X-Git-Url: http://demsky.eecs.uci.edu/git/?a=blobdiff_plain;f=test%2FTransforms%2FScalarRepl%2Fvector_promote.ll;h=5c82ae4d196dbf7285fd250b9889e3641a3e3d97;hb=8bf75ed41c95e50b62a4f8b03552d51ad6e86c7a;hp=a0d331719f06322bb57f8f0516bbbf1d41795ab5;hpb=7809ecd5b019d26498499121f4d9c0b7de2f0a14;p=oota-llvm.git

diff --git a/test/Transforms/ScalarRepl/vector_promote.ll b/test/Transforms/ScalarRepl/vector_promote.ll
index a0d331719f0..5c82ae4d196 100644
--- a/test/Transforms/ScalarRepl/vector_promote.ll
+++ b/test/Transforms/ScalarRepl/vector_promote.ll
@@ -1,56 +1,77 @@
-; RUN: llvm-as < %s | opt -scalarrepl | llvm-dis | not grep alloca
-; RUN: llvm-as < %s | opt -scalarrepl | llvm-dis | 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"
+target triple = "x86_64-apple-darwin10.0.0"
 
-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]
-	%tmp3 = add <4 x float> %tmp, %tmp		; <<4 x float>> [#uses=1]
+	%tmp3 = fadd <4 x float> %tmp, %tmp		; <<4 x float>> [#uses=1]
 	store <4 x float> %tmp3, <4 x float>* %G
 	%G.upgrd.1 = getelementptr <4 x float>* %G, i32 0, i32 0		; <float*> [#uses=1]
 	store float %f, float* %G.upgrd.1
 	%tmp4 = load <4 x float>* %G		; <<4 x float>> [#uses=2]
-	%tmp6 = add <4 x float> %tmp4, %tmp4		; <<4 x float>> [#uses=1]
+	%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) {
 entry:
 	%G = alloca <4 x float>, align 16		; <<4 x float>*> [#uses=3]
 	%tmp = load <4 x float>* %F		; <<4 x float>> [#uses=2]
-	%tmp3 = add <4 x float> %tmp, %tmp		; <<4 x float>> [#uses=1]
+	%tmp3 = fadd <4 x float> %tmp, %tmp		; <<4 x float>> [#uses=1]
 	store <4 x float> %tmp3, <4 x float>* %G
 	%tmp.upgrd.2 = getelementptr <4 x float>* %G, i32 0, i32 2		; <float*> [#uses=1]
 	store float %f, float* %tmp.upgrd.2
 	%tmp4 = load <4 x float>* %G		; <<4 x float>> [#uses=2]
-	%tmp6 = add <4 x float> %tmp4, %tmp4		; <<4 x float>> [#uses=1]
+	%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) {
 entry:
 	%G = alloca <4 x float>, align 16		; <<4 x float>*> [#uses=2]
 	%tmp = load <4 x float>* %F		; <<4 x float>> [#uses=2]
-	%tmp3 = add <4 x float> %tmp, %tmp		; <<4 x float>> [#uses=1]
+	%tmp3 = fadd <4 x float> %tmp, %tmp		; <<4 x float>> [#uses=1]
 	store <4 x float> %tmp3, <4 x float>* %G
 	%tmp.upgrd.3 = getelementptr <4 x float>* %G, i32 0, i32 2		; <float*> [#uses=1]
 	%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) {
 entry:
 	%G = alloca <4 x float>, align 16		; <<4 x float>*> [#uses=2]
 	%tmp = load <4 x float>* %F		; <<4 x float>> [#uses=2]
-	%tmp3 = add <4 x float> %tmp, %tmp		; <<4 x float>> [#uses=1]
+	%tmp3 = fadd <4 x float> %tmp, %tmp		; <<4 x float>> [#uses=1]
 	store <4 x float> %tmp3, <4 x float>* %G
 	%G.upgrd.5 = getelementptr <4 x float>* %G, i32 0, i32 0		; <float*> [#uses=1]
 	%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.
@@ -60,5 +81,33 @@ 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
 }
 
+define i64 @test6(<2 x float> %X) {
+	%X_addr = alloca <2 x float>
+        store <2 x float> %X, <2 x float>* %X_addr
+	%P = bitcast <2 x float>* %X_addr to i64*
+	%tmp = load i64* %P
+	ret i64 %tmp
+; CHECK: @test6
+; CHECK: bitcast <2 x float> %X to i64
+; CHECK: ret i64
+}
+
+%struct.test7 = type { [6 x i32] }
+
+define void @test7() {
+entry:
+  %memtmp = alloca %struct.test7, align 16
+  %0 = bitcast %struct.test7* %memtmp to <4 x i32>*
+  store <4 x i32> zeroinitializer, <4 x i32>* %0, align 16
+  %1 = getelementptr inbounds %struct.test7* %memtmp, i64 0, i32 0, i64 5
+  store i32 0, i32* %1, align 4
+  ret void
+; CHECK: @test7
+; CHECK-NOT: alloca
+; CHECK: and i192
+}