-; RUN: opt < %s -scalarrepl -S | not grep alloca
-; RUN: opt < %s -scalarrepl -S | grep {load <4 x float>}
+; RUN: opt < %s -scalarrepl -S | FileCheck %s
target datalayout = "E-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64"
-define void @test(<4 x float>* %F, float %f) {
+define void @test1(<4 x float>* %F, float %f) {
entry:
%G = alloca <4 x float>, align 16 ; <<4 x float>*> [#uses=3]
%tmp = load <4 x float>* %F ; <<4 x float>> [#uses=2]
%tmp6 = fadd <4 x float> %tmp4, %tmp4 ; <<4 x float>> [#uses=1]
store <4 x float> %tmp6, <4 x float>* %F
ret void
+; CHECK: @test1
+; CHECK-NOT: alloca
+; CHECK: %tmp = load <4 x float>* %F
+; CHECK: fadd <4 x float> %tmp, %tmp
+; CHECK-NEXT: insertelement <4 x float> %tmp3, float %f, i32 0
}
define void @test2(<4 x float>* %F, float %f) {
%tmp6 = fadd <4 x float> %tmp4, %tmp4 ; <<4 x float>> [#uses=1]
store <4 x float> %tmp6, <4 x float>* %F
ret void
+; CHECK: @test2
+; CHECK-NOT: alloca
+; CHECK: %tmp = load <4 x float>* %F
+; CHECK: fadd <4 x float> %tmp, %tmp
+; CHECK-NEXT: insertelement <4 x float> %tmp3, float %f, i32 2
}
define void @test3(<4 x float>* %F, float* %f) {
%tmp.upgrd.4 = load float* %tmp.upgrd.3 ; <float> [#uses=1]
store float %tmp.upgrd.4, float* %f
ret void
+; CHECK: @test3
+; CHECK-NOT: alloca
+; CHECK: %tmp = load <4 x float>* %F
+; CHECK: fadd <4 x float> %tmp, %tmp
+; CHECK-NEXT: extractelement <4 x float> %tmp3, i32 2
}
define void @test4(<4 x float>* %F, float* %f) {
%tmp.upgrd.6 = load float* %G.upgrd.5 ; <float> [#uses=1]
store float %tmp.upgrd.6, float* %f
ret void
+; CHECK: @test4
+; CHECK-NOT: alloca
+; CHECK: %tmp = load <4 x float>* %F
+; CHECK: fadd <4 x float> %tmp, %tmp
+; CHECK-NEXT: extractelement <4 x float> %tmp3, i32 0
}
define i32 @test5(float %X) { ;; should turn into bitcast.
%a = bitcast float* %X1 to i32*
%tmp = load i32* %a
ret i32 %tmp
+; CHECK: @test5
+; CHECK-NEXT: bitcast float %X to i32
+; CHECK-NEXT: ret i32
}