; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -O3 -mtriple=x86_64-pc-linux < %s | FileCheck %s
; RUN: llc -O3 -mtriple=x86_64-pc-linux -mattr=+avx < %s | FileCheck --check-prefix=AVX %s

define <1 x float> @constrained_vector_fdiv_v1f32() {
; CHECK-LABEL: constrained_vector_fdiv_v1f32:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    divss {{.*}}(%rip), %xmm0
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_fdiv_v1f32:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT:    vdivss {{.*}}(%rip), %xmm0, %xmm0
; AVX-NEXT:    retq
entry:
  %div = call <1 x float> @llvm.experimental.constrained.fdiv.v1f32(
           <1 x float> <float 1.000000e+00>,
           <1 x float> <float 1.000000e+01>,
           metadata !"round.dynamic",
           metadata !"fpexcept.strict")
  ret <1 x float> %div
}

define <2 x double> @constrained_vector_fdiv_v2f64() {
; CHECK-LABEL: constrained_vector_fdiv_v2f64:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    movapd {{.*#+}} xmm0 = [1.0E+0,2.0E+0]
; CHECK-NEXT:    divpd {{.*}}(%rip), %xmm0
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_fdiv_v2f64:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    vmovapd {{.*#+}} xmm0 = [1.0E+0,2.0E+0]
; AVX-NEXT:    vdivpd {{.*}}(%rip), %xmm0, %xmm0
; AVX-NEXT:    retq
entry:
  %div = call <2 x double> @llvm.experimental.constrained.fdiv.v2f64(
           <2 x double> <double 1.000000e+00, double 2.000000e+00>,
           <2 x double> <double 1.000000e+01, double 1.000000e+01>,
           metadata !"round.dynamic",
           metadata !"fpexcept.strict")
  ret <2 x double> %div
}

define <3 x float> @constrained_vector_fdiv_v3f32() {
; CHECK-LABEL: constrained_vector_fdiv_v3f32:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; CHECK-NEXT:    movss {{.*#+}} xmm2 = mem[0],zero,zero,zero
; CHECK-NEXT:    divss %xmm1, %xmm2
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    divss %xmm1, %xmm0
; CHECK-NEXT:    movss {{.*#+}} xmm3 = mem[0],zero,zero,zero
; CHECK-NEXT:    divss %xmm1, %xmm3
; CHECK-NEXT:    unpcklps {{.*#+}} xmm0 = xmm0[0],xmm3[0],xmm0[1],xmm3[1]
; CHECK-NEXT:    movlhps {{.*#+}} xmm0 = xmm0[0],xmm2[0]
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_fdiv_v3f32:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT:    vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; AVX-NEXT:    vdivss %xmm0, %xmm1, %xmm1
; AVX-NEXT:    vmovss {{.*#+}} xmm2 = mem[0],zero,zero,zero
; AVX-NEXT:    vdivss %xmm0, %xmm2, %xmm2
; AVX-NEXT:    vmovss {{.*#+}} xmm3 = mem[0],zero,zero,zero
; AVX-NEXT:    vdivss %xmm0, %xmm3, %xmm0
; AVX-NEXT:    vinsertps {{.*#+}} xmm0 = xmm2[0],xmm0[0],xmm2[2,3]
; AVX-NEXT:    vinsertps {{.*#+}} xmm0 = xmm0[0,1],xmm1[0],xmm0[3]
; AVX-NEXT:    retq
entry:
  %div = call <3 x float> @llvm.experimental.constrained.fdiv.v3f32(
           <3 x float> <float 1.000000e+00, float 2.000000e+00, float 3.000000e+00>,
           <3 x float> <float 1.000000e+01, float 1.000000e+01, float 1.000000e+01>,
           metadata !"round.dynamic",
           metadata !"fpexcept.strict")
  ret <3 x float> %div
}

define <3 x double> @constrained_vector_fdiv_v3f64() {
; CHECK-LABEL: constrained_vector_fdiv_v3f64:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    movapd {{.*#+}} xmm0 = [1.0E+0,2.0E+0]
; CHECK-NEXT:    divpd {{.*}}(%rip), %xmm0
; CHECK-NEXT:    movsd {{.*#+}} xmm1 = mem[0],zero
; CHECK-NEXT:    divsd {{.*}}(%rip), %xmm1
; CHECK-NEXT:    movsd %xmm1, -{{[0-9]+}}(%rsp)
; CHECK-NEXT:    movapd %xmm0, %xmm1
; CHECK-NEXT:    unpckhpd {{.*#+}} xmm1 = xmm1[1],xmm0[1]
; CHECK-NEXT:    fldl -{{[0-9]+}}(%rsp)
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_fdiv_v3f64:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    vdivsd {{.*}}(%rip), %xmm0, %xmm0
; AVX-NEXT:    vmovapd {{.*#+}} xmm1 = [1.0E+0,2.0E+0]
; AVX-NEXT:    vdivpd {{.*}}(%rip), %xmm1, %xmm1
; AVX-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
; AVX-NEXT:    retq
entry:
  %div = call <3 x double> @llvm.experimental.constrained.fdiv.v3f64(
           <3 x double> <double 1.000000e+00, double 2.000000e+00, double 3.000000e+00>,
           <3 x double> <double 1.000000e+01, double 1.000000e+01, double 1.000000e+01>,
           metadata !"round.dynamic",
           metadata !"fpexcept.strict")
  ret <3 x double> %div
}

define <4 x double> @constrained_vector_fdiv_v4f64() {
; CHECK-LABEL: constrained_vector_fdiv_v4f64:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    movapd {{.*#+}} xmm2 = [1.0E+1,1.0E+1]
; CHECK-NEXT:    movapd {{.*#+}} xmm0 = [1.0E+0,2.0E+0]
; CHECK-NEXT:    divpd %xmm2, %xmm0
; CHECK-NEXT:    movapd {{.*#+}} xmm1 = [3.0E+0,4.0E+0]
; CHECK-NEXT:    divpd %xmm2, %xmm1
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_fdiv_v4f64:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    vmovapd {{.*#+}} ymm0 = [1.0E+0,2.0E+0,3.0E+0,4.0E+0]
; AVX-NEXT:    vdivpd {{.*}}(%rip), %ymm0, %ymm0
; AVX-NEXT:    retq
entry:
  %div = call <4 x double> @llvm.experimental.constrained.fdiv.v4f64(
           <4 x double> <double 1.000000e+00, double 2.000000e+00,
                         double 3.000000e+00, double 4.000000e+00>,
           <4 x double> <double 1.000000e+01, double 1.000000e+01,
                         double 1.000000e+01, double 1.000000e+01>,
           metadata !"round.dynamic",
           metadata !"fpexcept.strict")
  ret <4 x double> %div
}

define <1 x float> @constrained_vector_frem_v1f32() {
; CHECK-LABEL: constrained_vector_frem_v1f32:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    pushq %rax
; CHECK-NEXT:    .cfi_def_cfa_offset 16
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; CHECK-NEXT:    callq fmodf
; CHECK-NEXT:    popq %rax
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_frem_v1f32:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    pushq %rax
; AVX-NEXT:    .cfi_def_cfa_offset 16
; AVX-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT:    vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; AVX-NEXT:    callq fmodf
; AVX-NEXT:    popq %rax
; AVX-NEXT:    .cfi_def_cfa_offset 8
; AVX-NEXT:    retq
entry:
  %rem = call <1 x float> @llvm.experimental.constrained.frem.v1f32(
           <1 x float> <float 1.000000e+00>,
           <1 x float> <float 1.000000e+01>,
           metadata !"round.dynamic",
           metadata !"fpexcept.strict")
  ret <1 x float> %rem
}

define <2 x double> @constrained_vector_frem_v2f64() {
; CHECK-LABEL: constrained_vector_frem_v2f64:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    subq $24, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 32
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    movsd {{.*#+}} xmm1 = mem[0],zero
; CHECK-NEXT:    callq fmod
; CHECK-NEXT:    movaps %xmm0, (%rsp) # 16-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    movsd {{.*#+}} xmm1 = mem[0],zero
; CHECK-NEXT:    callq fmod
; CHECK-NEXT:    unpcklpd (%rsp), %xmm0 # 16-byte Folded Reload
; CHECK-NEXT:    # xmm0 = xmm0[0],mem[0]
; CHECK-NEXT:    addq $24, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_frem_v2f64:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    subq $24, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 32
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    vmovsd {{.*#+}} xmm1 = mem[0],zero
; AVX-NEXT:    callq fmod
; AVX-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    vmovsd {{.*#+}} xmm1 = mem[0],zero
; AVX-NEXT:    callq fmod
; AVX-NEXT:    vunpcklpd (%rsp), %xmm0, %xmm0 # 16-byte Folded Reload
; AVX-NEXT:    # xmm0 = xmm0[0],mem[0]
; AVX-NEXT:    addq $24, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 8
; AVX-NEXT:    retq
entry:
  %rem = call <2 x double> @llvm.experimental.constrained.frem.v2f64(
           <2 x double> <double 1.000000e+00, double 2.000000e+00>,
           <2 x double> <double 1.000000e+01, double 1.000000e+01>,
           metadata !"round.dynamic",
           metadata !"fpexcept.strict")
  ret <2 x double> %rem
}

define <3 x float> @constrained_vector_frem_v3f32() {
; CHECK-LABEL: constrained_vector_frem_v3f32:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    subq $40, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 48
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; CHECK-NEXT:    callq fmodf
; CHECK-NEXT:    movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; CHECK-NEXT:    callq fmodf
; CHECK-NEXT:    movaps %xmm0, (%rsp) # 16-byte Spill
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; CHECK-NEXT:    callq fmodf
; CHECK-NEXT:    movaps (%rsp), %xmm1 # 16-byte Reload
; CHECK-NEXT:    unpcklps {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
; CHECK-NEXT:    unpcklpd {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Folded Reload
; CHECK-NEXT:    # xmm1 = xmm1[0],mem[0]
; CHECK-NEXT:    movaps %xmm1, %xmm0
; CHECK-NEXT:    addq $40, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_frem_v3f32:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    subq $40, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 48
; AVX-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT:    vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; AVX-NEXT:    callq fmodf
; AVX-NEXT:    vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; AVX-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT:    vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; AVX-NEXT:    callq fmodf
; AVX-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
; AVX-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT:    vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; AVX-NEXT:    callq fmodf
; AVX-NEXT:    vmovaps (%rsp), %xmm1 # 16-byte Reload
; AVX-NEXT:    vinsertps {{.*#+}} xmm0 = xmm1[0],xmm0[0],xmm1[2,3]
; AVX-NEXT:    vinsertps $32, {{[-0-9]+}}(%r{{[sb]}}p), %xmm0, %xmm0 # 16-byte Folded Reload
; AVX-NEXT:    # xmm0 = xmm0[0,1],mem[0],xmm0[3]
; AVX-NEXT:    addq $40, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 8
; AVX-NEXT:    retq
entry:
  %rem = call <3 x float> @llvm.experimental.constrained.frem.v3f32(
           <3 x float> <float 1.000000e+00, float 2.000000e+00, float 3.000000e+00>,
           <3 x float> <float 1.000000e+01, float 1.000000e+01, float 1.000000e+01>,
           metadata !"round.dynamic",
           metadata !"fpexcept.strict")
  ret <3 x float> %rem
}

define <3 x double> @constrained_vector_frem_v3f64() {
; CHECK-LABEL: constrained_vector_frem_v3f64:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    subq $24, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 32
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    movsd {{.*#+}} xmm1 = mem[0],zero
; CHECK-NEXT:    callq fmod
; CHECK-NEXT:    movsd %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    movsd {{.*#+}} xmm1 = mem[0],zero
; CHECK-NEXT:    callq fmod
; CHECK-NEXT:    movsd %xmm0, (%rsp) # 8-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    movsd {{.*#+}} xmm1 = mem[0],zero
; CHECK-NEXT:    callq fmod
; CHECK-NEXT:    movsd %xmm0, {{[0-9]+}}(%rsp)
; CHECK-NEXT:    fldl {{[0-9]+}}(%rsp)
; CHECK-NEXT:    movsd {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 8-byte Reload
; CHECK-NEXT:    # xmm0 = mem[0],zero
; CHECK-NEXT:    movsd (%rsp), %xmm1 # 8-byte Reload
; CHECK-NEXT:    # xmm1 = mem[0],zero
; CHECK-NEXT:    addq $24, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_frem_v3f64:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    subq $56, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 64
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    vmovsd {{.*#+}} xmm1 = mem[0],zero
; AVX-NEXT:    callq fmod
; AVX-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    vmovsd {{.*#+}} xmm1 = mem[0],zero
; AVX-NEXT:    callq fmod
; AVX-NEXT:    vunpcklpd (%rsp), %xmm0, %xmm0 # 16-byte Folded Reload
; AVX-NEXT:    # xmm0 = xmm0[0],mem[0]
; AVX-NEXT:    vmovups %ymm0, (%rsp) # 32-byte Spill
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    vmovsd {{.*#+}} xmm1 = mem[0],zero
; AVX-NEXT:    vzeroupper
; AVX-NEXT:    callq fmod
; AVX-NEXT:    vmovups (%rsp), %ymm1 # 32-byte Reload
; AVX-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
; AVX-NEXT:    addq $56, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 8
; AVX-NEXT:    retq
entry:
  %rem = call <3 x double> @llvm.experimental.constrained.frem.v3f64(
           <3 x double> <double 1.000000e+00, double 2.000000e+00, double 3.000000e+00>,
           <3 x double> <double 1.000000e+01, double 1.000000e+01, double 1.000000e+01>,
           metadata !"round.dynamic",
           metadata !"fpexcept.strict")
  ret <3 x double> %rem
}

define <4 x double> @constrained_vector_frem_v4f64() {
; CHECK-LABEL: constrained_vector_frem_v4f64:
; CHECK:       # %bb.0:
; CHECK-NEXT:    subq $40, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 48
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    movsd {{.*#+}} xmm1 = mem[0],zero
; CHECK-NEXT:    callq fmod
; CHECK-NEXT:    movaps %xmm0, (%rsp) # 16-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    movsd {{.*#+}} xmm1 = mem[0],zero
; CHECK-NEXT:    callq fmod
; CHECK-NEXT:    unpcklpd (%rsp), %xmm0 # 16-byte Folded Reload
; CHECK-NEXT:    # xmm0 = xmm0[0],mem[0]
; CHECK-NEXT:    movaps %xmm0, (%rsp) # 16-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    movsd {{.*#+}} xmm1 = mem[0],zero
; CHECK-NEXT:    callq fmod
; CHECK-NEXT:    movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    movsd {{.*#+}} xmm1 = mem[0],zero
; CHECK-NEXT:    callq fmod
; CHECK-NEXT:    movaps %xmm0, %xmm1
; CHECK-NEXT:    unpcklpd {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Folded Reload
; CHECK-NEXT:    # xmm1 = xmm1[0],mem[0]
; CHECK-NEXT:    movaps (%rsp), %xmm0 # 16-byte Reload
; CHECK-NEXT:    addq $40, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_frem_v4f64:
; AVX:       # %bb.0:
; AVX-NEXT:    subq $40, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 48
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    vmovsd {{.*#+}} xmm1 = mem[0],zero
; AVX-NEXT:    callq fmod
; AVX-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    vmovsd {{.*#+}} xmm1 = mem[0],zero
; AVX-NEXT:    callq fmod
; AVX-NEXT:    vunpcklpd (%rsp), %xmm0, %xmm0 # 16-byte Folded Reload
; AVX-NEXT:    # xmm0 = xmm0[0],mem[0]
; AVX-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    vmovsd {{.*#+}} xmm1 = mem[0],zero
; AVX-NEXT:    callq fmod
; AVX-NEXT:    vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    vmovsd {{.*#+}} xmm1 = mem[0],zero
; AVX-NEXT:    callq fmod
; AVX-NEXT:    vunpcklpd {{[-0-9]+}}(%r{{[sb]}}p), %xmm0, %xmm0 # 16-byte Folded Reload
; AVX-NEXT:    # xmm0 = xmm0[0],mem[0]
; AVX-NEXT:    vinsertf128 $1, (%rsp), %ymm0, %ymm0 # 16-byte Folded Reload
; AVX-NEXT:    addq $40, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 8
; AVX-NEXT:    retq
  %rem = call <4 x double> @llvm.experimental.constrained.frem.v4f64(
           <4 x double> <double 1.000000e+00, double 2.000000e+00,
                         double 3.000000e+00, double 4.000000e+00>,
           <4 x double> <double 1.000000e+01, double 1.000000e+01,
                         double 1.000000e+01, double 1.000000e+01>,
           metadata !"round.dynamic",
           metadata !"fpexcept.strict")
  ret <4 x double> %rem
}

define <1 x float> @constrained_vector_fmul_v1f32() {
; CHECK-LABEL: constrained_vector_fmul_v1f32:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    mulss {{.*}}(%rip), %xmm0
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_fmul_v1f32:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT:    vmulss {{.*}}(%rip), %xmm0, %xmm0
; AVX-NEXT:    retq
entry:
  %mul = call <1 x float> @llvm.experimental.constrained.fmul.v1f32(
           <1 x float> <float 0x7FF0000000000000>,
           <1 x float> <float 2.000000e+00>,
           metadata !"round.dynamic",
           metadata !"fpexcept.strict")
  ret <1 x float> %mul
}

define <2 x double> @constrained_vector_fmul_v2f64() {
; CHECK-LABEL: constrained_vector_fmul_v2f64:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    movapd {{.*#+}} xmm0 = [1.7976931348623157E+308,1.7976931348623157E+308]
; CHECK-NEXT:    mulpd {{.*}}(%rip), %xmm0
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_fmul_v2f64:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    vmovapd {{.*#+}} xmm0 = [1.7976931348623157E+308,1.7976931348623157E+308]
; AVX-NEXT:    vmulpd {{.*}}(%rip), %xmm0, %xmm0
; AVX-NEXT:    retq
entry:
  %mul = call <2 x double> @llvm.experimental.constrained.fmul.v2f64(
           <2 x double> <double 0x7FEFFFFFFFFFFFFF, double 0x7FEFFFFFFFFFFFFF>,
           <2 x double> <double 2.000000e+00, double 3.000000e+00>,
           metadata !"round.dynamic",
           metadata !"fpexcept.strict")
  ret <2 x double> %mul
}

define <3 x float> @constrained_vector_fmul_v3f32() {
; CHECK-LABEL: constrained_vector_fmul_v3f32:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; CHECK-NEXT:    movss {{.*#+}} xmm2 = mem[0],zero,zero,zero
; CHECK-NEXT:    mulss %xmm1, %xmm2
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    mulss %xmm1, %xmm0
; CHECK-NEXT:    mulss {{.*}}(%rip), %xmm1
; CHECK-NEXT:    unpcklps {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; CHECK-NEXT:    movlhps {{.*#+}} xmm0 = xmm0[0],xmm2[0]
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_fmul_v3f32:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT:    vmulss {{.*}}(%rip), %xmm0, %xmm1
; AVX-NEXT:    vmulss {{.*}}(%rip), %xmm0, %xmm2
; AVX-NEXT:    vmulss {{.*}}(%rip), %xmm0, %xmm0
; AVX-NEXT:    vinsertps {{.*#+}} xmm0 = xmm2[0],xmm0[0],xmm2[2,3]
; AVX-NEXT:    vinsertps {{.*#+}} xmm0 = xmm0[0,1],xmm1[0],xmm0[3]
; AVX-NEXT:    retq
entry:
  %mul = call <3 x float> @llvm.experimental.constrained.fmul.v3f32(
           <3 x float> <float 0x7FF0000000000000, float 0x7FF0000000000000,
                        float 0x7FF0000000000000>,
           <3 x float> <float 1.000000e+00, float 1.000000e+01, float 1.000000e+02>,
           metadata !"round.dynamic",
           metadata !"fpexcept.strict")
  ret <3 x float> %mul
}

define <3 x double> @constrained_vector_fmul_v3f64() {
; CHECK-LABEL: constrained_vector_fmul_v3f64:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    movapd {{.*#+}} xmm0 = [1.7976931348623157E+308,1.7976931348623157E+308]
; CHECK-NEXT:    mulpd {{.*}}(%rip), %xmm0
; CHECK-NEXT:    movsd {{.*#+}} xmm1 = mem[0],zero
; CHECK-NEXT:    mulsd {{.*}}(%rip), %xmm1
; CHECK-NEXT:    movsd %xmm1, -{{[0-9]+}}(%rsp)
; CHECK-NEXT:    movapd %xmm0, %xmm1
; CHECK-NEXT:    unpckhpd {{.*#+}} xmm1 = xmm1[1],xmm0[1]
; CHECK-NEXT:    fldl -{{[0-9]+}}(%rsp)
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_fmul_v3f64:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    vmulsd {{.*}}(%rip), %xmm0, %xmm0
; AVX-NEXT:    vmovapd {{.*#+}} xmm1 = [1.7976931348623157E+308,1.7976931348623157E+308]
; AVX-NEXT:    vmulpd {{.*}}(%rip), %xmm1, %xmm1
; AVX-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
; AVX-NEXT:    retq
entry:
  %mul = call <3 x double> @llvm.experimental.constrained.fmul.v3f64(
           <3 x double> <double 0x7FEFFFFFFFFFFFFF, double 0x7FEFFFFFFFFFFFFF,
                         double 0x7FEFFFFFFFFFFFFF>,
           <3 x double> <double 1.000000e+00, double 1.000000e+01, double 1.000000e+02>,
           metadata !"round.dynamic",
           metadata !"fpexcept.strict")
  ret <3 x double> %mul
}

define <4 x double> @constrained_vector_fmul_v4f64() {
; CHECK-LABEL: constrained_vector_fmul_v4f64:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    movapd {{.*#+}} xmm1 = [1.7976931348623157E+308,1.7976931348623157E+308]
; CHECK-NEXT:    movapd {{.*#+}} xmm0 = [2.0E+0,3.0E+0]
; CHECK-NEXT:    mulpd %xmm1, %xmm0
; CHECK-NEXT:    mulpd {{.*}}(%rip), %xmm1
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_fmul_v4f64:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    vmovapd {{.*#+}} ymm0 = [1.7976931348623157E+308,1.7976931348623157E+308,1.7976931348623157E+308,1.7976931348623157E+308]
; AVX-NEXT:    vmulpd {{.*}}(%rip), %ymm0, %ymm0
; AVX-NEXT:    retq
entry:
  %mul = call <4 x double> @llvm.experimental.constrained.fmul.v4f64(
           <4 x double> <double 0x7FEFFFFFFFFFFFFF, double 0x7FEFFFFFFFFFFFFF,
                         double 0x7FEFFFFFFFFFFFFF, double 0x7FEFFFFFFFFFFFFF>,
           <4 x double> <double 2.000000e+00, double 3.000000e+00,
                         double 4.000000e+00, double 5.000000e+00>,
           metadata !"round.dynamic",
           metadata !"fpexcept.strict")
  ret <4 x double> %mul
}

define <1 x float> @constrained_vector_fadd_v1f32() {
; CHECK-LABEL: constrained_vector_fadd_v1f32:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    addss {{.*}}(%rip), %xmm0
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_fadd_v1f32:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT:    vaddss {{.*}}(%rip), %xmm0, %xmm0
; AVX-NEXT:    retq
entry:
  %add = call <1 x float> @llvm.experimental.constrained.fadd.v1f32(
           <1 x float> <float 0x7FF0000000000000>,
           <1 x float> <float 1.0>,
           metadata !"round.dynamic",
           metadata !"fpexcept.strict")
  ret <1 x float> %add
}

define <2 x double> @constrained_vector_fadd_v2f64() {
; CHECK-LABEL: constrained_vector_fadd_v2f64:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    movapd {{.*#+}} xmm0 = [1.7976931348623157E+308,1.7976931348623157E+308]
; CHECK-NEXT:    addpd {{.*}}(%rip), %xmm0
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_fadd_v2f64:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    vmovapd {{.*#+}} xmm0 = [1.7976931348623157E+308,1.7976931348623157E+308]
; AVX-NEXT:    vaddpd {{.*}}(%rip), %xmm0, %xmm0
; AVX-NEXT:    retq
entry:
  %add = call <2 x double> @llvm.experimental.constrained.fadd.v2f64(
           <2 x double> <double 0x7FEFFFFFFFFFFFFF, double 0x7FEFFFFFFFFFFFFF>,
           <2 x double> <double 1.000000e+00, double 1.000000e-01>,
           metadata !"round.dynamic",
           metadata !"fpexcept.strict")
  ret <2 x double> %add
}

define <3 x float> @constrained_vector_fadd_v3f32() {
; CHECK-LABEL: constrained_vector_fadd_v3f32:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    xorps %xmm1, %xmm1
; CHECK-NEXT:    movss {{.*#+}} xmm2 = mem[0],zero,zero,zero
; CHECK-NEXT:    addss %xmm2, %xmm1
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    addss %xmm2, %xmm0
; CHECK-NEXT:    addss {{.*}}(%rip), %xmm2
; CHECK-NEXT:    unpcklps {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; CHECK-NEXT:    movlhps {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_fadd_v3f32:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    vxorps %xmm0, %xmm0, %xmm0
; AVX-NEXT:    vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; AVX-NEXT:    vaddss %xmm0, %xmm1, %xmm0
; AVX-NEXT:    vaddss {{.*}}(%rip), %xmm1, %xmm2
; AVX-NEXT:    vaddss {{.*}}(%rip), %xmm1, %xmm1
; AVX-NEXT:    vinsertps {{.*#+}} xmm1 = xmm2[0],xmm1[0],xmm2[2,3]
; AVX-NEXT:    vinsertps {{.*#+}} xmm0 = xmm1[0,1],xmm0[0],xmm1[3]
; AVX-NEXT:    retq
entry:
  %add = call <3 x float> @llvm.experimental.constrained.fadd.v3f32(
           <3 x float> <float 0xFFFFFFFFE0000000, float 0xFFFFFFFFE0000000,
                        float 0xFFFFFFFFE0000000>,
           <3 x float> <float 2.0, float 1.0, float 0.0>,
           metadata !"round.dynamic",
           metadata !"fpexcept.strict")
  ret <3 x float> %add
}

define <3 x double> @constrained_vector_fadd_v3f64() {
; CHECK-LABEL: constrained_vector_fadd_v3f64:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    movapd {{.*#+}} xmm0 = [1.7976931348623157E+308,1.7976931348623157E+308]
; CHECK-NEXT:    addpd {{.*}}(%rip), %xmm0
; CHECK-NEXT:    xorpd %xmm1, %xmm1
; CHECK-NEXT:    addsd {{.*}}(%rip), %xmm1
; CHECK-NEXT:    movsd %xmm1, -{{[0-9]+}}(%rsp)
; CHECK-NEXT:    movapd %xmm0, %xmm1
; CHECK-NEXT:    unpckhpd {{.*#+}} xmm1 = xmm1[1],xmm0[1]
; CHECK-NEXT:    fldl -{{[0-9]+}}(%rsp)
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_fadd_v3f64:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    vxorpd %xmm0, %xmm0, %xmm0
; AVX-NEXT:    vaddsd {{.*}}(%rip), %xmm0, %xmm0
; AVX-NEXT:    vmovapd {{.*#+}} xmm1 = [1.7976931348623157E+308,1.7976931348623157E+308]
; AVX-NEXT:    vaddpd {{.*}}(%rip), %xmm1, %xmm1
; AVX-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
; AVX-NEXT:    retq
entry:
  %add = call <3 x double> @llvm.experimental.constrained.fadd.v3f64(
           <3 x double> <double 0x7FEFFFFFFFFFFFFF, double 0x7FEFFFFFFFFFFFFF,
                         double 0x7FEFFFFFFFFFFFFF>,
           <3 x double> <double 2.0, double 1.0, double 0.0>,
           metadata !"round.dynamic",
           metadata !"fpexcept.strict")
  ret <3 x double> %add
}

define <4 x double> @constrained_vector_fadd_v4f64() {
; CHECK-LABEL: constrained_vector_fadd_v4f64:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    movapd {{.*#+}} xmm1 = [1.7976931348623157E+308,1.7976931348623157E+308]
; CHECK-NEXT:    movapd {{.*#+}} xmm0 = [1.0E+0,1.0000000000000001E-1]
; CHECK-NEXT:    addpd %xmm1, %xmm0
; CHECK-NEXT:    addpd {{.*}}(%rip), %xmm1
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_fadd_v4f64:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    vmovapd {{.*#+}} ymm0 = [1.7976931348623157E+308,1.7976931348623157E+308,1.7976931348623157E+308,1.7976931348623157E+308]
; AVX-NEXT:    vaddpd {{.*}}(%rip), %ymm0, %ymm0
; AVX-NEXT:    retq
entry:
  %add = call <4 x double> @llvm.experimental.constrained.fadd.v4f64(
           <4 x double> <double 0x7FEFFFFFFFFFFFFF, double 0x7FEFFFFFFFFFFFFF,
                         double 0x7FEFFFFFFFFFFFFF, double 0x7FEFFFFFFFFFFFFF>,
           <4 x double> <double 1.000000e+00, double 1.000000e-01,
                         double 2.000000e+00, double 2.000000e-01>,
           metadata !"round.dynamic",
           metadata !"fpexcept.strict")
  ret <4 x double> %add
}

define <1 x float> @constrained_vector_fsub_v1f32() {
; CHECK-LABEL: constrained_vector_fsub_v1f32:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    subss {{.*}}(%rip), %xmm0
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_fsub_v1f32:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT:    vsubss {{.*}}(%rip), %xmm0, %xmm0
; AVX-NEXT:    retq
entry:
  %sub = call <1 x float> @llvm.experimental.constrained.fsub.v1f32(
           <1 x float> <float 0x7FF0000000000000>,
           <1 x float> <float 1.000000e+00>,
           metadata !"round.dynamic",
           metadata !"fpexcept.strict")
  ret <1 x float> %sub
}

define <2 x double> @constrained_vector_fsub_v2f64() {
; CHECK-LABEL: constrained_vector_fsub_v2f64:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    movapd {{.*#+}} xmm0 = [-1.7976931348623157E+308,-1.7976931348623157E+308]
; CHECK-NEXT:    subpd {{.*}}(%rip), %xmm0
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_fsub_v2f64:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    vmovapd {{.*#+}} xmm0 = [-1.7976931348623157E+308,-1.7976931348623157E+308]
; AVX-NEXT:    vsubpd {{.*}}(%rip), %xmm0, %xmm0
; AVX-NEXT:    retq
entry:
  %sub = call <2 x double> @llvm.experimental.constrained.fsub.v2f64(
           <2 x double> <double 0xFFEFFFFFFFFFFFFF, double 0xFFEFFFFFFFFFFFFF>,
           <2 x double> <double 1.000000e+00, double 1.000000e-01>,
           metadata !"round.dynamic",
           metadata !"fpexcept.strict")
  ret <2 x double> %sub
}

define <3 x float> @constrained_vector_fsub_v3f32() {
; CHECK-LABEL: constrained_vector_fsub_v3f32:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    xorps %xmm0, %xmm0
; CHECK-NEXT:    movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; CHECK-NEXT:    movaps %xmm1, %xmm2
; CHECK-NEXT:    subss %xmm0, %xmm2
; CHECK-NEXT:    movaps %xmm1, %xmm0
; CHECK-NEXT:    subss {{.*}}(%rip), %xmm0
; CHECK-NEXT:    subss {{.*}}(%rip), %xmm1
; CHECK-NEXT:    unpcklps {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; CHECK-NEXT:    movlhps {{.*#+}} xmm0 = xmm0[0],xmm2[0]
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_fsub_v3f32:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    vxorps %xmm0, %xmm0, %xmm0
; AVX-NEXT:    vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; AVX-NEXT:    vsubss %xmm0, %xmm1, %xmm0
; AVX-NEXT:    vsubss {{.*}}(%rip), %xmm1, %xmm2
; AVX-NEXT:    vsubss {{.*}}(%rip), %xmm1, %xmm1
; AVX-NEXT:    vinsertps {{.*#+}} xmm1 = xmm2[0],xmm1[0],xmm2[2,3]
; AVX-NEXT:    vinsertps {{.*#+}} xmm0 = xmm1[0,1],xmm0[0],xmm1[3]
; AVX-NEXT:    retq
entry:
  %sub = call <3 x float> @llvm.experimental.constrained.fsub.v3f32(
           <3 x float> <float 0xFFFFFFFFE0000000, float 0xFFFFFFFFE0000000,
                        float 0xFFFFFFFFE0000000>,
           <3 x float> <float 2.0, float 1.0, float 0.0>,
           metadata !"round.dynamic",
           metadata !"fpexcept.strict")
  ret <3 x float> %sub
}

define <3 x double> @constrained_vector_fsub_v3f64() {
; CHECK-LABEL: constrained_vector_fsub_v3f64:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    xorpd %xmm0, %xmm0
; CHECK-NEXT:    movsd {{.*#+}} xmm1 = mem[0],zero
; CHECK-NEXT:    subsd %xmm0, %xmm1
; CHECK-NEXT:    movapd {{.*#+}} xmm0 = [-1.7976931348623157E+308,-1.7976931348623157E+308]
; CHECK-NEXT:    subpd {{.*}}(%rip), %xmm0
; CHECK-NEXT:    movsd %xmm1, -{{[0-9]+}}(%rsp)
; CHECK-NEXT:    movapd %xmm0, %xmm1
; CHECK-NEXT:    unpckhpd {{.*#+}} xmm1 = xmm1[1],xmm0[1]
; CHECK-NEXT:    fldl -{{[0-9]+}}(%rsp)
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_fsub_v3f64:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    vxorpd %xmm0, %xmm0, %xmm0
; AVX-NEXT:    vmovsd {{.*#+}} xmm1 = mem[0],zero
; AVX-NEXT:    vsubsd %xmm0, %xmm1, %xmm0
; AVX-NEXT:    vmovapd {{.*#+}} xmm1 = [-1.7976931348623157E+308,-1.7976931348623157E+308]
; AVX-NEXT:    vsubpd {{.*}}(%rip), %xmm1, %xmm1
; AVX-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
; AVX-NEXT:    retq
entry:
  %sub = call <3 x double> @llvm.experimental.constrained.fsub.v3f64(
           <3 x double> <double 0xFFEFFFFFFFFFFFFF, double 0xFFEFFFFFFFFFFFFF,
                         double 0xFFEFFFFFFFFFFFFF>,
           <3 x double> <double 2.0, double 1.0, double 0.0>,
           metadata !"round.dynamic",
           metadata !"fpexcept.strict")
  ret <3 x double> %sub
}

define <4 x double> @constrained_vector_fsub_v4f64() {
; CHECK-LABEL: constrained_vector_fsub_v4f64:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    movapd {{.*#+}} xmm1 = [-1.7976931348623157E+308,-1.7976931348623157E+308]
; CHECK-NEXT:    movapd %xmm1, %xmm0
; CHECK-NEXT:    subpd {{.*}}(%rip), %xmm0
; CHECK-NEXT:    subpd {{.*}}(%rip), %xmm1
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_fsub_v4f64:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    vmovapd {{.*#+}} ymm0 = [-1.7976931348623157E+308,-1.7976931348623157E+308,-1.7976931348623157E+308,-1.7976931348623157E+308]
; AVX-NEXT:    vsubpd {{.*}}(%rip), %ymm0, %ymm0
; AVX-NEXT:    retq
entry:
  %sub = call <4 x double> @llvm.experimental.constrained.fsub.v4f64(
           <4 x double> <double 0xFFEFFFFFFFFFFFFF, double 0xFFEFFFFFFFFFFFFF,
                         double 0xFFEFFFFFFFFFFFFF, double 0xFFEFFFFFFFFFFFFF>,
           <4 x double> <double 1.000000e+00, double 1.000000e-01,
                         double 2.000000e+00, double 2.000000e-01>,
           metadata !"round.dynamic",
           metadata !"fpexcept.strict")
  ret <4 x double> %sub
}

define <1 x float> @constrained_vector_sqrt_v1f32() {
; CHECK-LABEL: constrained_vector_sqrt_v1f32:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    sqrtss %xmm0, %xmm0
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_sqrt_v1f32:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT:    vsqrtss %xmm0, %xmm0, %xmm0
; AVX-NEXT:    retq
entry:
  %sqrt = call <1 x float> @llvm.experimental.constrained.sqrt.v1f32(
                              <1 x float> <float 42.0>,
                              metadata !"round.dynamic",
                              metadata !"fpexcept.strict")
  ret <1 x float> %sqrt
}

define <2 x double> @constrained_vector_sqrt_v2f64() {
; CHECK-LABEL: constrained_vector_sqrt_v2f64:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    sqrtpd {{.*}}(%rip), %xmm0
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_sqrt_v2f64:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    vsqrtpd {{.*}}(%rip), %xmm0
; AVX-NEXT:    retq
entry:
  %sqrt = call <2 x double> @llvm.experimental.constrained.sqrt.v2f64(
                              <2 x double> <double 42.0, double 42.1>,
                              metadata !"round.dynamic",
                              metadata !"fpexcept.strict")
  ret <2 x double> %sqrt
}

define <3 x float> @constrained_vector_sqrt_v3f32() {
; CHECK-LABEL: constrained_vector_sqrt_v3f32:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    sqrtss %xmm0, %xmm1
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    sqrtss %xmm0, %xmm0
; CHECK-NEXT:    movss {{.*#+}} xmm2 = mem[0],zero,zero,zero
; CHECK-NEXT:    sqrtss %xmm2, %xmm2
; CHECK-NEXT:    unpcklps {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; CHECK-NEXT:    movlhps {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_sqrt_v3f32:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT:    vsqrtss %xmm0, %xmm0, %xmm0
; AVX-NEXT:    vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; AVX-NEXT:    vsqrtss %xmm1, %xmm1, %xmm1
; AVX-NEXT:    vmovss {{.*#+}} xmm2 = mem[0],zero,zero,zero
; AVX-NEXT:    vsqrtss %xmm2, %xmm2, %xmm2
; AVX-NEXT:    vinsertps {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[2,3]
; AVX-NEXT:    vinsertps {{.*#+}} xmm0 = xmm1[0,1],xmm0[0],xmm1[3]
; AVX-NEXT:    retq
entry:
  %sqrt = call <3 x float> @llvm.experimental.constrained.sqrt.v3f32(
                              <3 x float> <float 42.0, float 43.0, float 44.0>,
                              metadata !"round.dynamic",
                              metadata !"fpexcept.strict")
  ret <3 x float> %sqrt
}

define <3 x double> @constrained_vector_sqrt_v3f64() {
; CHECK-LABEL: constrained_vector_sqrt_v3f64:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    sqrtsd %xmm0, %xmm1
; CHECK-NEXT:    sqrtpd {{.*}}(%rip), %xmm0
; CHECK-NEXT:    movsd %xmm1, -{{[0-9]+}}(%rsp)
; CHECK-NEXT:    movapd %xmm0, %xmm1
; CHECK-NEXT:    unpckhpd {{.*#+}} xmm1 = xmm1[1],xmm0[1]
; CHECK-NEXT:    fldl -{{[0-9]+}}(%rsp)
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_sqrt_v3f64:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    vsqrtsd %xmm0, %xmm0, %xmm0
; AVX-NEXT:    vsqrtpd {{.*}}(%rip), %xmm1
; AVX-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
; AVX-NEXT:    retq
entry:
  %sqrt = call <3 x double> @llvm.experimental.constrained.sqrt.v3f64(
                          <3 x double> <double 42.0, double 42.1, double 42.2>,
                          metadata !"round.dynamic",
                          metadata !"fpexcept.strict")
  ret <3 x double> %sqrt
}

define <4 x double> @constrained_vector_sqrt_v4f64() {
; CHECK-LABEL: constrained_vector_sqrt_v4f64:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    sqrtpd {{.*}}(%rip), %xmm0
; CHECK-NEXT:    sqrtpd {{.*}}(%rip), %xmm1
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_sqrt_v4f64:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    vsqrtpd {{.*}}(%rip), %ymm0
; AVX-NEXT:    retq
 entry:
  %sqrt = call <4 x double> @llvm.experimental.constrained.sqrt.v4f64(
                              <4 x double> <double 42.0, double 42.1,
                                            double 42.2, double 42.3>,
                              metadata !"round.dynamic",
                              metadata !"fpexcept.strict")
  ret <4 x double> %sqrt
}

define <1 x float> @constrained_vector_pow_v1f32() {
; CHECK-LABEL: constrained_vector_pow_v1f32:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    pushq %rax
; CHECK-NEXT:    .cfi_def_cfa_offset 16
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; CHECK-NEXT:    callq powf
; CHECK-NEXT:    popq %rax
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_pow_v1f32:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    pushq %rax
; AVX-NEXT:    .cfi_def_cfa_offset 16
; AVX-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT:    vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; AVX-NEXT:    callq powf
; AVX-NEXT:    popq %rax
; AVX-NEXT:    .cfi_def_cfa_offset 8
; AVX-NEXT:    retq
entry:
  %pow = call <1 x float> @llvm.experimental.constrained.pow.v1f32(
                             <1 x float> <float 42.0>,
                             <1 x float> <float 3.0>,
                             metadata !"round.dynamic",
                             metadata !"fpexcept.strict")
  ret <1 x float> %pow
}

define <2 x double> @constrained_vector_pow_v2f64() {
; CHECK-LABEL: constrained_vector_pow_v2f64:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    subq $24, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 32
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    movsd {{.*#+}} xmm1 = mem[0],zero
; CHECK-NEXT:    callq pow
; CHECK-NEXT:    movaps %xmm0, (%rsp) # 16-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    movsd {{.*#+}} xmm1 = mem[0],zero
; CHECK-NEXT:    callq pow
; CHECK-NEXT:    unpcklpd (%rsp), %xmm0 # 16-byte Folded Reload
; CHECK-NEXT:    # xmm0 = xmm0[0],mem[0]
; CHECK-NEXT:    addq $24, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_pow_v2f64:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    subq $24, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 32
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    vmovsd {{.*#+}} xmm1 = mem[0],zero
; AVX-NEXT:    callq pow
; AVX-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    vmovsd {{.*#+}} xmm1 = mem[0],zero
; AVX-NEXT:    callq pow
; AVX-NEXT:    vunpcklpd (%rsp), %xmm0, %xmm0 # 16-byte Folded Reload
; AVX-NEXT:    # xmm0 = xmm0[0],mem[0]
; AVX-NEXT:    addq $24, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 8
; AVX-NEXT:    retq
entry:
  %pow = call <2 x double> @llvm.experimental.constrained.pow.v2f64(
                             <2 x double> <double 42.1, double 42.2>,
                             <2 x double> <double 3.0, double 3.0>,
                             metadata !"round.dynamic",
                             metadata !"fpexcept.strict")
  ret <2 x double> %pow
}

define <3 x float> @constrained_vector_pow_v3f32() {
; CHECK-LABEL: constrained_vector_pow_v3f32:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    subq $40, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 48
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; CHECK-NEXT:    callq powf
; CHECK-NEXT:    movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; CHECK-NEXT:    callq powf
; CHECK-NEXT:    movaps %xmm0, (%rsp) # 16-byte Spill
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; CHECK-NEXT:    callq powf
; CHECK-NEXT:    movaps (%rsp), %xmm1 # 16-byte Reload
; CHECK-NEXT:    unpcklps {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
; CHECK-NEXT:    unpcklpd {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Folded Reload
; CHECK-NEXT:    # xmm1 = xmm1[0],mem[0]
; CHECK-NEXT:    movaps %xmm1, %xmm0
; CHECK-NEXT:    addq $40, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_pow_v3f32:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    subq $40, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 48
; AVX-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT:    vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; AVX-NEXT:    callq powf
; AVX-NEXT:    vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; AVX-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT:    vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; AVX-NEXT:    callq powf
; AVX-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
; AVX-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT:    vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; AVX-NEXT:    callq powf
; AVX-NEXT:    vmovaps (%rsp), %xmm1 # 16-byte Reload
; AVX-NEXT:    vinsertps {{.*#+}} xmm0 = xmm1[0],xmm0[0],xmm1[2,3]
; AVX-NEXT:    vinsertps $32, {{[-0-9]+}}(%r{{[sb]}}p), %xmm0, %xmm0 # 16-byte Folded Reload
; AVX-NEXT:    # xmm0 = xmm0[0,1],mem[0],xmm0[3]
; AVX-NEXT:    addq $40, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 8
; AVX-NEXT:    retq
entry:
  %pow = call <3 x float> @llvm.experimental.constrained.pow.v3f32(
                             <3 x float> <float 42.0, float 43.0, float 44.0>,
                             <3 x float> <float 3.0, float 3.0, float 3.0>,
                             metadata !"round.dynamic",
                             metadata !"fpexcept.strict")
  ret <3 x float> %pow
}

define <3 x double> @constrained_vector_pow_v3f64() {
; CHECK-LABEL: constrained_vector_pow_v3f64:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    subq $24, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 32
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    movsd {{.*#+}} xmm1 = mem[0],zero
; CHECK-NEXT:    callq pow
; CHECK-NEXT:    movsd %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    movsd {{.*#+}} xmm1 = mem[0],zero
; CHECK-NEXT:    callq pow
; CHECK-NEXT:    movsd %xmm0, (%rsp) # 8-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    movsd {{.*#+}} xmm1 = mem[0],zero
; CHECK-NEXT:    callq pow
; CHECK-NEXT:    movsd %xmm0, {{[0-9]+}}(%rsp)
; CHECK-NEXT:    fldl {{[0-9]+}}(%rsp)
; CHECK-NEXT:    movsd {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 8-byte Reload
; CHECK-NEXT:    # xmm0 = mem[0],zero
; CHECK-NEXT:    movsd (%rsp), %xmm1 # 8-byte Reload
; CHECK-NEXT:    # xmm1 = mem[0],zero
; CHECK-NEXT:    addq $24, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_pow_v3f64:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    subq $56, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 64
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    vmovsd {{.*#+}} xmm1 = mem[0],zero
; AVX-NEXT:    callq pow
; AVX-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    vmovsd {{.*#+}} xmm1 = mem[0],zero
; AVX-NEXT:    callq pow
; AVX-NEXT:    vunpcklpd (%rsp), %xmm0, %xmm0 # 16-byte Folded Reload
; AVX-NEXT:    # xmm0 = xmm0[0],mem[0]
; AVX-NEXT:    vmovups %ymm0, (%rsp) # 32-byte Spill
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    vmovsd {{.*#+}} xmm1 = mem[0],zero
; AVX-NEXT:    vzeroupper
; AVX-NEXT:    callq pow
; AVX-NEXT:    vmovups (%rsp), %ymm1 # 32-byte Reload
; AVX-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
; AVX-NEXT:    addq $56, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 8
; AVX-NEXT:    retq
entry:
  %pow = call <3 x double> @llvm.experimental.constrained.pow.v3f64(
                          <3 x double> <double 42.0, double 42.1, double 42.2>,
                          <3 x double> <double 3.0, double 3.0, double 3.0>,
                          metadata !"round.dynamic",
                          metadata !"fpexcept.strict")
  ret <3 x double> %pow
}

define <4 x double> @constrained_vector_pow_v4f64() {
; CHECK-LABEL: constrained_vector_pow_v4f64:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    subq $40, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 48
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    movsd {{.*#+}} xmm1 = mem[0],zero
; CHECK-NEXT:    callq pow
; CHECK-NEXT:    movaps %xmm0, (%rsp) # 16-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    movsd {{.*#+}} xmm1 = mem[0],zero
; CHECK-NEXT:    callq pow
; CHECK-NEXT:    unpcklpd (%rsp), %xmm0 # 16-byte Folded Reload
; CHECK-NEXT:    # xmm0 = xmm0[0],mem[0]
; CHECK-NEXT:    movaps %xmm0, (%rsp) # 16-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    movsd {{.*#+}} xmm1 = mem[0],zero
; CHECK-NEXT:    callq pow
; CHECK-NEXT:    movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    movsd {{.*#+}} xmm1 = mem[0],zero
; CHECK-NEXT:    callq pow
; CHECK-NEXT:    movaps %xmm0, %xmm1
; CHECK-NEXT:    unpcklpd {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Folded Reload
; CHECK-NEXT:    # xmm1 = xmm1[0],mem[0]
; CHECK-NEXT:    movaps (%rsp), %xmm0 # 16-byte Reload
; CHECK-NEXT:    addq $40, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_pow_v4f64:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    subq $40, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 48
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    vmovsd {{.*#+}} xmm1 = mem[0],zero
; AVX-NEXT:    callq pow
; AVX-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    vmovsd {{.*#+}} xmm1 = mem[0],zero
; AVX-NEXT:    callq pow
; AVX-NEXT:    vunpcklpd (%rsp), %xmm0, %xmm0 # 16-byte Folded Reload
; AVX-NEXT:    # xmm0 = xmm0[0],mem[0]
; AVX-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    vmovsd {{.*#+}} xmm1 = mem[0],zero
; AVX-NEXT:    callq pow
; AVX-NEXT:    vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    vmovsd {{.*#+}} xmm1 = mem[0],zero
; AVX-NEXT:    callq pow
; AVX-NEXT:    vunpcklpd {{[-0-9]+}}(%r{{[sb]}}p), %xmm0, %xmm0 # 16-byte Folded Reload
; AVX-NEXT:    # xmm0 = xmm0[0],mem[0]
; AVX-NEXT:    vinsertf128 $1, (%rsp), %ymm0, %ymm0 # 16-byte Folded Reload
; AVX-NEXT:    addq $40, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 8
; AVX-NEXT:    retq
entry:
  %pow = call <4 x double> @llvm.experimental.constrained.pow.v4f64(
                             <4 x double> <double 42.1, double 42.2,
                                           double 42.3, double 42.4>,
                             <4 x double> <double 3.0, double 3.0,
                                           double 3.0, double 3.0>,
                             metadata !"round.dynamic",
                             metadata !"fpexcept.strict")
  ret <4 x double> %pow
}

define <1 x float> @constrained_vector_powi_v1f32() {
; CHECK-LABEL: constrained_vector_powi_v1f32:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    pushq %rax
; CHECK-NEXT:    .cfi_def_cfa_offset 16
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    movl $3, %edi
; CHECK-NEXT:    callq __powisf2
; CHECK-NEXT:    popq %rax
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_powi_v1f32:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    pushq %rax
; AVX-NEXT:    .cfi_def_cfa_offset 16
; AVX-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT:    movl $3, %edi
; AVX-NEXT:    callq __powisf2
; AVX-NEXT:    popq %rax
; AVX-NEXT:    .cfi_def_cfa_offset 8
; AVX-NEXT:    retq
entry:
  %powi = call <1 x float> @llvm.experimental.constrained.powi.v1f32(
                              <1 x float> <float 42.0>,
                              i32 3,
                              metadata !"round.dynamic",
                              metadata !"fpexcept.strict")
  ret <1 x float> %powi
}

define <2 x double> @constrained_vector_powi_v2f64() {
; CHECK-LABEL: constrained_vector_powi_v2f64:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    subq $24, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 32
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    movl $3, %edi
; CHECK-NEXT:    callq __powidf2
; CHECK-NEXT:    movaps %xmm0, (%rsp) # 16-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    movl $3, %edi
; CHECK-NEXT:    callq __powidf2
; CHECK-NEXT:    unpcklpd (%rsp), %xmm0 # 16-byte Folded Reload
; CHECK-NEXT:    # xmm0 = xmm0[0],mem[0]
; CHECK-NEXT:    addq $24, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_powi_v2f64:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    subq $24, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 32
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    movl $3, %edi
; AVX-NEXT:    callq __powidf2
; AVX-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    movl $3, %edi
; AVX-NEXT:    callq __powidf2
; AVX-NEXT:    vunpcklpd (%rsp), %xmm0, %xmm0 # 16-byte Folded Reload
; AVX-NEXT:    # xmm0 = xmm0[0],mem[0]
; AVX-NEXT:    addq $24, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 8
; AVX-NEXT:    retq
entry:
  %powi = call <2 x double> @llvm.experimental.constrained.powi.v2f64(
                              <2 x double> <double 42.1, double 42.2>,
                              i32 3,
                              metadata !"round.dynamic",
                              metadata !"fpexcept.strict")
  ret <2 x double> %powi
}

define <3 x float> @constrained_vector_powi_v3f32() {
; CHECK-LABEL: constrained_vector_powi_v3f32:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    subq $40, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 48
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    movl $3, %edi
; CHECK-NEXT:    callq __powisf2
; CHECK-NEXT:    movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    movl $3, %edi
; CHECK-NEXT:    callq __powisf2
; CHECK-NEXT:    movaps %xmm0, (%rsp) # 16-byte Spill
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    movl $3, %edi
; CHECK-NEXT:    callq __powisf2
; CHECK-NEXT:    movaps (%rsp), %xmm1 # 16-byte Reload
; CHECK-NEXT:    unpcklps {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
; CHECK-NEXT:    unpcklpd {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Folded Reload
; CHECK-NEXT:    # xmm1 = xmm1[0],mem[0]
; CHECK-NEXT:    movaps %xmm1, %xmm0
; CHECK-NEXT:    addq $40, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_powi_v3f32:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    subq $40, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 48
; AVX-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT:    movl $3, %edi
; AVX-NEXT:    callq __powisf2
; AVX-NEXT:    vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; AVX-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT:    movl $3, %edi
; AVX-NEXT:    callq __powisf2
; AVX-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
; AVX-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT:    movl $3, %edi
; AVX-NEXT:    callq __powisf2
; AVX-NEXT:    vmovaps (%rsp), %xmm1 # 16-byte Reload
; AVX-NEXT:    vinsertps {{.*#+}} xmm0 = xmm1[0],xmm0[0],xmm1[2,3]
; AVX-NEXT:    vinsertps $32, {{[-0-9]+}}(%r{{[sb]}}p), %xmm0, %xmm0 # 16-byte Folded Reload
; AVX-NEXT:    # xmm0 = xmm0[0,1],mem[0],xmm0[3]
; AVX-NEXT:    addq $40, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 8
; AVX-NEXT:    retq
entry:
  %powi = call <3 x float> @llvm.experimental.constrained.powi.v3f32(
                              <3 x float> <float 42.0, float 43.0, float 44.0>,
                              i32 3,
                              metadata !"round.dynamic",
                              metadata !"fpexcept.strict")
  ret <3 x float> %powi
}

define <3 x double> @constrained_vector_powi_v3f64() {
; CHECK-LABEL: constrained_vector_powi_v3f64:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    subq $24, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 32
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    movl $3, %edi
; CHECK-NEXT:    callq __powidf2
; CHECK-NEXT:    movsd %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    movl $3, %edi
; CHECK-NEXT:    callq __powidf2
; CHECK-NEXT:    movsd %xmm0, (%rsp) # 8-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    movl $3, %edi
; CHECK-NEXT:    callq __powidf2
; CHECK-NEXT:    movsd %xmm0, {{[0-9]+}}(%rsp)
; CHECK-NEXT:    fldl {{[0-9]+}}(%rsp)
; CHECK-NEXT:    movsd {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 8-byte Reload
; CHECK-NEXT:    # xmm0 = mem[0],zero
; CHECK-NEXT:    movsd (%rsp), %xmm1 # 8-byte Reload
; CHECK-NEXT:    # xmm1 = mem[0],zero
; CHECK-NEXT:    addq $24, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_powi_v3f64:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    subq $56, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 64
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    movl $3, %edi
; AVX-NEXT:    callq __powidf2
; AVX-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    movl $3, %edi
; AVX-NEXT:    callq __powidf2
; AVX-NEXT:    vunpcklpd (%rsp), %xmm0, %xmm0 # 16-byte Folded Reload
; AVX-NEXT:    # xmm0 = xmm0[0],mem[0]
; AVX-NEXT:    vmovups %ymm0, (%rsp) # 32-byte Spill
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    movl $3, %edi
; AVX-NEXT:    vzeroupper
; AVX-NEXT:    callq __powidf2
; AVX-NEXT:    vmovups (%rsp), %ymm1 # 32-byte Reload
; AVX-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
; AVX-NEXT:    addq $56, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 8
; AVX-NEXT:    retq
entry:
  %powi = call <3 x double> @llvm.experimental.constrained.powi.v3f64(
                          <3 x double> <double 42.0, double 42.1, double 42.2>,
                          i32 3,
                          metadata !"round.dynamic",
                          metadata !"fpexcept.strict")
  ret <3 x double> %powi
}

define <4 x double> @constrained_vector_powi_v4f64() {
; CHECK-LABEL: constrained_vector_powi_v4f64:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    subq $40, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 48
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    movl $3, %edi
; CHECK-NEXT:    callq __powidf2
; CHECK-NEXT:    movaps %xmm0, (%rsp) # 16-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    movl $3, %edi
; CHECK-NEXT:    callq __powidf2
; CHECK-NEXT:    unpcklpd (%rsp), %xmm0 # 16-byte Folded Reload
; CHECK-NEXT:    # xmm0 = xmm0[0],mem[0]
; CHECK-NEXT:    movaps %xmm0, (%rsp) # 16-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    movl $3, %edi
; CHECK-NEXT:    callq __powidf2
; CHECK-NEXT:    movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    movl $3, %edi
; CHECK-NEXT:    callq __powidf2
; CHECK-NEXT:    movaps %xmm0, %xmm1
; CHECK-NEXT:    unpcklpd {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Folded Reload
; CHECK-NEXT:    # xmm1 = xmm1[0],mem[0]
; CHECK-NEXT:    movaps (%rsp), %xmm0 # 16-byte Reload
; CHECK-NEXT:    addq $40, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_powi_v4f64:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    subq $40, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 48
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    movl $3, %edi
; AVX-NEXT:    callq __powidf2
; AVX-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    movl $3, %edi
; AVX-NEXT:    callq __powidf2
; AVX-NEXT:    vunpcklpd (%rsp), %xmm0, %xmm0 # 16-byte Folded Reload
; AVX-NEXT:    # xmm0 = xmm0[0],mem[0]
; AVX-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    movl $3, %edi
; AVX-NEXT:    callq __powidf2
; AVX-NEXT:    vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    movl $3, %edi
; AVX-NEXT:    callq __powidf2
; AVX-NEXT:    vunpcklpd {{[-0-9]+}}(%r{{[sb]}}p), %xmm0, %xmm0 # 16-byte Folded Reload
; AVX-NEXT:    # xmm0 = xmm0[0],mem[0]
; AVX-NEXT:    vinsertf128 $1, (%rsp), %ymm0, %ymm0 # 16-byte Folded Reload
; AVX-NEXT:    addq $40, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 8
; AVX-NEXT:    retq
entry:
  %powi = call <4 x double> @llvm.experimental.constrained.powi.v4f64(
                              <4 x double> <double 42.1, double 42.2,
                                            double 42.3, double 42.4>,
                              i32 3,
                              metadata !"round.dynamic",
                              metadata !"fpexcept.strict")
  ret <4 x double> %powi
}

define <1 x float> @constrained_vector_sin_v1f32() {
; CHECK-LABEL: constrained_vector_sin_v1f32:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    pushq %rax
; CHECK-NEXT:    .cfi_def_cfa_offset 16
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    callq sinf
; CHECK-NEXT:    popq %rax
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_sin_v1f32:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    pushq %rax
; AVX-NEXT:    .cfi_def_cfa_offset 16
; AVX-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT:    callq sinf
; AVX-NEXT:    popq %rax
; AVX-NEXT:    .cfi_def_cfa_offset 8
; AVX-NEXT:    retq
entry:
  %sin = call <1 x float> @llvm.experimental.constrained.sin.v1f32(
                             <1 x float> <float 42.0>,
                             metadata !"round.dynamic",
                             metadata !"fpexcept.strict")
  ret <1 x float> %sin
}

define <2 x double> @constrained_vector_sin_v2f64() {
; CHECK-LABEL: constrained_vector_sin_v2f64:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    subq $24, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 32
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq sin
; CHECK-NEXT:    movaps %xmm0, (%rsp) # 16-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq sin
; CHECK-NEXT:    unpcklpd (%rsp), %xmm0 # 16-byte Folded Reload
; CHECK-NEXT:    # xmm0 = xmm0[0],mem[0]
; CHECK-NEXT:    addq $24, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_sin_v2f64:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    subq $24, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 32
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    callq sin
; AVX-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    callq sin
; AVX-NEXT:    vunpcklpd (%rsp), %xmm0, %xmm0 # 16-byte Folded Reload
; AVX-NEXT:    # xmm0 = xmm0[0],mem[0]
; AVX-NEXT:    addq $24, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 8
; AVX-NEXT:    retq
entry:
  %sin = call <2 x double> @llvm.experimental.constrained.sin.v2f64(
                             <2 x double> <double 42.0, double 42.1>,
                             metadata !"round.dynamic",
                             metadata !"fpexcept.strict")
  ret <2 x double> %sin
}

define <3 x float> @constrained_vector_sin_v3f32() {
; CHECK-LABEL: constrained_vector_sin_v3f32:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    subq $40, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 48
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    callq sinf
; CHECK-NEXT:    movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    callq sinf
; CHECK-NEXT:    movaps %xmm0, (%rsp) # 16-byte Spill
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    callq sinf
; CHECK-NEXT:    movaps (%rsp), %xmm1 # 16-byte Reload
; CHECK-NEXT:    unpcklps {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
; CHECK-NEXT:    unpcklpd {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Folded Reload
; CHECK-NEXT:    # xmm1 = xmm1[0],mem[0]
; CHECK-NEXT:    movaps %xmm1, %xmm0
; CHECK-NEXT:    addq $40, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_sin_v3f32:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    subq $40, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 48
; AVX-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT:    callq sinf
; AVX-NEXT:    vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; AVX-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT:    callq sinf
; AVX-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
; AVX-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT:    callq sinf
; AVX-NEXT:    vmovaps (%rsp), %xmm1 # 16-byte Reload
; AVX-NEXT:    vinsertps {{.*#+}} xmm0 = xmm1[0],xmm0[0],xmm1[2,3]
; AVX-NEXT:    vinsertps $32, {{[-0-9]+}}(%r{{[sb]}}p), %xmm0, %xmm0 # 16-byte Folded Reload
; AVX-NEXT:    # xmm0 = xmm0[0,1],mem[0],xmm0[3]
; AVX-NEXT:    addq $40, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 8
; AVX-NEXT:    retq
entry:
  %sin = call <3 x float> @llvm.experimental.constrained.sin.v3f32(
                              <3 x float> <float 42.0, float 43.0, float 44.0>,
                              metadata !"round.dynamic",
                              metadata !"fpexcept.strict")
  ret <3 x float> %sin
}

define <3 x double> @constrained_vector_sin_v3f64() {
; CHECK-LABEL: constrained_vector_sin_v3f64:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    subq $24, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 32
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq sin
; CHECK-NEXT:    movsd %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq sin
; CHECK-NEXT:    movsd %xmm0, (%rsp) # 8-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq sin
; CHECK-NEXT:    movsd %xmm0, {{[0-9]+}}(%rsp)
; CHECK-NEXT:    fldl {{[0-9]+}}(%rsp)
; CHECK-NEXT:    movsd {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 8-byte Reload
; CHECK-NEXT:    # xmm0 = mem[0],zero
; CHECK-NEXT:    movsd (%rsp), %xmm1 # 8-byte Reload
; CHECK-NEXT:    # xmm1 = mem[0],zero
; CHECK-NEXT:    addq $24, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_sin_v3f64:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    subq $56, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 64
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    callq sin
; AVX-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    callq sin
; AVX-NEXT:    vunpcklpd (%rsp), %xmm0, %xmm0 # 16-byte Folded Reload
; AVX-NEXT:    # xmm0 = xmm0[0],mem[0]
; AVX-NEXT:    vmovups %ymm0, (%rsp) # 32-byte Spill
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    vzeroupper
; AVX-NEXT:    callq sin
; AVX-NEXT:    vmovups (%rsp), %ymm1 # 32-byte Reload
; AVX-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
; AVX-NEXT:    addq $56, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 8
; AVX-NEXT:    retq
entry:
  %sin = call <3 x double> @llvm.experimental.constrained.sin.v3f64(
                          <3 x double> <double 42.0, double 42.1, double 42.2>,
                          metadata !"round.dynamic",
                          metadata !"fpexcept.strict")
  ret <3 x double> %sin
}

define <4 x double> @constrained_vector_sin_v4f64() {
; CHECK-LABEL: constrained_vector_sin_v4f64:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    subq $40, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 48
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq sin
; CHECK-NEXT:    movaps %xmm0, (%rsp) # 16-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq sin
; CHECK-NEXT:    unpcklpd (%rsp), %xmm0 # 16-byte Folded Reload
; CHECK-NEXT:    # xmm0 = xmm0[0],mem[0]
; CHECK-NEXT:    movaps %xmm0, (%rsp) # 16-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq sin
; CHECK-NEXT:    movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq sin
; CHECK-NEXT:    movaps %xmm0, %xmm1
; CHECK-NEXT:    unpcklpd {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Folded Reload
; CHECK-NEXT:    # xmm1 = xmm1[0],mem[0]
; CHECK-NEXT:    movaps (%rsp), %xmm0 # 16-byte Reload
; CHECK-NEXT:    addq $40, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_sin_v4f64:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    subq $40, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 48
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    callq sin
; AVX-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    callq sin
; AVX-NEXT:    vunpcklpd (%rsp), %xmm0, %xmm0 # 16-byte Folded Reload
; AVX-NEXT:    # xmm0 = xmm0[0],mem[0]
; AVX-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    callq sin
; AVX-NEXT:    vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    callq sin
; AVX-NEXT:    vunpcklpd {{[-0-9]+}}(%r{{[sb]}}p), %xmm0, %xmm0 # 16-byte Folded Reload
; AVX-NEXT:    # xmm0 = xmm0[0],mem[0]
; AVX-NEXT:    vinsertf128 $1, (%rsp), %ymm0, %ymm0 # 16-byte Folded Reload
; AVX-NEXT:    addq $40, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 8
; AVX-NEXT:    retq
entry:
  %sin = call <4 x double> @llvm.experimental.constrained.sin.v4f64(
                             <4 x double> <double 42.0, double 42.1,
                                           double 42.2, double 42.3>,
                             metadata !"round.dynamic",
                             metadata !"fpexcept.strict")
  ret <4 x double> %sin
}

define <1 x float> @constrained_vector_cos_v1f32() {
; CHECK-LABEL: constrained_vector_cos_v1f32:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    pushq %rax
; CHECK-NEXT:    .cfi_def_cfa_offset 16
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    callq cosf
; CHECK-NEXT:    popq %rax
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_cos_v1f32:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    pushq %rax
; AVX-NEXT:    .cfi_def_cfa_offset 16
; AVX-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT:    callq cosf
; AVX-NEXT:    popq %rax
; AVX-NEXT:    .cfi_def_cfa_offset 8
; AVX-NEXT:    retq
entry:
  %cos = call <1 x float> @llvm.experimental.constrained.cos.v1f32(
                             <1 x float> <float 42.0>,
                             metadata !"round.dynamic",
                             metadata !"fpexcept.strict")
  ret <1 x float> %cos
}

define <2 x double> @constrained_vector_cos_v2f64() {
; CHECK-LABEL: constrained_vector_cos_v2f64:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    subq $24, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 32
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq cos
; CHECK-NEXT:    movaps %xmm0, (%rsp) # 16-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq cos
; CHECK-NEXT:    unpcklpd (%rsp), %xmm0 # 16-byte Folded Reload
; CHECK-NEXT:    # xmm0 = xmm0[0],mem[0]
; CHECK-NEXT:    addq $24, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_cos_v2f64:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    subq $24, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 32
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    callq cos
; AVX-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    callq cos
; AVX-NEXT:    vunpcklpd (%rsp), %xmm0, %xmm0 # 16-byte Folded Reload
; AVX-NEXT:    # xmm0 = xmm0[0],mem[0]
; AVX-NEXT:    addq $24, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 8
; AVX-NEXT:    retq
entry:
  %cos = call <2 x double> @llvm.experimental.constrained.cos.v2f64(
                             <2 x double> <double 42.0, double 42.1>,
                             metadata !"round.dynamic",
                             metadata !"fpexcept.strict")
  ret <2 x double> %cos
}

define <3 x float> @constrained_vector_cos_v3f32() {
; CHECK-LABEL: constrained_vector_cos_v3f32:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    subq $40, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 48
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    callq cosf
; CHECK-NEXT:    movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    callq cosf
; CHECK-NEXT:    movaps %xmm0, (%rsp) # 16-byte Spill
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    callq cosf
; CHECK-NEXT:    movaps (%rsp), %xmm1 # 16-byte Reload
; CHECK-NEXT:    unpcklps {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
; CHECK-NEXT:    unpcklpd {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Folded Reload
; CHECK-NEXT:    # xmm1 = xmm1[0],mem[0]
; CHECK-NEXT:    movaps %xmm1, %xmm0
; CHECK-NEXT:    addq $40, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_cos_v3f32:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    subq $40, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 48
; AVX-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT:    callq cosf
; AVX-NEXT:    vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; AVX-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT:    callq cosf
; AVX-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
; AVX-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT:    callq cosf
; AVX-NEXT:    vmovaps (%rsp), %xmm1 # 16-byte Reload
; AVX-NEXT:    vinsertps {{.*#+}} xmm0 = xmm1[0],xmm0[0],xmm1[2,3]
; AVX-NEXT:    vinsertps $32, {{[-0-9]+}}(%r{{[sb]}}p), %xmm0, %xmm0 # 16-byte Folded Reload
; AVX-NEXT:    # xmm0 = xmm0[0,1],mem[0],xmm0[3]
; AVX-NEXT:    addq $40, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 8
; AVX-NEXT:    retq
entry:
  %cos = call <3 x float> @llvm.experimental.constrained.cos.v3f32(
                              <3 x float> <float 42.0, float 43.0, float 44.0>,
                              metadata !"round.dynamic",
                              metadata !"fpexcept.strict")
  ret <3 x float> %cos
}

define <3 x double> @constrained_vector_cos_v3f64() {
; CHECK-LABEL: constrained_vector_cos_v3f64:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    subq $24, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 32
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq cos
; CHECK-NEXT:    movsd %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq cos
; CHECK-NEXT:    movsd %xmm0, (%rsp) # 8-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq cos
; CHECK-NEXT:    movsd %xmm0, {{[0-9]+}}(%rsp)
; CHECK-NEXT:    fldl {{[0-9]+}}(%rsp)
; CHECK-NEXT:    movsd {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 8-byte Reload
; CHECK-NEXT:    # xmm0 = mem[0],zero
; CHECK-NEXT:    movsd (%rsp), %xmm1 # 8-byte Reload
; CHECK-NEXT:    # xmm1 = mem[0],zero
; CHECK-NEXT:    addq $24, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_cos_v3f64:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    subq $56, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 64
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    callq cos
; AVX-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    callq cos
; AVX-NEXT:    vunpcklpd (%rsp), %xmm0, %xmm0 # 16-byte Folded Reload
; AVX-NEXT:    # xmm0 = xmm0[0],mem[0]
; AVX-NEXT:    vmovups %ymm0, (%rsp) # 32-byte Spill
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    vzeroupper
; AVX-NEXT:    callq cos
; AVX-NEXT:    vmovups (%rsp), %ymm1 # 32-byte Reload
; AVX-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
; AVX-NEXT:    addq $56, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 8
; AVX-NEXT:    retq
entry:
  %cos = call <3 x double> @llvm.experimental.constrained.cos.v3f64(
                          <3 x double> <double 42.0, double 42.1, double 42.2>,
                          metadata !"round.dynamic",
                          metadata !"fpexcept.strict")
  ret <3 x double> %cos
}

define <4 x double> @constrained_vector_cos_v4f64() {
; CHECK-LABEL: constrained_vector_cos_v4f64:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    subq $40, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 48
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq cos
; CHECK-NEXT:    movaps %xmm0, (%rsp) # 16-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq cos
; CHECK-NEXT:    unpcklpd (%rsp), %xmm0 # 16-byte Folded Reload
; CHECK-NEXT:    # xmm0 = xmm0[0],mem[0]
; CHECK-NEXT:    movaps %xmm0, (%rsp) # 16-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq cos
; CHECK-NEXT:    movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq cos
; CHECK-NEXT:    movaps %xmm0, %xmm1
; CHECK-NEXT:    unpcklpd {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Folded Reload
; CHECK-NEXT:    # xmm1 = xmm1[0],mem[0]
; CHECK-NEXT:    movaps (%rsp), %xmm0 # 16-byte Reload
; CHECK-NEXT:    addq $40, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_cos_v4f64:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    subq $40, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 48
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    callq cos
; AVX-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    callq cos
; AVX-NEXT:    vunpcklpd (%rsp), %xmm0, %xmm0 # 16-byte Folded Reload
; AVX-NEXT:    # xmm0 = xmm0[0],mem[0]
; AVX-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    callq cos
; AVX-NEXT:    vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    callq cos
; AVX-NEXT:    vunpcklpd {{[-0-9]+}}(%r{{[sb]}}p), %xmm0, %xmm0 # 16-byte Folded Reload
; AVX-NEXT:    # xmm0 = xmm0[0],mem[0]
; AVX-NEXT:    vinsertf128 $1, (%rsp), %ymm0, %ymm0 # 16-byte Folded Reload
; AVX-NEXT:    addq $40, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 8
; AVX-NEXT:    retq
entry:
  %cos = call <4 x double> @llvm.experimental.constrained.cos.v4f64(
                             <4 x double> <double 42.0, double 42.1,
                                           double 42.2, double 42.3>,
                             metadata !"round.dynamic",
                             metadata !"fpexcept.strict")
  ret <4 x double> %cos
}

define <1 x float> @constrained_vector_exp_v1f32() {
; CHECK-LABEL: constrained_vector_exp_v1f32:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    pushq %rax
; CHECK-NEXT:    .cfi_def_cfa_offset 16
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    callq expf
; CHECK-NEXT:    popq %rax
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_exp_v1f32:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    pushq %rax
; AVX-NEXT:    .cfi_def_cfa_offset 16
; AVX-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT:    callq expf
; AVX-NEXT:    popq %rax
; AVX-NEXT:    .cfi_def_cfa_offset 8
; AVX-NEXT:    retq
entry:
  %exp = call <1 x float> @llvm.experimental.constrained.exp.v1f32(
                             <1 x float> <float 42.0>,
                             metadata !"round.dynamic",
                             metadata !"fpexcept.strict")
  ret <1 x float> %exp
}

define <2 x double> @constrained_vector_exp_v2f64() {
; CHECK-LABEL: constrained_vector_exp_v2f64:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    subq $24, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 32
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq exp
; CHECK-NEXT:    movaps %xmm0, (%rsp) # 16-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq exp
; CHECK-NEXT:    unpcklpd (%rsp), %xmm0 # 16-byte Folded Reload
; CHECK-NEXT:    # xmm0 = xmm0[0],mem[0]
; CHECK-NEXT:    addq $24, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_exp_v2f64:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    subq $24, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 32
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    callq exp
; AVX-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    callq exp
; AVX-NEXT:    vunpcklpd (%rsp), %xmm0, %xmm0 # 16-byte Folded Reload
; AVX-NEXT:    # xmm0 = xmm0[0],mem[0]
; AVX-NEXT:    addq $24, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 8
; AVX-NEXT:    retq
entry:
  %exp = call <2 x double> @llvm.experimental.constrained.exp.v2f64(
                             <2 x double> <double 42.0, double 42.1>,
                             metadata !"round.dynamic",
                             metadata !"fpexcept.strict")
  ret <2 x double> %exp
}

define <3 x float> @constrained_vector_exp_v3f32() {
; CHECK-LABEL: constrained_vector_exp_v3f32:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    subq $40, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 48
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    callq expf
; CHECK-NEXT:    movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    callq expf
; CHECK-NEXT:    movaps %xmm0, (%rsp) # 16-byte Spill
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    callq expf
; CHECK-NEXT:    movaps (%rsp), %xmm1 # 16-byte Reload
; CHECK-NEXT:    unpcklps {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
; CHECK-NEXT:    unpcklpd {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Folded Reload
; CHECK-NEXT:    # xmm1 = xmm1[0],mem[0]
; CHECK-NEXT:    movaps %xmm1, %xmm0
; CHECK-NEXT:    addq $40, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_exp_v3f32:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    subq $40, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 48
; AVX-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT:    callq expf
; AVX-NEXT:    vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; AVX-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT:    callq expf
; AVX-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
; AVX-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT:    callq expf
; AVX-NEXT:    vmovaps (%rsp), %xmm1 # 16-byte Reload
; AVX-NEXT:    vinsertps {{.*#+}} xmm0 = xmm1[0],xmm0[0],xmm1[2,3]
; AVX-NEXT:    vinsertps $32, {{[-0-9]+}}(%r{{[sb]}}p), %xmm0, %xmm0 # 16-byte Folded Reload
; AVX-NEXT:    # xmm0 = xmm0[0,1],mem[0],xmm0[3]
; AVX-NEXT:    addq $40, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 8
; AVX-NEXT:    retq
entry:
  %exp = call <3 x float> @llvm.experimental.constrained.exp.v3f32(
                              <3 x float> <float 42.0, float 43.0, float 44.0>,
                              metadata !"round.dynamic",
                              metadata !"fpexcept.strict")
  ret <3 x float> %exp
}

define <3 x double> @constrained_vector_exp_v3f64() {
; CHECK-LABEL: constrained_vector_exp_v3f64:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    subq $24, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 32
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq exp
; CHECK-NEXT:    movsd %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq exp
; CHECK-NEXT:    movsd %xmm0, (%rsp) # 8-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq exp
; CHECK-NEXT:    movsd %xmm0, {{[0-9]+}}(%rsp)
; CHECK-NEXT:    fldl {{[0-9]+}}(%rsp)
; CHECK-NEXT:    movsd {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 8-byte Reload
; CHECK-NEXT:    # xmm0 = mem[0],zero
; CHECK-NEXT:    movsd (%rsp), %xmm1 # 8-byte Reload
; CHECK-NEXT:    # xmm1 = mem[0],zero
; CHECK-NEXT:    addq $24, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_exp_v3f64:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    subq $56, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 64
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    callq exp
; AVX-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    callq exp
; AVX-NEXT:    vunpcklpd (%rsp), %xmm0, %xmm0 # 16-byte Folded Reload
; AVX-NEXT:    # xmm0 = xmm0[0],mem[0]
; AVX-NEXT:    vmovups %ymm0, (%rsp) # 32-byte Spill
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    vzeroupper
; AVX-NEXT:    callq exp
; AVX-NEXT:    vmovups (%rsp), %ymm1 # 32-byte Reload
; AVX-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
; AVX-NEXT:    addq $56, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 8
; AVX-NEXT:    retq
entry:
  %exp = call <3 x double> @llvm.experimental.constrained.exp.v3f64(
                          <3 x double> <double 42.0, double 42.1, double 42.2>,
                          metadata !"round.dynamic",
                          metadata !"fpexcept.strict")
  ret <3 x double> %exp
}

define <4 x double> @constrained_vector_exp_v4f64() {
; CHECK-LABEL: constrained_vector_exp_v4f64:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    subq $40, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 48
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq exp
; CHECK-NEXT:    movaps %xmm0, (%rsp) # 16-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq exp
; CHECK-NEXT:    unpcklpd (%rsp), %xmm0 # 16-byte Folded Reload
; CHECK-NEXT:    # xmm0 = xmm0[0],mem[0]
; CHECK-NEXT:    movaps %xmm0, (%rsp) # 16-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq exp
; CHECK-NEXT:    movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq exp
; CHECK-NEXT:    movaps %xmm0, %xmm1
; CHECK-NEXT:    unpcklpd {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Folded Reload
; CHECK-NEXT:    # xmm1 = xmm1[0],mem[0]
; CHECK-NEXT:    movaps (%rsp), %xmm0 # 16-byte Reload
; CHECK-NEXT:    addq $40, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_exp_v4f64:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    subq $40, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 48
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    callq exp
; AVX-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    callq exp
; AVX-NEXT:    vunpcklpd (%rsp), %xmm0, %xmm0 # 16-byte Folded Reload
; AVX-NEXT:    # xmm0 = xmm0[0],mem[0]
; AVX-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    callq exp
; AVX-NEXT:    vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    callq exp
; AVX-NEXT:    vunpcklpd {{[-0-9]+}}(%r{{[sb]}}p), %xmm0, %xmm0 # 16-byte Folded Reload
; AVX-NEXT:    # xmm0 = xmm0[0],mem[0]
; AVX-NEXT:    vinsertf128 $1, (%rsp), %ymm0, %ymm0 # 16-byte Folded Reload
; AVX-NEXT:    addq $40, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 8
; AVX-NEXT:    retq
entry:
  %exp = call <4 x double> @llvm.experimental.constrained.exp.v4f64(
                             <4 x double> <double 42.0, double 42.1,
                                           double 42.2, double 42.3>,
                             metadata !"round.dynamic",
                             metadata !"fpexcept.strict")
  ret <4 x double> %exp
}

define <1 x float> @constrained_vector_exp2_v1f32() {
; CHECK-LABEL: constrained_vector_exp2_v1f32:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    pushq %rax
; CHECK-NEXT:    .cfi_def_cfa_offset 16
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    callq exp2f
; CHECK-NEXT:    popq %rax
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_exp2_v1f32:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    pushq %rax
; AVX-NEXT:    .cfi_def_cfa_offset 16
; AVX-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT:    callq exp2f
; AVX-NEXT:    popq %rax
; AVX-NEXT:    .cfi_def_cfa_offset 8
; AVX-NEXT:    retq
entry:
  %exp2 = call <1 x float> @llvm.experimental.constrained.exp2.v1f32(
                             <1 x float> <float 42.0>,
                             metadata !"round.dynamic",
                             metadata !"fpexcept.strict")
  ret <1 x float> %exp2
}

define <2 x double> @constrained_vector_exp2_v2f64() {
; CHECK-LABEL: constrained_vector_exp2_v2f64:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    subq $24, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 32
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq exp2
; CHECK-NEXT:    movaps %xmm0, (%rsp) # 16-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq exp2
; CHECK-NEXT:    unpcklpd (%rsp), %xmm0 # 16-byte Folded Reload
; CHECK-NEXT:    # xmm0 = xmm0[0],mem[0]
; CHECK-NEXT:    addq $24, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_exp2_v2f64:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    subq $24, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 32
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    callq exp2
; AVX-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    callq exp2
; AVX-NEXT:    vunpcklpd (%rsp), %xmm0, %xmm0 # 16-byte Folded Reload
; AVX-NEXT:    # xmm0 = xmm0[0],mem[0]
; AVX-NEXT:    addq $24, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 8
; AVX-NEXT:    retq
entry:
  %exp2 = call <2 x double> @llvm.experimental.constrained.exp2.v2f64(
                              <2 x double> <double 42.1, double 42.0>,
                              metadata !"round.dynamic",
                              metadata !"fpexcept.strict")
  ret <2 x double> %exp2
}

define <3 x float> @constrained_vector_exp2_v3f32() {
; CHECK-LABEL: constrained_vector_exp2_v3f32:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    subq $40, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 48
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    callq exp2f
; CHECK-NEXT:    movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    callq exp2f
; CHECK-NEXT:    movaps %xmm0, (%rsp) # 16-byte Spill
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    callq exp2f
; CHECK-NEXT:    movaps (%rsp), %xmm1 # 16-byte Reload
; CHECK-NEXT:    unpcklps {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
; CHECK-NEXT:    unpcklpd {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Folded Reload
; CHECK-NEXT:    # xmm1 = xmm1[0],mem[0]
; CHECK-NEXT:    movaps %xmm1, %xmm0
; CHECK-NEXT:    addq $40, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_exp2_v3f32:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    subq $40, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 48
; AVX-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT:    callq exp2f
; AVX-NEXT:    vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; AVX-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT:    callq exp2f
; AVX-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
; AVX-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT:    callq exp2f
; AVX-NEXT:    vmovaps (%rsp), %xmm1 # 16-byte Reload
; AVX-NEXT:    vinsertps {{.*#+}} xmm0 = xmm1[0],xmm0[0],xmm1[2,3]
; AVX-NEXT:    vinsertps $32, {{[-0-9]+}}(%r{{[sb]}}p), %xmm0, %xmm0 # 16-byte Folded Reload
; AVX-NEXT:    # xmm0 = xmm0[0,1],mem[0],xmm0[3]
; AVX-NEXT:    addq $40, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 8
; AVX-NEXT:    retq
entry:
  %exp2 = call <3 x float> @llvm.experimental.constrained.exp2.v3f32(
                              <3 x float> <float 42.0, float 43.0, float 44.0>,
                              metadata !"round.dynamic",
                              metadata !"fpexcept.strict")
  ret <3 x float> %exp2
}

define <3 x double> @constrained_vector_exp2_v3f64() {
; CHECK-LABEL: constrained_vector_exp2_v3f64:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    subq $24, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 32
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq exp2
; CHECK-NEXT:    movsd %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq exp2
; CHECK-NEXT:    movsd %xmm0, (%rsp) # 8-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq exp2
; CHECK-NEXT:    movsd %xmm0, {{[0-9]+}}(%rsp)
; CHECK-NEXT:    fldl {{[0-9]+}}(%rsp)
; CHECK-NEXT:    movsd {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 8-byte Reload
; CHECK-NEXT:    # xmm0 = mem[0],zero
; CHECK-NEXT:    movsd (%rsp), %xmm1 # 8-byte Reload
; CHECK-NEXT:    # xmm1 = mem[0],zero
; CHECK-NEXT:    addq $24, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_exp2_v3f64:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    subq $56, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 64
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    callq exp2
; AVX-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    callq exp2
; AVX-NEXT:    vunpcklpd (%rsp), %xmm0, %xmm0 # 16-byte Folded Reload
; AVX-NEXT:    # xmm0 = xmm0[0],mem[0]
; AVX-NEXT:    vmovups %ymm0, (%rsp) # 32-byte Spill
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    vzeroupper
; AVX-NEXT:    callq exp2
; AVX-NEXT:    vmovups (%rsp), %ymm1 # 32-byte Reload
; AVX-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
; AVX-NEXT:    addq $56, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 8
; AVX-NEXT:    retq
entry:
  %exp2 = call <3 x double> @llvm.experimental.constrained.exp2.v3f64(
                          <3 x double> <double 42.0, double 42.1, double 42.2>,
                          metadata !"round.dynamic",
                          metadata !"fpexcept.strict")
  ret <3 x double> %exp2
}

define <4 x double> @constrained_vector_exp2_v4f64() {
; CHECK-LABEL: constrained_vector_exp2_v4f64:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    subq $40, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 48
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq exp2
; CHECK-NEXT:    movaps %xmm0, (%rsp) # 16-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq exp2
; CHECK-NEXT:    unpcklpd (%rsp), %xmm0 # 16-byte Folded Reload
; CHECK-NEXT:    # xmm0 = xmm0[0],mem[0]
; CHECK-NEXT:    movaps %xmm0, (%rsp) # 16-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq exp2
; CHECK-NEXT:    movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq exp2
; CHECK-NEXT:    movaps %xmm0, %xmm1
; CHECK-NEXT:    unpcklpd {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Folded Reload
; CHECK-NEXT:    # xmm1 = xmm1[0],mem[0]
; CHECK-NEXT:    movaps (%rsp), %xmm0 # 16-byte Reload
; CHECK-NEXT:    addq $40, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_exp2_v4f64:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    subq $40, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 48
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    callq exp2
; AVX-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    callq exp2
; AVX-NEXT:    vunpcklpd (%rsp), %xmm0, %xmm0 # 16-byte Folded Reload
; AVX-NEXT:    # xmm0 = xmm0[0],mem[0]
; AVX-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    callq exp2
; AVX-NEXT:    vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    callq exp2
; AVX-NEXT:    vunpcklpd {{[-0-9]+}}(%r{{[sb]}}p), %xmm0, %xmm0 # 16-byte Folded Reload
; AVX-NEXT:    # xmm0 = xmm0[0],mem[0]
; AVX-NEXT:    vinsertf128 $1, (%rsp), %ymm0, %ymm0 # 16-byte Folded Reload
; AVX-NEXT:    addq $40, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 8
; AVX-NEXT:    retq
entry:
  %exp2 = call <4 x double> @llvm.experimental.constrained.exp2.v4f64(
                              <4 x double> <double 42.1, double 42.2,
                                            double 42.3, double 42.4>,
                              metadata !"round.dynamic",
                              metadata !"fpexcept.strict")
  ret <4 x double> %exp2
}

define <1 x float> @constrained_vector_log_v1f32() {
; CHECK-LABEL: constrained_vector_log_v1f32:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    pushq %rax
; CHECK-NEXT:    .cfi_def_cfa_offset 16
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    callq logf
; CHECK-NEXT:    popq %rax
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_log_v1f32:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    pushq %rax
; AVX-NEXT:    .cfi_def_cfa_offset 16
; AVX-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT:    callq logf
; AVX-NEXT:    popq %rax
; AVX-NEXT:    .cfi_def_cfa_offset 8
; AVX-NEXT:    retq
entry:
  %log = call <1 x float> @llvm.experimental.constrained.log.v1f32(
                             <1 x float> <float 42.0>,
                             metadata !"round.dynamic",
                             metadata !"fpexcept.strict")
  ret <1 x float> %log
}

define <2 x double> @constrained_vector_log_v2f64() {
; CHECK-LABEL: constrained_vector_log_v2f64:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    subq $24, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 32
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq log
; CHECK-NEXT:    movaps %xmm0, (%rsp) # 16-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq log
; CHECK-NEXT:    unpcklpd (%rsp), %xmm0 # 16-byte Folded Reload
; CHECK-NEXT:    # xmm0 = xmm0[0],mem[0]
; CHECK-NEXT:    addq $24, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_log_v2f64:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    subq $24, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 32
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    callq log
; AVX-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    callq log
; AVX-NEXT:    vunpcklpd (%rsp), %xmm0, %xmm0 # 16-byte Folded Reload
; AVX-NEXT:    # xmm0 = xmm0[0],mem[0]
; AVX-NEXT:    addq $24, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 8
; AVX-NEXT:    retq
entry:
  %log = call <2 x double> @llvm.experimental.constrained.log.v2f64(
                             <2 x double> <double 42.0, double 42.1>,
                             metadata !"round.dynamic",
                             metadata !"fpexcept.strict")
  ret <2 x double> %log
}

define <3 x float> @constrained_vector_log_v3f32() {
; CHECK-LABEL: constrained_vector_log_v3f32:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    subq $40, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 48
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    callq logf
; CHECK-NEXT:    movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    callq logf
; CHECK-NEXT:    movaps %xmm0, (%rsp) # 16-byte Spill
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    callq logf
; CHECK-NEXT:    movaps (%rsp), %xmm1 # 16-byte Reload
; CHECK-NEXT:    unpcklps {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
; CHECK-NEXT:    unpcklpd {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Folded Reload
; CHECK-NEXT:    # xmm1 = xmm1[0],mem[0]
; CHECK-NEXT:    movaps %xmm1, %xmm0
; CHECK-NEXT:    addq $40, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_log_v3f32:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    subq $40, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 48
; AVX-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT:    callq logf
; AVX-NEXT:    vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; AVX-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT:    callq logf
; AVX-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
; AVX-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT:    callq logf
; AVX-NEXT:    vmovaps (%rsp), %xmm1 # 16-byte Reload
; AVX-NEXT:    vinsertps {{.*#+}} xmm0 = xmm1[0],xmm0[0],xmm1[2,3]
; AVX-NEXT:    vinsertps $32, {{[-0-9]+}}(%r{{[sb]}}p), %xmm0, %xmm0 # 16-byte Folded Reload
; AVX-NEXT:    # xmm0 = xmm0[0,1],mem[0],xmm0[3]
; AVX-NEXT:    addq $40, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 8
; AVX-NEXT:    retq
entry:
  %log = call <3 x float> @llvm.experimental.constrained.log.v3f32(
                              <3 x float> <float 42.0, float 43.0, float 44.0>,
                              metadata !"round.dynamic",
                              metadata !"fpexcept.strict")
  ret <3 x float> %log
}

define <3 x double> @constrained_vector_log_v3f64() {
; CHECK-LABEL: constrained_vector_log_v3f64:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    subq $24, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 32
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq log
; CHECK-NEXT:    movsd %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq log
; CHECK-NEXT:    movsd %xmm0, (%rsp) # 8-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq log
; CHECK-NEXT:    movsd %xmm0, {{[0-9]+}}(%rsp)
; CHECK-NEXT:    fldl {{[0-9]+}}(%rsp)
; CHECK-NEXT:    movsd {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 8-byte Reload
; CHECK-NEXT:    # xmm0 = mem[0],zero
; CHECK-NEXT:    movsd (%rsp), %xmm1 # 8-byte Reload
; CHECK-NEXT:    # xmm1 = mem[0],zero
; CHECK-NEXT:    addq $24, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_log_v3f64:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    subq $56, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 64
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    callq log
; AVX-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    callq log
; AVX-NEXT:    vunpcklpd (%rsp), %xmm0, %xmm0 # 16-byte Folded Reload
; AVX-NEXT:    # xmm0 = xmm0[0],mem[0]
; AVX-NEXT:    vmovups %ymm0, (%rsp) # 32-byte Spill
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    vzeroupper
; AVX-NEXT:    callq log
; AVX-NEXT:    vmovups (%rsp), %ymm1 # 32-byte Reload
; AVX-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
; AVX-NEXT:    addq $56, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 8
; AVX-NEXT:    retq
entry:
  %log = call <3 x double> @llvm.experimental.constrained.log.v3f64(
                          <3 x double> <double 42.0, double 42.1, double 42.2>,
                          metadata !"round.dynamic",
                          metadata !"fpexcept.strict")
  ret <3 x double> %log
}

define <4 x double> @constrained_vector_log_v4f64() {
; CHECK-LABEL: constrained_vector_log_v4f64:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    subq $40, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 48
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq log
; CHECK-NEXT:    movaps %xmm0, (%rsp) # 16-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq log
; CHECK-NEXT:    unpcklpd (%rsp), %xmm0 # 16-byte Folded Reload
; CHECK-NEXT:    # xmm0 = xmm0[0],mem[0]
; CHECK-NEXT:    movaps %xmm0, (%rsp) # 16-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq log
; CHECK-NEXT:    movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq log
; CHECK-NEXT:    movaps %xmm0, %xmm1
; CHECK-NEXT:    unpcklpd {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Folded Reload
; CHECK-NEXT:    # xmm1 = xmm1[0],mem[0]
; CHECK-NEXT:    movaps (%rsp), %xmm0 # 16-byte Reload
; CHECK-NEXT:    addq $40, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_log_v4f64:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    subq $40, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 48
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    callq log
; AVX-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    callq log
; AVX-NEXT:    vunpcklpd (%rsp), %xmm0, %xmm0 # 16-byte Folded Reload
; AVX-NEXT:    # xmm0 = xmm0[0],mem[0]
; AVX-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    callq log
; AVX-NEXT:    vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    callq log
; AVX-NEXT:    vunpcklpd {{[-0-9]+}}(%r{{[sb]}}p), %xmm0, %xmm0 # 16-byte Folded Reload
; AVX-NEXT:    # xmm0 = xmm0[0],mem[0]
; AVX-NEXT:    vinsertf128 $1, (%rsp), %ymm0, %ymm0 # 16-byte Folded Reload
; AVX-NEXT:    addq $40, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 8
; AVX-NEXT:    retq
entry:
  %log = call <4 x double> @llvm.experimental.constrained.log.v4f64(
                             <4 x double> <double 42.0, double 42.1,
                                           double 42.2, double 42.3>,
                             metadata !"round.dynamic",
                             metadata !"fpexcept.strict")
  ret <4 x double> %log
}

define <1 x float> @constrained_vector_log10_v1f32() {
; CHECK-LABEL: constrained_vector_log10_v1f32:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    pushq %rax
; CHECK-NEXT:    .cfi_def_cfa_offset 16
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    callq log10f
; CHECK-NEXT:    popq %rax
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_log10_v1f32:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    pushq %rax
; AVX-NEXT:    .cfi_def_cfa_offset 16
; AVX-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT:    callq log10f
; AVX-NEXT:    popq %rax
; AVX-NEXT:    .cfi_def_cfa_offset 8
; AVX-NEXT:    retq
entry:
  %log10 = call <1 x float> @llvm.experimental.constrained.log10.v1f32(
                             <1 x float> <float 42.0>,
                             metadata !"round.dynamic",
                             metadata !"fpexcept.strict")
  ret <1 x float> %log10
}

define <2 x double> @constrained_vector_log10_v2f64() {
; CHECK-LABEL: constrained_vector_log10_v2f64:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    subq $24, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 32
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq log10
; CHECK-NEXT:    movaps %xmm0, (%rsp) # 16-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq log10
; CHECK-NEXT:    unpcklpd (%rsp), %xmm0 # 16-byte Folded Reload
; CHECK-NEXT:    # xmm0 = xmm0[0],mem[0]
; CHECK-NEXT:    addq $24, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_log10_v2f64:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    subq $24, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 32
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    callq log10
; AVX-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    callq log10
; AVX-NEXT:    vunpcklpd (%rsp), %xmm0, %xmm0 # 16-byte Folded Reload
; AVX-NEXT:    # xmm0 = xmm0[0],mem[0]
; AVX-NEXT:    addq $24, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 8
; AVX-NEXT:    retq
entry:
  %log10 = call <2 x double> @llvm.experimental.constrained.log10.v2f64(
                               <2 x double> <double 42.0, double 42.1>,
                               metadata !"round.dynamic",
                               metadata !"fpexcept.strict")
  ret <2 x double> %log10
}

define <3 x float> @constrained_vector_log10_v3f32() {
; CHECK-LABEL: constrained_vector_log10_v3f32:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    subq $40, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 48
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    callq log10f
; CHECK-NEXT:    movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    callq log10f
; CHECK-NEXT:    movaps %xmm0, (%rsp) # 16-byte Spill
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    callq log10f
; CHECK-NEXT:    movaps (%rsp), %xmm1 # 16-byte Reload
; CHECK-NEXT:    unpcklps {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
; CHECK-NEXT:    unpcklpd {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Folded Reload
; CHECK-NEXT:    # xmm1 = xmm1[0],mem[0]
; CHECK-NEXT:    movaps %xmm1, %xmm0
; CHECK-NEXT:    addq $40, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_log10_v3f32:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    subq $40, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 48
; AVX-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT:    callq log10f
; AVX-NEXT:    vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; AVX-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT:    callq log10f
; AVX-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
; AVX-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT:    callq log10f
; AVX-NEXT:    vmovaps (%rsp), %xmm1 # 16-byte Reload
; AVX-NEXT:    vinsertps {{.*#+}} xmm0 = xmm1[0],xmm0[0],xmm1[2,3]
; AVX-NEXT:    vinsertps $32, {{[-0-9]+}}(%r{{[sb]}}p), %xmm0, %xmm0 # 16-byte Folded Reload
; AVX-NEXT:    # xmm0 = xmm0[0,1],mem[0],xmm0[3]
; AVX-NEXT:    addq $40, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 8
; AVX-NEXT:    retq
entry:
  %log10 = call <3 x float> @llvm.experimental.constrained.log10.v3f32(
                              <3 x float> <float 42.0, float 43.0, float 44.0>,
                              metadata !"round.dynamic",
                              metadata !"fpexcept.strict")
  ret <3 x float> %log10
}

define <3 x double> @constrained_vector_log10_v3f64() {
; CHECK-LABEL: constrained_vector_log10_v3f64:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    subq $24, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 32
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq log10
; CHECK-NEXT:    movsd %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq log10
; CHECK-NEXT:    movsd %xmm0, (%rsp) # 8-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq log10
; CHECK-NEXT:    movsd %xmm0, {{[0-9]+}}(%rsp)
; CHECK-NEXT:    fldl {{[0-9]+}}(%rsp)
; CHECK-NEXT:    movsd {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 8-byte Reload
; CHECK-NEXT:    # xmm0 = mem[0],zero
; CHECK-NEXT:    movsd (%rsp), %xmm1 # 8-byte Reload
; CHECK-NEXT:    # xmm1 = mem[0],zero
; CHECK-NEXT:    addq $24, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_log10_v3f64:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    subq $56, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 64
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    callq log10
; AVX-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    callq log10
; AVX-NEXT:    vunpcklpd (%rsp), %xmm0, %xmm0 # 16-byte Folded Reload
; AVX-NEXT:    # xmm0 = xmm0[0],mem[0]
; AVX-NEXT:    vmovups %ymm0, (%rsp) # 32-byte Spill
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    vzeroupper
; AVX-NEXT:    callq log10
; AVX-NEXT:    vmovups (%rsp), %ymm1 # 32-byte Reload
; AVX-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
; AVX-NEXT:    addq $56, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 8
; AVX-NEXT:    retq
entry:
  %log10 = call <3 x double> @llvm.experimental.constrained.log10.v3f64(
                          <3 x double> <double 42.0, double 42.1, double 42.2>,
                          metadata !"round.dynamic",
                          metadata !"fpexcept.strict")
  ret <3 x double> %log10
}

define <4 x double> @constrained_vector_log10_v4f64() {
; CHECK-LABEL: constrained_vector_log10_v4f64:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    subq $40, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 48
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq log10
; CHECK-NEXT:    movaps %xmm0, (%rsp) # 16-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq log10
; CHECK-NEXT:    unpcklpd (%rsp), %xmm0 # 16-byte Folded Reload
; CHECK-NEXT:    # xmm0 = xmm0[0],mem[0]
; CHECK-NEXT:    movaps %xmm0, (%rsp) # 16-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq log10
; CHECK-NEXT:    movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq log10
; CHECK-NEXT:    movaps %xmm0, %xmm1
; CHECK-NEXT:    unpcklpd {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Folded Reload
; CHECK-NEXT:    # xmm1 = xmm1[0],mem[0]
; CHECK-NEXT:    movaps (%rsp), %xmm0 # 16-byte Reload
; CHECK-NEXT:    addq $40, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_log10_v4f64:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    subq $40, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 48
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    callq log10
; AVX-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    callq log10
; AVX-NEXT:    vunpcklpd (%rsp), %xmm0, %xmm0 # 16-byte Folded Reload
; AVX-NEXT:    # xmm0 = xmm0[0],mem[0]
; AVX-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    callq log10
; AVX-NEXT:    vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    callq log10
; AVX-NEXT:    vunpcklpd {{[-0-9]+}}(%r{{[sb]}}p), %xmm0, %xmm0 # 16-byte Folded Reload
; AVX-NEXT:    # xmm0 = xmm0[0],mem[0]
; AVX-NEXT:    vinsertf128 $1, (%rsp), %ymm0, %ymm0 # 16-byte Folded Reload
; AVX-NEXT:    addq $40, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 8
; AVX-NEXT:    retq
entry:
  %log10 = call <4 x double> @llvm.experimental.constrained.log10.v4f64(
                               <4 x double> <double 42.0, double 42.1,
                                             double 42.2, double 42.3>,
                               metadata !"round.dynamic",
                               metadata !"fpexcept.strict")
  ret <4 x double> %log10
}

define <1 x float> @constrained_vector_log2_v1f32() {
; CHECK-LABEL: constrained_vector_log2_v1f32:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    pushq %rax
; CHECK-NEXT:    .cfi_def_cfa_offset 16
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    callq log2f
; CHECK-NEXT:    popq %rax
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_log2_v1f32:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    pushq %rax
; AVX-NEXT:    .cfi_def_cfa_offset 16
; AVX-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT:    callq log2f
; AVX-NEXT:    popq %rax
; AVX-NEXT:    .cfi_def_cfa_offset 8
; AVX-NEXT:    retq
entry:
  %log2 = call <1 x float> @llvm.experimental.constrained.log2.v1f32(
                             <1 x float> <float 42.0>,
                             metadata !"round.dynamic",
                             metadata !"fpexcept.strict")
  ret <1 x float> %log2
}

define <2 x double> @constrained_vector_log2_v2f64() {
; CHECK-LABEL: constrained_vector_log2_v2f64:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    subq $24, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 32
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq log2
; CHECK-NEXT:    movaps %xmm0, (%rsp) # 16-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq log2
; CHECK-NEXT:    unpcklpd (%rsp), %xmm0 # 16-byte Folded Reload
; CHECK-NEXT:    # xmm0 = xmm0[0],mem[0]
; CHECK-NEXT:    addq $24, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_log2_v2f64:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    subq $24, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 32
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    callq log2
; AVX-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    callq log2
; AVX-NEXT:    vunpcklpd (%rsp), %xmm0, %xmm0 # 16-byte Folded Reload
; AVX-NEXT:    # xmm0 = xmm0[0],mem[0]
; AVX-NEXT:    addq $24, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 8
; AVX-NEXT:    retq
entry:
  %log2 = call <2 x double> @llvm.experimental.constrained.log2.v2f64(
                              <2 x double> <double 42.0, double 42.1>,
                              metadata !"round.dynamic",
                              metadata !"fpexcept.strict")
  ret <2 x double> %log2
}

define <3 x float> @constrained_vector_log2_v3f32() {
; CHECK-LABEL: constrained_vector_log2_v3f32:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    subq $40, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 48
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    callq log2f
; CHECK-NEXT:    movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    callq log2f
; CHECK-NEXT:    movaps %xmm0, (%rsp) # 16-byte Spill
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    callq log2f
; CHECK-NEXT:    movaps (%rsp), %xmm1 # 16-byte Reload
; CHECK-NEXT:    unpcklps {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
; CHECK-NEXT:    unpcklpd {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Folded Reload
; CHECK-NEXT:    # xmm1 = xmm1[0],mem[0]
; CHECK-NEXT:    movaps %xmm1, %xmm0
; CHECK-NEXT:    addq $40, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_log2_v3f32:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    subq $40, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 48
; AVX-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT:    callq log2f
; AVX-NEXT:    vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; AVX-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT:    callq log2f
; AVX-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
; AVX-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT:    callq log2f
; AVX-NEXT:    vmovaps (%rsp), %xmm1 # 16-byte Reload
; AVX-NEXT:    vinsertps {{.*#+}} xmm0 = xmm1[0],xmm0[0],xmm1[2,3]
; AVX-NEXT:    vinsertps $32, {{[-0-9]+}}(%r{{[sb]}}p), %xmm0, %xmm0 # 16-byte Folded Reload
; AVX-NEXT:    # xmm0 = xmm0[0,1],mem[0],xmm0[3]
; AVX-NEXT:    addq $40, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 8
; AVX-NEXT:    retq
entry:
  %log2 = call <3 x float> @llvm.experimental.constrained.log2.v3f32(
                              <3 x float> <float 42.0, float 43.0, float 44.0>,
                              metadata !"round.dynamic",
                              metadata !"fpexcept.strict")
  ret <3 x float> %log2
}

define <3 x double> @constrained_vector_log2_v3f64() {
; CHECK-LABEL: constrained_vector_log2_v3f64:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    subq $24, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 32
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq log2
; CHECK-NEXT:    movsd %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq log2
; CHECK-NEXT:    movsd %xmm0, (%rsp) # 8-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq log2
; CHECK-NEXT:    movsd %xmm0, {{[0-9]+}}(%rsp)
; CHECK-NEXT:    fldl {{[0-9]+}}(%rsp)
; CHECK-NEXT:    movsd {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 8-byte Reload
; CHECK-NEXT:    # xmm0 = mem[0],zero
; CHECK-NEXT:    movsd (%rsp), %xmm1 # 8-byte Reload
; CHECK-NEXT:    # xmm1 = mem[0],zero
; CHECK-NEXT:    addq $24, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_log2_v3f64:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    subq $56, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 64
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    callq log2
; AVX-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    callq log2
; AVX-NEXT:    vunpcklpd (%rsp), %xmm0, %xmm0 # 16-byte Folded Reload
; AVX-NEXT:    # xmm0 = xmm0[0],mem[0]
; AVX-NEXT:    vmovups %ymm0, (%rsp) # 32-byte Spill
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    vzeroupper
; AVX-NEXT:    callq log2
; AVX-NEXT:    vmovups (%rsp), %ymm1 # 32-byte Reload
; AVX-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
; AVX-NEXT:    addq $56, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 8
; AVX-NEXT:    retq
entry:
  %log2 = call <3 x double> @llvm.experimental.constrained.log2.v3f64(
                          <3 x double> <double 42.0, double 42.1, double 42.2>,
                          metadata !"round.dynamic",
                          metadata !"fpexcept.strict")
  ret <3 x double> %log2
}

define <4 x double> @constrained_vector_log2_v4f64() {
; CHECK-LABEL: constrained_vector_log2_v4f64:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    subq $40, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 48
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq log2
; CHECK-NEXT:    movaps %xmm0, (%rsp) # 16-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq log2
; CHECK-NEXT:    unpcklpd (%rsp), %xmm0 # 16-byte Folded Reload
; CHECK-NEXT:    # xmm0 = xmm0[0],mem[0]
; CHECK-NEXT:    movaps %xmm0, (%rsp) # 16-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq log2
; CHECK-NEXT:    movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq log2
; CHECK-NEXT:    movaps %xmm0, %xmm1
; CHECK-NEXT:    unpcklpd {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Folded Reload
; CHECK-NEXT:    # xmm1 = xmm1[0],mem[0]
; CHECK-NEXT:    movaps (%rsp), %xmm0 # 16-byte Reload
; CHECK-NEXT:    addq $40, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_log2_v4f64:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    subq $40, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 48
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    callq log2
; AVX-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    callq log2
; AVX-NEXT:    vunpcklpd (%rsp), %xmm0, %xmm0 # 16-byte Folded Reload
; AVX-NEXT:    # xmm0 = xmm0[0],mem[0]
; AVX-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    callq log2
; AVX-NEXT:    vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    callq log2
; AVX-NEXT:    vunpcklpd {{[-0-9]+}}(%r{{[sb]}}p), %xmm0, %xmm0 # 16-byte Folded Reload
; AVX-NEXT:    # xmm0 = xmm0[0],mem[0]
; AVX-NEXT:    vinsertf128 $1, (%rsp), %ymm0, %ymm0 # 16-byte Folded Reload
; AVX-NEXT:    addq $40, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 8
; AVX-NEXT:    retq
entry:
  %log2 = call <4 x double> @llvm.experimental.constrained.log2.v4f64(
                              <4 x double> <double 42.0, double 42.1,
                                            double 42.2, double 42.3>,
                              metadata !"round.dynamic",
                              metadata !"fpexcept.strict")
  ret <4 x double> %log2
}

define <1 x float> @constrained_vector_rint_v1f32() {
; CHECK-LABEL: constrained_vector_rint_v1f32:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    pushq %rax
; CHECK-NEXT:    .cfi_def_cfa_offset 16
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    callq rintf
; CHECK-NEXT:    popq %rax
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_rint_v1f32:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT:    vroundss $4, %xmm0, %xmm0, %xmm0
; AVX-NEXT:    retq
entry:
  %rint = call <1 x float> @llvm.experimental.constrained.rint.v1f32(
                             <1 x float> <float 42.0>,
                             metadata !"round.dynamic",
                             metadata !"fpexcept.strict")
  ret <1 x float> %rint
}

define <2 x double> @constrained_vector_rint_v2f64() {
; CHECK-LABEL: constrained_vector_rint_v2f64:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    subq $24, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 32
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq rint
; CHECK-NEXT:    movaps %xmm0, (%rsp) # 16-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq rint
; CHECK-NEXT:    unpcklpd (%rsp), %xmm0 # 16-byte Folded Reload
; CHECK-NEXT:    # xmm0 = xmm0[0],mem[0]
; CHECK-NEXT:    addq $24, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_rint_v2f64:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    vroundpd $4, {{.*}}(%rip), %xmm0
; AVX-NEXT:    retq
entry:
  %rint = call <2 x double> @llvm.experimental.constrained.rint.v2f64(
                        <2 x double> <double 42.1, double 42.0>,
                        metadata !"round.dynamic",
                        metadata !"fpexcept.strict")
  ret <2 x double> %rint
}

define <3 x float> @constrained_vector_rint_v3f32() {
; CHECK-LABEL: constrained_vector_rint_v3f32:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    subq $40, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 48
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    callq rintf
; CHECK-NEXT:    movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    callq rintf
; CHECK-NEXT:    movaps %xmm0, (%rsp) # 16-byte Spill
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    callq rintf
; CHECK-NEXT:    movaps (%rsp), %xmm1 # 16-byte Reload
; CHECK-NEXT:    unpcklps {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
; CHECK-NEXT:    unpcklpd {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Folded Reload
; CHECK-NEXT:    # xmm1 = xmm1[0],mem[0]
; CHECK-NEXT:    movaps %xmm1, %xmm0
; CHECK-NEXT:    addq $40, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_rint_v3f32:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT:    vroundss $4, %xmm0, %xmm0, %xmm0
; AVX-NEXT:    vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; AVX-NEXT:    vroundss $4, %xmm1, %xmm1, %xmm1
; AVX-NEXT:    vmovss {{.*#+}} xmm2 = mem[0],zero,zero,zero
; AVX-NEXT:    vroundss $4, %xmm2, %xmm2, %xmm2
; AVX-NEXT:    vinsertps {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[2,3]
; AVX-NEXT:    vinsertps {{.*#+}} xmm0 = xmm1[0,1],xmm0[0],xmm1[3]
; AVX-NEXT:    retq
 entry:
  %rint = call <3 x float> @llvm.experimental.constrained.rint.v3f32(
                              <3 x float> <float 42.0, float 43.0, float 44.0>,
                              metadata !"round.dynamic",
                              metadata !"fpexcept.strict")
  ret <3 x float> %rint
}

define <3 x double> @constrained_vector_rint_v3f64() {
; CHECK-LABEL: constrained_vector_rint_v3f64:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    subq $24, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 32
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq rint
; CHECK-NEXT:    movsd %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq rint
; CHECK-NEXT:    movsd %xmm0, (%rsp) # 8-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq rint
; CHECK-NEXT:    movsd %xmm0, {{[0-9]+}}(%rsp)
; CHECK-NEXT:    fldl {{[0-9]+}}(%rsp)
; CHECK-NEXT:    movsd {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 8-byte Reload
; CHECK-NEXT:    # xmm0 = mem[0],zero
; CHECK-NEXT:    movsd (%rsp), %xmm1 # 8-byte Reload
; CHECK-NEXT:    # xmm1 = mem[0],zero
; CHECK-NEXT:    addq $24, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_rint_v3f64:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    vroundsd $4, %xmm0, %xmm0, %xmm0
; AVX-NEXT:    vroundpd $4, {{.*}}(%rip), %xmm1
; AVX-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
; AVX-NEXT:    retq
entry:
  %rint = call <3 x double> @llvm.experimental.constrained.rint.v3f64(
                          <3 x double> <double 42.0, double 42.1, double 42.2>,
                          metadata !"round.dynamic",
                          metadata !"fpexcept.strict")
  ret <3 x double> %rint
}

define <4 x double> @constrained_vector_rint_v4f64() {
; CHECK-LABEL: constrained_vector_rint_v4f64:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    subq $40, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 48
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq rint
; CHECK-NEXT:    movaps %xmm0, (%rsp) # 16-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq rint
; CHECK-NEXT:    unpcklpd (%rsp), %xmm0 # 16-byte Folded Reload
; CHECK-NEXT:    # xmm0 = xmm0[0],mem[0]
; CHECK-NEXT:    movaps %xmm0, (%rsp) # 16-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq rint
; CHECK-NEXT:    movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq rint
; CHECK-NEXT:    movaps %xmm0, %xmm1
; CHECK-NEXT:    unpcklpd {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Folded Reload
; CHECK-NEXT:    # xmm1 = xmm1[0],mem[0]
; CHECK-NEXT:    movaps (%rsp), %xmm0 # 16-byte Reload
; CHECK-NEXT:    addq $40, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_rint_v4f64:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    vroundpd $4, {{.*}}(%rip), %ymm0
; AVX-NEXT:    retq
entry:
  %rint = call <4 x double> @llvm.experimental.constrained.rint.v4f64(
                        <4 x double> <double 42.1, double 42.2,
                                      double 42.3, double 42.4>,
                        metadata !"round.dynamic",
                        metadata !"fpexcept.strict")
  ret <4 x double> %rint
}

define <1 x float> @constrained_vector_nearbyint_v1f32() {
; CHECK-LABEL: constrained_vector_nearbyint_v1f32:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    pushq %rax
; CHECK-NEXT:    .cfi_def_cfa_offset 16
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    callq nearbyintf
; CHECK-NEXT:    popq %rax
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_nearbyint_v1f32:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT:    vroundss $12, %xmm0, %xmm0, %xmm0
; AVX-NEXT:    retq
entry:
  %nearby = call <1 x float> @llvm.experimental.constrained.nearbyint.v1f32(
                               <1 x float> <float 42.0>,
                               metadata !"round.dynamic",
                               metadata !"fpexcept.strict")
  ret <1 x float> %nearby
}

define <2 x double> @constrained_vector_nearbyint_v2f64() {
; CHECK-LABEL: constrained_vector_nearbyint_v2f64:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    subq $24, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 32
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq nearbyint
; CHECK-NEXT:    movaps %xmm0, (%rsp) # 16-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq nearbyint
; CHECK-NEXT:    unpcklpd (%rsp), %xmm0 # 16-byte Folded Reload
; CHECK-NEXT:    # xmm0 = xmm0[0],mem[0]
; CHECK-NEXT:    addq $24, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_nearbyint_v2f64:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    vroundpd $12, {{.*}}(%rip), %xmm0
; AVX-NEXT:    retq
entry:
  %nearby = call <2 x double> @llvm.experimental.constrained.nearbyint.v2f64(
                                <2 x double> <double 42.1, double 42.0>,
                                metadata !"round.dynamic",
                                metadata !"fpexcept.strict")
  ret <2 x double> %nearby
}

define <3 x float> @constrained_vector_nearbyint_v3f32() {
; CHECK-LABEL: constrained_vector_nearbyint_v3f32:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    subq $40, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 48
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    callq nearbyintf
; CHECK-NEXT:    movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    callq nearbyintf
; CHECK-NEXT:    movaps %xmm0, (%rsp) # 16-byte Spill
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    callq nearbyintf
; CHECK-NEXT:    movaps (%rsp), %xmm1 # 16-byte Reload
; CHECK-NEXT:    unpcklps {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
; CHECK-NEXT:    unpcklpd {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Folded Reload
; CHECK-NEXT:    # xmm1 = xmm1[0],mem[0]
; CHECK-NEXT:    movaps %xmm1, %xmm0
; CHECK-NEXT:    addq $40, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_nearbyint_v3f32:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT:    vroundss $12, %xmm0, %xmm0, %xmm0
; AVX-NEXT:    vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; AVX-NEXT:    vroundss $12, %xmm1, %xmm1, %xmm1
; AVX-NEXT:    vmovss {{.*#+}} xmm2 = mem[0],zero,zero,zero
; AVX-NEXT:    vroundss $12, %xmm2, %xmm2, %xmm2
; AVX-NEXT:    vinsertps {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[2,3]
; AVX-NEXT:    vinsertps {{.*#+}} xmm0 = xmm1[0,1],xmm0[0],xmm1[3]
; AVX-NEXT:    retq
entry:
  %nearby = call <3 x float> @llvm.experimental.constrained.nearbyint.v3f32(
                              <3 x float> <float 42.0, float 43.0, float 44.0>,
                              metadata !"round.dynamic",
                              metadata !"fpexcept.strict")
  ret <3 x float> %nearby
}

define <3 x double> @constrained_vector_nearby_v3f64() {
; CHECK-LABEL: constrained_vector_nearby_v3f64:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    subq $24, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 32
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq nearbyint
; CHECK-NEXT:    movsd %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq nearbyint
; CHECK-NEXT:    movsd %xmm0, (%rsp) # 8-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq nearbyint
; CHECK-NEXT:    movsd %xmm0, {{[0-9]+}}(%rsp)
; CHECK-NEXT:    fldl {{[0-9]+}}(%rsp)
; CHECK-NEXT:    movsd {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 8-byte Reload
; CHECK-NEXT:    # xmm0 = mem[0],zero
; CHECK-NEXT:    movsd (%rsp), %xmm1 # 8-byte Reload
; CHECK-NEXT:    # xmm1 = mem[0],zero
; CHECK-NEXT:    addq $24, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_nearby_v3f64:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    vroundsd $12, %xmm0, %xmm0, %xmm0
; AVX-NEXT:    vroundpd $12, {{.*}}(%rip), %xmm1
; AVX-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
; AVX-NEXT:    retq
entry:
  %nearby = call <3 x double> @llvm.experimental.constrained.nearbyint.v3f64(
                          <3 x double> <double 42.0, double 42.1, double 42.2>,
                          metadata !"round.dynamic",
                          metadata !"fpexcept.strict")
  ret <3 x double> %nearby
}

define <4 x double> @constrained_vector_nearbyint_v4f64() {
; CHECK-LABEL: constrained_vector_nearbyint_v4f64:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    subq $40, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 48
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq nearbyint
; CHECK-NEXT:    movaps %xmm0, (%rsp) # 16-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq nearbyint
; CHECK-NEXT:    unpcklpd (%rsp), %xmm0 # 16-byte Folded Reload
; CHECK-NEXT:    # xmm0 = xmm0[0],mem[0]
; CHECK-NEXT:    movaps %xmm0, (%rsp) # 16-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq nearbyint
; CHECK-NEXT:    movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq nearbyint
; CHECK-NEXT:    movaps %xmm0, %xmm1
; CHECK-NEXT:    unpcklpd {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Folded Reload
; CHECK-NEXT:    # xmm1 = xmm1[0],mem[0]
; CHECK-NEXT:    movaps (%rsp), %xmm0 # 16-byte Reload
; CHECK-NEXT:    addq $40, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_nearbyint_v4f64:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    vroundpd $12, {{.*}}(%rip), %ymm0
; AVX-NEXT:    retq
entry:
  %nearby = call <4 x double> @llvm.experimental.constrained.nearbyint.v4f64(
                                <4 x double> <double 42.1, double 42.2,
                                              double 42.3, double 42.4>,
                                metadata !"round.dynamic",
                                metadata !"fpexcept.strict")
  ret <4 x double> %nearby
}

define <1 x float> @constrained_vector_maxnum_v1f32() {
; CHECK-LABEL: constrained_vector_maxnum_v1f32:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    pushq %rax
; CHECK-NEXT:    .cfi_def_cfa_offset 16
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; CHECK-NEXT:    callq fmaxf
; CHECK-NEXT:    popq %rax
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_maxnum_v1f32:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    pushq %rax
; AVX-NEXT:    .cfi_def_cfa_offset 16
; AVX-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT:    vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; AVX-NEXT:    callq fmaxf
; AVX-NEXT:    popq %rax
; AVX-NEXT:    .cfi_def_cfa_offset 8
; AVX-NEXT:    retq
entry:
  %max = call <1 x float> @llvm.experimental.constrained.maxnum.v1f32(
                               <1 x float> <float 42.0>, <1 x float> <float 41.0>,
                               metadata !"round.dynamic",
                               metadata !"fpexcept.strict")
  ret <1 x float> %max
}

define <2 x double> @constrained_vector_maxnum_v2f64() {
; CHECK-LABEL: constrained_vector_maxnum_v2f64:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    subq $24, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 32
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    movsd {{.*#+}} xmm1 = mem[0],zero
; CHECK-NEXT:    callq fmax
; CHECK-NEXT:    movaps %xmm0, (%rsp) # 16-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    movsd {{.*#+}} xmm1 = mem[0],zero
; CHECK-NEXT:    callq fmax
; CHECK-NEXT:    unpcklpd (%rsp), %xmm0 # 16-byte Folded Reload
; CHECK-NEXT:    # xmm0 = xmm0[0],mem[0]
; CHECK-NEXT:    addq $24, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_maxnum_v2f64:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    subq $24, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 32
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    vmovsd {{.*#+}} xmm1 = mem[0],zero
; AVX-NEXT:    callq fmax
; AVX-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    vmovsd {{.*#+}} xmm1 = mem[0],zero
; AVX-NEXT:    callq fmax
; AVX-NEXT:    vunpcklpd (%rsp), %xmm0, %xmm0 # 16-byte Folded Reload
; AVX-NEXT:    # xmm0 = xmm0[0],mem[0]
; AVX-NEXT:    addq $24, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 8
; AVX-NEXT:    retq
entry:
  %max = call <2 x double> @llvm.experimental.constrained.maxnum.v2f64(
                                <2 x double> <double 43.0, double 42.0>,
                                <2 x double> <double 41.0, double 40.0>,
                                metadata !"round.dynamic",
                                metadata !"fpexcept.strict")
  ret <2 x double> %max
}

define <3 x float> @constrained_vector_maxnum_v3f32() {
; CHECK-LABEL: constrained_vector_maxnum_v3f32:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    subq $40, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 48
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; CHECK-NEXT:    callq fmaxf
; CHECK-NEXT:    movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; CHECK-NEXT:    movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    callq fmaxf
; CHECK-NEXT:    movaps %xmm0, (%rsp) # 16-byte Spill
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; CHECK-NEXT:    callq fmaxf
; CHECK-NEXT:    movaps (%rsp), %xmm1 # 16-byte Reload
; CHECK-NEXT:    unpcklps {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
; CHECK-NEXT:    unpcklpd {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Folded Reload
; CHECK-NEXT:    # xmm1 = xmm1[0],mem[0]
; CHECK-NEXT:    movaps %xmm1, %xmm0
; CHECK-NEXT:    addq $40, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_maxnum_v3f32:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    subq $40, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 48
; AVX-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT:    vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; AVX-NEXT:    callq fmaxf
; AVX-NEXT:    vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; AVX-NEXT:    vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; AVX-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT:    callq fmaxf
; AVX-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
; AVX-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT:    vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; AVX-NEXT:    callq fmaxf
; AVX-NEXT:    vmovaps (%rsp), %xmm1 # 16-byte Reload
; AVX-NEXT:    vinsertps {{.*#+}} xmm0 = xmm1[0],xmm0[0],xmm1[2,3]
; AVX-NEXT:    vinsertps $32, {{[-0-9]+}}(%r{{[sb]}}p), %xmm0, %xmm0 # 16-byte Folded Reload
; AVX-NEXT:    # xmm0 = xmm0[0,1],mem[0],xmm0[3]
; AVX-NEXT:    addq $40, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 8
; AVX-NEXT:    retq
entry:
  %max = call <3 x float> @llvm.experimental.constrained.maxnum.v3f32(
                              <3 x float> <float 43.0, float 44.0, float 45.0>,
                              <3 x float> <float 41.0, float 42.0, float 43.0>,
                              metadata !"round.dynamic",
                              metadata !"fpexcept.strict")
  ret <3 x float> %max
}

define <3 x double> @constrained_vector_max_v3f64() {
; CHECK-LABEL: constrained_vector_max_v3f64:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    subq $24, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 32
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    movsd {{.*#+}} xmm1 = mem[0],zero
; CHECK-NEXT:    callq fmax
; CHECK-NEXT:    movsd %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    movsd {{.*#+}} xmm1 = mem[0],zero
; CHECK-NEXT:    callq fmax
; CHECK-NEXT:    movsd %xmm0, (%rsp) # 8-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    movsd {{.*#+}} xmm1 = mem[0],zero
; CHECK-NEXT:    callq fmax
; CHECK-NEXT:    movsd %xmm0, {{[0-9]+}}(%rsp)
; CHECK-NEXT:    fldl {{[0-9]+}}(%rsp)
; CHECK-NEXT:    movsd {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 8-byte Reload
; CHECK-NEXT:    # xmm0 = mem[0],zero
; CHECK-NEXT:    movsd (%rsp), %xmm1 # 8-byte Reload
; CHECK-NEXT:    # xmm1 = mem[0],zero
; CHECK-NEXT:    addq $24, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_max_v3f64:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    subq $56, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 64
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    vmovsd {{.*#+}} xmm1 = mem[0],zero
; AVX-NEXT:    callq fmax
; AVX-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    vmovsd {{.*#+}} xmm1 = mem[0],zero
; AVX-NEXT:    callq fmax
; AVX-NEXT:    vunpcklpd (%rsp), %xmm0, %xmm0 # 16-byte Folded Reload
; AVX-NEXT:    # xmm0 = xmm0[0],mem[0]
; AVX-NEXT:    vmovups %ymm0, (%rsp) # 32-byte Spill
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    vmovsd {{.*#+}} xmm1 = mem[0],zero
; AVX-NEXT:    vzeroupper
; AVX-NEXT:    callq fmax
; AVX-NEXT:    vmovups (%rsp), %ymm1 # 32-byte Reload
; AVX-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
; AVX-NEXT:    addq $56, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 8
; AVX-NEXT:    retq
entry:
  %max = call <3 x double> @llvm.experimental.constrained.maxnum.v3f64(
                          <3 x double> <double 43.0, double 44.0, double 45.0>,
                          <3 x double> <double 40.0, double 41.0, double 42.0>,
                          metadata !"round.dynamic",
                          metadata !"fpexcept.strict")
  ret <3 x double> %max
}

define <4 x double> @constrained_vector_maxnum_v4f64() {
; CHECK-LABEL: constrained_vector_maxnum_v4f64:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    subq $40, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 48
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    movsd {{.*#+}} xmm1 = mem[0],zero
; CHECK-NEXT:    callq fmax
; CHECK-NEXT:    movaps %xmm0, (%rsp) # 16-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    movsd {{.*#+}} xmm1 = mem[0],zero
; CHECK-NEXT:    callq fmax
; CHECK-NEXT:    unpcklpd (%rsp), %xmm0 # 16-byte Folded Reload
; CHECK-NEXT:    # xmm0 = xmm0[0],mem[0]
; CHECK-NEXT:    movaps %xmm0, (%rsp) # 16-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    movsd {{.*#+}} xmm1 = mem[0],zero
; CHECK-NEXT:    callq fmax
; CHECK-NEXT:    movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    movsd {{.*#+}} xmm1 = mem[0],zero
; CHECK-NEXT:    callq fmax
; CHECK-NEXT:    movaps %xmm0, %xmm1
; CHECK-NEXT:    unpcklpd {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Folded Reload
; CHECK-NEXT:    # xmm1 = xmm1[0],mem[0]
; CHECK-NEXT:    movaps (%rsp), %xmm0 # 16-byte Reload
; CHECK-NEXT:    addq $40, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_maxnum_v4f64:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    subq $40, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 48
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    vmovsd {{.*#+}} xmm1 = mem[0],zero
; AVX-NEXT:    callq fmax
; AVX-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    vmovsd {{.*#+}} xmm1 = mem[0],zero
; AVX-NEXT:    callq fmax
; AVX-NEXT:    vunpcklpd (%rsp), %xmm0, %xmm0 # 16-byte Folded Reload
; AVX-NEXT:    # xmm0 = xmm0[0],mem[0]
; AVX-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    vmovsd {{.*#+}} xmm1 = mem[0],zero
; AVX-NEXT:    callq fmax
; AVX-NEXT:    vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    vmovsd {{.*#+}} xmm1 = mem[0],zero
; AVX-NEXT:    callq fmax
; AVX-NEXT:    vunpcklpd {{[-0-9]+}}(%r{{[sb]}}p), %xmm0, %xmm0 # 16-byte Folded Reload
; AVX-NEXT:    # xmm0 = xmm0[0],mem[0]
; AVX-NEXT:    vinsertf128 $1, (%rsp), %ymm0, %ymm0 # 16-byte Folded Reload
; AVX-NEXT:    addq $40, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 8
; AVX-NEXT:    retq
entry:
  %max = call <4 x double> @llvm.experimental.constrained.maxnum.v4f64(
                                <4 x double> <double 44.0, double 45.0,
                                              double 46.0, double 47.0>,
                                <4 x double> <double 40.0, double 41.0,
                                              double 42.0, double 43.0>,
                                metadata !"round.dynamic",
                                metadata !"fpexcept.strict")
  ret <4 x double> %max
}

define <1 x float> @constrained_vector_minnum_v1f32() {
; CHECK-LABEL: constrained_vector_minnum_v1f32:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    pushq %rax
; CHECK-NEXT:    .cfi_def_cfa_offset 16
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; CHECK-NEXT:    callq fminf
; CHECK-NEXT:    popq %rax
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_minnum_v1f32:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    pushq %rax
; AVX-NEXT:    .cfi_def_cfa_offset 16
; AVX-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT:    vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; AVX-NEXT:    callq fminf
; AVX-NEXT:    popq %rax
; AVX-NEXT:    .cfi_def_cfa_offset 8
; AVX-NEXT:    retq
 entry:
  %min = call <1 x float> @llvm.experimental.constrained.minnum.v1f32(
                               <1 x float> <float 42.0>, <1 x float> <float 41.0>,
                               metadata !"round.dynamic",
                               metadata !"fpexcept.strict")
  ret <1 x float> %min
}

define <2 x double> @constrained_vector_minnum_v2f64() {
; CHECK-LABEL: constrained_vector_minnum_v2f64:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    subq $24, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 32
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    movsd {{.*#+}} xmm1 = mem[0],zero
; CHECK-NEXT:    callq fmin
; CHECK-NEXT:    movaps %xmm0, (%rsp) # 16-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    movsd {{.*#+}} xmm1 = mem[0],zero
; CHECK-NEXT:    callq fmin
; CHECK-NEXT:    unpcklpd (%rsp), %xmm0 # 16-byte Folded Reload
; CHECK-NEXT:    # xmm0 = xmm0[0],mem[0]
; CHECK-NEXT:    addq $24, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_minnum_v2f64:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    subq $24, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 32
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    vmovsd {{.*#+}} xmm1 = mem[0],zero
; AVX-NEXT:    callq fmin
; AVX-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    vmovsd {{.*#+}} xmm1 = mem[0],zero
; AVX-NEXT:    callq fmin
; AVX-NEXT:    vunpcklpd (%rsp), %xmm0, %xmm0 # 16-byte Folded Reload
; AVX-NEXT:    # xmm0 = xmm0[0],mem[0]
; AVX-NEXT:    addq $24, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 8
; AVX-NEXT:    retq
entry:
  %min = call <2 x double> @llvm.experimental.constrained.minnum.v2f64(
                                <2 x double> <double 43.0, double 42.0>,
                                <2 x double> <double 41.0, double 40.0>,
                                metadata !"round.dynamic",
                                metadata !"fpexcept.strict")
  ret <2 x double> %min
}

define <3 x float> @constrained_vector_minnum_v3f32() {
; CHECK-LABEL: constrained_vector_minnum_v3f32:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    subq $40, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 48
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; CHECK-NEXT:    callq fminf
; CHECK-NEXT:    movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; CHECK-NEXT:    movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    callq fminf
; CHECK-NEXT:    movaps %xmm0, (%rsp) # 16-byte Spill
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; CHECK-NEXT:    callq fminf
; CHECK-NEXT:    movaps (%rsp), %xmm1 # 16-byte Reload
; CHECK-NEXT:    unpcklps {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
; CHECK-NEXT:    unpcklpd {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Folded Reload
; CHECK-NEXT:    # xmm1 = xmm1[0],mem[0]
; CHECK-NEXT:    movaps %xmm1, %xmm0
; CHECK-NEXT:    addq $40, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_minnum_v3f32:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    subq $40, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 48
; AVX-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT:    vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; AVX-NEXT:    callq fminf
; AVX-NEXT:    vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; AVX-NEXT:    vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; AVX-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT:    callq fminf
; AVX-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
; AVX-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT:    vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; AVX-NEXT:    callq fminf
; AVX-NEXT:    vmovaps (%rsp), %xmm1 # 16-byte Reload
; AVX-NEXT:    vinsertps {{.*#+}} xmm0 = xmm1[0],xmm0[0],xmm1[2,3]
; AVX-NEXT:    vinsertps $32, {{[-0-9]+}}(%r{{[sb]}}p), %xmm0, %xmm0 # 16-byte Folded Reload
; AVX-NEXT:    # xmm0 = xmm0[0,1],mem[0],xmm0[3]
; AVX-NEXT:    addq $40, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 8
; AVX-NEXT:    retq
entry:
  %min = call <3 x float> @llvm.experimental.constrained.minnum.v3f32(
                              <3 x float> <float 43.0, float 44.0, float 45.0>,
                              <3 x float> <float 41.0, float 42.0, float 43.0>,
                              metadata !"round.dynamic",
                              metadata !"fpexcept.strict")
  ret <3 x float> %min
}

define <3 x double> @constrained_vector_min_v3f64() {
; CHECK-LABEL: constrained_vector_min_v3f64:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    subq $24, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 32
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    movsd {{.*#+}} xmm1 = mem[0],zero
; CHECK-NEXT:    callq fmin
; CHECK-NEXT:    movsd %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    movsd {{.*#+}} xmm1 = mem[0],zero
; CHECK-NEXT:    callq fmin
; CHECK-NEXT:    movsd %xmm0, (%rsp) # 8-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    movsd {{.*#+}} xmm1 = mem[0],zero
; CHECK-NEXT:    callq fmin
; CHECK-NEXT:    movsd %xmm0, {{[0-9]+}}(%rsp)
; CHECK-NEXT:    fldl {{[0-9]+}}(%rsp)
; CHECK-NEXT:    movsd {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 8-byte Reload
; CHECK-NEXT:    # xmm0 = mem[0],zero
; CHECK-NEXT:    movsd (%rsp), %xmm1 # 8-byte Reload
; CHECK-NEXT:    # xmm1 = mem[0],zero
; CHECK-NEXT:    addq $24, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_min_v3f64:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    subq $56, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 64
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    vmovsd {{.*#+}} xmm1 = mem[0],zero
; AVX-NEXT:    callq fmin
; AVX-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    vmovsd {{.*#+}} xmm1 = mem[0],zero
; AVX-NEXT:    callq fmin
; AVX-NEXT:    vunpcklpd (%rsp), %xmm0, %xmm0 # 16-byte Folded Reload
; AVX-NEXT:    # xmm0 = xmm0[0],mem[0]
; AVX-NEXT:    vmovups %ymm0, (%rsp) # 32-byte Spill
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    vmovsd {{.*#+}} xmm1 = mem[0],zero
; AVX-NEXT:    vzeroupper
; AVX-NEXT:    callq fmin
; AVX-NEXT:    vmovups (%rsp), %ymm1 # 32-byte Reload
; AVX-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
; AVX-NEXT:    addq $56, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 8
; AVX-NEXT:    retq
entry:
 %min = call <3 x double> @llvm.experimental.constrained.minnum.v3f64(
                          <3 x double> <double 43.0, double 44.0, double 45.0>,
                          <3 x double> <double 40.0, double 41.0, double 42.0>,
                          metadata !"round.dynamic",
                          metadata !"fpexcept.strict")
  ret <3 x double> %min
}

define <4 x double> @constrained_vector_minnum_v4f64() {
; CHECK-LABEL: constrained_vector_minnum_v4f64:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    subq $40, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 48
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    movsd {{.*#+}} xmm1 = mem[0],zero
; CHECK-NEXT:    callq fmin
; CHECK-NEXT:    movaps %xmm0, (%rsp) # 16-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    movsd {{.*#+}} xmm1 = mem[0],zero
; CHECK-NEXT:    callq fmin
; CHECK-NEXT:    unpcklpd (%rsp), %xmm0 # 16-byte Folded Reload
; CHECK-NEXT:    # xmm0 = xmm0[0],mem[0]
; CHECK-NEXT:    movaps %xmm0, (%rsp) # 16-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    movsd {{.*#+}} xmm1 = mem[0],zero
; CHECK-NEXT:    callq fmin
; CHECK-NEXT:    movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    movsd {{.*#+}} xmm1 = mem[0],zero
; CHECK-NEXT:    callq fmin
; CHECK-NEXT:    movaps %xmm0, %xmm1
; CHECK-NEXT:    unpcklpd {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Folded Reload
; CHECK-NEXT:    # xmm1 = xmm1[0],mem[0]
; CHECK-NEXT:    movaps (%rsp), %xmm0 # 16-byte Reload
; CHECK-NEXT:    addq $40, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_minnum_v4f64:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    subq $40, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 48
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    vmovsd {{.*#+}} xmm1 = mem[0],zero
; AVX-NEXT:    callq fmin
; AVX-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    vmovsd {{.*#+}} xmm1 = mem[0],zero
; AVX-NEXT:    callq fmin
; AVX-NEXT:    vunpcklpd (%rsp), %xmm0, %xmm0 # 16-byte Folded Reload
; AVX-NEXT:    # xmm0 = xmm0[0],mem[0]
; AVX-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    vmovsd {{.*#+}} xmm1 = mem[0],zero
; AVX-NEXT:    callq fmin
; AVX-NEXT:    vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    vmovsd {{.*#+}} xmm1 = mem[0],zero
; AVX-NEXT:    callq fmin
; AVX-NEXT:    vunpcklpd {{[-0-9]+}}(%r{{[sb]}}p), %xmm0, %xmm0 # 16-byte Folded Reload
; AVX-NEXT:    # xmm0 = xmm0[0],mem[0]
; AVX-NEXT:    vinsertf128 $1, (%rsp), %ymm0, %ymm0 # 16-byte Folded Reload
; AVX-NEXT:    addq $40, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 8
; AVX-NEXT:    retq
entry:
  %min = call <4 x double> @llvm.experimental.constrained.minnum.v4f64(
                                <4 x double> <double 44.0, double 45.0,
                                              double 46.0, double 47.0>,
                                <4 x double> <double 40.0, double 41.0,
                                              double 42.0, double 43.0>,
                                metadata !"round.dynamic",
                                metadata !"fpexcept.strict")
  ret <4 x double> %min
}

define <1 x float> @constrained_vector_ceil_v1f32() {
; CHECK-LABEL: constrained_vector_ceil_v1f32:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    pushq %rax
; CHECK-NEXT:    .cfi_def_cfa_offset 16
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    callq ceilf
; CHECK-NEXT:    popq %rax
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_ceil_v1f32:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT:    vroundss $10, %xmm0, %xmm0, %xmm0
; AVX-NEXT:    retq
entry:
  %ceil = call <1 x float> @llvm.experimental.constrained.ceil.v1f32(
                               <1 x float> <float 1.5>,
                               metadata !"round.dynamic",
                               metadata !"fpexcept.strict")
  ret <1 x float> %ceil
}

define <2 x double> @constrained_vector_ceil_v2f64() {
; CHECK-LABEL: constrained_vector_ceil_v2f64:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    subq $24, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 32
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq ceil
; CHECK-NEXT:    movaps %xmm0, (%rsp) # 16-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq ceil
; CHECK-NEXT:    unpcklpd (%rsp), %xmm0 # 16-byte Folded Reload
; CHECK-NEXT:    # xmm0 = xmm0[0],mem[0]
; CHECK-NEXT:    addq $24, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_ceil_v2f64:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    vroundpd $10, {{.*}}(%rip), %xmm0
; AVX-NEXT:    retq
entry:
  %ceil = call <2 x double> @llvm.experimental.constrained.ceil.v2f64(
                                <2 x double> <double 1.1, double 1.9>,
                                metadata !"round.dynamic",
                                metadata !"fpexcept.strict")
  ret <2 x double> %ceil
}

define <3 x float> @constrained_vector_ceil_v3f32() {
; CHECK-LABEL: constrained_vector_ceil_v3f32:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    subq $40, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 48
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    callq ceilf
; CHECK-NEXT:    movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    callq ceilf
; CHECK-NEXT:    movaps %xmm0, (%rsp) # 16-byte Spill
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    callq ceilf
; CHECK-NEXT:    movaps (%rsp), %xmm1 # 16-byte Reload
; CHECK-NEXT:    unpcklps {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
; CHECK-NEXT:    unpcklpd {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Folded Reload
; CHECK-NEXT:    # xmm1 = xmm1[0],mem[0]
; CHECK-NEXT:    movaps %xmm1, %xmm0
; CHECK-NEXT:    addq $40, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_ceil_v3f32:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT:    vroundss $10, %xmm0, %xmm0, %xmm0
; AVX-NEXT:    vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; AVX-NEXT:    vroundss $10, %xmm1, %xmm1, %xmm1
; AVX-NEXT:    vmovss {{.*#+}} xmm2 = mem[0],zero,zero,zero
; AVX-NEXT:    vroundss $10, %xmm2, %xmm2, %xmm2
; AVX-NEXT:    vinsertps {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[2,3]
; AVX-NEXT:    vinsertps {{.*#+}} xmm0 = xmm1[0,1],xmm0[0],xmm1[3]
; AVX-NEXT:    retq
entry:
  %ceil = call <3 x float> @llvm.experimental.constrained.ceil.v3f32(
                              <3 x float> <float 1.5, float 2.5, float 3.5>,
                              metadata !"round.dynamic",
                              metadata !"fpexcept.strict")
  ret <3 x float> %ceil
}

define <3 x double> @constrained_vector_ceil_v3f64() {
; CHECK-LABEL: constrained_vector_ceil_v3f64:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    subq $24, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 32
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq ceil
; CHECK-NEXT:    movsd %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq ceil
; CHECK-NEXT:    movsd %xmm0, (%rsp) # 8-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq ceil
; CHECK-NEXT:    movsd %xmm0, {{[0-9]+}}(%rsp)
; CHECK-NEXT:    fldl {{[0-9]+}}(%rsp)
; CHECK-NEXT:    movsd {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 8-byte Reload
; CHECK-NEXT:    # xmm0 = mem[0],zero
; CHECK-NEXT:    movsd (%rsp), %xmm1 # 8-byte Reload
; CHECK-NEXT:    # xmm1 = mem[0],zero
; CHECK-NEXT:    addq $24, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_ceil_v3f64:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    vroundsd $10, %xmm0, %xmm0, %xmm0
; AVX-NEXT:    vroundpd $10, {{.*}}(%rip), %xmm1
; AVX-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
; AVX-NEXT:    retq
entry:
  %ceil = call <3 x double> @llvm.experimental.constrained.ceil.v3f64(
                          <3 x double> <double 1.1, double 1.9, double 1.5>,
                          metadata !"round.dynamic",
                          metadata !"fpexcept.strict")
  ret <3 x double> %ceil
}

define <1 x float> @constrained_vector_floor_v1f32() {
; CHECK-LABEL: constrained_vector_floor_v1f32:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    pushq %rax
; CHECK-NEXT:    .cfi_def_cfa_offset 16
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    callq floorf
; CHECK-NEXT:    popq %rax
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_floor_v1f32:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT:    vroundss $9, %xmm0, %xmm0, %xmm0
; AVX-NEXT:    retq
entry:
  %floor = call <1 x float> @llvm.experimental.constrained.floor.v1f32(
                               <1 x float> <float 1.5>,
                               metadata !"round.dynamic",
                               metadata !"fpexcept.strict")
  ret <1 x float> %floor
}


define <2 x double> @constrained_vector_floor_v2f64() {
; CHECK-LABEL: constrained_vector_floor_v2f64:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    subq $24, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 32
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq floor
; CHECK-NEXT:    movaps %xmm0, (%rsp) # 16-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq floor
; CHECK-NEXT:    unpcklpd (%rsp), %xmm0 # 16-byte Folded Reload
; CHECK-NEXT:    # xmm0 = xmm0[0],mem[0]
; CHECK-NEXT:    addq $24, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_floor_v2f64:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    vroundpd $9, {{.*}}(%rip), %xmm0
; AVX-NEXT:    retq
entry:
  %floor = call <2 x double> @llvm.experimental.constrained.floor.v2f64(
                                <2 x double> <double 1.1, double 1.9>,
                                metadata !"round.dynamic",
                                metadata !"fpexcept.strict")
  ret <2 x double> %floor
}

define <3 x float> @constrained_vector_floor_v3f32() {
; CHECK-LABEL: constrained_vector_floor_v3f32:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    subq $40, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 48
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    callq floorf
; CHECK-NEXT:    movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    callq floorf
; CHECK-NEXT:    movaps %xmm0, (%rsp) # 16-byte Spill
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    callq floorf
; CHECK-NEXT:    movaps (%rsp), %xmm1 # 16-byte Reload
; CHECK-NEXT:    unpcklps {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
; CHECK-NEXT:    unpcklpd {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Folded Reload
; CHECK-NEXT:    # xmm1 = xmm1[0],mem[0]
; CHECK-NEXT:    movaps %xmm1, %xmm0
; CHECK-NEXT:    addq $40, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_floor_v3f32:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT:    vroundss $9, %xmm0, %xmm0, %xmm0
; AVX-NEXT:    vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; AVX-NEXT:    vroundss $9, %xmm1, %xmm1, %xmm1
; AVX-NEXT:    vmovss {{.*#+}} xmm2 = mem[0],zero,zero,zero
; AVX-NEXT:    vroundss $9, %xmm2, %xmm2, %xmm2
; AVX-NEXT:    vinsertps {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[2,3]
; AVX-NEXT:    vinsertps {{.*#+}} xmm0 = xmm1[0,1],xmm0[0],xmm1[3]
; AVX-NEXT:    retq
entry:
  %floor = call <3 x float> @llvm.experimental.constrained.floor.v3f32(
                              <3 x float> <float 1.5, float 2.5, float 3.5>,
                              metadata !"round.dynamic",
                              metadata !"fpexcept.strict")
  ret <3 x float> %floor
}

define <3 x double> @constrained_vector_floor_v3f64() {
; CHECK-LABEL: constrained_vector_floor_v3f64:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    subq $24, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 32
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq floor
; CHECK-NEXT:    movsd %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq floor
; CHECK-NEXT:    movsd %xmm0, (%rsp) # 8-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq floor
; CHECK-NEXT:    movsd %xmm0, {{[0-9]+}}(%rsp)
; CHECK-NEXT:    fldl {{[0-9]+}}(%rsp)
; CHECK-NEXT:    movsd {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 8-byte Reload
; CHECK-NEXT:    # xmm0 = mem[0],zero
; CHECK-NEXT:    movsd (%rsp), %xmm1 # 8-byte Reload
; CHECK-NEXT:    # xmm1 = mem[0],zero
; CHECK-NEXT:    addq $24, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_floor_v3f64:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    vroundsd $9, %xmm0, %xmm0, %xmm0
; AVX-NEXT:    vroundpd $9, {{.*}}(%rip), %xmm1
; AVX-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
; AVX-NEXT:    retq
entry:
  %floor = call <3 x double> @llvm.experimental.constrained.floor.v3f64(
                          <3 x double> <double 1.1, double 1.9, double 1.5>,
                          metadata !"round.dynamic",
                          metadata !"fpexcept.strict")
  ret <3 x double> %floor
}

define <1 x float> @constrained_vector_round_v1f32() {
; CHECK-LABEL: constrained_vector_round_v1f32:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    pushq %rax
; CHECK-NEXT:    .cfi_def_cfa_offset 16
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    callq roundf
; CHECK-NEXT:    popq %rax
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_round_v1f32:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    pushq %rax
; AVX-NEXT:    .cfi_def_cfa_offset 16
; AVX-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT:    callq roundf
; AVX-NEXT:    popq %rax
; AVX-NEXT:    .cfi_def_cfa_offset 8
; AVX-NEXT:    retq
entry:
  %round = call <1 x float> @llvm.experimental.constrained.round.v1f32(
                               <1 x float> <float 1.5>,
                               metadata !"round.dynamic",
                               metadata !"fpexcept.strict")
  ret <1 x float> %round
}

define <2 x double> @constrained_vector_round_v2f64() {
; CHECK-LABEL: constrained_vector_round_v2f64:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    subq $24, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 32
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq round
; CHECK-NEXT:    movaps %xmm0, (%rsp) # 16-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq round
; CHECK-NEXT:    unpcklpd (%rsp), %xmm0 # 16-byte Folded Reload
; CHECK-NEXT:    # xmm0 = xmm0[0],mem[0]
; CHECK-NEXT:    addq $24, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_round_v2f64:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    subq $24, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 32
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    callq round
; AVX-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    callq round
; AVX-NEXT:    vunpcklpd (%rsp), %xmm0, %xmm0 # 16-byte Folded Reload
; AVX-NEXT:    # xmm0 = xmm0[0],mem[0]
; AVX-NEXT:    addq $24, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 8
; AVX-NEXT:    retq
entry:
  %round = call <2 x double> @llvm.experimental.constrained.round.v2f64(
                                <2 x double> <double 1.1, double 1.9>,
                                metadata !"round.dynamic",
                                metadata !"fpexcept.strict")
  ret <2 x double> %round
}

define <3 x float> @constrained_vector_round_v3f32() {
; CHECK-LABEL: constrained_vector_round_v3f32:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    subq $40, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 48
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    callq roundf
; CHECK-NEXT:    movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    callq roundf
; CHECK-NEXT:    movaps %xmm0, (%rsp) # 16-byte Spill
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    callq roundf
; CHECK-NEXT:    movaps (%rsp), %xmm1 # 16-byte Reload
; CHECK-NEXT:    unpcklps {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
; CHECK-NEXT:    unpcklpd {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Folded Reload
; CHECK-NEXT:    # xmm1 = xmm1[0],mem[0]
; CHECK-NEXT:    movaps %xmm1, %xmm0
; CHECK-NEXT:    addq $40, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_round_v3f32:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    subq $40, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 48
; AVX-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT:    callq roundf
; AVX-NEXT:    vmovaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; AVX-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT:    callq roundf
; AVX-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
; AVX-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT:    callq roundf
; AVX-NEXT:    vmovaps (%rsp), %xmm1 # 16-byte Reload
; AVX-NEXT:    vinsertps {{.*#+}} xmm0 = xmm1[0],xmm0[0],xmm1[2,3]
; AVX-NEXT:    vinsertps $32, {{[-0-9]+}}(%r{{[sb]}}p), %xmm0, %xmm0 # 16-byte Folded Reload
; AVX-NEXT:    # xmm0 = xmm0[0,1],mem[0],xmm0[3]
; AVX-NEXT:    addq $40, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 8
; AVX-NEXT:    retq
entry:
  %round = call <3 x float> @llvm.experimental.constrained.round.v3f32(
                              <3 x float> <float 1.5, float 2.5, float 3.5>,
                              metadata !"round.dynamic",
                              metadata !"fpexcept.strict")
  ret <3 x float> %round
}


define <3 x double> @constrained_vector_round_v3f64() {
; CHECK-LABEL: constrained_vector_round_v3f64:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    subq $24, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 32
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq round
; CHECK-NEXT:    movsd %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq round
; CHECK-NEXT:    movsd %xmm0, (%rsp) # 8-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq round
; CHECK-NEXT:    movsd %xmm0, {{[0-9]+}}(%rsp)
; CHECK-NEXT:    fldl {{[0-9]+}}(%rsp)
; CHECK-NEXT:    movsd {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 8-byte Reload
; CHECK-NEXT:    # xmm0 = mem[0],zero
; CHECK-NEXT:    movsd (%rsp), %xmm1 # 8-byte Reload
; CHECK-NEXT:    # xmm1 = mem[0],zero
; CHECK-NEXT:    addq $24, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_round_v3f64:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    subq $56, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 64
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    callq round
; AVX-NEXT:    vmovaps %xmm0, (%rsp) # 16-byte Spill
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    callq round
; AVX-NEXT:    vunpcklpd (%rsp), %xmm0, %xmm0 # 16-byte Folded Reload
; AVX-NEXT:    # xmm0 = xmm0[0],mem[0]
; AVX-NEXT:    vmovups %ymm0, (%rsp) # 32-byte Spill
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    vzeroupper
; AVX-NEXT:    callq round
; AVX-NEXT:    vmovups (%rsp), %ymm1 # 32-byte Reload
; AVX-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
; AVX-NEXT:    addq $56, %rsp
; AVX-NEXT:    .cfi_def_cfa_offset 8
; AVX-NEXT:    retq
entry:
  %round = call <3 x double> @llvm.experimental.constrained.round.v3f64(
                          <3 x double> <double 1.1, double 1.9, double 1.5>,
                          metadata !"round.dynamic",
                          metadata !"fpexcept.strict")
  ret <3 x double> %round
}

define <1 x float> @constrained_vector_trunc_v1f32() {
; CHECK-LABEL: constrained_vector_trunc_v1f32:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    pushq %rax
; CHECK-NEXT:    .cfi_def_cfa_offset 16
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    callq truncf
; CHECK-NEXT:    popq %rax
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_trunc_v1f32:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT:    vroundss $11, %xmm0, %xmm0, %xmm0
; AVX-NEXT:    retq
entry:
  %trunc = call <1 x float> @llvm.experimental.constrained.trunc.v1f32(
                               <1 x float> <float 1.5>,
                               metadata !"round.dynamic",
                               metadata !"fpexcept.strict")
  ret <1 x float> %trunc
}

define <2 x double> @constrained_vector_trunc_v2f64() {
; CHECK-LABEL: constrained_vector_trunc_v2f64:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    subq $24, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 32
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq trunc
; CHECK-NEXT:    movaps %xmm0, (%rsp) # 16-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq trunc
; CHECK-NEXT:    unpcklpd (%rsp), %xmm0 # 16-byte Folded Reload
; CHECK-NEXT:    # xmm0 = xmm0[0],mem[0]
; CHECK-NEXT:    addq $24, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_trunc_v2f64:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    vroundpd $11, {{.*}}(%rip), %xmm0
; AVX-NEXT:    retq
entry:
  %trunc = call <2 x double> @llvm.experimental.constrained.trunc.v2f64(
                                <2 x double> <double 1.1, double 1.9>,
                                metadata !"round.dynamic",
                                metadata !"fpexcept.strict")
  ret <2 x double> %trunc
}

define <3 x float> @constrained_vector_trunc_v3f32() {
; CHECK-LABEL: constrained_vector_trunc_v3f32:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    subq $40, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 48
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    callq truncf
; CHECK-NEXT:    movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    callq truncf
; CHECK-NEXT:    movaps %xmm0, (%rsp) # 16-byte Spill
; CHECK-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT:    callq truncf
; CHECK-NEXT:    movaps (%rsp), %xmm1 # 16-byte Reload
; CHECK-NEXT:    unpcklps {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
; CHECK-NEXT:    unpcklpd {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Folded Reload
; CHECK-NEXT:    # xmm1 = xmm1[0],mem[0]
; CHECK-NEXT:    movaps %xmm1, %xmm0
; CHECK-NEXT:    addq $40, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_trunc_v3f32:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; AVX-NEXT:    vroundss $11, %xmm0, %xmm0, %xmm0
; AVX-NEXT:    vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; AVX-NEXT:    vroundss $11, %xmm1, %xmm1, %xmm1
; AVX-NEXT:    vmovss {{.*#+}} xmm2 = mem[0],zero,zero,zero
; AVX-NEXT:    vroundss $11, %xmm2, %xmm2, %xmm2
; AVX-NEXT:    vinsertps {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[2,3]
; AVX-NEXT:    vinsertps {{.*#+}} xmm0 = xmm1[0,1],xmm0[0],xmm1[3]
; AVX-NEXT:    retq
entry:
  %trunc = call <3 x float> @llvm.experimental.constrained.trunc.v3f32(
                              <3 x float> <float 1.5, float 2.5, float 3.5>,
                              metadata !"round.dynamic",
                              metadata !"fpexcept.strict")
  ret <3 x float> %trunc
}

define <3 x double> @constrained_vector_trunc_v3f64() {
; CHECK-LABEL: constrained_vector_trunc_v3f64:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    subq $24, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 32
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq trunc
; CHECK-NEXT:    movsd %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq trunc
; CHECK-NEXT:    movsd %xmm0, (%rsp) # 8-byte Spill
; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
; CHECK-NEXT:    callq trunc
; CHECK-NEXT:    movsd %xmm0, {{[0-9]+}}(%rsp)
; CHECK-NEXT:    fldl {{[0-9]+}}(%rsp)
; CHECK-NEXT:    movsd {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 8-byte Reload
; CHECK-NEXT:    # xmm0 = mem[0],zero
; CHECK-NEXT:    movsd (%rsp), %xmm1 # 8-byte Reload
; CHECK-NEXT:    # xmm1 = mem[0],zero
; CHECK-NEXT:    addq $24, %rsp
; CHECK-NEXT:    .cfi_def_cfa_offset 8
; CHECK-NEXT:    retq
;
; AVX-LABEL: constrained_vector_trunc_v3f64:
; AVX:       # %bb.0: # %entry
; AVX-NEXT:    vmovsd {{.*#+}} xmm0 = mem[0],zero
; AVX-NEXT:    vroundsd $11, %xmm0, %xmm0, %xmm0
; AVX-NEXT:    vroundpd $11, {{.*}}(%rip), %xmm1
; AVX-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
; AVX-NEXT:    retq
entry:
  %trunc = call <3 x double> @llvm.experimental.constrained.trunc.v3f64(
                          <3 x double> <double 1.1, double 1.9, double 1.5>,
                          metadata !"round.dynamic",
                          metadata !"fpexcept.strict")
  ret <3 x double> %trunc
}


; Single width declarations
declare <2 x double> @llvm.experimental.constrained.fadd.v2f64(<2 x double>, <2 x double>, metadata, metadata)
declare <2 x double> @llvm.experimental.constrained.fsub.v2f64(<2 x double>, <2 x double>, metadata, metadata)
declare <2 x double> @llvm.experimental.constrained.fmul.v2f64(<2 x double>, <2 x double>, metadata, metadata)
declare <2 x double> @llvm.experimental.constrained.fdiv.v2f64(<2 x double>, <2 x double>, metadata, metadata)
declare <2 x double> @llvm.experimental.constrained.frem.v2f64(<2 x double>, <2 x double>, metadata, metadata)
declare <2 x double> @llvm.experimental.constrained.sqrt.v2f64(<2 x double>, metadata, metadata)
declare <2 x double> @llvm.experimental.constrained.pow.v2f64(<2 x double>, <2 x double>, metadata, metadata)
declare <2 x double> @llvm.experimental.constrained.powi.v2f64(<2 x double>, i32, metadata, metadata)
declare <2 x double> @llvm.experimental.constrained.sin.v2f64(<2 x double>, metadata, metadata)
declare <2 x double> @llvm.experimental.constrained.cos.v2f64(<2 x double>, metadata, metadata)
declare <2 x double> @llvm.experimental.constrained.exp.v2f64(<2 x double>, metadata, metadata)
declare <2 x double> @llvm.experimental.constrained.exp2.v2f64(<2 x double>, metadata, metadata)
declare <2 x double> @llvm.experimental.constrained.log.v2f64(<2 x double>, metadata, metadata)
declare <2 x double> @llvm.experimental.constrained.log10.v2f64(<2 x double>, metadata, metadata)
declare <2 x double> @llvm.experimental.constrained.log2.v2f64(<2 x double>, metadata, metadata)
declare <2 x double> @llvm.experimental.constrained.rint.v2f64(<2 x double>, metadata, metadata)
declare <2 x double> @llvm.experimental.constrained.nearbyint.v2f64(<2 x double>, metadata, metadata)
declare <2 x double> @llvm.experimental.constrained.maxnum.v2f64(<2 x double>, <2 x double>, metadata, metadata)
declare <2 x double> @llvm.experimental.constrained.minnum.v2f64(<2 x double>, <2 x double>, metadata, metadata)
declare <2 x double> @llvm.experimental.constrained.ceil.v2f64(<2 x double>, metadata, metadata)
declare <2 x double> @llvm.experimental.constrained.floor.v2f64(<2 x double>, metadata, metadata)
declare <2 x double> @llvm.experimental.constrained.round.v2f64(<2 x double>, metadata, metadata)
declare <2 x double> @llvm.experimental.constrained.trunc.v2f64(<2 x double>, metadata, metadata)

; Scalar width declarations
declare <1 x float> @llvm.experimental.constrained.fadd.v1f32(<1 x float>, <1 x float>, metadata, metadata)
declare <1 x float> @llvm.experimental.constrained.fsub.v1f32(<1 x float>, <1 x float>, metadata, metadata)
declare <1 x float> @llvm.experimental.constrained.fmul.v1f32(<1 x float>, <1 x float>, metadata, metadata)
declare <1 x float> @llvm.experimental.constrained.fdiv.v1f32(<1 x float>, <1 x float>, metadata, metadata)
declare <1 x float> @llvm.experimental.constrained.frem.v1f32(<1 x float>, <1 x float>, metadata, metadata)
declare <1 x float> @llvm.experimental.constrained.sqrt.v1f32(<1 x float>, metadata, metadata)
declare <1 x float> @llvm.experimental.constrained.pow.v1f32(<1 x float>, <1 x float>, metadata, metadata)
declare <1 x float> @llvm.experimental.constrained.powi.v1f32(<1 x float>, i32, metadata, metadata)
declare <1 x float> @llvm.experimental.constrained.sin.v1f32(<1 x float>, metadata, metadata)
declare <1 x float> @llvm.experimental.constrained.cos.v1f32(<1 x float>, metadata, metadata)
declare <1 x float> @llvm.experimental.constrained.exp.v1f32(<1 x float>, metadata, metadata)
declare <1 x float> @llvm.experimental.constrained.exp2.v1f32(<1 x float>, metadata, metadata)
declare <1 x float> @llvm.experimental.constrained.log.v1f32(<1 x float>, metadata, metadata)
declare <1 x float> @llvm.experimental.constrained.log10.v1f32(<1 x float>, metadata, metadata)
declare <1 x float> @llvm.experimental.constrained.log2.v1f32(<1 x float>, metadata, metadata)
declare <1 x float> @llvm.experimental.constrained.rint.v1f32(<1 x float>, metadata, metadata)
declare <1 x float> @llvm.experimental.constrained.nearbyint.v1f32(<1 x float>, metadata, metadata)
declare <1 x float> @llvm.experimental.constrained.maxnum.v1f32(<1 x float>, <1 x float>, metadata, metadata)
declare <1 x float> @llvm.experimental.constrained.minnum.v1f32(<1 x float>, <1 x float>, metadata, metadata)
declare <1 x float> @llvm.experimental.constrained.ceil.v1f32(<1 x float>, metadata, metadata)
declare <1 x float> @llvm.experimental.constrained.floor.v1f32(<1 x float>, metadata, metadata)
declare <1 x float> @llvm.experimental.constrained.round.v1f32(<1 x float>, metadata, metadata)
declare <1 x float> @llvm.experimental.constrained.trunc.v1f32(<1 x float>, metadata, metadata)

; Illegal width declarations
declare <3 x float> @llvm.experimental.constrained.fadd.v3f32(<3 x float>, <3 x float>, metadata, metadata)
declare <3 x double> @llvm.experimental.constrained.fadd.v3f64(<3 x double>, <3 x double>, metadata, metadata)
declare <3 x float> @llvm.experimental.constrained.fsub.v3f32(<3 x float>, <3 x float>, metadata, metadata)
declare <3 x double> @llvm.experimental.constrained.fsub.v3f64(<3 x double>, <3 x double>, metadata, metadata)
declare <3 x float> @llvm.experimental.constrained.fmul.v3f32(<3 x float>, <3 x float>, metadata, metadata)
declare <3 x double> @llvm.experimental.constrained.fmul.v3f64(<3 x double>, <3 x double>, metadata, metadata)
declare <3 x float> @llvm.experimental.constrained.fdiv.v3f32(<3 x float>, <3 x float>, metadata, metadata)
declare <3 x double> @llvm.experimental.constrained.fdiv.v3f64(<3 x double>, <3 x double>, metadata, metadata)
declare <3 x float> @llvm.experimental.constrained.frem.v3f32(<3 x float>, <3 x float>, metadata, metadata)
declare <3 x double> @llvm.experimental.constrained.frem.v3f64(<3 x double>, <3 x double>, metadata, metadata)
declare <3 x float> @llvm.experimental.constrained.sqrt.v3f32(<3 x float>, metadata, metadata)
declare <3 x double> @llvm.experimental.constrained.sqrt.v3f64(<3 x double>, metadata, metadata)
declare <3 x float> @llvm.experimental.constrained.pow.v3f32(<3 x float>, <3 x float>, metadata, metadata)
declare <3 x double> @llvm.experimental.constrained.pow.v3f64(<3 x double>, <3 x double>, metadata, metadata)
declare <3 x float> @llvm.experimental.constrained.powi.v3f32(<3 x float>, i32, metadata, metadata)
declare <3 x double> @llvm.experimental.constrained.powi.v3f64(<3 x double>, i32, metadata, metadata)
declare <3 x float> @llvm.experimental.constrained.sin.v3f32(<3 x float>, metadata, metadata)
declare <3 x double> @llvm.experimental.constrained.sin.v3f64(<3 x double>, metadata, metadata)
declare <3 x float> @llvm.experimental.constrained.cos.v3f32(<3 x float>, metadata, metadata)
declare <3 x double> @llvm.experimental.constrained.cos.v3f64(<3 x double>, metadata, metadata)
declare <3 x float> @llvm.experimental.constrained.exp.v3f32(<3 x float>, metadata, metadata)
declare <3 x double> @llvm.experimental.constrained.exp.v3f64(<3 x double>, metadata, metadata)
declare <3 x float> @llvm.experimental.constrained.exp2.v3f32(<3 x float>, metadata, metadata)
declare <3 x double> @llvm.experimental.constrained.exp2.v3f64(<3 x double>, metadata, metadata)
declare <3 x float> @llvm.experimental.constrained.log.v3f32(<3 x float>, metadata, metadata)
declare <3 x double> @llvm.experimental.constrained.log.v3f64(<3 x double>, metadata, metadata)
declare <3 x float> @llvm.experimental.constrained.log10.v3f32(<3 x float>, metadata, metadata)
declare <3 x double> @llvm.experimental.constrained.log10.v3f64(<3 x double>, metadata, metadata)
declare <3 x float> @llvm.experimental.constrained.log2.v3f32(<3 x float>, metadata, metadata)
declare <3 x double> @llvm.experimental.constrained.log2.v3f64(<3 x double>, metadata, metadata)
declare <3 x float> @llvm.experimental.constrained.rint.v3f32(<3 x float>, metadata, metadata)
declare <3 x double> @llvm.experimental.constrained.rint.v3f64(<3 x double>, metadata, metadata)
declare <3 x float> @llvm.experimental.constrained.nearbyint.v3f32(<3 x float>, metadata, metadata)
declare <3 x double> @llvm.experimental.constrained.nearbyint.v3f64(<3 x double>, metadata, metadata)
declare <3 x float> @llvm.experimental.constrained.maxnum.v3f32(<3 x float>, <3 x float>, metadata, metadata)
declare <3 x double> @llvm.experimental.constrained.maxnum.v3f64(<3 x double>, <3 x double>, metadata, metadata)
declare <3 x float> @llvm.experimental.constrained.minnum.v3f32(<3 x float>, <3 x float>, metadata, metadata)
declare <3 x double> @llvm.experimental.constrained.minnum.v3f64(<3 x double>, <3 x double>, metadata, metadata)
declare <3 x float> @llvm.experimental.constrained.ceil.v3f32(<3 x float>, metadata, metadata)
declare <3 x double> @llvm.experimental.constrained.ceil.v3f64(<3 x double>, metadata, metadata)
declare <3 x float> @llvm.experimental.constrained.floor.v3f32(<3 x float>, metadata, metadata)
declare <3 x double> @llvm.experimental.constrained.floor.v3f64(<3 x double>, metadata, metadata)
declare <3 x float> @llvm.experimental.constrained.round.v3f32(<3 x float>, metadata, metadata)
declare <3 x double> @llvm.experimental.constrained.round.v3f64(<3 x double>, metadata, metadata)
declare <3 x float> @llvm.experimental.constrained.trunc.v3f32(<3 x float>, metadata, metadata)
declare <3 x double> @llvm.experimental.constrained.trunc.v3f64(<3 x double>, metadata, metadata)

; Double width declarations
declare <4 x double> @llvm.experimental.constrained.fadd.v4f64(<4 x double>, <4 x double>, metadata, metadata)
declare <4 x double> @llvm.experimental.constrained.fsub.v4f64(<4 x double>, <4 x double>, metadata, metadata)
declare <4 x double> @llvm.experimental.constrained.fmul.v4f64(<4 x double>, <4 x double>, metadata, metadata)
declare <4 x double> @llvm.experimental.constrained.fdiv.v4f64(<4 x double>, <4 x double>, metadata, metadata)
declare <4 x double> @llvm.experimental.constrained.frem.v4f64(<4 x double>, <4 x double>, metadata, metadata)
declare <4 x double> @llvm.experimental.constrained.sqrt.v4f64(<4 x double>, metadata, metadata)
declare <4 x double> @llvm.experimental.constrained.pow.v4f64(<4 x double>, <4 x double>, metadata, metadata)
declare <4 x double> @llvm.experimental.constrained.powi.v4f64(<4 x double>, i32, metadata, metadata)
declare <4 x double> @llvm.experimental.constrained.sin.v4f64(<4 x double>, metadata, metadata)
declare <4 x double> @llvm.experimental.constrained.cos.v4f64(<4 x double>, metadata, metadata)
declare <4 x double> @llvm.experimental.constrained.exp.v4f64(<4 x double>, metadata, metadata)
declare <4 x double> @llvm.experimental.constrained.exp2.v4f64(<4 x double>, metadata, metadata)
declare <4 x double> @llvm.experimental.constrained.log.v4f64(<4 x double>, metadata, metadata)
declare <4 x double> @llvm.experimental.constrained.log10.v4f64(<4 x double>, metadata, metadata)
declare <4 x double> @llvm.experimental.constrained.log2.v4f64(<4 x double>, metadata, metadata)
declare <4 x double> @llvm.experimental.constrained.rint.v4f64(<4 x double>, metadata, metadata)
declare <4 x double> @llvm.experimental.constrained.nearbyint.v4f64(<4 x double>, metadata, metadata)
declare <4 x double> @llvm.experimental.constrained.maxnum.v4f64(<4 x double>, <4 x double>, metadata, metadata)
declare <4 x double> @llvm.experimental.constrained.minnum.v4f64(<4 x double>, <4 x double>, metadata, metadata)
declare <4 x double> @llvm.experimental.constrained.ceil.v4f64(<4 x double>, metadata, metadata)
declare <4 x double> @llvm.experimental.constrained.floor.v4f64(<4 x double>, metadata, metadata)
declare <4 x double> @llvm.experimental.constrained.round.v4f64(<4 x double>, metadata, metadata)
declare <4 x double> @llvm.experimental.constrained.trunc.v4f64(<4 x double>, metadata, metadata)