[llvm-commits] [llvm] r165101 - in /llvm/trunk: lib/Transforms/Scalar/SROA.cpp test/Transforms/SROA/alignment.ll

[Chandler Carruth]

Author: chandlerc
Date: Wed Oct  3 03:26:28 2012
New Revision: 165101

URL: http://llvm.org/viewvc/llvm-project?rev=165101&view=rev
Log:
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.

Modified:
    llvm/trunk/lib/Transforms/Scalar/SROA.cpp
    llvm/trunk/test/Transforms/SROA/alignment.ll

Modified: llvm/trunk/lib/Transforms/Scalar/SROA.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Transforms/Scalar/SROA.cpp?rev=165101&r1=165100&r2=165101&view=diff
==============================================================================
--- llvm/trunk/lib/Transforms/Scalar/SROA.cpp (original)
+++ llvm/trunk/lib/Transforms/Scalar/SROA.cpp Wed Oct  3 03:26:28 2012
@@ -2585,6 +2585,12 @@
       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)

Modified: llvm/trunk/test/Transforms/SROA/alignment.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/Transforms/SROA/alignment.ll?rev=165101&r1=165100&r2=165101&view=diff
==============================================================================
--- llvm/trunk/test/Transforms/SROA/alignment.ll (original)
+++ llvm/trunk/test/Transforms/SROA/alignment.ll Wed Oct  3 03:26:28 2012
@@ -169,3 +169,34 @@
 
   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
+}