v1f64_v1f32(<1 x double> %a, <1 x float> %b) #0 {
; CHECK-LABEL: test_copysign_v1f64_v1f32:
; CHECK:       ; %bb.0:
; CHECK-NEXT:    movi.2d v2, #0xffffffffffffffff
; CHECK-NEXT:    fcvtl v1.2d, v1.2s
; CHECK-NEXT:    ; kill: def $d0 killed $d0 def $q0
; CHECK-NEXT:    fneg.2d v2, v2
; CHECK-NEXT:    bif.16b v0, v1, v2
; CHECK-NEXT:    ; kill: def $d0 killed $d0 killed $q0
; CHECK-NEXT:    ret
  %tmp0 = fpext <1 x float> %b to <1 x double>
  %r = call <1 x double> @llvm.copysign.v1f64(<1 x double> %a, <1 x double> %tmp0)
  ret <1 x double> %r
}

define <1 x double> @test_copysign_v1f64_v1f64(<1 x double> %a, <1 x double> %b) #0 {
; CHECK-LABEL: test_copysign_v1f64_v1f64:
; CHECK:       ; %bb.0:
; CHECK-NEXT:    movi.2d v2, #0xffffffffffffffff
; CHECK-NEXT:    ; kill: def $d0 killed $d0 def $q0
; CHECK-NEXT:    ; kill: def $d1 killed $d1 def $q1
; CHECK-NEXT:    fneg.2d v2, v2
; CHECK-NEXT:    bif.16b v0, v1, v2
; CHECK-NEXT:    ; kill: def $d0 killed $d0 killed $q0
; CHECK-NEXT:    ret
  %r = call <1 x double> @llvm.copysign.v1f64(<1 x double> %a, <1 x double> %b)
  ret <1 x double> %r
}

declare <1 x double> @llvm.copysign.v1f64(<1 x double> %a, <1 x double> %b) #0

;============ v2f32

define <2 x float> @test_copysign_v2f32_v2f32(<2 x float> %a, <2 x float> %b) #0 {
; CHECK-LABEL: test_copysign_v2f32_v2f32:
; CHECK:       ; %bb.0:
; CHECK-NEXT:    mvni.2s v2, #128, lsl #24
; CHECK-NEXT:    bif.8b v0, v1, v2
; CHECK-NEXT:    ret
  %r = call <2 x float> @llvm.copysign.v2f32(<2 x float> %a, <2 x float> %b)
  ret <2 x float> %r
}

define <2 x float> @test_copysign_v2f32_v2f64(<2 x float> %a, <2 x double> %b) #0 {
; CHECK-LABEL: test_copysign_v2f32_v2f64:
; CHECK:       ; %bb.0:
; CHECK-NEXT:    fcvtn v1.2s, v1.2d
; CHECK-NEXT:    mvni.2s v2, #128, lsl #24
; CHECK-NEXT:    bif.8b v0, v1, v2
; CHECK-NEXT:    ret
  %tmp0 = fptrunc <2 x double> %b to <2 x float>
  %r = call <2 x float> @llvm.copysign.v2f32(<2 x float> %a, <2 x float> %tmp0)
  ret <2 x float> %r
}

declare <2 x float> @llvm.copysign.v2f32(<2 x float> %a, <2 x float> %b) #0

;============ v4f32

define <4 x float> @test_copysign_v4f32_v4f32(<4 x float> %a, <4 x float> %b) #0 {
; CHECK-LABEL: test_copysign_v4f32_v4f32:
; CHECK:       ; %bb.0:
; CHECK-NEXT:    mvni.4s v2, #128, lsl #24
; CHECK-NEXT:    bif.16b v0, v1, v2
; CHECK-NEXT:    ret
  %r = call <4 x float> @llvm.copysign.v4f32(<4 x float> %a, <4 x float> %b)
  ret <4 x float> %r
}

; SplitVecOp #1
define <4 x float> @test_copysign_v4f32_v4f64(<4 x float> %a, <4 x double> %b) #0 {
; CHECK-LABEL: test_copysign_v4f32_v4f64:
; CHECK:       ; %bb.0:
; CHECK-NEXT:    fcvtn v1.2s, v1.2d
; CHECK-NEXT:    fcvtn2 v1.4s, v2.2d
; CHECK-NEXT:    mvni.4s v2, #128, lsl #24
; CHECK-NEXT:    bif.16b v0, v1, v2
; CHECK-NEXT:    ret
  %tmp0 = fptrunc <4 x double> %b to <4 x float>
  %r = call <4 x float> @llvm.copysign.v4f32(<4 x float> %a, <4 x float> %tmp0)
  ret <4 x float> %r
}

declare <4 x float> @llvm.copysign.v4f32(<4 x float> %a, <4 x float> %b) #0

;============ v2f64

define <2 x double> @test_copysign_v2f64_v232(<2 x double> %a, <2 x float> %b) #0 {
; CHECK-LABEL: test_copysign_v2f64_v232:
; CHECK:       ; %bb.0:
; CHECK-NEXT:    movi.2d v2, #0xffffffffffffffff
; CHECK-NEXT:    fcvtl v1.2d, v1.2s
; CHECK-NEXT:    fneg.2d v2, v2
; CHECK-NEXT:    bif.16b v0, v1, v2
; CHECK-NEXT:    ret
  %tmp0 = fpext <2 x float> %b to <2 x double>
  %r = call <2 x double> @llvm.copysign.v2f64(<2 x double> %a, <2 x double> %tmp0)
  ret <2 x double> %r
}

define <2 x double> @test_copysign_v2f64_v2f64(<2 x double> %a, <2 x double> %b) #0 {
; CHECK-LABEL: test_copysign_v2f64_v2f64:
; CHECK:       ; %bb.0:
; CHECK-NEXT:    movi.2d v2, #0xffffffffffffffff
; CHECK-NEXT:    fneg.2d v2, v2
; CHECK-NEXT:    bif.16b v0, v1, v2
; CHECK-NEXT:    ret
  %r = call <2 x double> @llvm.copysign.v2f64(<2 x double> %a, <2 x double> %b)
  ret <2 x double> %r
}

declare <2 x double> @llvm.copysign.v2f64(<2 x double> %a, <2 x double> %b) #0

;============ v4f64

; SplitVecRes mismatched
define <4 x double> @test_copysign_v4f64_v4f32(<4 x double> %a, <4 x float> %b) #0 {
; CHECK-LABEL: test_copysign_v4f64_v4f32:
; CHECK:       ; %bb.0:
; CHECK-NEXT:    movi.2d v3, #0xffffffffffffffff
; CHECK-NEXT:    fcvtl v4.2d, v2.2s
; CHECK-NEXT:    fcvtl2 v2.2d, v2.4s
; CHECK-NEXT:    fneg.2d v3, v3
; CHECK-NEXT:    bif.16b v1, v2, v3
; CHECK-NEXT:    bif.16b v0, v4, v3
; CHECK-NEXT:    ret
  %tmp0 = fpext <4 x float> %b to <4 x double>
  %r = call <4 x double> @llvm.copysign.v4f64(<4 x double> %a, <4 x double> %tmp0)
  ret <4 x double> %r
}

; SplitVecRes same
define <4 x double> @test_copysign_v4f64_v4f64(<4 x double> %a, <4 x double> %b) #0 {
; CHECK-LABEL: test_copysign_v4f64_v4f64:
; CHECK:       ; %bb.0:
; CHECK-NEXT:    movi.2d v4, #0xffffffffffffffff
; CHECK-NEXT:    fneg.2d v4, v4
; CHECK-NEXT:    bif.16b v0, v2, v4
; CHECK-NEXT:    bif.16b v1, v3, v4
; CHECK-NEXT:    ret
  %r = call <4 x double> @llvm.copysign.v4f64(<4 x double> %a, <4 x double> %b)
  ret <4 x double> %r
}

declare <4 x double> @llvm.copysign.v4f64(<4 x double> %a, <4 x double> %b) #0

;============ v4f16

define <4 x half> @test_copysign_v4f16_v4f16(<4 x half> %a, <4 x half> %b) #0 {
; CHECK-LABEL: test_copysign_v4f16_v4f16:
; CHECK:       ; %bb.0:
; CHECK-NEXT:    mvni.4h v2, #128, lsl #8
; CHECK-NEXT:    bif.8b v0, v1, v2
; CHECK-NEXT:    ret
  %r = call <4 x half> @llvm.copysign.v4f16(<4 x half> %a, <4 x half> %b)
  ret <4 x half> %r
}

define <4 x half> @test_copysign_v4f16_v4f32(<4 x half> %a, <4 x float> %b) #0 {
; CHECK-LABEL: test_copysign_v4f16_v4f32:
; CHECK:       ; %bb.0:
; CHECK-NEXT:    fcvtn v1.4h, v1.4s
; CHECK-NEXT:    mvni.4h v2, #128, lsl #8
; CHECK-NEXT:    bif.8b v0, v1, v2
; CHECK-NEXT:    ret
  %tmp0 = fptrunc <4 x float> %b to <4 x half>
  %r = call <4 x half> @llvm.copysign.v4f16(<4 x half> %a, <4 x half> %tmp0)
  ret <4 x half> %r
}

define <4 x half> @test_copysign_v4f16_v4f64(<4 x half> %a, <4 x double> %b) #0 {
; CHECK-LABEL: test_copysign_v4f16_v4f64:
; CHECK:       ; %bb.0:
; CHECK-NEXT:    fcvtxn v1.2s, v1.2d
; CHECK-NEXT:    fcvtxn2 v1.4s, v2.2d
; CHECK-NEXT:    mvni.4h v2, #128, lsl #8
; CHECK-NEXT:    fcvtn v1.4h, v1.4s
; CHECK-NEXT:    bif.8b v0, v1, v2
; CHECK-NEXT:    ret
  %tmp0 = fptrunc <4 x double> %b to <4 x half>
  %r = call <4 x half> @llvm.copysign.v4f16(<4 x half> %a, <4 x half> %tmp0)
  ret <4 x half> %r
}

declare <4 x half> @llvm.copysign.v4f16(<4 x half> %a, <4 x half> %b) #0

;============ v8f16

define <8 x half> @test_copysign_v8f16_v8f16(<8 x half> %a, <8 x half> %b) #0 {
; CHECK-LABEL: test_copysign_v8f16_v8f16:
; CHECK:       ; %bb.0:
; CHECK-NEXT:    mvni.8h v2, #128, lsl #8
; CHECK-NEXT:    bif.16b v0, v1, v2
; CHECK-NEXT:    ret
  %r = call <8 x half> @llvm.copysign.v8f16(<8 x half> %a, <8 x half> %b)
  ret <8 x half> %r
}

define <8 x half> @test_copysign_v8f16_v8f32(<8 x half> %a, <8 x float> %b) #0 {
; CHECK-LABEL: test_copysign_v8f16_v8f32:
; CHECK:       ; %bb.0:
; CHECK-NEXT:    fcvtn v1.4h, v1.4s
; CHECK-NEXT:    fcvtn2 v1.8h, v2.4s
; CHECK-NEXT:    mvni.8h v2, #128, lsl #8
; CHECK-NEXT:    bif.16b v0, v1, v2
; CHECK-NEXT:    ret
  %tmp0 = fptrunc <8 x float> %b to <8 x half>
  %r = call <8 x half> @llvm.copysign.v8f16(<8 x half> %a, <8 x half> %tmp0)
  ret <8 x half> %r
}

declare <8 x half> @llvm.copysign.v8f16(<8 x half> %a, <8 x half> %b) #0

;============ v4bf16

define <4 x bfloat> @test_copysign_v4bf16_v4bf16(<4 x bfloat> %a, <4 x bfloat> %b) #0 {
; CHECK-LABEL: test_copysign_v4bf16_v4bf16:
; CHECK:       ; %bb.0:
; CHECK-NEXT:    mvni.4h v2, #128, lsl #8
; CHECK-NEXT:    bif.8b v0, v1, v2
; CHECK-NEXT:    ret
  %r = call <4 x bfloat> @llvm.copysign.v4bf16(<4 x bfloat> %a, <4 x bfloat> %b)
  ret <4 x bfloat> %r
}

define <4 x bfloat> @test_copysign_v4bf16_v4f32(<4 x bfloat> %a, <4 x float> %b) #0 {
; CHECK-LABEL: test_copysign_v4bf16_v4f32:
; CHECK:       ; %bb.0:
; CHECK-NEXT:    movi.4s v2, #1
; CHECK-NEXT:    movi.4s v3, #127, msl #8
; CHECK-NEXT:    ushr.4s v4, v1, #16
; CHECK-NEXT:    and.16b v2, v4, v2
; CHECK-NEXT:    add.4s v3, v1, v3
; CHECK-NEXT:    fcmeq.4s v4, v1, v1
; CHECK-NEXT:    orr.4s v1, #64, lsl #16
; CHECK-NEXT:    add.4s v2, v2, v3
; CHECK-NEXT:    bit.16b v1, v2, v4
; CHECK-NEXT:    mvni.4h v2, #128, lsl #8
; CHECK-NEXT:    shrn.4h v1, v1, #16
; CHECK-NEXT:    bif.8b v0, v1, v2
; CHECK-NEXT:    ret
  %tmp0 = fptrunc <4 x float> %b to <4 x bfloat>
  %r = call <4 x bfloat> @llvm.copysign.v4bf16(<4 x bfloat> %a, <4 x bfloat> %tmp0)
  ret <4 x bfloat> %r
}

define <4 x bfloat> @test_copysign_v4bf16_v4f64(<4 x bfloat> %a, <4 x double> %b) #0 {
; CHECK-LABEL: test_copysign_v4bf16_v4f64:
; CHECK:       ; %bb.0:
; CHECK-NEXT:    fcvtxn v1.2s, v1.2d
; CHECK-NEXT:    movi.4s v3, #127, msl #8
; CHECK-NEXT:    fcvtxn2 v1.4s, v2.2d
; CHECK-NEXT:    movi.4s v2, #1
; CHECK-NEXT:    ushr.4s v4, v1, #16
; CHECK-NEXT:    add.4s v3, v1, v3
; CHECK-NEXT:    and.16b v2, v4, v2
; CHECK-NEXT:    fcmeq.4s v4, v1, v1
; CHECK-NEXT:    orr.4s v1, #64, lsl #16
; CHECK-NEXT:    add.4s v2, v2, v3
; CHECK-NEXT:    bit.16b v1, v2, v4
; CHECK-NEXT:    mvni.4h v2, #128, lsl #8
; CHECK-NEXT:    shrn.4h v1, v1, #16
; CHECK-NEXT:    bif.8b v0, v1, v2
; CHECK-NEXT:    ret
  %tmp0 = fptrunc <4 x double> %b to <4 x bfloat>
  %r = call <4 x bfloat> @llvm.copysign.v4bf16(<4 x bfloat> %a, <4 x bfloat> %tmp0)
  ret <4 x bfloat> %r
}

declare <4 x bfloat> @llvm.copysign.v4bf16(<4 x bfloat> %a, <4 x bfloat> %b) #0

;============ v8bf16

define <8 x bfloat> @test_copysign_v8bf16_v8bf16(<8 x bfloat> %a, <8 x bfloat> %b) #0 {
; CHECK-LABEL: test_copysign_v8bf16_v8bf16:
; CHECK:       ; %bb.0:
; CHECK-NEXT:    mvni.8h v2, #128, lsl #8
; CHECK-NEXT:    bif.16b v0, v1, v2
; CHECK-NEXT:    ret
  %r = call <8 x bfloat> @llvm.copysign.v8bf16(<8 x bfloat> %a, <8 x bfloat> %b)
  ret <8 x bfloat> %r
}

define <8 x bfloat> @test_copysign_v8bf16_v8f32(<8 x bfloat> %a, <8 x float> %b) #0 {
; CHECK-LABEL: test_copysign_v8bf16_v8f32:
; CHECK:       ; %bb.0:
; CHECK-NEXT:    movi.4s v3, #1
; CHECK-NEXT:    movi.4s v4, #127, msl #8
; CHECK-NEXT:    ushr.4s v5, v2, #16
; CHECK-NEXT:    ushr.4s v6, v1, #16
; CHECK-NEXT:    and.16b v5, v5, v3
; CHECK-NEXT:    add.4s v7, v2, v4
; CHECK-NEXT:    and.16b v3, v6, v3
; CHECK-NEXT:    add.4s v4, v1, v4
; CHECK-NEXT:    fcmeq.4s v6, v2, v2
; CHECK-NEXT:    orr.4s v2, #64, lsl #16
; CHECK-NEXT:    add.4s v5, v5, v7
; CHECK-NEXT:    fcmeq.4s v7, v1, v1
; CHECK-NEXT:    orr.4s v1, #64, lsl #16
; CHECK-NEXT:    add.4s v3, v3, v4
; CHECK-NEXT:    bit.16b v2, v5, v6
; CHECK-NEXT:    bit.16b v1, v3, v7
; CHECK-NEXT:    uzp2.8h v1, v1, v2
; CHECK-NEXT:    mvni.8h v2, #128, lsl #8
; CHECK-NEXT:    bif.16b v0, v1, v2
; CHECK-NEXT:    ret
  %tmp0 = fptrunc <8 x float> %b to <8 x bfloat>
  %r = call <8 x bfloat> @llvm.copysign.v8bf16(<8 x bfloat> %a, <8 x bfloat> %tmp0)
  ret <8 x bfloat> %r
}

declare <8 x bfloat> @llvm.copysign.v8bf16(<8 x bfloat> %a, <8 x bfloat> %b) #0

attributes #0 = { nounwind }
;; NOTE: These prefixes are unused and the list is autogenerated. Do not add tests below this line:
; FP16: {{.*}}
; NOFP16: {{.*}}