From: Chandler Carruth <chandlerc@gmail.com>
Date: Sun, 7 Apr 2013 11:47:54 +0000 (+0000)
Subject: Fix PR15674 (and PR15603): a SROA think-o.
X-Git-Tag: android-x86-6.0-r1~154^2~752
X-Git-Url: http://git.osdn.net/view?a=commitdiff_plain;h=05c7e7f99dfa1ff353c3d13e71143b61baa583f6;p=android-x86%2Fexternal-llvm.git

Fix PR15674 (and PR15603): a SROA think-o.

The fix for PR14972 in r177055 introduced a real think-o in the *store*
side, likely because I was much more focused on the load side. While we
can arbitrarily widen (or narrow) a loaded value, we can't arbitrarily
widen a value to be stored, as that changes the width of memory access!
Lock down the code path in the store rewriting which would do this to
only handle the intended circumstance.

All of the existing tests continue to pass, and I've added a test from
the PR.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@178974 91177308-0d34-0410-b5e6-96231b3b80d8
---

diff --git a/lib/Transforms/Scalar/SROA.cpp b/lib/Transforms/Scalar/SROA.cpp
index f6bb365216f..1e18873950d 100644
--- a/lib/Transforms/Scalar/SROA.cpp
+++ b/lib/Transforms/Scalar/SROA.cpp
@@ -2671,6 +2671,7 @@ private:
 
     StoreInst *NewSI;
     if (BeginOffset == NewAllocaBeginOffset &&
+        EndOffset == NewAllocaEndOffset &&
         canConvertValue(TD, V->getType(), NewAllocaTy)) {
       V = convertValue(TD, IRB, V, NewAllocaTy);
       NewSI = IRB.CreateAlignedStore(V, &NewAI, NewAI.getAlignment(),
diff --git a/test/Transforms/SROA/basictest.ll b/test/Transforms/SROA/basictest.ll
index 30dd2177434..6078adead03 100644
--- a/test/Transforms/SROA/basictest.ll
+++ b/test/Transforms/SROA/basictest.ll
@@ -1243,3 +1243,66 @@ entry:
   %v = load i32* %a
   ret i32 %v
 }
+
+define void @PR15674(i8* %data, i8* %src, i32 %size) {
+; Arrange (via control flow) to have unmerged stores of a particular width to
+; an alloca where we incrementally store from the end of the array toward the
+; beginning of the array. Ensure that the final integer store, despite being
+; convertable to the integer type that we end up promoting this alloca toward,
+; doesn't get widened to a full alloca store.
+; CHECK: @PR15674
+
+entry:
+  %tmp = alloca [4 x i8], align 1
+; CHECK: alloca i32
+
+  switch i32 %size, label %end [
+    i32 4, label %bb4
+    i32 3, label %bb3
+    i32 2, label %bb2
+    i32 1, label %bb1
+  ]
+
+bb4:
+  %src.gep3 = getelementptr inbounds i8* %src, i32 3
+  %src.3 = load i8* %src.gep3
+  %tmp.gep3 = getelementptr inbounds [4 x i8]* %tmp, i32 0, i32 3
+  store i8 %src.3, i8* %tmp.gep3
+; CHECK: store i8
+
+  br label %bb3
+
+bb3:
+  %src.gep2 = getelementptr inbounds i8* %src, i32 2
+  %src.2 = load i8* %src.gep2
+  %tmp.gep2 = getelementptr inbounds [4 x i8]* %tmp, i32 0, i32 2
+  store i8 %src.2, i8* %tmp.gep2
+; CHECK: store i8
+
+  br label %bb2
+
+bb2:
+  %src.gep1 = getelementptr inbounds i8* %src, i32 1
+  %src.1 = load i8* %src.gep1
+  %tmp.gep1 = getelementptr inbounds [4 x i8]* %tmp, i32 0, i32 1
+  store i8 %src.1, i8* %tmp.gep1
+; CHECK: store i8
+
+  br label %bb1
+
+bb1:
+  %src.gep0 = getelementptr inbounds i8* %src, i32 0
+  %src.0 = load i8* %src.gep0
+  %tmp.gep0 = getelementptr inbounds [4 x i8]* %tmp, i32 0, i32 0
+  store i8 %src.0, i8* %tmp.gep0
+; CHECK: store i8
+
+  br label %end
+
+end:
+  %tmp.raw = bitcast [4 x i8]* %tmp to i8*
+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %data, i8* %tmp.raw, i32 %size, i32 1, i1 false)
+  ret void
+; CHECK: ret void
+}
+