fix a small oversight in the "eliminate memcpy from constant global"

optimization.  If the alloca that is "memcpy'd from constant" also has
a memcpy from *it*, ignore it: it is a load.  We now optimize the testcase to:

define void @test2() {
  %B = alloca %T
  %a = bitcast %T* @G to i8*
  %b = bitcast %T* %B to i8*
  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %b, i8* %a, i64 124, i32 4, i1 false)
  call void @bar(i8* %b)
  ret void
}

previously we would generate:

define void @test() {
  %B = alloca %T
  %b = bitcast %T* %B to i8*
  %G.0 = getelementptr inbounds %T* @G, i32 0, i32 0
  %tmp3 = load i8* %G.0, align 4
  %G.1 = getelementptr inbounds %T* @G, i32 0, i32 1
  %G.15 = bitcast [123 x i8]* %G.1 to i8*
  %1 = bitcast [123 x i8]* %G.1 to i984*
  %srcval = load i984* %1, align 1
  %B.0 = getelementptr inbounds %T* %B, i32 0, i32 0
  store i8 %tmp3, i8* %B.0, align 4
  %B.1 = getelementptr inbounds %T* %B, i32 0, i32 1
  %B.12 = bitcast [123 x i8]* %B.1 to i8*
  %2 = bitcast [123 x i8]* %B.1 to i984*
  store i984 %srcval, i984* %2, align 1
  call void @bar(i8* %b)
  ret void
}

llvm-svn: 119682

1 files changed, 29 insertions, 0 deletions

diff --git a/llvm/test/Transforms/ScalarRepl/memcpy-from-global.ll b/llvm/test/Transforms/ScalarRepl/memcpy-from-global.ll
index 592bf328d4b..e807177357b 100644
--- a/llvm/test/Transforms/ScalarRepl/memcpy-from-global.ll
+++ b/llvm/test/Transforms/ScalarRepl/memcpy-from-global.ll
@@ -39,3 +39,32 @@ entry:
 }
 
 declare void @llvm.memcpy.i32(i8*, i8*, i32, i32)
+
+
+
+declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i32, i1) nounwind
+
+%T = type { i8, [123 x i8] }
+
+@G = constant %T {i8 1, [123 x i8] zeroinitializer }
+
+define void @test2() {
+  %A = alloca %T
+  %B = alloca %T
+  %a = bitcast %T* %A to i8*
+  %b = bitcast %T* %B to i8*
+
+; CHECK: @test2
+
+; %A alloca is deleted
+; CHECK-NEXT: %B = alloca %T
+
+; use @G instead of %A
+; CHECK-NEXT: %a = bitcast %T* @G to i8*
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %a, i8* bitcast (%T* @G to i8*), i64 124, i32 4, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %b, i8* %a, i64 124, i32 4, i1 false)
+  call void @bar(i8* %b)
+  ret void
+}
+
+declare void @bar(i8*)