llvm/test/CodeGen/AArch64/llvm.sincospi.ll

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 2
; RUN: llc -mtriple=aarch64-gnu-linux < %s | FileCheck -check-prefixes=CHECK %s

define { half, half } @test_sincospi_f16(half %a) {
; CHECK-LABEL: test_sincospi_f16:
; CHECK:       // %bb.0:
; CHECK-NEXT:    str x30, [sp, #-16]! // 8-byte Folded Spill
; CHECK-NEXT:    .cfi_def_cfa_offset 16
; CHECK-NEXT:    .cfi_offset w30, -16
; CHECK-NEXT:    fcvt s0, h0
; CHECK-NEXT:    add x0, sp, #12
; CHECK-NEXT:    add x1, sp, #8
; CHECK-NEXT:    bl sincospif
; CHECK-NEXT:    ldp s1, s0, [sp, #8]
; CHECK-NEXT:    fcvt h0, s0
; CHECK-NEXT:    fcvt h1, s1
; CHECK-NEXT:    ldr x30, [sp], #16 // 8-byte Folded Reload
; CHECK-NEXT:    ret
  %result = call { half, half } @llvm.sincospi.f16(half %a)
  ret { half, half } %result
}

define half @test_sincospi_f16_only_use_sin(half %a) {
; CHECK-LABEL: test_sincospi_f16_only_use_sin:
; CHECK:       // %bb.0:
; CHECK-NEXT:    str x30, [sp, #-16]! // 8-byte Folded Spill
; CHECK-NEXT:    .cfi_def_cfa_offset 16
; CHECK-NEXT:    .cfi_offset w30, -16
; CHECK-NEXT:    fcvt s0, h0
; CHECK-NEXT:    add x0, sp, #12
; CHECK-NEXT:    add x1, sp, #8
; CHECK-NEXT:    bl sincospif
; CHECK-NEXT:    ldr s0, [sp, #12]
; CHECK-NEXT:    fcvt h0, s0
; CHECK-NEXT:    ldr x30, [sp], #16 // 8-byte Folded Reload
; CHECK-NEXT:    ret
  %result = call { half, half } @llvm.sincospi.f16(half %a)
  %result.0 = extractvalue { half, half } %result, 0
  ret half %result.0
}

define half @test_sincospi_f16_only_use_cos(half %a) {
; CHECK-LABEL: test_sincospi_f16_only_use_cos:
; CHECK:       // %bb.0:
; CHECK-NEXT:    str x30, [sp, #-16]! // 8-byte Folded Spill
; CHECK-NEXT:    .cfi_def_cfa_offset 16
; CHECK-NEXT:    .cfi_offset w30, -16
; CHECK-NEXT:    fcvt s0, h0
; CHECK-NEXT:    add x0, sp, #12
; CHECK-NEXT:    add x1, sp, #8
; CHECK-NEXT:    bl sincospif
; CHECK-NEXT:    ldr s0, [sp, #8]
; CHECK-NEXT:    fcvt h0, s0
; CHECK-NEXT:    ldr x30, [sp], #16 // 8-byte Folded Reload
; CHECK-NEXT:    ret
  %result = call { half, half } @llvm.sincospi.f16(half %a)
  %result.1 = extractvalue { half, half } %result, 1
  ret half %result.1
}

define { <2 x half>, <2 x half> } @test_sincospi_v2f16(<2 x half> %a) {
; CHECK-LABEL: test_sincospi_v2f16:
; CHECK:       // %bb.0:
; CHECK-NEXT:    sub sp, sp, #64
; CHECK-NEXT:    str x30, [sp, #48] // 8-byte Folded Spill
; CHECK-NEXT:    .cfi_def_cfa_offset 64
; CHECK-NEXT:    .cfi_offset w30, -16
; CHECK-NEXT:    // kill: def $d0 killed $d0 def $q0
; CHECK-NEXT:    mov h1, v0.h[1]
; CHECK-NEXT:    str q0, [sp] // 16-byte Folded Spill
; CHECK-NEXT:    add x0, sp, #36
; CHECK-NEXT:    add x1, sp, #32
; CHECK-NEXT:    fcvt s0, h1
; CHECK-NEXT:    bl sincospif
; CHECK-NEXT:    ldr q0, [sp] // 16-byte Folded Reload
; CHECK-NEXT:    add x0, sp, #28
; CHECK-NEXT:    add x1, sp, #24
; CHECK-NEXT:    fcvt s0, h0
; CHECK-NEXT:    bl sincospif
; CHECK-NEXT:    ldr q0, [sp] // 16-byte Folded Reload
; CHECK-NEXT:    add x0, sp, #44
; CHECK-NEXT:    add x1, sp, #40
; CHECK-NEXT:    mov h0, v0.h[2]
; CHECK-NEXT:    fcvt s0, h0
; CHECK-NEXT:    bl sincospif
; CHECK-NEXT:    ldr q0, [sp] // 16-byte Folded Reload
; CHECK-NEXT:    add x0, sp, #60
; CHECK-NEXT:    add x1, sp, #56
; CHECK-NEXT:    mov h0, v0.h[3]
; CHECK-NEXT:    fcvt s0, h0
; CHECK-NEXT:    bl sincospif
; CHECK-NEXT:    ldp s2, s0, [sp, #32]
; CHECK-NEXT:    ldr x30, [sp, #48] // 8-byte Folded Reload
; CHECK-NEXT:    ldp s3, s1, [sp, #24]
; CHECK-NEXT:    fcvt h4, s0
; CHECK-NEXT:    fcvt h2, s2
; CHECK-NEXT:    fcvt h0, s1
; CHECK-NEXT:    fcvt h1, s3
; CHECK-NEXT:    ldp s5, s3, [sp, #40]
; CHECK-NEXT:    fcvt h3, s3
; CHECK-NEXT:    mov v0.h[1], v4.h[0]
; CHECK-NEXT:    fcvt h4, s5
; CHECK-NEXT:    mov v1.h[1], v2.h[0]
; CHECK-NEXT:    ldp s5, s2, [sp, #56]
; CHECK-NEXT:    mov v0.h[2], v3.h[0]
; CHECK-NEXT:    fcvt h2, s2
; CHECK-NEXT:    fcvt h3, s5
; CHECK-NEXT:    mov v1.h[2], v4.h[0]
; CHECK-NEXT:    mov v0.h[3], v2.h[0]
; CHECK-NEXT:    mov v1.h[3], v3.h[0]
; CHECK-NEXT:    // kill: def $d0 killed $d0 killed $q0
; CHECK-NEXT:    // kill: def $d1 killed $d1 killed $q1
; CHECK-NEXT:    add sp, sp, #64
; CHECK-NEXT:    ret
  %result = call { <2 x half>, <2 x half> } @llvm.sincospi.v2f16(<2 x half> %a)
  ret { <2 x half>, <2 x half> } %result
}

define { float, float } @test_sincospi_f32(float %a) {
; CHECK-LABEL: test_sincospi_f32:
; CHECK:       // %bb.0:
; CHECK-NEXT:    str x30, [sp, #-16]! // 8-byte Folded Spill
; CHECK-NEXT:    .cfi_def_cfa_offset 16
; CHECK-NEXT:    .cfi_offset w30, -16
; CHECK-NEXT:    add x0, sp, #12
; CHECK-NEXT:    add x1, sp, #8
; CHECK-NEXT:    bl sincospif
; CHECK-NEXT:    ldp s1, s0, [sp, #8]
; CHECK-NEXT:    ldr x30, [sp], #16 // 8-byte Folded Reload
; CHECK-NEXT:    ret
  %result = call { float, float } @llvm.sincospi.f32(float %a)
  ret { float, float } %result
}

define { <3 x float>, <3 x float> } @test_sincospi_v3f32(<3 x float> %a) {
; CHECK-LABEL: test_sincospi_v3f32:
; CHECK:       // %bb.0:
; CHECK-NEXT:    sub sp, sp, #80
; CHECK-NEXT:    str x30, [sp, #32] // 8-byte Folded Spill
; CHECK-NEXT:    stp x22, x21, [sp, #48] // 16-byte Folded Spill
; CHECK-NEXT:    stp x20, x19, [sp, #64] // 16-byte Folded Spill
; CHECK-NEXT:    .cfi_def_cfa_offset 80
; CHECK-NEXT:    .cfi_offset w19, -8
; CHECK-NEXT:    .cfi_offset w20, -16
; CHECK-NEXT:    .cfi_offset w21, -24
; CHECK-NEXT:    .cfi_offset w22, -32
; CHECK-NEXT:    .cfi_offset w30, -48
; CHECK-NEXT:    add x0, sp, #20
; CHECK-NEXT:    add x1, sp, #16
; CHECK-NEXT:    str q0, [sp] // 16-byte Folded Spill
; CHECK-NEXT:    // kill: def $s0 killed $s0 killed $q0
; CHECK-NEXT:    bl sincospif
; CHECK-NEXT:    ldr q0, [sp] // 16-byte Folded Reload
; CHECK-NEXT:    add x0, sp, #28
; CHECK-NEXT:    add x1, sp, #24
; CHECK-NEXT:    add x19, sp, #28
; CHECK-NEXT:    add x20, sp, #24
; CHECK-NEXT:    mov s0, v0.s[1]
; CHECK-NEXT:    bl sincospif
; CHECK-NEXT:    ldr q0, [sp] // 16-byte Folded Reload
; CHECK-NEXT:    add x0, sp, #44
; CHECK-NEXT:    add x1, sp, #40
; CHECK-NEXT:    add x21, sp, #44
; CHECK-NEXT:    add x22, sp, #40
; CHECK-NEXT:    mov s0, v0.s[2]
; CHECK-NEXT:    bl sincospif
; CHECK-NEXT:    ldp s1, s0, [sp, #16]
; CHECK-NEXT:    ldr x30, [sp, #32] // 8-byte Folded Reload
; CHECK-NEXT:    ld1 { v0.s }[1], [x19]
; CHECK-NEXT:    ld1 { v1.s }[1], [x20]
; CHECK-NEXT:    ldp x20, x19, [sp, #64] // 16-byte Folded Reload
; CHECK-NEXT:    ld1 { v0.s }[2], [x21]
; CHECK-NEXT:    ld1 { v1.s }[2], [x22]
; CHECK-NEXT:    ldp x22, x21, [sp, #48] // 16-byte Folded Reload
; CHECK-NEXT:    add sp, sp, #80
; CHECK-NEXT:    ret
  %result = call { <3 x float>, <3 x float> } @llvm.sincospi.v3f32(<3 x float> %a)
  ret { <3 x float>, <3 x float> } %result
}

define { <2 x float>, <2 x float> } @test_sincospi_v2f32(<2 x float> %a) {
; CHECK-LABEL: test_sincospi_v2f32:
; CHECK:       // %bb.0:
; CHECK-NEXT:    sub sp, sp, #64
; CHECK-NEXT:    str x30, [sp, #32] // 8-byte Folded Spill
; CHECK-NEXT:    stp x20, x19, [sp, #48] // 16-byte Folded Spill
; CHECK-NEXT:    .cfi_def_cfa_offset 64
; CHECK-NEXT:    .cfi_offset w19, -8
; CHECK-NEXT:    .cfi_offset w20, -16
; CHECK-NEXT:    .cfi_offset w30, -32
; CHECK-NEXT:    // kill: def $d0 killed $d0 def $q0
; CHECK-NEXT:    add x0, sp, #44
; CHECK-NEXT:    add x1, sp, #40
; CHECK-NEXT:    str q0, [sp] // 16-byte Folded Spill
; CHECK-NEXT:    // kill: def $s0 killed $s0 killed $q0
; CHECK-NEXT:    bl sincospif
; CHECK-NEXT:    ldr q0, [sp] // 16-byte Folded Reload
; CHECK-NEXT:    add x0, sp, #28
; CHECK-NEXT:    add x1, sp, #24
; CHECK-NEXT:    add x19, sp, #28
; CHECK-NEXT:    add x20, sp, #24
; CHECK-NEXT:    mov s0, v0.s[1]
; CHECK-NEXT:    bl sincospif
; CHECK-NEXT:    ldp s1, s0, [sp, #40]
; CHECK-NEXT:    ldr x30, [sp, #32] // 8-byte Folded Reload
; CHECK-NEXT:    ld1 { v0.s }[1], [x19]
; CHECK-NEXT:    ld1 { v1.s }[1], [x20]
; CHECK-NEXT:    ldp x20, x19, [sp, #48] // 16-byte Folded Reload
; CHECK-NEXT:    // kill: def $d0 killed $d0 killed $q0
; CHECK-NEXT:    // kill: def $d1 killed $d1 killed $q1
; CHECK-NEXT:    add sp, sp, #64
; CHECK-NEXT:    ret
  %result = call { <2 x float>, <2 x float> } @llvm.sincospi.v2f32(<2 x float> %a)
  ret { <2 x float>, <2 x float> } %result
}

define { double, double } @test_sincospi_f64(double %a) {
; CHECK-LABEL: test_sincospi_f64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    sub sp, sp, #32
; CHECK-NEXT:    str x30, [sp, #16] // 8-byte Folded Spill
; CHECK-NEXT:    .cfi_def_cfa_offset 32
; CHECK-NEXT:    .cfi_offset w30, -16
; CHECK-NEXT:    add x0, sp, #24
; CHECK-NEXT:    add x1, sp, #8
; CHECK-NEXT:    bl sincospi
; CHECK-NEXT:    ldr d0, [sp, #24]
; CHECK-NEXT:    ldr d1, [sp, #8]
; CHECK-NEXT:    ldr x30, [sp, #16] // 8-byte Folded Reload
; CHECK-NEXT:    add sp, sp, #32
; CHECK-NEXT:    ret
  %result = call { double, double } @llvm.sincospi.f64(double %a)
  ret { double, double } %result
}

define { <2 x double>, <2 x double> } @test_sincospi_v2f64(<2 x double> %a) {
; CHECK-LABEL: test_sincospi_v2f64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    sub sp, sp, #80
; CHECK-NEXT:    str x30, [sp, #48] // 8-byte Folded Spill
; CHECK-NEXT:    stp x20, x19, [sp, #64] // 16-byte Folded Spill
; CHECK-NEXT:    .cfi_def_cfa_offset 80
; CHECK-NEXT:    .cfi_offset w19, -8
; CHECK-NEXT:    .cfi_offset w20, -16
; CHECK-NEXT:    .cfi_offset w30, -32
; CHECK-NEXT:    add x0, sp, #56
; CHECK-NEXT:    add x1, sp, #40
; CHECK-NEXT:    str q0, [sp] // 16-byte Folded Spill
; CHECK-NEXT:    // kill: def $d0 killed $d0 killed $q0
; CHECK-NEXT:    bl sincospi
; CHECK-NEXT:    ldr q0, [sp] // 16-byte Folded Reload
; CHECK-NEXT:    add x0, sp, #32
; CHECK-NEXT:    add x1, sp, #24
; CHECK-NEXT:    add x19, sp, #32
; CHECK-NEXT:    add x20, sp, #24
; CHECK-NEXT:    mov d0, v0.d[1]
; CHECK-NEXT:    bl sincospi
; CHECK-NEXT:    ldr d0, [sp, #56]
; CHECK-NEXT:    ldr d1, [sp, #40]
; CHECK-NEXT:    ldr x30, [sp, #48] // 8-byte Folded Reload
; CHECK-NEXT:    ld1 { v0.d }[1], [x19]
; CHECK-NEXT:    ld1 { v1.d }[1], [x20]
; CHECK-NEXT:    ldp x20, x19, [sp, #64] // 16-byte Folded Reload
; CHECK-NEXT:    add sp, sp, #80
; CHECK-NEXT:    ret
  %result = call { <2 x double>, <2 x double> } @llvm.sincospi.v2f64(<2 x double> %a)
  ret { <2 x double>, <2 x double> } %result
}