From 08e5f49f90a82ab2aacb2fe096a239625eb17e84 Mon Sep 17 00:00:00 2001
From: Chandler Carruth <chandlerc@gmail.com>
Date: Wed, 3 Oct 2012 08:26:28 +0000
Subject: [PATCH] Fix an issue where we failed to adjust the alignment
 constraint on a memcpy to reflect that '0' has a different meaning when
 applied to a load or store. Now we correctly use underaligned loads and
 stores for the test case added.

llvm-svn: 165101
---
 llvm/lib/Transforms/Scalar/SROA.cpp    |  6 ++++++
 llvm/test/Transforms/SROA/alignment.ll | 31 +++++++++++++++++++++++++++++++
 2 files changed, 37 insertions(+)

diff --git a/llvm/lib/Transforms/Scalar/SROA.cpp b/llvm/lib/Transforms/Scalar/SROA.cpp
index 58bae09..f4fd857 100644
--- a/llvm/lib/Transforms/Scalar/SROA.cpp
+++ b/llvm/lib/Transforms/Scalar/SROA.cpp
@@ -2585,6 +2585,12 @@ private:
       return false;
     }
 
+    // Note that we clamp the alignment to 1 here as a 0 alignment for a memcpy
+    // is equivalent to 1, but that isn't true if we end up rewriting this as
+    // a load or store.
+    if (!Align)
+      Align = 1;
+
     Value *SrcPtr = OtherPtr;
     Value *DstPtr = &NewAI;
     if (!IsDest)
diff --git a/llvm/test/Transforms/SROA/alignment.ll b/llvm/test/Transforms/SROA/alignment.ll
index f8f3270..9fe3bcbb 100644
--- a/llvm/test/Transforms/SROA/alignment.ll
+++ b/llvm/test/Transforms/SROA/alignment.ll
@@ -169,3 +169,34 @@ entry:
 
   ret void
 }
+
+define void @test7(i8* %out) {
+; Test that we properly compute the destination alignment when rewriting
+; memcpys as direct loads or stores.
+; CHECK: @test7
+; CHECK-NOT: alloca
+
+entry:
+  %a = alloca [16 x i8]
+  %raw1 = getelementptr inbounds [16 x i8]* %a, i32 0, i32 0
+  %ptr1 = bitcast i8* %raw1 to double*
+  %raw2 = getelementptr inbounds [16 x i8]* %a, i32 0, i32 8
+  %ptr2 = bitcast i8* %raw2 to double*
+
+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %raw1, i8* %out, i32 16, i32 0, i1 false)
+; CHECK: %[[val2:.*]] = load double* %{{.*}}, align 1
+; CHECK: %[[val1:.*]] = load double* %{{.*}}, align 1
+
+  %val1 = load double* %ptr2, align 1
+  %val2 = load double* %ptr1, align 1
+
+  store double %val1, double* %ptr1, align 1
+  store double %val2, double* %ptr2, align 1
+
+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %out, i8* %raw1, i32 16, i32 0, i1 false)
+; CHECK: store double %[[val1]], double* %{{.*}}, align 1
+; CHECK: store double %[[val2]], double* %{{.*}}, align 1
+
+  ret void
+; CHECK: ret void
+}
-- 
2.7.4