; RUN: grep pshufd %t | count 1
; RUN: not grep {sub.*esp} %t
-define void @test(<4 x float>* %res, <4 x float>* %A, <4 x float>* %B) {
+define void @test(<4 x float>* %res, <4 x float>* %A, <4 x float>* %B) nounwind {
%tmp = load <4 x float>* %B ; <<4 x float>> [#uses=2]
%tmp3 = load <4 x float>* %A ; <<4 x float>> [#uses=2]
%tmp.upgrd.1 = extractelement <4 x float> %tmp3, i32 0 ; <float> [#uses=1]
ret void
}
-define void @test2(<4 x float> %X, <4 x float>* %res) {
+define void @test2(<4 x float> %X, <4 x float>* %res) nounwind {
%tmp5 = shufflevector <4 x float> %X, <4 x float> undef, <4 x i32> < i32 2, i32 6, i32 3, i32 7 > ; <<4 x float>> [#uses=1]
store <4 x float> %tmp5, <4 x float>* %res
ret void
; RUN: grep movlhps %t | count 1
; RUN: grep movhlps %t | count 1
-define <4 x float> @test1(<4 x float>* %x, <4 x float>* %y) {
+define <4 x float> @test1(<4 x float>* %x, <4 x float>* %y) nounwind {
%tmp = load <4 x float>* %y ; <<4 x float>> [#uses=2]
%tmp5 = load <4 x float>* %x ; <<4 x float>> [#uses=2]
%tmp9 = fadd <4 x float> %tmp5, %tmp ; <<4 x float>> [#uses=1]
ret <4 x float> %tmp27
}
-define <4 x float> @movhl(<4 x float>* %x, <4 x float>* %y) {
+define <4 x float> @movhl(<4 x float>* %x, <4 x float>* %y) nounwind {
entry:
%tmp = load <4 x float>* %y ; <<4 x float>> [#uses=1]
%tmp3 = load <4 x float>* %x ; <<4 x float>> [#uses=1]
; RUN: grep shuf %t | count 2
; RUN: not grep unpck %t
-define void @test(<4 x float>* %res, <4 x float>* %A, <4 x float>* %B, <4 x float>* %C) {
+define void @test(<4 x float>* %res, <4 x float>* %A, <4 x float>* %B, <4 x float>* %C) nounwind {
%tmp3 = load <4 x float>* %B ; <<4 x float>> [#uses=1]
%tmp5 = load <4 x float>* %C ; <<4 x float>> [#uses=1]
%tmp11 = shufflevector <4 x float> %tmp3, <4 x float> %tmp5, <4 x i32> < i32 1, i32 4, i32 1, i32 5 > ; <<4 x float>> [#uses=1]
target triple = "i686-apple-darwin"
@x = external global [4 x i32]
-define <2 x i64> @test1() {
+define <2 x i64> @test1() nounwind {
%tmp = load i32* getelementptr ([4 x i32]* @x, i32 0, i32 0) ; <i32> [#uses=1]
%tmp3 = load i32* getelementptr ([4 x i32]* @x, i32 0, i32 1) ; <i32> [#uses=1]
%tmp5 = load i32* getelementptr ([4 x i32]* @x, i32 0, i32 2) ; <i32> [#uses=1]
ret <2 x i64> %tmp16
}
-define <4 x float> @test2(i32 %dummy, float %a, float %b, float %c, float %d) {
+define <4 x float> @test2(i32 %dummy, float %a, float %b, float %c, float %d) nounwind {
%tmp = insertelement <4 x float> undef, float %a, i32 0 ; <<4 x float>> [#uses=1]
%tmp11 = insertelement <4 x float> %tmp, float %b, i32 1 ; <<4 x float>> [#uses=1]
%tmp12 = insertelement <4 x float> %tmp11, float %c, i32 2 ; <<4 x float>> [#uses=1]
ret <4 x float> %tmp13
}
-define <4 x float> @test3(float %a, float %b, float %c, float %d) {
+define <4 x float> @test3(float %a, float %b, float %c, float %d) nounwind {
%tmp = insertelement <4 x float> undef, float %a, i32 0 ; <<4 x float>> [#uses=1]
%tmp11 = insertelement <4 x float> %tmp, float %b, i32 1 ; <<4 x float>> [#uses=1]
%tmp12 = insertelement <4 x float> %tmp11, float %c, i32 2 ; <<4 x float>> [#uses=1]
ret <4 x float> %tmp13
}
-define <2 x double> @test4(double %a, double %b) {
+define <2 x double> @test4(double %a, double %b) nounwind {
%tmp = insertelement <2 x double> undef, double %a, i32 0 ; <<2 x double>> [#uses=1]
%tmp7 = insertelement <2 x double> %tmp, double %b, i32 1 ; <<2 x double>> [#uses=1]
ret <2 x double> %tmp7
; RUN: grep pxor %t | count 1
; RUN: not grep shufps %t
-define void @test() {
+define void @test() nounwind {
bitcast <4 x i32> zeroinitializer to <4 x float> ; <<4 x float>>:1 [#uses=1]
shufflevector <4 x float> %1, <4 x float> zeroinitializer, <4 x i32> zeroinitializer ; <<4 x float>>:2 [#uses=1]
store <4 x float> %2, <4 x float>* null
- unreachable
+ ret void
}
; RUN: llc < %s -march=x86 -mattr=+sse2 | \
; RUN: not grep shufps
-define void @test(<4 x float>* %res, <4 x float>* %A) {
+define void @test(<4 x float>* %res, <4 x float>* %A) nounwind {
%tmp1 = load <4 x float>* %A ; <<4 x float>> [#uses=1]
%tmp2 = shufflevector <4 x float> %tmp1, <4 x float> undef, <4 x i32> < i32 0, i32 5, i32 6, i32 7 > ; <<4 x float>> [#uses=1]
store <4 x float> %tmp2, <4 x float>* %res
; RUN: llc < %s -march=x86 -mattr=+sse2 | FileCheck %s
-define <4 x i32> @test(i8** %ptr) {
+define <4 x i32> @test(i8** %ptr) nounwind {
; CHECK: pxor
; CHECK: punpcklbw
; CHECK: punpcklwd