Codebase Browser
llvm
Go to App

llvm/llvm/test/Transforms/SLPVectorizer/AArch64/accelerate-vector-functions.ll 

; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -passes=inject-tli-mappings,slp-vectorizer -vector-library=Accelerate -S %s | FileCheck %s
; RUN: opt -passes=inject-tli-mappings,slp-vectorizer -S %s | FileCheck --check-prefix NOACCELERATE %s

target datalayout = "e-m:o-i64:64-i128:128-n32:64-S128"
target triple = "arm64-apple-ios14.0.0"

declare float @llvm.sin.f32(float)

; Accelerate provides sin() for <4 x float>
define <4 x float> @int_sin_4x(ptr %a) {
; CHECK-LABEL: @int_sin_4x(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = load <4 x float>, ptr [[A:%.*]], align 16
; CHECK-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @vsinf(<4 x float> [[TMP0]])
; CHECK-NEXT:    ret <4 x float> [[TMP1]]
;
; NOACCELERATE-LABEL: @int_sin_4x(
; NOACCELERATE-NEXT:  entry:
; NOACCELERATE-NEXT:    [[TMP0:%.*]] = load <4 x float>, ptr [[A:%.*]], align 16
; NOACCELERATE-NEXT:    [[VECEXT:%.*]] = extractelement <4 x float> [[TMP0]], i32 0
; NOACCELERATE-NEXT:    [[TMP1:%.*]] = tail call fast float @llvm.sin.f32(float [[VECEXT]])
; NOACCELERATE-NEXT:    [[VECINS:%.*]] = insertelement <4 x float> undef, float [[TMP1]], i32 0
; NOACCELERATE-NEXT:    [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i32 1
; NOACCELERATE-NEXT:    [[TMP2:%.*]] = tail call fast float @llvm.sin.f32(float [[VECEXT_1]])
; NOACCELERATE-NEXT:    [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP2]], i32 1
; NOACCELERATE-NEXT:    [[TMP3:%.*]] = shufflevector <4 x float> [[TMP0]], <4 x float> poison, <2 x i32> <i32 2, i32 3>
; NOACCELERATE-NEXT:    [[TMP4:%.*]] = call fast <2 x float> @llvm.sin.v2f32(<2 x float> [[TMP3]])
; NOACCELERATE-NEXT:    [[TMP5:%.*]] = shufflevector <2 x float> [[TMP4]], <2 x float> poison, <4 x i32> <i32 0, i32 1, i32 poison, i32 poison>
; NOACCELERATE-NEXT:    [[VECINS_31:%.*]] = shufflevector <4 x float> [[VECINS_1]], <4 x float> [[TMP5]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>
; NOACCELERATE-NEXT:    ret <4 x float> [[VECINS_31]]
;
entry:
  %0 = load <4 x float>, ptr %a, align 16
  %vecext = extractelement <4 x float> %0, i32 0
  %1 = tail call fast float @llvm.sin.f32(float %vecext)
  %vecins = insertelement <4 x float> undef, float %1, i32 0
  %vecext.1 = extractelement <4 x float> %0, i32 1
  %2 = tail call fast float @llvm.sin.f32(float %vecext.1)
  %vecins.1 = insertelement <4 x float> %vecins, float %2, i32 1
  %vecext.2 = extractelement <4 x float> %0, i32 2
  %3 = tail call fast float @llvm.sin.f32(float %vecext.2)
  %vecins.2 = insertelement <4 x float> %vecins.1, float %3, i32 2
  %vecext.3 = extractelement <4 x float> %0, i32 3
  %4 = tail call fast float @llvm.sin.f32(float %vecext.3)
  %vecins.3 = insertelement <4 x float> %vecins.2, float %4, i32 3
  ret <4 x float> %vecins.3
}

declare float @ceilf(float) readonly nounwind willreturn

define <4 x float> @ceil_4x(ptr %a) {
; CHECK-LABEL: @ceil_4x(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = load <4 x float>, ptr [[A:%.*]], align 16
; CHECK-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @llvm.ceil.v4f32(<4 x float> [[TMP0]])
; CHECK-NEXT:    ret <4 x float> [[TMP1]]
;
; NOACCELERATE-LABEL: @ceil_4x(
; NOACCELERATE-NEXT:  entry:
; NOACCELERATE-NEXT:    [[TMP0:%.*]] = load <4 x float>, ptr [[A:%.*]], align 16
; NOACCELERATE-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @llvm.ceil.v4f32(<4 x float> [[TMP0]])
; NOACCELERATE-NEXT:    ret <4 x float> [[TMP1]]
;
entry:
  %0 = load <4 x float>, ptr %a, align 16
  %vecext = extractelement <4 x float> %0, i32 0
  %1 = tail call fast float @ceilf(float %vecext)
  %vecins = insertelement <4 x float> undef, float %1, i32 0
  %vecext.1 = extractelement <4 x float> %0, i32 1
  %2 = tail call fast float @ceilf(float %vecext.1)
  %vecins.1 = insertelement <4 x float> %vecins, float %2, i32 1
  %vecext.2 = extractelement <4 x float> %0, i32 2
  %3 = tail call fast float @ceilf(float %vecext.2)
  %vecins.2 = insertelement <4 x float> %vecins.1, float %3, i32 2
  %vecext.3 = extractelement <4 x float> %0, i32 3
  %4 = tail call fast float @ceilf(float %vecext.3)
  %vecins.3 = insertelement <4 x float> %vecins.2, float %4, i32 3
  ret <4 x float> %vecins.3
}

declare float @fabsf(float) readonly nounwind willreturn

define <4 x float> @fabs_4x(ptr %a) {
; CHECK-LABEL: @fabs_4x(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = load <4 x float>, ptr [[A:%.*]], align 16
; CHECK-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @llvm.fabs.v4f32(<4 x float> [[TMP0]])
; CHECK-NEXT:    ret <4 x float> [[TMP1]]
;
; NOACCELERATE-LABEL: @fabs_4x(
; NOACCELERATE-NEXT:  entry:
; NOACCELERATE-NEXT:    [[TMP0:%.*]] = load <4 x float>, ptr [[A:%.*]], align 16
; NOACCELERATE-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @llvm.fabs.v4f32(<4 x float> [[TMP0]])
; NOACCELERATE-NEXT:    ret <4 x float> [[TMP1]]
;
entry:
  %0 = load <4 x float>, ptr %a, align 16
  %vecext = extractelement <4 x float> %0, i32 0
  %1 = tail call fast float @fabsf(float %vecext)
  %vecins = insertelement <4 x float> undef, float %1, i32 0
  %vecext.1 = extractelement <4 x float> %0, i32 1
  %2 = tail call fast float @fabsf(float %vecext.1)
  %vecins.1 = insertelement <4 x float> %vecins, float %2, i32 1
  %vecext.2 = extractelement <4 x float> %0, i32 2
  %3 = tail call fast float @fabsf(float %vecext.2)
  %vecins.2 = insertelement <4 x float> %vecins.1, float %3, i32 2
  %vecext.3 = extractelement <4 x float> %0, i32 3
  %4 = tail call fast float @fabsf(float %vecext.3)
  %vecins.3 = insertelement <4 x float> %vecins.2, float %4, i32 3
  ret <4 x float> %vecins.3
}
declare float @llvm.fabs.f32(float)
define <4 x float> @int_fabs_4x(ptr %a) {
; CHECK-LABEL: @int_fabs_4x(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = load <4 x float>, ptr [[A:%.*]], align 16
; CHECK-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @llvm.fabs.v4f32(<4 x float> [[TMP0]])
; CHECK-NEXT:    ret <4 x float> [[TMP1]]
;
; NOACCELERATE-LABEL: @int_fabs_4x(
; NOACCELERATE-NEXT:  entry:
; NOACCELERATE-NEXT:    [[TMP0:%.*]] = load <4 x float>, ptr [[A:%.*]], align 16
; NOACCELERATE-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @llvm.fabs.v4f32(<4 x float> [[TMP0]])
; NOACCELERATE-NEXT:    ret <4 x float> [[TMP1]]
;
entry:
  %0 = load <4 x float>, ptr %a, align 16
  %vecext = extractelement <4 x float> %0, i32 0
  %1 = tail call fast float @llvm.fabs.f32(float %vecext)
  %vecins = insertelement <4 x float> undef, float %1, i32 0
  %vecext.1 = extractelement <4 x float> %0, i32 1
  %2 = tail call fast float @llvm.fabs.f32(float %vecext.1)
  %vecins.1 = insertelement <4 x float> %vecins, float %2, i32 1
  %vecext.2 = extractelement <4 x float> %0, i32 2
  %3 = tail call fast float @llvm.fabs.f32(float %vecext.2)
  %vecins.2 = insertelement <4 x float> %vecins.1, float %3, i32 2
  %vecext.3 = extractelement <4 x float> %0, i32 3
  %4 = tail call fast float @llvm.fabs.f32(float %vecext.3)
  %vecins.3 = insertelement <4 x float> %vecins.2, float %4, i32 3
  ret <4 x float> %vecins.3
}
declare float @floorf(float) readonly nounwind willreturn
define <4 x float> @floor_4x(ptr %a) {
; CHECK-LABEL: @floor_4x(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = load <4 x float>, ptr [[A:%.*]], align 16
; CHECK-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @llvm.floor.v4f32(<4 x float> [[TMP0]])
; CHECK-NEXT:    ret <4 x float> [[TMP1]]
;
; NOACCELERATE-LABEL: @floor_4x(
; NOACCELERATE-NEXT:  entry:
; NOACCELERATE-NEXT:    [[TMP0:%.*]] = load <4 x float>, ptr [[A:%.*]], align 16
; NOACCELERATE-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @llvm.floor.v4f32(<4 x float> [[TMP0]])
; NOACCELERATE-NEXT:    ret <4 x float> [[TMP1]]
;
entry:
  %0 = load <4 x float>, ptr %a, align 16
  %vecext = extractelement <4 x float> %0, i32 0
  %1 = tail call fast float @floorf(float %vecext)
  %vecins = insertelement <4 x float> undef, float %1, i32 0
  %vecext.1 = extractelement <4 x float> %0, i32 1
  %2 = tail call fast float @floorf(float %vecext.1)
  %vecins.1 = insertelement <4 x float> %vecins, float %2, i32 1
  %vecext.2 = extractelement <4 x float> %0, i32 2
  %3 = tail call fast float @floorf(float %vecext.2)
  %vecins.2 = insertelement <4 x float> %vecins.1, float %3, i32 2
  %vecext.3 = extractelement <4 x float> %0, i32 3
  %4 = tail call fast float @floorf(float %vecext.3)
  %vecins.3 = insertelement <4 x float> %vecins.2, float %4, i32 3
  ret <4 x float> %vecins.3
}
declare float @sqrtf(float) readonly nounwind willreturn
define <4 x float> @sqrt_4x(ptr %a) {
; CHECK-LABEL: @sqrt_4x(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = load <4 x float>, ptr [[A:%.*]], align 16
; CHECK-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @llvm.sqrt.v4f32(<4 x float> [[TMP0]])
; CHECK-NEXT:    ret <4 x float> [[TMP1]]
;
; NOACCELERATE-LABEL: @sqrt_4x(
; NOACCELERATE-NEXT:  entry:
; NOACCELERATE-NEXT:    [[TMP0:%.*]] = load <4 x float>, ptr [[A:%.*]], align 16
; NOACCELERATE-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @llvm.sqrt.v4f32(<4 x float> [[TMP0]])
; NOACCELERATE-NEXT:    ret <4 x float> [[TMP1]]
;
entry:
  %0 = load <4 x float>, ptr %a, align 16
  %vecext = extractelement <4 x float> %0, i32 0
  %1 = tail call fast float @sqrtf(float %vecext)
  %vecins = insertelement <4 x float> undef, float %1, i32 0
  %vecext.1 = extractelement <4 x float> %0, i32 1
  %2 = tail call fast float @sqrtf(float %vecext.1)
  %vecins.1 = insertelement <4 x float> %vecins, float %2, i32 1
  %vecext.2 = extractelement <4 x float> %0, i32 2
  %3 = tail call fast float @sqrtf(float %vecext.2)
  %vecins.2 = insertelement <4 x float> %vecins.1, float %3, i32 2
  %vecext.3 = extractelement <4 x float> %0, i32 3
  %4 = tail call fast float @sqrtf(float %vecext.3)
  %vecins.3 = insertelement <4 x float> %vecins.2, float %4, i32 3
  ret <4 x float> %vecins.3
}
declare float @expf(float) readonly nounwind willreturn
define <4 x float> @exp_4x(ptr %a) {
; CHECK-LABEL: @exp_4x(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = load <4 x float>, ptr [[A:%.*]], align 16
; CHECK-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @vexpf(<4 x float> [[TMP0]])
; CHECK-NEXT:    ret <4 x float> [[TMP1]]
;
; NOACCELERATE-LABEL: @exp_4x(
; NOACCELERATE-NEXT:  entry:
; NOACCELERATE-NEXT:    [[TMP0:%.*]] = load <4 x float>, ptr [[A:%.*]], align 16
; NOACCELERATE-NEXT:    [[VECEXT:%.*]] = extractelement <4 x float> [[TMP0]], i32 0
; NOACCELERATE-NEXT:    [[TMP1:%.*]] = tail call fast float @expf(float [[VECEXT]])
; NOACCELERATE-NEXT:    [[VECINS:%.*]] = insertelement <4 x float> undef, float [[TMP1]], i32 0
; NOACCELERATE-NEXT:    [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i32 1
; NOACCELERATE-NEXT:    [[TMP2:%.*]] = tail call fast float @expf(float [[VECEXT_1]])
; NOACCELERATE-NEXT:    [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP2]], i32 1
; NOACCELERATE-NEXT:    [[TMP3:%.*]] = shufflevector <4 x float> [[TMP0]], <4 x float> poison, <2 x i32> <i32 2, i32 3>
; NOACCELERATE-NEXT:    [[TMP4:%.*]] = call fast <2 x float> @llvm.exp.v2f32(<2 x float> [[TMP3]])
; NOACCELERATE-NEXT:    [[TMP5:%.*]] = shufflevector <2 x float> [[TMP4]], <2 x float> poison, <4 x i32> <i32 0, i32 1, i32 poison, i32 poison>
; NOACCELERATE-NEXT:    [[VECINS_31:%.*]] = shufflevector <4 x float> [[VECINS_1]], <4 x float> [[TMP5]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>
; NOACCELERATE-NEXT:    ret <4 x float> [[VECINS_31]]
;
entry:
  %0 = load <4 x float>, ptr %a, align 16
  %vecext = extractelement <4 x float> %0, i32 0
  %1 = tail call fast float @expf(float %vecext)
  %vecins = insertelement <4 x float> undef, float %1, i32 0
  %vecext.1 = extractelement <4 x float> %0, i32 1
  %2 = tail call fast float @expf(float %vecext.1)
  %vecins.1 = insertelement <4 x float> %vecins, float %2, i32 1
  %vecext.2 = extractelement <4 x float> %0, i32 2
  %3 = tail call fast float @expf(float %vecext.2)
  %vecins.2 = insertelement <4 x float> %vecins.1, float %3, i32 2
  %vecext.3 = extractelement <4 x float> %0, i32 3
  %4 = tail call fast float @expf(float %vecext.3)
  %vecins.3 = insertelement <4 x float> %vecins.2, float %4, i32 3
  ret <4 x float> %vecins.3
}
declare float @expm1f(float) readonly nounwind willreturn
define <4 x float> @expm1_4x(ptr %a) {
; CHECK-LABEL: @expm1_4x(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = load <4 x float>, ptr [[A:%.*]], align 16
; CHECK-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @vexpm1f(<4 x float> [[TMP0]])
; CHECK-NEXT:    ret <4 x float> [[TMP1]]
;
; NOACCELERATE-LABEL: @expm1_4x(
; NOACCELERATE-NEXT:  entry:
; NOACCELERATE-NEXT:    [[TMP0:%.*]] = load <4 x float>, ptr [[A:%.*]], align 16
; NOACCELERATE-NEXT:    [[VECEXT:%.*]] = extractelement <4 x float> [[TMP0]], i32 0
; NOACCELERATE-NEXT:    [[TMP1:%.*]] = tail call fast float @expm1f(float [[VECEXT]])
; NOACCELERATE-NEXT:    [[VECINS:%.*]] = insertelement <4 x float> undef, float [[TMP1]], i32 0
; NOACCELERATE-NEXT:    [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i32 1
; NOACCELERATE-NEXT:    [[TMP2:%.*]] = tail call fast float @expm1f(float [[VECEXT_1]])
; NOACCELERATE-NEXT:    [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP2]], i32 1
; NOACCELERATE-NEXT:    [[VECEXT_2:%.*]] = extractelement <4 x float> [[TMP0]], i32 2
; NOACCELERATE-NEXT:    [[TMP3:%.*]] = tail call fast float @expm1f(float [[VECEXT_2]])
; NOACCELERATE-NEXT:    [[VECINS_2:%.*]] = insertelement <4 x float> [[VECINS_1]], float [[TMP3]], i32 2
; NOACCELERATE-NEXT:    [[VECEXT_3:%.*]] = extractelement <4 x float> [[TMP0]], i32 3
; NOACCELERATE-NEXT:    [[TMP4:%.*]] = tail call fast float @expm1f(float [[VECEXT_3]])
; NOACCELERATE-NEXT:    [[VECINS_3:%.*]] = insertelement <4 x float> [[VECINS_2]], float [[TMP4]], i32 3
; NOACCELERATE-NEXT:    ret <4 x float> [[VECINS_3]]
;
entry:
  %0 = load <4 x float>, ptr %a, align 16
  %vecext = extractelement <4 x float> %0, i32 0
  %1 = tail call fast float @expm1f(float %vecext)
  %vecins = insertelement <4 x float> undef, float %1, i32 0
  %vecext.1 = extractelement <4 x float> %0, i32 1
  %2 = tail call fast float @expm1f(float %vecext.1)
  %vecins.1 = insertelement <4 x float> %vecins, float %2, i32 1
  %vecext.2 = extractelement <4 x float> %0, i32 2
  %3 = tail call fast float @expm1f(float %vecext.2)
  %vecins.2 = insertelement <4 x float> %vecins.1, float %3, i32 2
  %vecext.3 = extractelement <4 x float> %0, i32 3
  %4 = tail call fast float @expm1f(float %vecext.3)
  %vecins.3 = insertelement <4 x float> %vecins.2, float %4, i32 3
  ret <4 x float> %vecins.3
}
declare float @logf(float) readonly nounwind willreturn
define <4 x float> @log_4x(ptr %a) {
; CHECK-LABEL: @log_4x(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = load <4 x float>, ptr [[A:%.*]], align 16
; CHECK-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @vlogf(<4 x float> [[TMP0]])
; CHECK-NEXT:    ret <4 x float> [[TMP1]]
;
; NOACCELERATE-LABEL: @log_4x(
; NOACCELERATE-NEXT:  entry:
; NOACCELERATE-NEXT:    [[TMP0:%.*]] = load <4 x float>, ptr [[A:%.*]], align 16
; NOACCELERATE-NEXT:    [[VECEXT:%.*]] = extractelement <4 x float> [[TMP0]], i32 0
; NOACCELERATE-NEXT:    [[TMP1:%.*]] = tail call fast float @logf(float [[VECEXT]])
; NOACCELERATE-NEXT:    [[VECINS:%.*]] = insertelement <4 x float> undef, float [[TMP1]], i32 0
; NOACCELERATE-NEXT:    [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i32 1
; NOACCELERATE-NEXT:    [[TMP2:%.*]] = tail call fast float @logf(float [[VECEXT_1]])
; NOACCELERATE-NEXT:    [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP2]], i32 1
; NOACCELERATE-NEXT:    [[TMP3:%.*]] = shufflevector <4 x float> [[TMP0]], <4 x float> poison, <2 x i32> <i32 2, i32 3>
; NOACCELERATE-NEXT:    [[TMP4:%.*]] = call fast <2 x float> @llvm.log.v2f32(<2 x float> [[TMP3]])
; NOACCELERATE-NEXT:    [[TMP5:%.*]] = shufflevector <2 x float> [[TMP4]], <2 x float> poison, <4 x i32> <i32 0, i32 1, i32 poison, i32 poison>
; NOACCELERATE-NEXT:    [[VECINS_31:%.*]] = shufflevector <4 x float> [[VECINS_1]], <4 x float> [[TMP5]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>
; NOACCELERATE-NEXT:    ret <4 x float> [[VECINS_31]]
;
entry:
  %0 = load <4 x float>, ptr %a, align 16
  %vecext = extractelement <4 x float> %0, i32 0
  %1 = tail call fast float @logf(float %vecext)
  %vecins = insertelement <4 x float> undef, float %1, i32 0
  %vecext.1 = extractelement <4 x float> %0, i32 1
  %2 = tail call fast float @logf(float %vecext.1)
  %vecins.1 = insertelement <4 x float> %vecins, float %2, i32 1
  %vecext.2 = extractelement <4 x float> %0, i32 2
  %3 = tail call fast float @logf(float %vecext.2)
  %vecins.2 = insertelement <4 x float> %vecins.1, float %3, i32 2
  %vecext.3 = extractelement <4 x float> %0, i32 3
  %4 = tail call fast float @logf(float %vecext.3)
  %vecins.3 = insertelement <4 x float> %vecins.2, float %4, i32 3
  ret <4 x float> %vecins.3
}
declare float @log1pf(float) readonly nounwind willreturn
define <4 x float> @log1p_4x(ptr %a) {
; CHECK-LABEL: @log1p_4x(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = load <4 x float>, ptr [[A:%.*]], align 16
; CHECK-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @vlog1pf(<4 x float> [[TMP0]])
; CHECK-NEXT:    ret <4 x float> [[TMP1]]
;
; NOACCELERATE-LABEL: @log1p_4x(
; NOACCELERATE-NEXT:  entry:
; NOACCELERATE-NEXT:    [[TMP0:%.*]] = load <4 x float>, ptr [[A:%.*]], align 16
; NOACCELERATE-NEXT:    [[VECEXT:%.*]] = extractelement <4 x float> [[TMP0]], i32 0
; NOACCELERATE-NEXT:    [[TMP1:%.*]] = tail call fast float @log1pf(float [[VECEXT]])
; NOACCELERATE-NEXT:    [[VECINS:%.*]] = insertelement <4 x float> undef, float [[TMP1]], i32 0
; NOACCELERATE-NEXT:    [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i32 1
; NOACCELERATE-NEXT:    [[TMP2:%.*]] = tail call fast float @log1pf(float [[VECEXT_1]])
; NOACCELERATE-NEXT:    [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP2]], i32 1
; NOACCELERATE-NEXT:    [[VECEXT_2:%.*]] = extractelement <4 x float> [[TMP0]], i32 2
; NOACCELERATE-NEXT:    [[TMP3:%.*]] = tail call fast float @log1pf(float [[VECEXT_2]])
; NOACCELERATE-NEXT:    [[VECINS_2:%.*]] = insertelement <4 x float> [[VECINS_1]], float [[TMP3]], i32 2
; NOACCELERATE-NEXT:    [[VECEXT_3:%.*]] = extractelement <4 x float> [[TMP0]], i32 3
; NOACCELERATE-NEXT:    [[TMP4:%.*]] = tail call fast float @log1pf(float [[VECEXT_3]])
; NOACCELERATE-NEXT:    [[VECINS_3:%.*]] = insertelement <4 x float> [[VECINS_2]], float [[TMP4]], i32 3
; NOACCELERATE-NEXT:    ret <4 x float> [[VECINS_3]]
;
entry:
  %0 = load <4 x float>, ptr %a, align 16
  %vecext = extractelement <4 x float> %0, i32 0
  %1 = tail call fast float @log1pf(float %vecext)
  %vecins = insertelement <4 x float> undef, float %1, i32 0
  %vecext.1 = extractelement <4 x float> %0, i32 1
  %2 = tail call fast float @log1pf(float %vecext.1)
  %vecins.1 = insertelement <4 x float> %vecins, float %2, i32 1
  %vecext.2 = extractelement <4 x float> %0, i32 2
  %3 = tail call fast float @log1pf(float %vecext.2)
  %vecins.2 = insertelement <4 x float> %vecins.1, float %3, i32 2
  %vecext.3 = extractelement <4 x float> %0, i32 3
  %4 = tail call fast float @log1pf(float %vecext.3)
  %vecins.3 = insertelement <4 x float> %vecins.2, float %4, i32 3
  ret <4 x float> %vecins.3
}
declare float @log10pf(float) readonly nounwind willreturn
define <4 x float> @log10p_4x(ptr %a) {
; CHECK-LABEL: @log10p_4x(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = load <4 x float>, ptr [[A:%.*]], align 16
; CHECK-NEXT:    [[VECEXT:%.*]] = extractelement <4 x float> [[TMP0]], i32 0
; CHECK-NEXT:    [[TMP1:%.*]] = tail call fast float @log10pf(float [[VECEXT]])
; CHECK-NEXT:    [[VECINS:%.*]] = insertelement <4 x float> undef, float [[TMP1]], i32 0
; CHECK-NEXT:    [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i32 1
; CHECK-NEXT:    [[TMP2:%.*]] = tail call fast float @log10pf(float [[VECEXT_1]])
; CHECK-NEXT:    [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP2]], i32 1
; CHECK-NEXT:    [[VECEXT_2:%.*]] = extractelement <4 x float> [[TMP0]], i32 2
; CHECK-NEXT:    [[TMP3:%.*]] = tail call fast float @log10pf(float [[VECEXT_2]])
; CHECK-NEXT:    [[VECINS_2:%.*]] = insertelement <4 x float> [[VECINS_1]], float [[TMP3]], i32 2
; CHECK-NEXT:    [[VECEXT_3:%.*]] = extractelement <4 x float> [[TMP0]], i32 3
; CHECK-NEXT:    [[TMP4:%.*]] = tail call fast float @log10pf(float [[VECEXT_3]])
; CHECK-NEXT:    [[VECINS_3:%.*]] = insertelement <4 x float> [[VECINS_2]], float [[TMP4]], i32 3
; CHECK-NEXT:    ret <4 x float> [[VECINS_3]]
;
; NOACCELERATE-LABEL: @log10p_4x(
; NOACCELERATE-NEXT:  entry:
; NOACCELERATE-NEXT:    [[TMP0:%.*]] = load <4 x float>, ptr [[A:%.*]], align 16
; NOACCELERATE-NEXT:    [[VECEXT:%.*]] = extractelement <4 x float> [[TMP0]], i32 0
; NOACCELERATE-NEXT:    [[TMP1:%.*]] = tail call fast float @log10pf(float [[VECEXT]])
; NOACCELERATE-NEXT:    [[VECINS:%.*]] = insertelement <4 x float> undef, float [[TMP1]], i32 0
; NOACCELERATE-NEXT:    [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i32 1
; NOACCELERATE-NEXT:    [[TMP2:%.*]] = tail call fast float @log10pf(float [[VECEXT_1]])
; NOACCELERATE-NEXT:    [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP2]], i32 1
; NOACCELERATE-NEXT:    [[VECEXT_2:%.*]] = extractelement <4 x float> [[TMP0]], i32 2
; NOACCELERATE-NEXT:    [[TMP3:%.*]] = tail call fast float @log10pf(float [[VECEXT_2]])
; NOACCELERATE-NEXT:    [[VECINS_2:%.*]] = insertelement <4 x float> [[VECINS_1]], float [[TMP3]], i32 2
; NOACCELERATE-NEXT:    [[VECEXT_3:%.*]] = extractelement <4 x float> [[TMP0]], i32 3
; NOACCELERATE-NEXT:    [[TMP4:%.*]] = tail call fast float @log10pf(float [[VECEXT_3]])
; NOACCELERATE-NEXT:    [[VECINS_3:%.*]] = insertelement <4 x float> [[VECINS_2]], float [[TMP4]], i32 3
; NOACCELERATE-NEXT:    ret <4 x float> [[VECINS_3]]
;
entry:
  %0 = load <4 x float>, ptr %a, align 16
  %vecext = extractelement <4 x float> %0, i32 0
  %1 = tail call fast float @log10pf(float %vecext)
  %vecins = insertelement <4 x float> undef, float %1, i32 0
  %vecext.1 = extractelement <4 x float> %0, i32 1
  %2 = tail call fast float @log10pf(float %vecext.1)
  %vecins.1 = insertelement <4 x float> %vecins, float %2, i32 1
  %vecext.2 = extractelement <4 x float> %0, i32 2
  %3 = tail call fast float @log10pf(float %vecext.2)
  %vecins.2 = insertelement <4 x float> %vecins.1, float %3, i32 2
  %vecext.3 = extractelement <4 x float> %0, i32 3
  %4 = tail call fast float @log10pf(float %vecext.3)
  %vecins.3 = insertelement <4 x float> %vecins.2, float %4, i32 3
  ret <4 x float> %vecins.3
}
declare float @logbf(float) readonly nounwind willreturn
define <4 x float> @logb_4x(ptr %a) {
; CHECK-LABEL: @logb_4x(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = load <4 x float>, ptr [[A:%.*]], align 16
; CHECK-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @vlogbf(<4 x float> [[TMP0]])
; CHECK-NEXT:    ret <4 x float> [[TMP1]]
;
; NOACCELERATE-LABEL: @logb_4x(
; NOACCELERATE-NEXT:  entry:
; NOACCELERATE-NEXT:    [[TMP0:%.*]] = load <4 x float>, ptr [[A:%.*]], align 16
; NOACCELERATE-NEXT:    [[VECEXT:%.*]] = extractelement <4 x float> [[TMP0]], i32 0
; NOACCELERATE-NEXT:    [[TMP1:%.*]] = tail call fast float @logbf(float [[VECEXT]])
; NOACCELERATE-NEXT:    [[VECINS:%.*]] = insertelement <4 x float> undef, float [[TMP1]], i32 0
; NOACCELERATE-NEXT:    [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i32 1
; NOACCELERATE-NEXT:    [[TMP2:%.*]] = tail call fast float @logbf(float [[VECEXT_1]])
; NOACCELERATE-NEXT:    [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP2]], i32 1
; NOACCELERATE-NEXT:    [[VECEXT_2:%.*]] = extractelement <4 x float> [[TMP0]], i32 2
; NOACCELERATE-NEXT:    [[TMP3:%.*]] = tail call fast float @logbf(float [[VECEXT_2]])
; NOACCELERATE-NEXT:    [[VECINS_2:%.*]] = insertelement <4 x float> [[VECINS_1]], float [[TMP3]], i32 2
; NOACCELERATE-NEXT:    [[VECEXT_3:%.*]] = extractelement <4 x float> [[TMP0]], i32 3
; NOACCELERATE-NEXT:    [[TMP4:%.*]] = tail call fast float @logbf(float [[VECEXT_3]])
; NOACCELERATE-NEXT:    [[VECINS_3:%.*]] = insertelement <4 x float> [[VECINS_2]], float [[TMP4]], i32 3
; NOACCELERATE-NEXT:    ret <4 x float> [[VECINS_3]]
;
entry:
  %0 = load <4 x float>, ptr %a, align 16
  %vecext = extractelement <4 x float> %0, i32 0
  %1 = tail call fast float @logbf(float %vecext)
  %vecins = insertelement <4 x float> undef, float %1, i32 0
  %vecext.1 = extractelement <4 x float> %0, i32 1
  %2 = tail call fast float @logbf(float %vecext.1)
  %vecins.1 = insertelement <4 x float> %vecins, float %2, i32 1
  %vecext.2 = extractelement <4 x float> %0, i32 2
  %3 = tail call fast float @logbf(float %vecext.2)
  %vecins.2 = insertelement <4 x float> %vecins.1, float %3, i32 2
  %vecext.3 = extractelement <4 x float> %0, i32 3
  %4 = tail call fast float @logbf(float %vecext.3)
  %vecins.3 = insertelement <4 x float> %vecins.2, float %4, i32 3
  ret <4 x float> %vecins.3
}
declare float @sinf(float) readonly nounwind willreturn
define <4 x float> @sin_4x(ptr %a) {
; CHECK-LABEL: @sin_4x(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = load <4 x float>, ptr [[A:%.*]], align 16
; CHECK-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @vsinf(<4 x float> [[TMP0]])
; CHECK-NEXT:    ret <4 x float> [[TMP1]]
;
; NOACCELERATE-LABEL: @sin_4x(
; NOACCELERATE-NEXT:  entry:
; NOACCELERATE-NEXT:    [[TMP0:%.*]] = load <4 x float>, ptr [[A:%.*]], align 16
; NOACCELERATE-NEXT:    [[VECEXT:%.*]] = extractelement <4 x float> [[TMP0]], i32 0
; NOACCELERATE-NEXT:    [[TMP1:%.*]] = tail call fast float @sinf(float [[VECEXT]])
; NOACCELERATE-NEXT:    [[VECINS:%.*]] = insertelement <4 x float> undef, float [[TMP1]], i32 0
; NOACCELERATE-NEXT:    [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i32 1
; NOACCELERATE-NEXT:    [[TMP2:%.*]] = tail call fast float @sinf(float [[VECEXT_1]])
; NOACCELERATE-NEXT:    [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP2]], i32 1
; NOACCELERATE-NEXT:    [[TMP3:%.*]] = shufflevector <4 x float> [[TMP0]], <4 x float> poison, <2 x i32> <i32 2, i32 3>
; NOACCELERATE-NEXT:    [[TMP4:%.*]] = call fast <2 x float> @llvm.sin.v2f32(<2 x float> [[TMP3]])
; NOACCELERATE-NEXT:    [[TMP5:%.*]] = shufflevector <2 x float> [[TMP4]], <2 x float> poison, <4 x i32> <i32 0, i32 1, i32 poison, i32 poison>
; NOACCELERATE-NEXT:    [[VECINS_31:%.*]] = shufflevector <4 x float> [[VECINS_1]], <4 x float> [[TMP5]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>
; NOACCELERATE-NEXT:    ret <4 x float> [[VECINS_31]]
;
entry:
  %0 = load <4 x float>, ptr %a, align 16
  %vecext = extractelement <4 x float> %0, i32 0
  %1 = tail call fast float @sinf(float %vecext)
  %vecins = insertelement <4 x float> undef, float %1, i32 0
  %vecext.1 = extractelement <4 x float> %0, i32 1
  %2 = tail call fast float @sinf(float %vecext.1)
  %vecins.1 = insertelement <4 x float> %vecins, float %2, i32 1
  %vecext.2 = extractelement <4 x float> %0, i32 2
  %3 = tail call fast float @sinf(float %vecext.2)
  %vecins.2 = insertelement <4 x float> %vecins.1, float %3, i32 2
  %vecext.3 = extractelement <4 x float> %0, i32 3
  %4 = tail call fast float @sinf(float %vecext.3)
  %vecins.3 = insertelement <4 x float> %vecins.2, float %4, i32 3
  ret <4 x float> %vecins.3
}
declare float @cosf(float) readonly nounwind willreturn
define <4 x float> @cos_4x(ptr %a) {
; CHECK-LABEL: @cos_4x(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = load <4 x float>, ptr [[A:%.*]], align 16
; CHECK-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @vcosf(<4 x float> [[TMP0]])
; CHECK-NEXT:    ret <4 x float> [[TMP1]]
;
; NOACCELERATE-LABEL: @cos_4x(
; NOACCELERATE-NEXT:  entry:
; NOACCELERATE-NEXT:    [[TMP0:%.*]] = load <4 x float>, ptr [[A:%.*]], align 16
; NOACCELERATE-NEXT:    [[VECEXT:%.*]] = extractelement <4 x float> [[TMP0]], i32 0
; NOACCELERATE-NEXT:    [[TMP1:%.*]] = tail call fast float @cosf(float [[VECEXT]])
; NOACCELERATE-NEXT:    [[VECINS:%.*]] = insertelement <4 x float> undef, float [[TMP1]], i32 0
; NOACCELERATE-NEXT:    [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i32 1
; NOACCELERATE-NEXT:    [[TMP2:%.*]] = tail call fast float @cosf(float [[VECEXT_1]])
; NOACCELERATE-NEXT:    [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP2]], i32 1
; NOACCELERATE-NEXT:    [[TMP3:%.*]] = shufflevector <4 x float> [[TMP0]], <4 x float> poison, <2 x i32> <i32 2, i32 3>
; NOACCELERATE-NEXT:    [[TMP4:%.*]] = call fast <2 x float> @llvm.cos.v2f32(<2 x float> [[TMP3]])
; NOACCELERATE-NEXT:    [[TMP5:%.*]] = shufflevector <2 x float> [[TMP4]], <2 x float> poison, <4 x i32> <i32 0, i32 1, i32 poison, i32 poison>
; NOACCELERATE-NEXT:    [[VECINS_31:%.*]] = shufflevector <4 x float> [[VECINS_1]], <4 x float> [[TMP5]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>
; NOACCELERATE-NEXT:    ret <4 x float> [[VECINS_31]]
;
entry:
  %0 = load <4 x float>, ptr %a, align 16
  %vecext = extractelement <4 x float> %0, i32 0
  %1 = tail call fast float @cosf(float %vecext)
  %vecins = insertelement <4 x float> undef, float %1, i32 0
  %vecext.1 = extractelement <4 x float> %0, i32 1
  %2 = tail call fast float @cosf(float %vecext.1)
  %vecins.1 = insertelement <4 x float> %vecins, float %2, i32 1
  %vecext.2 = extractelement <4 x float> %0, i32 2
  %3 = tail call fast float @cosf(float %vecext.2)
  %vecins.2 = insertelement <4 x float> %vecins.1, float %3, i32 2
  %vecext.3 = extractelement <4 x float> %0, i32 3
  %4 = tail call fast float @cosf(float %vecext.3)
  %vecins.3 = insertelement <4 x float> %vecins.2, float %4, i32 3
  ret <4 x float> %vecins.3
}
declare float @tanf(float) readonly nounwind willreturn
define <4 x float> @tan_4x(ptr %a) {
; CHECK-LABEL: @tan_4x(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = load <4 x float>, ptr [[A:%.*]], align 16
; CHECK-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @vtanf(<4 x float> [[TMP0]])
; CHECK-NEXT:    ret <4 x float> [[TMP1]]
;
; NOACCELERATE-LABEL: @tan_4x(
; NOACCELERATE-NEXT:  entry:
; NOACCELERATE-NEXT:    [[TMP0:%.*]] = load <4 x float>, ptr [[A:%.*]], align 16
; NOACCELERATE-NEXT:    [[VECEXT:%.*]] = extractelement <4 x float> [[TMP0]], i32 0
; NOACCELERATE-NEXT:    [[TMP1:%.*]] = tail call fast float @tanf(float [[VECEXT]])
; NOACCELERATE-NEXT:    [[VECINS:%.*]] = insertelement <4 x float> undef, float [[TMP1]], i32 0
; NOACCELERATE-NEXT:    [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i32 1
; NOACCELERATE-NEXT:    [[TMP2:%.*]] = tail call fast float @tanf(float [[VECEXT_1]])
; NOACCELERATE-NEXT:    [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP2]], i32 1
; NOACCELERATE-NEXT:    [[TMP3:%.*]] = shufflevector <4 x float> [[TMP0]], <4 x float> poison, <2 x i32> <i32 2, i32 3>
; NOACCELERATE-NEXT:    [[TMP4:%.*]] = call fast <2 x float> @llvm.tan.v2f32(<2 x float> [[TMP3]])
; NOACCELERATE-NEXT:    [[TMP5:%.*]] = shufflevector <2 x float> [[TMP4]], <2 x float> poison, <4 x i32> <i32 0, i32 1, i32 poison, i32 poison>
; NOACCELERATE-NEXT:    [[VECINS_31:%.*]] = shufflevector <4 x float> [[VECINS_1]], <4 x float> [[TMP5]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>
; NOACCELERATE-NEXT:    ret <4 x float> [[VECINS_31]]
;
entry:
  %0 = load <4 x float>, ptr %a, align 16
  %vecext = extractelement <4 x float> %0, i32 0
  %1 = tail call fast float @tanf(float %vecext)
  %vecins = insertelement <4 x float> undef, float %1, i32 0
  %vecext.1 = extractelement <4 x float> %0, i32 1
  %2 = tail call fast float @tanf(float %vecext.1)
  %vecins.1 = insertelement <4 x float> %vecins, float %2, i32 1
  %vecext.2 = extractelement <4 x float> %0, i32 2
  %3 = tail call fast float @tanf(float %vecext.2)
  %vecins.2 = insertelement <4 x float> %vecins.1, float %3, i32 2
  %vecext.3 = extractelement <4 x float> %0, i32 3
  %4 = tail call fast float @tanf(float %vecext.3)
  %vecins.3 = insertelement <4 x float> %vecins.2, float %4, i32 3
  ret <4 x float> %vecins.3
}
declare float @asinf(float) readonly nounwind willreturn
define <4 x float> @asin_4x(ptr %a) {
; CHECK-LABEL: @asin_4x(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = load <4 x float>, ptr [[A:%.*]], align 16
; CHECK-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @vasinf(<4 x float> [[TMP0]])
; CHECK-NEXT:    ret <4 x float> [[TMP1]]
;
; NOACCELERATE-LABEL: @asin_4x(
; NOACCELERATE-NEXT:  entry:
; NOACCELERATE-NEXT:    [[TMP0:%.*]] = load <4 x float>, ptr [[A:%.*]], align 16
; NOACCELERATE-NEXT:    [[VECEXT:%.*]] = extractelement <4 x float> [[TMP0]], i32 0
; NOACCELERATE-NEXT:    [[TMP1:%.*]] = tail call fast float @asinf(float [[VECEXT]])
; NOACCELERATE-NEXT:    [[VECINS:%.*]] = insertelement <4 x float> undef, float [[TMP1]], i32 0
; NOACCELERATE-NEXT:    [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i32 1
; NOACCELERATE-NEXT:    [[TMP2:%.*]] = tail call fast float @asinf(float [[VECEXT_1]])
; NOACCELERATE-NEXT:    [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP2]], i32 1
; NOACCELERATE-NEXT:    [[TMP3:%.*]] = shufflevector <4 x float> [[TMP0]], <4 x float> poison, <2 x i32> <i32 2, i32 3>
; NOACCELERATE-NEXT:    [[TMP4:%.*]] = call fast <2 x float> @llvm.asin.v2f32(<2 x float> [[TMP3]])
; NOACCELERATE-NEXT:    [[TMP5:%.*]] = shufflevector <2 x float> [[TMP4]], <2 x float> poison, <4 x i32> <i32 0, i32 1, i32 poison, i32 poison>
; NOACCELERATE-NEXT:    [[VECINS_31:%.*]] = shufflevector <4 x float> [[VECINS_1]], <4 x float> [[TMP5]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>
; NOACCELERATE-NEXT:    ret <4 x float> [[VECINS_31]]
;
entry:
  %0 = load <4 x float>, ptr %a, align 16
  %vecext = extractelement <4 x float> %0, i32 0
  %1 = tail call fast float @asinf(float %vecext)
  %vecins = insertelement <4 x float> undef, float %1, i32 0
  %vecext.1 = extractelement <4 x float> %0, i32 1
  %2 = tail call fast float @asinf(float %vecext.1)
  %vecins.1 = insertelement <4 x float> %vecins, float %2, i32 1
  %vecext.2 = extractelement <4 x float> %0, i32 2
  %3 = tail call fast float @asinf(float %vecext.2)
  %vecins.2 = insertelement <4 x float> %vecins.1, float %3, i32 2
  %vecext.3 = extractelement <4 x float> %0, i32 3
  %4 = tail call fast float @asinf(float %vecext.3)
  %vecins.3 = insertelement <4 x float> %vecins.2, float %4, i32 3
  ret <4 x float> %vecins.3
}
define <4 x float> @int_asin_4x(ptr %a) {
; CHECK-LABEL: @int_asin_4x(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = load <4 x float>, ptr [[A:%.*]], align 16
; CHECK-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @vasinf(<4 x float> [[TMP0]])
; CHECK-NEXT:    ret <4 x float> [[TMP1]]
;
; NOACCELERATE-LABEL: @int_asin_4x(
; NOACCELERATE-NEXT:  entry:
; NOACCELERATE-NEXT:    [[TMP0:%.*]] = load <4 x float>, ptr [[A:%.*]], align 16
; NOACCELERATE-NEXT:    [[VECEXT:%.*]] = extractelement <4 x float> [[TMP0]], i32 0
; NOACCELERATE-NEXT:    [[TMP1:%.*]] = tail call fast float @llvm.asin.f32(float [[VECEXT]])
; NOACCELERATE-NEXT:    [[VECINS:%.*]] = insertelement <4 x float> undef, float [[TMP1]], i32 0
; NOACCELERATE-NEXT:    [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i32 1
; NOACCELERATE-NEXT:    [[TMP2:%.*]] = tail call fast float @llvm.asin.f32(float [[VECEXT_1]])
; NOACCELERATE-NEXT:    [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP2]], i32 1
; NOACCELERATE-NEXT:    [[TMP3:%.*]] = shufflevector <4 x float> [[TMP0]], <4 x float> poison, <2 x i32> <i32 2, i32 3>
; NOACCELERATE-NEXT:    [[TMP4:%.*]] = call fast <2 x float> @llvm.asin.v2f32(<2 x float> [[TMP3]])
; NOACCELERATE-NEXT:    [[TMP5:%.*]] = shufflevector <2 x float> [[TMP4]], <2 x float> poison, <4 x i32> <i32 0, i32 1, i32 poison, i32 poison>
; NOACCELERATE-NEXT:    [[VECINS_31:%.*]] = shufflevector <4 x float> [[VECINS_1]], <4 x float> [[TMP5]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>
; NOACCELERATE-NEXT:    ret <4 x float> [[VECINS_31]]
;
entry:
  %0 = load <4 x float>, ptr %a, align 16
  %vecext = extractelement <4 x float> %0, i32 0
  %1 = tail call fast float @llvm.asin.f32(float %vecext)
  %vecins = insertelement <4 x float> undef, float %1, i32 0
  %vecext.1 = extractelement <4 x float> %0, i32 1
  %2 = tail call fast float @llvm.asin.f32(float %vecext.1)
  %vecins.1 = insertelement <4 x float> %vecins, float %2, i32 1
  %vecext.2 = extractelement <4 x float> %0, i32 2
  %3 = tail call fast float @llvm.asin.f32(float %vecext.2)
  %vecins.2 = insertelement <4 x float> %vecins.1, float %3, i32 2
  %vecext.3 = extractelement <4 x float> %0, i32 3
  %4 = tail call fast float @llvm.asin.f32(float %vecext.3)
  %vecins.3 = insertelement <4 x float> %vecins.2, float %4, i32 3
  ret <4 x float> %vecins.3
}
declare float @acosf(float) readonly nounwind willreturn
define <4 x float> @acos_4x(ptr %a) {
; CHECK-LABEL: @acos_4x(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = load <4 x float>, ptr [[A:%.*]], align 16
; CHECK-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @vacosf(<4 x float> [[TMP0]])
; CHECK-NEXT:    ret <4 x float> [[TMP1]]
;
; NOACCELERATE-LABEL: @acos_4x(
; NOACCELERATE-NEXT:  entry:
; NOACCELERATE-NEXT:    [[TMP0:%.*]] = load <4 x float>, ptr [[A:%.*]], align 16
; NOACCELERATE-NEXT:    [[VECEXT:%.*]] = extractelement <4 x float> [[TMP0]], i32 0
; NOACCELERATE-NEXT:    [[TMP1:%.*]] = tail call fast float @acosf(float [[VECEXT]])
; NOACCELERATE-NEXT:    [[VECINS:%.*]] = insertelement <4 x float> undef, float [[TMP1]], i32 0
; NOACCELERATE-NEXT:    [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i32 1
; NOACCELERATE-NEXT:    [[TMP2:%.*]] = tail call fast float @acosf(float [[VECEXT_1]])
; NOACCELERATE-NEXT:    [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP2]], i32 1
; NOACCELERATE-NEXT:    [[TMP3:%.*]] = shufflevector <4 x float> [[TMP0]], <4 x float> poison, <2 x i32> <i32 2, i32 3>
; NOACCELERATE-NEXT:    [[TMP4:%.*]] = call fast <2 x float> @llvm.acos.v2f32(<2 x float> [[TMP3]])
; NOACCELERATE-NEXT:    [[TMP5:%.*]] = shufflevector <2 x float> [[TMP4]], <2 x float> poison, <4 x i32> <i32 0, i32 1, i32 poison, i32 poison>
; NOACCELERATE-NEXT:    [[VECINS_31:%.*]] = shufflevector <4 x float> [[VECINS_1]], <4 x float> [[TMP5]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>
; NOACCELERATE-NEXT:    ret <4 x float> [[VECINS_31]]
;
entry:
  %0 = load <4 x float>, ptr %a, align 16
  %vecext = extractelement <4 x float> %0, i32 0
  %1 = tail call fast float @acosf(float %vecext)
  %vecins = insertelement <4 x float> undef, float %1, i32 0
  %vecext.1 = extractelement <4 x float> %0, i32 1
  %2 = tail call fast float @acosf(float %vecext.1)
  %vecins.1 = insertelement <4 x float> %vecins, float %2, i32 1
  %vecext.2 = extractelement <4 x float> %0, i32 2
  %3 = tail call fast float @acosf(float %vecext.2)
  %vecins.2 = insertelement <4 x float> %vecins.1, float %3, i32 2
  %vecext.3 = extractelement <4 x float> %0, i32 3
  %4 = tail call fast float @acosf(float %vecext.3)
  %vecins.3 = insertelement <4 x float> %vecins.2, float %4, i32 3
  ret <4 x float> %vecins.3
}
define <4 x float> @int_acos_4x(ptr %a) {
; CHECK-LABEL: @int_acos_4x(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = load <4 x float>, ptr [[A:%.*]], align 16
; CHECK-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @vacosf(<4 x float> [[TMP0]])
; CHECK-NEXT:    ret <4 x float> [[TMP1]]
;
; NOACCELERATE-LABEL: @int_acos_4x(
; NOACCELERATE-NEXT:  entry:
; NOACCELERATE-NEXT:    [[TMP0:%.*]] = load <4 x float>, ptr [[A:%.*]], align 16
; NOACCELERATE-NEXT:    [[VECEXT:%.*]] = extractelement <4 x float> [[TMP0]], i32 0
; NOACCELERATE-NEXT:    [[TMP1:%.*]] = tail call fast float @llvm.acos.f32(float [[VECEXT]])
; NOACCELERATE-NEXT:    [[VECINS:%.*]] = insertelement <4 x float> undef, float [[TMP1]], i32 0
; NOACCELERATE-NEXT:    [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i32 1
; NOACCELERATE-NEXT:    [[TMP2:%.*]] = tail call fast float @llvm.acos.f32(float [[VECEXT_1]])
; NOACCELERATE-NEXT:    [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP2]], i32 1
; NOACCELERATE-NEXT:    [[TMP3:%.*]] = shufflevector <4 x float> [[TMP0]], <4 x float> poison, <2 x i32> <i32 2, i32 3>
; NOACCELERATE-NEXT:    [[TMP4:%.*]] = call fast <2 x float> @llvm.acos.v2f32(<2 x float> [[TMP3]])
; NOACCELERATE-NEXT:    [[TMP5:%.*]] = shufflevector <2 x float> [[TMP4]], <2 x float> poison, <4 x i32> <i32 0, i32 1, i32 poison, i32 poison>
; NOACCELERATE-NEXT:    [[VECINS_31:%.*]] = shufflevector <4 x float> [[VECINS_1]], <4 x float> [[TMP5]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>
; NOACCELERATE-NEXT:    ret <4 x float> [[VECINS_31]]
;
entry:
  %0 = load <4 x float>, ptr %a, align 16
  %vecext = extractelement <4 x float> %0, i32 0
  %1 = tail call fast float @llvm.acos.f32(float %vecext)
  %vecins = insertelement <4 x float> undef, float %1, i32 0
  %vecext.1 = extractelement <4 x float> %0, i32 1
  %2 = tail call fast float @llvm.acos.f32(float %vecext.1)
  %vecins.1 = insertelement <4 x float> %vecins, float %2, i32 1
  %vecext.2 = extractelement <4 x float> %0, i32 2
  %3 = tail call fast float @llvm.acos.f32(float %vecext.2)
  %vecins.2 = insertelement <4 x float> %vecins.1, float %3, i32 2
  %vecext.3 = extractelement <4 x float> %0, i32 3
  %4 = tail call fast float @llvm.acos.f32(float %vecext.3)
  %vecins.3 = insertelement <4 x float> %vecins.2, float %4, i32 3
  ret <4 x float> %vecins.3
}
declare float @atanf(float) readonly nounwind willreturn
define <4 x float> @atan_4x(ptr %a) {
; CHECK-LABEL: @atan_4x(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = load <4 x float>, ptr [[A:%.*]], align 16
; CHECK-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @vatanf(<4 x float> [[TMP0]])
; CHECK-NEXT:    ret <4 x float> [[TMP1]]
;
; NOACCELERATE-LABEL: @atan_4x(
; NOACCELERATE-NEXT:  entry:
; NOACCELERATE-NEXT:    [[TMP0:%.*]] = load <4 x float>, ptr [[A:%.*]], align 16
; NOACCELERATE-NEXT:    [[VECEXT:%.*]] = extractelement <4 x float> [[TMP0]], i32 0
; NOACCELERATE-NEXT:    [[TMP1:%.*]] = tail call fast float @atanf(float [[VECEXT]])
; NOACCELERATE-NEXT:    [[VECINS:%.*]] = insertelement <4 x float> undef, float [[TMP1]], i32 0
; NOACCELERATE-NEXT:    [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i32 1
; NOACCELERATE-NEXT:    [[TMP2:%.*]] = tail call fast float @atanf(float [[VECEXT_1]])
; NOACCELERATE-NEXT:    [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP2]], i32 1
; NOACCELERATE-NEXT:    [[TMP3:%.*]] = shufflevector <4 x float> [[TMP0]], <4 x float> poison, <2 x i32> <i32 2, i32 3>
; NOACCELERATE-NEXT:    [[TMP4:%.*]] = call fast <2 x float> @llvm.atan.v2f32(<2 x float> [[TMP3]])
; NOACCELERATE-NEXT:    [[TMP5:%.*]] = shufflevector <2 x float> [[TMP4]], <2 x float> poison, <4 x i32> <i32 0, i32 1, i32 poison, i32 poison>
; NOACCELERATE-NEXT:    [[VECINS_31:%.*]] = shufflevector <4 x float> [[VECINS_1]], <4 x float> [[TMP5]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>
; NOACCELERATE-NEXT:    ret <4 x float> [[VECINS_31]]
;
entry:
  %0 = load <4 x float>, ptr %a, align 16
  %vecext = extractelement <4 x float> %0, i32 0
  %1 = tail call fast float @atanf(float %vecext)
  %vecins = insertelement <4 x float> undef, float %1, i32 0
  %vecext.1 = extractelement <4 x float> %0, i32 1
  %2 = tail call fast float @atanf(float %vecext.1)
  %vecins.1 = insertelement <4 x float> %vecins, float %2, i32 1
  %vecext.2 = extractelement <4 x float> %0, i32 2
  %3 = tail call fast float @atanf(float %vecext.2)
  %vecins.2 = insertelement <4 x float> %vecins.1, float %3, i32 2
  %vecext.3 = extractelement <4 x float> %0, i32 3
  %4 = tail call fast float @atanf(float %vecext.3)
  %vecins.3 = insertelement <4 x float> %vecins.2, float %4, i32 3
  ret <4 x float> %vecins.3
}
define <4 x float> @int_atan_4x(ptr %a) {
; CHECK-LABEL: @int_atan_4x(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = load <4 x float>, ptr [[A:%.*]], align 16
; CHECK-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @vatanf(<4 x float> [[TMP0]])
; CHECK-NEXT:    ret <4 x float> [[TMP1]]
;
; NOACCELERATE-LABEL: @int_atan_4x(
; NOACCELERATE-NEXT:  entry:
; NOACCELERATE-NEXT:    [[TMP0:%.*]] = load <4 x float>, ptr [[A:%.*]], align 16
; NOACCELERATE-NEXT:    [[VECEXT:%.*]] = extractelement <4 x float> [[TMP0]], i32 0
; NOACCELERATE-NEXT:    [[TMP1:%.*]] = tail call fast float @llvm.atan.f32(float [[VECEXT]])
; NOACCELERATE-NEXT:    [[VECINS:%.*]] = insertelement <4 x float> undef, float [[TMP1]], i32 0
; NOACCELERATE-NEXT:    [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i32 1
; NOACCELERATE-NEXT:    [[TMP2:%.*]] = tail call fast float @llvm.atan.f32(float [[VECEXT_1]])
; NOACCELERATE-NEXT:    [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP2]], i32 1
; NOACCELERATE-NEXT:    [[TMP3:%.*]] = shufflevector <4 x float> [[TMP0]], <4 x float> poison, <2 x i32> <i32 2, i32 3>
; NOACCELERATE-NEXT:    [[TMP4:%.*]] = call fast <2 x float> @llvm.atan.v2f32(<2 x float> [[TMP3]])
; NOACCELERATE-NEXT:    [[TMP5:%.*]] = shufflevector <2 x float> [[TMP4]], <2 x float> poison, <4 x i32> <i32 0, i32 1, i32 poison, i32 poison>
; NOACCELERATE-NEXT:    [[VECINS_31:%.*]] = shufflevector <4 x float> [[VECINS_1]], <4 x float> [[TMP5]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>
; NOACCELERATE-NEXT:    ret <4 x float> [[VECINS_31]]
;
entry:
  %0 = load <4 x float>, ptr %a, align 16
  %vecext = extractelement <4 x float> %0, i32 0
  %1 = tail call fast float @llvm.atan.f32(float %vecext)
  %vecins = insertelement <4 x float> undef, float %1, i32 0
  %vecext.1 = extractelement <4 x float> %0, i32 1
  %2 = tail call fast float @llvm.atan.f32(float %vecext.1)
  %vecins.1 = insertelement <4 x float> %vecins, float %2, i32 1
  %vecext.2 = extractelement <4 x float> %0, i32 2
  %3 = tail call fast float @llvm.atan.f32(float %vecext.2)
  %vecins.2 = insertelement <4 x float> %vecins.1, float %3, i32 2
  %vecext.3 = extractelement <4 x float> %0, i32 3
  %4 = tail call fast float @llvm.atan.f32(float %vecext.3)
  %vecins.3 = insertelement <4 x float> %vecins.2, float %4, i32 3
  ret <4 x float> %vecins.3
}
declare float @sinhf(float) readonly nounwind willreturn
define <4 x float> @sinh_4x(ptr %a) {
; CHECK-LABEL: @sinh_4x(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = load <4 x float>, ptr [[A:%.*]], align 16
; CHECK-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @vsinhf(<4 x float> [[TMP0]])
; CHECK-NEXT:    ret <4 x float> [[TMP1]]
;
; NOACCELERATE-LABEL: @sinh_4x(
; NOACCELERATE-NEXT:  entry:
; NOACCELERATE-NEXT:    [[TMP0:%.*]] = load <4 x float>, ptr [[A:%.*]], align 16
; NOACCELERATE-NEXT:    [[VECEXT:%.*]] = extractelement <4 x float> [[TMP0]], i32 0
; NOACCELERATE-NEXT:    [[TMP1:%.*]] = tail call fast float @sinhf(float [[VECEXT]])
; NOACCELERATE-NEXT:    [[VECINS:%.*]] = insertelement <4 x float> undef, float [[TMP1]], i32 0
; NOACCELERATE-NEXT:    [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i32 1
; NOACCELERATE-NEXT:    [[TMP2:%.*]] = tail call fast float @sinhf(float [[VECEXT_1]])
; NOACCELERATE-NEXT:    [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP2]], i32 1
; NOACCELERATE-NEXT:    [[TMP3:%.*]] = shufflevector <4 x float> [[TMP0]], <4 x float> poison, <2 x i32> <i32 2, i32 3>
; NOACCELERATE-NEXT:    [[TMP4:%.*]] = call fast <2 x float> @llvm.sinh.v2f32(<2 x float> [[TMP3]])
; NOACCELERATE-NEXT:    [[TMP5:%.*]] = shufflevector <2 x float> [[TMP4]], <2 x float> poison, <4 x i32> <i32 0, i32 1, i32 poison, i32 poison>
; NOACCELERATE-NEXT:    [[VECINS_31:%.*]] = shufflevector <4 x float> [[VECINS_1]], <4 x float> [[TMP5]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>
; NOACCELERATE-NEXT:    ret <4 x float> [[VECINS_31]]
;
entry:
  %0 = load <4 x float>, ptr %a, align 16
  %vecext = extractelement <4 x float> %0, i32 0
  %1 = tail call fast float @sinhf(float %vecext)
  %vecins = insertelement <4 x float> undef, float %1, i32 0
  %vecext.1 = extractelement <4 x float> %0, i32 1
  %2 = tail call fast float @sinhf(float %vecext.1)
  %vecins.1 = insertelement <4 x float> %vecins, float %2, i32 1
  %vecext.2 = extractelement <4 x float> %0, i32 2
  %3 = tail call fast float @sinhf(float %vecext.2)
  %vecins.2 = insertelement <4 x float> %vecins.1, float %3, i32 2
  %vecext.3 = extractelement <4 x float> %0, i32 3
  %4 = tail call fast float @sinhf(float %vecext.3)
  %vecins.3 = insertelement <4 x float> %vecins.2, float %4, i32 3
  ret <4 x float> %vecins.3
}
define <4 x float> @int_sinh_4x(ptr %a) {
; CHECK-LABEL: @int_sinh_4x(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = load <4 x float>, ptr [[A:%.*]], align 16
; CHECK-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @vsinhf(<4 x float> [[TMP0]])
; CHECK-NEXT:    ret <4 x float> [[TMP1]]
;
; NOACCELERATE-LABEL: @int_sinh_4x(
; NOACCELERATE-NEXT:  entry:
; NOACCELERATE-NEXT:    [[TMP0:%.*]] = load <4 x float>, ptr [[A:%.*]], align 16
; NOACCELERATE-NEXT:    [[VECEXT:%.*]] = extractelement <4 x float> [[TMP0]], i32 0
; NOACCELERATE-NEXT:    [[TMP1:%.*]] = tail call fast float @llvm.sinh.f32(float [[VECEXT]])
; NOACCELERATE-NEXT:    [[VECINS:%.*]] = insertelement <4 x float> undef, float [[TMP1]], i32 0
; NOACCELERATE-NEXT:    [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i32 1
; NOACCELERATE-NEXT:    [[TMP2:%.*]] = tail call fast float @llvm.sinh.f32(float [[VECEXT_1]])
; NOACCELERATE-NEXT:    [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP2]], i32 1
; NOACCELERATE-NEXT:    [[TMP3:%.*]] = shufflevector <4 x float> [[TMP0]], <4 x float> poison, <2 x i32> <i32 2, i32 3>
; NOACCELERATE-NEXT:    [[TMP4:%.*]] = call fast <2 x float> @llvm.sinh.v2f32(<2 x float> [[TMP3]])
; NOACCELERATE-NEXT:    [[TMP5:%.*]] = shufflevector <2 x float> [[TMP4]], <2 x float> poison, <4 x i32> <i32 0, i32 1, i32 poison, i32 poison>
; NOACCELERATE-NEXT:    [[VECINS_31:%.*]] = shufflevector <4 x float> [[VECINS_1]], <4 x float> [[TMP5]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>
; NOACCELERATE-NEXT:    ret <4 x float> [[VECINS_31]]
;
entry:
  %0 = load <4 x float>, ptr %a, align 16
  %vecext = extractelement <4 x float> %0, i32 0
  %1 = tail call fast float @llvm.sinh.f32(float %vecext)
  %vecins = insertelement <4 x float> undef, float %1, i32 0
  %vecext.1 = extractelement <4 x float> %0, i32 1
  %2 = tail call fast float @llvm.sinh.f32(float %vecext.1)
  %vecins.1 = insertelement <4 x float> %vecins, float %2, i32 1
  %vecext.2 = extractelement <4 x float> %0, i32 2
  %3 = tail call fast float @llvm.sinh.f32(float %vecext.2)
  %vecins.2 = insertelement <4 x float> %vecins.1, float %3, i32 2
  %vecext.3 = extractelement <4 x float> %0, i32 3
  %4 = tail call fast float @llvm.sinh.f32(float %vecext.3)
  %vecins.3 = insertelement <4 x float> %vecins.2, float %4, i32 3
  ret <4 x float> %vecins.3
}
declare float @coshf(float) readonly nounwind willreturn
define <4 x float> @cosh_4x(ptr %a) {
; CHECK-LABEL: @cosh_4x(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = load <4 x float>, ptr [[A:%.*]], align 16
; CHECK-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @vcoshf(<4 x float> [[TMP0]])
; CHECK-NEXT:    ret <4 x float> [[TMP1]]
;
; NOACCELERATE-LABEL: @cosh_4x(
; NOACCELERATE-NEXT:  entry:
; NOACCELERATE-NEXT:    [[TMP0:%.*]] = load <4 x float>, ptr [[A:%.*]], align 16
; NOACCELERATE-NEXT:    [[VECEXT:%.*]] = extractelement <4 x float> [[TMP0]], i32 0
; NOACCELERATE-NEXT:    [[TMP1:%.*]] = tail call fast float @coshf(float [[VECEXT]])
; NOACCELERATE-NEXT:    [[VECINS:%.*]] = insertelement <4 x float> undef, float [[TMP1]], i32 0
; NOACCELERATE-NEXT:    [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i32 1
; NOACCELERATE-NEXT:    [[TMP2:%.*]] = tail call fast float @coshf(float [[VECEXT_1]])
; NOACCELERATE-NEXT:    [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP2]], i32 1
; NOACCELERATE-NEXT:    [[TMP3:%.*]] = shufflevector <4 x float> [[TMP0]], <4 x float> poison, <2 x i32> <i32 2, i32 3>
; NOACCELERATE-NEXT:    [[TMP4:%.*]] = call fast <2 x float> @llvm.cosh.v2f32(<2 x float> [[TMP3]])
; NOACCELERATE-NEXT:    [[TMP5:%.*]] = shufflevector <2 x float> [[TMP4]], <2 x float> poison, <4 x i32> <i32 0, i32 1, i32 poison, i32 poison>
; NOACCELERATE-NEXT:    [[VECINS_31:%.*]] = shufflevector <4 x float> [[VECINS_1]], <4 x float> [[TMP5]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>
; NOACCELERATE-NEXT:    ret <4 x float> [[VECINS_31]]
;
entry:
  %0 = load <4 x float>, ptr %a, align 16
  %vecext = extractelement <4 x float> %0, i32 0
  %1 = tail call fast float @coshf(float %vecext)
  %vecins = insertelement <4 x float> undef, float %1, i32 0
  %vecext.1 = extractelement <4 x float> %0, i32 1
  %2 = tail call fast float @coshf(float %vecext.1)
  %vecins.1 = insertelement <4 x float> %vecins, float %2, i32 1
  %vecext.2 = extractelement <4 x float> %0, i32 2
  %3 = tail call fast float @coshf(float %vecext.2)
  %vecins.2 = insertelement <4 x float> %vecins.1, float %3, i32 2
  %vecext.3 = extractelement <4 x float> %0, i32 3
  %4 = tail call fast float @coshf(float %vecext.3)
  %vecins.3 = insertelement <4 x float> %vecins.2, float %4, i32 3
  ret <4 x float> %vecins.3
}
define <4 x float> @int_cosh_4x(ptr %a) {
; CHECK-LABEL: @int_cosh_4x(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = load <4 x float>, ptr [[A:%.*]], align 16
; CHECK-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @vcoshf(<4 x float> [[TMP0]])
; CHECK-NEXT:    ret <4 x float> [[TMP1]]
;
; NOACCELERATE-LABEL: @int_cosh_4x(
; NOACCELERATE-NEXT:  entry:
; NOACCELERATE-NEXT:    [[TMP0:%.*]] = load <4 x float>, ptr [[A:%.*]], align 16
; NOACCELERATE-NEXT:    [[VECEXT:%.*]] = extractelement <4 x float> [[TMP0]], i32 0
; NOACCELERATE-NEXT:    [[TMP1:%.*]] = tail call fast float @llvm.cosh.f32(float [[VECEXT]])
; NOACCELERATE-NEXT:    [[VECINS:%.*]] = insertelement <4 x float> undef, float [[TMP1]], i32 0
; NOACCELERATE-NEXT:    [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i32 1
; NOACCELERATE-NEXT:    [[TMP2:%.*]] = tail call fast float @llvm.cosh.f32(float [[VECEXT_1]])
; NOACCELERATE-NEXT:    [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP2]], i32 1
; NOACCELERATE-NEXT:    [[TMP3:%.*]] = shufflevector <4 x float> [[TMP0]], <4 x float> poison, <2 x i32> <i32 2, i32 3>
; NOACCELERATE-NEXT:    [[TMP4:%.*]] = call fast <2 x float> @llvm.cosh.v2f32(<2 x float> [[TMP3]])
; NOACCELERATE-NEXT:    [[TMP5:%.*]] = shufflevector <2 x float> [[TMP4]], <2 x float> poison, <4 x i32> <i32 0, i32 1, i32 poison, i32 poison>
; NOACCELERATE-NEXT:    [[VECINS_31:%.*]] = shufflevector <4 x float> [[VECINS_1]], <4 x float> [[TMP5]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>
; NOACCELERATE-NEXT:    ret <4 x float> [[VECINS_31]]
;
entry:
  %0 = load <4 x float>, ptr %a, align 16
  %vecext = extractelement <4 x float> %0, i32 0
  %1 = tail call fast float @llvm.cosh.f32(float %vecext)
  %vecins = insertelement <4 x float> undef, float %1, i32 0
  %vecext.1 = extractelement <4 x float> %0, i32 1
  %2 = tail call fast float @llvm.cosh.f32(float %vecext.1)
  %vecins.1 = insertelement <4 x float> %vecins, float %2, i32 1
  %vecext.2 = extractelement <4 x float> %0, i32 2
  %3 = tail call fast float @llvm.cosh.f32(float %vecext.2)
  %vecins.2 = insertelement <4 x float> %vecins.1, float %3, i32 2
  %vecext.3 = extractelement <4 x float> %0, i32 3
  %4 = tail call fast float @llvm.cosh.f32(float %vecext.3)
  %vecins.3 = insertelement <4 x float> %vecins.2, float %4, i32 3
  ret <4 x float> %vecins.3
}
declare float @tanhf(float) readonly nounwind willreturn
define <4 x float> @tanh_4x(ptr %a) {
; CHECK-LABEL: @tanh_4x(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = load <4 x float>, ptr [[A:%.*]], align 16
; CHECK-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @vtanhf(<4 x float> [[TMP0]])
; CHECK-NEXT:    ret <4 x float> [[TMP1]]
;
; NOACCELERATE-LABEL: @tanh_4x(
; NOACCELERATE-NEXT:  entry:
; NOACCELERATE-NEXT:    [[TMP0:%.*]] = load <4 x float>, ptr [[A:%.*]], align 16
; NOACCELERATE-NEXT:    [[VECEXT:%.*]] = extractelement <4 x float> [[TMP0]], i32 0
; NOACCELERATE-NEXT:    [[TMP1:%.*]] = tail call fast float @tanhf(float [[VECEXT]])
; NOACCELERATE-NEXT:    [[VECINS:%.*]] = insertelement <4 x float> undef, float [[TMP1]], i32 0
; NOACCELERATE-NEXT:    [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i32 1
; NOACCELERATE-NEXT:    [[TMP2:%.*]] = tail call fast float @tanhf(float [[VECEXT_1]])
; NOACCELERATE-NEXT:    [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP2]], i32 1
; NOACCELERATE-NEXT:    [[TMP3:%.*]] = shufflevector <4 x float> [[TMP0]], <4 x float> poison, <2 x i32> <i32 2, i32 3>
; NOACCELERATE-NEXT:    [[TMP4:%.*]] = call fast <2 x float> @llvm.tanh.v2f32(<2 x float> [[TMP3]])
; NOACCELERATE-NEXT:    [[TMP5:%.*]] = shufflevector <2 x float> [[TMP4]], <2 x float> poison, <4 x i32> <i32 0, i32 1, i32 poison, i32 poison>
; NOACCELERATE-NEXT:    [[VECINS_31:%.*]] = shufflevector <4 x float> [[VECINS_1]], <4 x float> [[TMP5]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>
; NOACCELERATE-NEXT:    ret <4 x float> [[VECINS_31]]
;
entry:
  %0 = load <4 x float>, ptr %a, align 16
  %vecext = extractelement <4 x float> %0, i32 0
  %1 = tail call fast float @tanhf(float %vecext)
  %vecins = insertelement <4 x float> undef, float %1, i32 0
  %vecext.1 = extractelement <4 x float> %0, i32 1
  %2 = tail call fast float @tanhf(float %vecext.1)
  %vecins.1 = insertelement <4 x float> %vecins, float %2, i32 1
  %vecext.2 = extractelement <4 x float> %0, i32 2
  %3 = tail call fast float @tanhf(float %vecext.2)
  %vecins.2 = insertelement <4 x float> %vecins.1, float %3, i32 2
  %vecext.3 = extractelement <4 x float> %0, i32 3
  %4 = tail call fast float @tanhf(float %vecext.3)
  %vecins.3 = insertelement <4 x float> %vecins.2, float %4, i32 3
  ret <4 x float> %vecins.3
}
define <4 x float> @int_tanh_4x(ptr %a) {
; CHECK-LABEL: @int_tanh_4x(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = load <4 x float>, ptr [[A:%.*]], align 16
; CHECK-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @vtanhf(<4 x float> [[TMP0]])
; CHECK-NEXT:    ret <4 x float> [[TMP1]]
;
; NOACCELERATE-LABEL: @int_tanh_4x(
; NOACCELERATE-NEXT:  entry:
; NOACCELERATE-NEXT:    [[TMP0:%.*]] = load <4 x float>, ptr [[A:%.*]], align 16
; NOACCELERATE-NEXT:    [[VECEXT:%.*]] = extractelement <4 x float> [[TMP0]], i32 0
; NOACCELERATE-NEXT:    [[TMP1:%.*]] = tail call fast float @llvm.tanh.f32(float [[VECEXT]])
; NOACCELERATE-NEXT:    [[VECINS:%.*]] = insertelement <4 x float> undef, float [[TMP1]], i32 0
; NOACCELERATE-NEXT:    [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i32 1
; NOACCELERATE-NEXT:    [[TMP2:%.*]] = tail call fast float @llvm.tanh.f32(float [[VECEXT_1]])
; NOACCELERATE-NEXT:    [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP2]], i32 1
; NOACCELERATE-NEXT:    [[TMP3:%.*]] = shufflevector <4 x float> [[TMP0]], <4 x float> poison, <2 x i32> <i32 2, i32 3>
; NOACCELERATE-NEXT:    [[TMP4:%.*]] = call fast <2 x float> @llvm.tanh.v2f32(<2 x float> [[TMP3]])
; NOACCELERATE-NEXT:    [[TMP5:%.*]] = shufflevector <2 x float> [[TMP4]], <2 x float> poison, <4 x i32> <i32 0, i32 1, i32 poison, i32 poison>
; NOACCELERATE-NEXT:    [[VECINS_31:%.*]] = shufflevector <4 x float> [[VECINS_1]], <4 x float> [[TMP5]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>
; NOACCELERATE-NEXT:    ret <4 x float> [[VECINS_31]]
;
entry:
  %0 = load <4 x float>, ptr %a, align 16
  %vecext = extractelement <4 x float> %0, i32 0
  %1 = tail call fast float @llvm.tanh.f32(float %vecext)
  %vecins = insertelement <4 x float> undef, float %1, i32 0
  %vecext.1 = extractelement <4 x float> %0, i32 1
  %2 = tail call fast float @llvm.tanh.f32(float %vecext.1)
  %vecins.1 = insertelement <4 x float> %vecins, float %2, i32 1
  %vecext.2 = extractelement <4 x float> %0, i32 2
  %3 = tail call fast float @llvm.tanh.f32(float %vecext.2)
  %vecins.2 = insertelement <4 x float> %vecins.1, float %3, i32 2
  %vecext.3 = extractelement <4 x float> %0, i32 3
  %4 = tail call fast float @llvm.tanh.f32(float %vecext.3)
  %vecins.3 = insertelement <4 x float> %vecins.2, float %4, i32 3
  ret <4 x float> %vecins.3
}
declare float @asinhf(float) readonly nounwind willreturn
define <4 x float> @asinh_4x(ptr %a) {
; CHECK-LABEL: @asinh_4x(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = load <4 x float>, ptr [[A:%.*]], align 16
; CHECK-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @vasinhf(<4 x float> [[TMP0]])
; CHECK-NEXT:    ret <4 x float> [[TMP1]]
;
; NOACCELERATE-LABEL: @asinh_4x(
; NOACCELERATE-NEXT:  entry:
; NOACCELERATE-NEXT:    [[TMP0:%.*]] = load <4 x float>, ptr [[A:%.*]], align 16
; NOACCELERATE-NEXT:    [[VECEXT:%.*]] = extractelement <4 x float> [[TMP0]], i32 0
; NOACCELERATE-NEXT:    [[TMP1:%.*]] = tail call fast float @asinhf(float [[VECEXT]])
; NOACCELERATE-NEXT:    [[VECINS:%.*]] = insertelement <4 x float> undef, float [[TMP1]], i32 0
; NOACCELERATE-NEXT:    [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i32 1
; NOACCELERATE-NEXT:    [[TMP2:%.*]] = tail call fast float @asinhf(float [[VECEXT_1]])
; NOACCELERATE-NEXT:    [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP2]], i32 1
; NOACCELERATE-NEXT:    [[VECEXT_2:%.*]] = extractelement <4 x float> [[TMP0]], i32 2
; NOACCELERATE-NEXT:    [[TMP3:%.*]] = tail call fast float @asinhf(float [[VECEXT_2]])
; NOACCELERATE-NEXT:    [[VECINS_2:%.*]] = insertelement <4 x float> [[VECINS_1]], float [[TMP3]], i32 2
; NOACCELERATE-NEXT:    [[VECEXT_3:%.*]] = extractelement <4 x float> [[TMP0]], i32 3
; NOACCELERATE-NEXT:    [[TMP4:%.*]] = tail call fast float @asinhf(float [[VECEXT_3]])
; NOACCELERATE-NEXT:    [[VECINS_3:%.*]] = insertelement <4 x float> [[VECINS_2]], float [[TMP4]], i32 3
; NOACCELERATE-NEXT:    ret <4 x float> [[VECINS_3]]
;
entry:
  %0 = load <4 x float>, ptr %a, align 16
  %vecext = extractelement <4 x float> %0, i32 0
  %1 = tail call fast float @asinhf(float %vecext)
  %vecins = insertelement <4 x float> undef, float %1, i32 0
  %vecext.1 = extractelement <4 x float> %0, i32 1
  %2 = tail call fast float @asinhf(float %vecext.1)
  %vecins.1 = insertelement <4 x float> %vecins, float %2, i32 1
  %vecext.2 = extractelement <4 x float> %0, i32 2
  %3 = tail call fast float @asinhf(float %vecext.2)
  %vecins.2 = insertelement <4 x float> %vecins.1, float %3, i32 2
  %vecext.3 = extractelement <4 x float> %0, i32 3
  %4 = tail call fast float @asinhf(float %vecext.3)
  %vecins.3 = insertelement <4 x float> %vecins.2, float %4, i32 3
  ret <4 x float> %vecins.3
}
declare float @acoshf(float) readonly nounwind willreturn
define <4 x float> @acosh_4x(ptr %a) {
; CHECK-LABEL: @acosh_4x(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = load <4 x float>, ptr [[A:%.*]], align 16
; CHECK-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @vacoshf(<4 x float> [[TMP0]])
; CHECK-NEXT:    ret <4 x float> [[TMP1]]
;
; NOACCELERATE-LABEL: @acosh_4x(
; NOACCELERATE-NEXT:  entry:
; NOACCELERATE-NEXT:    [[TMP0:%.*]] = load <4 x float>, ptr [[A:%.*]], align 16
; NOACCELERATE-NEXT:    [[VECEXT:%.*]] = extractelement <4 x float> [[TMP0]], i32 0
; NOACCELERATE-NEXT:    [[TMP1:%.*]] = tail call fast float @acoshf(float [[VECEXT]])
; NOACCELERATE-NEXT:    [[VECINS:%.*]] = insertelement <4 x float> undef, float [[TMP1]], i32 0
; NOACCELERATE-NEXT:    [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i32 1
; NOACCELERATE-NEXT:    [[TMP2:%.*]] = tail call fast float @acoshf(float [[VECEXT_1]])
; NOACCELERATE-NEXT:    [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP2]], i32 1
; NOACCELERATE-NEXT:    [[VECEXT_2:%.*]] = extractelement <4 x float> [[TMP0]], i32 2
; NOACCELERATE-NEXT:    [[TMP3:%.*]] = tail call fast float @acoshf(float [[VECEXT_2]])
; NOACCELERATE-NEXT:    [[VECINS_2:%.*]] = insertelement <4 x float> [[VECINS_1]], float [[TMP3]], i32 2
; NOACCELERATE-NEXT:    [[VECEXT_3:%.*]] = extractelement <4 x float> [[TMP0]], i32 3
; NOACCELERATE-NEXT:    [[TMP4:%.*]] = tail call fast float @acoshf(float [[VECEXT_3]])
; NOACCELERATE-NEXT:    [[VECINS_3:%.*]] = insertelement <4 x float> [[VECINS_2]], float [[TMP4]], i32 3
; NOACCELERATE-NEXT:    ret <4 x float> [[VECINS_3]]
;
entry:
  %0 = load <4 x float>, ptr %a, align 16
  %vecext = extractelement <4 x float> %0, i32 0
  %1 = tail call fast float @acoshf(float %vecext)
  %vecins = insertelement <4 x float> undef, float %1, i32 0
  %vecext.1 = extractelement <4 x float> %0, i32 1
  %2 = tail call fast float @acoshf(float %vecext.1)
  %vecins.1 = insertelement <4 x float> %vecins, float %2, i32 1
  %vecext.2 = extractelement <4 x float> %0, i32 2
  %3 = tail call fast float @acoshf(float %vecext.2)
  %vecins.2 = insertelement <4 x float> %vecins.1, float %3, i32 2
  %vecext.3 = extractelement <4 x float> %0, i32 3
  %4 = tail call fast float @acoshf(float %vecext.3)
  %vecins.3 = insertelement <4 x float> %vecins.2, float %4, i32 3
  ret <4 x float> %vecins.3
}
declare float @atanhf(float) readonly nounwind willreturn
define <4 x float> @atanh_4x(ptr %a) {
; CHECK-LABEL: @atanh_4x(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = load <4 x float>, ptr [[A:%.*]], align 16
; CHECK-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @vatanhf(<4 x float> [[TMP0]])
; CHECK-NEXT:    ret <4 x float> [[TMP1]]
;
; NOACCELERATE-LABEL: @atanh_4x(
; NOACCELERATE-NEXT:  entry:
; NOACCELERATE-NEXT:    [[TMP0:%.*]] = load <4 x float>, ptr [[A:%.*]], align 16
; NOACCELERATE-NEXT:    [[VECEXT:%.*]] = extractelement <4 x float> [[TMP0]], i32 0
; NOACCELERATE-NEXT:    [[TMP1:%.*]] = tail call fast float @atanhf(float [[VECEXT]])
; NOACCELERATE-NEXT:    [[VECINS:%.*]] = insertelement <4 x float> undef, float [[TMP1]], i32 0
; NOACCELERATE-NEXT:    [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i32 1
; NOACCELERATE-NEXT:    [[TMP2:%.*]] = tail call fast float @atanhf(float [[VECEXT_1]])
; NOACCELERATE-NEXT:    [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP2]], i32 1
; NOACCELERATE-NEXT:    [[VECEXT_2:%.*]] = extractelement <4 x float> [[TMP0]], i32 2
; NOACCELERATE-NEXT:    [[TMP3:%.*]] = tail call fast float @atanhf(float [[VECEXT_2]])
; NOACCELERATE-NEXT:    [[VECINS_2:%.*]] = insertelement <4 x float> [[VECINS_1]], float [[TMP3]], i32 2
; NOACCELERATE-NEXT:    [[VECEXT_3:%.*]] = extractelement <4 x float> [[TMP0]], i32 3
; NOACCELERATE-NEXT:    [[TMP4:%.*]] = tail call fast float @atanhf(float [[VECEXT_3]])
; NOACCELERATE-NEXT:    [[VECINS_3:%.*]] = insertelement <4 x float> [[VECINS_2]], float [[TMP4]], i32 3
; NOACCELERATE-NEXT:    ret <4 x float> [[VECINS_3]]
;
entry:
  %0 = load <4 x float>, ptr %a, align 16
  %vecext = extractelement <4 x float> %0, i32 0
  %1 = tail call fast float @atanhf(float %vecext)
  %vecins = insertelement <4 x float> undef, float %1, i32 0
  %vecext.1 = extractelement <4 x float> %0, i32 1
  %2 = tail call fast float @atanhf(float %vecext.1)
  %vecins.1 = insertelement <4 x float> %vecins, float %2, i32 1
  %vecext.2 = extractelement <4 x float> %0, i32 2
  %3 = tail call fast float @atanhf(float %vecext.2)
  %vecins.2 = insertelement <4 x float> %vecins.1, float %3, i32 2
  %vecext.3 = extractelement <4 x float> %0, i32 3
  %4 = tail call fast float @atanhf(float %vecext.3)
  %vecins.3 = insertelement <4 x float> %vecins.2, float %4, i32 3
  ret <4 x float> %vecins.3
}

; Accelerate *does not* provide sin() for <2 x float>.
define <2 x float> @sin_2x(ptr %a) {
; CHECK-LABEL: @sin_2x(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = load <2 x float>, ptr [[A:%.*]], align 16
; CHECK-NEXT:    [[VECEXT:%.*]] = extractelement <2 x float> [[TMP0]], i32 0
; CHECK-NEXT:    [[TMP1:%.*]] = tail call fast float @llvm.sin.f32(float [[VECEXT]]) #[[ATTR2:[0-9]+]]
; CHECK-NEXT:    [[VECINS:%.*]] = insertelement <2 x float> undef, float [[TMP1]], i32 0
; CHECK-NEXT:    [[VECEXT_1:%.*]] = extractelement <2 x float> [[TMP0]], i32 1
; CHECK-NEXT:    [[TMP2:%.*]] = tail call fast float @llvm.sin.f32(float [[VECEXT_1]]) #[[ATTR2]]
; CHECK-NEXT:    [[VECINS_1:%.*]] = insertelement <2 x float> [[VECINS]], float [[TMP2]], i32 1
; CHECK-NEXT:    ret <2 x float> [[VECINS_1]]
;
; NOACCELERATE-LABEL: @sin_2x(
; NOACCELERATE-NEXT:  entry:
; NOACCELERATE-NEXT:    [[TMP0:%.*]] = load <2 x float>, ptr [[A:%.*]], align 16
; NOACCELERATE-NEXT:    [[VECEXT:%.*]] = extractelement <2 x float> [[TMP0]], i32 0
; NOACCELERATE-NEXT:    [[TMP1:%.*]] = tail call fast float @llvm.sin.f32(float [[VECEXT]])
; NOACCELERATE-NEXT:    [[VECINS:%.*]] = insertelement <2 x float> undef, float [[TMP1]], i32 0
; NOACCELERATE-NEXT:    [[VECEXT_1:%.*]] = extractelement <2 x float> [[TMP0]], i32 1
; NOACCELERATE-NEXT:    [[TMP2:%.*]] = tail call fast float @llvm.sin.f32(float [[VECEXT_1]])
; NOACCELERATE-NEXT:    [[VECINS_1:%.*]] = insertelement <2 x float> [[VECINS]], float [[TMP2]], i32 1
; NOACCELERATE-NEXT:    ret <2 x float> [[VECINS_1]]
;
entry:
  %0 = load <2 x float>, ptr %a, align 16
  %vecext = extractelement <2 x float> %0, i32 0
  %1 = tail call fast float @llvm.sin.f32(float %vecext)
  %vecins = insertelement <2 x float> undef, float %1, i32 0
  %vecext.1 = extractelement <2 x float> %0, i32 1
  %2 = tail call fast float @llvm.sin.f32(float %vecext.1)
  %vecins.1 = insertelement <2 x float> %vecins, float %2, i32 1
  ret <2 x float> %vecins.1
}


declare float @llvm.cos.f32(float)

; Accelerate provides cos() for <4 x float>
define <4 x float> @int_cos_4x(ptr %a) {
; CHECK-LABEL: @int_cos_4x(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = load <4 x float>, ptr [[A:%.*]], align 16
; CHECK-NEXT:    [[TMP1:%.*]] = call fast <4 x float> @vcosf(<4 x float> [[TMP0]])
; CHECK-NEXT:    ret <4 x float> [[TMP1]]
;
; NOACCELERATE-LABEL: @int_cos_4x(
; NOACCELERATE-NEXT:  entry:
; NOACCELERATE-NEXT:    [[TMP0:%.*]] = load <4 x float>, ptr [[A:%.*]], align 16
; NOACCELERATE-NEXT:    [[VECEXT:%.*]] = extractelement <4 x float> [[TMP0]], i32 0
; NOACCELERATE-NEXT:    [[TMP1:%.*]] = tail call fast float @llvm.cos.f32(float [[VECEXT]])
; NOACCELERATE-NEXT:    [[VECINS:%.*]] = insertelement <4 x float> undef, float [[TMP1]], i32 0
; NOACCELERATE-NEXT:    [[VECEXT_1:%.*]] = extractelement <4 x float> [[TMP0]], i32 1
; NOACCELERATE-NEXT:    [[TMP2:%.*]] = tail call fast float @llvm.cos.f32(float [[VECEXT_1]])
; NOACCELERATE-NEXT:    [[VECINS_1:%.*]] = insertelement <4 x float> [[VECINS]], float [[TMP2]], i32 1
; NOACCELERATE-NEXT:    [[TMP3:%.*]] = shufflevector <4 x float> [[TMP0]], <4 x float> poison, <2 x i32> <i32 2, i32 3>
; NOACCELERATE-NEXT:    [[TMP4:%.*]] = call fast <2 x float> @llvm.cos.v2f32(<2 x float> [[TMP3]])
; NOACCELERATE-NEXT:    [[TMP5:%.*]] = shufflevector <2 x float> [[TMP4]], <2 x float> poison, <4 x i32> <i32 0, i32 1, i32 poison, i32 poison>
; NOACCELERATE-NEXT:    [[VECINS_31:%.*]] = shufflevector <4 x float> [[VECINS_1]], <4 x float> [[TMP5]], <4 x i32> <i32 0, i32 1, i32 4, i32 5>
; NOACCELERATE-NEXT:    ret <4 x float> [[VECINS_31]]
;
entry:
  %0 = load <4 x float>, ptr %a, align 16
  %vecext = extractelement <4 x float> %0, i32 0
  %1 = tail call fast float @llvm.cos.f32(float %vecext)
  %vecins = insertelement <4 x float> undef, float %1, i32 0
  %vecext.1 = extractelement <4 x float> %0, i32 1
  %2 = tail call fast float @llvm.cos.f32(float %vecext.1)
  %vecins.1 = insertelement <4 x float> %vecins, float %2, i32 1
  %vecext.2 = extractelement <4 x float> %0, i32 2
  %3 = tail call fast float @llvm.cos.f32(float %vecext.2)
  %vecins.2 = insertelement <4 x float> %vecins.1, float %3, i32 2
  %vecext.3 = extractelement <4 x float> %0, i32 3
  %4 = tail call fast float @llvm.cos.f32(float %vecext.3)
  %vecins.3 = insertelement <4 x float> %vecins.2, float %4, i32 3
  ret <4 x float> %vecins.3
}

; Accelerate *does not* provide cos() for <2 x float>.
define <2 x float> @cos_2x(ptr %a) {
; CHECK-LABEL: @cos_2x(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = load <2 x float>, ptr [[A:%.*]], align 16
; CHECK-NEXT:    [[VECEXT:%.*]] = extractelement <2 x float> [[TMP0]], i32 0
; CHECK-NEXT:    [[TMP1:%.*]] = tail call fast float @llvm.cos.f32(float [[VECEXT]]) #[[ATTR3:[0-9]+]]
; CHECK-NEXT:    [[VECINS:%.*]] = insertelement <2 x float> undef, float [[TMP1]], i32 0
; CHECK-NEXT:    [[VECEXT_1:%.*]] = extractelement <2 x float> [[TMP0]], i32 1
; CHECK-NEXT:    [[TMP2:%.*]] = tail call fast float @llvm.cos.f32(float [[VECEXT_1]]) #[[ATTR3]]
; CHECK-NEXT:    [[VECINS_1:%.*]] = insertelement <2 x float> [[VECINS]], float [[TMP2]], i32 1
; CHECK-NEXT:    ret <2 x float> [[VECINS_1]]
;
; NOACCELERATE-LABEL: @cos_2x(
; NOACCELERATE-NEXT:  entry:
; NOACCELERATE-NEXT:    [[TMP0:%.*]] = load <2 x float>, ptr [[A:%.*]], align 16
; NOACCELERATE-NEXT:    [[VECEXT:%.*]] = extractelement <2 x float> [[TMP0]], i32 0
; NOACCELERATE-NEXT:    [[TMP1:%.*]] = tail call fast float @llvm.cos.f32(float [[VECEXT]])
; NOACCELERATE-NEXT:    [[VECINS:%.*]] = insertelement <2 x float> undef, float [[TMP1]], i32 0
; NOACCELERATE-NEXT:    [[VECEXT_1:%.*]] = extractelement <2 x float> [[TMP0]], i32 1
; NOACCELERATE-NEXT:    [[TMP2:%.*]] = tail call fast float @llvm.cos.f32(float [[VECEXT_1]])
; NOACCELERATE-NEXT:    [[VECINS_1:%.*]] = insertelement <2 x float> [[VECINS]], float [[TMP2]], i32 1
; NOACCELERATE-NEXT:    ret <2 x float> [[VECINS_1]]
;
entry:
  %0 = load <2 x float>, ptr %a, align 16
  %vecext = extractelement <2 x float> %0, i32 0
  %1 = tail call fast float @llvm.cos.f32(float %vecext)
  %vecins = insertelement <2 x float> undef, float %1, i32 0
  %vecext.1 = extractelement <2 x float> %0, i32 1
  %2 = tail call fast float @llvm.cos.f32(float %vecext.1)
  %vecins.1 = insertelement <2 x float> %vecins, float %2, i32 1
  ret <2 x float> %vecins.1
}