When folding a load from a global constant, if the load started in the middle

of an array element (rather than at the beginning of the element) and extended
into the next element, then the load from the second element was being handled
wrong due to incorrect updating of the notion of which byte to load next.  This
fixes PR13442.  Thanks to Chris Smowton for reporting the problem, analyzing it
and providing a fix.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@160711 91177308-0d34-0410-b5e6-96231b3b80d8

2 files changed, 20 insertions, 5 deletions

diff --git a/lib/Analysis/ConstantFolding.cpp b/lib/Analysis/ConstantFolding.cpp
index 7ced848..a7c9e55 100644
--- a/lib/Analysis/ConstantFolding.cpp
+++ b/lib/Analysis/ConstantFolding.cpp
@@ -358,17 +358,20 @@ static bool ReadDataFromGlobal(Constant *C, uint64_t ByteOffset,
       NumElts = AT->getNumElements();
     else
       NumElts = cast<VectorType>(C->getType())->getNumElements();
-    
+
     for (; Index != NumElts; ++Index) {
       if (!ReadDataFromGlobal(C->getAggregateElement(Index), Offset, CurPtr,
                               BytesLeft, TD))
         return false;
-      if (EltSize >= BytesLeft)
+
+      uint64_t BytesWritten = EltSize - Offset;
+      assert(BytesWritten <= EltSize && "Not indexing into this element?");
+      if (BytesWritten >= BytesLeft)
         return true;
-      
+
       Offset = 0;
-      BytesLeft -= EltSize;
-      CurPtr += EltSize;
+      BytesLeft -= BytesWritten;
+      CurPtr += BytesWritten;
     }
     return true;
   }
diff --git a/test/Transforms/InstCombine/2012-07-25-LoadPart.ll b/test/Transforms/InstCombine/2012-07-25-LoadPart.ll
new file mode 100644
index 0000000..01dce7c
--- /dev/null
+++ b/test/Transforms/InstCombine/2012-07-25-LoadPart.ll
@@ -0,0 +1,12 @@
+; RUN: opt < %s -instcombine -S | FileCheck %s
+; PR13442
+
+target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f32:32:32-f64:32:64-v64:64:64-v128:128:128-a0:0:64-f80:32:32-n8:16:32-S128"
+
+@test = constant [4 x i32] [i32 1, i32 2, i32 3, i32 4]
+
+define i64 @foo() {
+  %ret = load i64* bitcast (i8* getelementptr (i8* bitcast ([4 x i32]* @test to i8*), i64 2) to i64*)
+  ret i64 %ret
+  ; CHECK: ret i64 844424930263040
+}