Merging r275866:

------------------------------------------------------------------------
r275866 | tnorthover | 2016-07-18 11:28:52 -0700 (Mon, 18 Jul 2016) | 6 lines

CodeGenPrep: use correct function to determine Global's alignment.

Elsewhere (particularly computeKnownBits) we assume that a global will be
aligned to the value returned by Value::getPointerAlignment. This is used to
boost the alignment on memcpy/memset, so any target-specific request can only
increase that value.
------------------------------------------------------------------------

git-svn-id: https://llvm.org/svn/llvm-project/llvm/branches/release_39@275918 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/CodeGen/CodeGenPrepare.cpp b/lib/CodeGen/CodeGenPrepare.cpp
index d396137fa319e2545c65f837e1f9c3974ef23890..ede404149a1c05d6275dfe830054e4db9918f3d2 100644 (file)
--- a/lib/CodeGen/CodeGenPrepare.cpp
+++ b/lib/CodeGen/CodeGenPrepare.cpp
@@ -1780,7 +1780,7 @@ bool CodeGenPrepare::optimizeCallInst(CallInst *CI, bool& ModifiedDT) {
       // forbidden.
       GlobalVariable *GV;
       if ((GV = dyn_cast<GlobalVariable>(Val)) && GV->canIncreaseAlignment() &&
-          GV->getAlignment() < PrefAlign &&
+          GV->getPointerAlignment(*DL) < PrefAlign &&
           DL->getTypeAllocSize(GV->getValueType()) >=
               MinSize + Offset2)
         GV->setAlignment(PrefAlign);

diff --git a/test/CodeGen/ARM/memfunc.ll b/test/CodeGen/ARM/memfunc.ll
index a47fa4adfa24c4f7f5f1447efb0c9f73c8b49f0d..bc60d8e4f0ecd66c8b24571d1206aac73deec8f3 100644 (file)
--- a/test/CodeGen/ARM/memfunc.ll
+++ b/test/CodeGen/ARM/memfunc.ll
@@ -386,6 +386,8 @@ entry:
 @arr5 = weak global [7 x i8] c"\01\02\03\04\05\06\07", align 1
 @arr6 = weak_odr global [7 x i8] c"\01\02\03\04\05\06\07", align 1
 @arr7 = external global [7 x i8], align 1
+@arr8 = internal global [128 x i8] undef
+@arr9 = weak_odr global [128 x i8] undef
 define void @f9(i8* %dest, i32 %n) {
 entry:
   call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* getelementptr inbounds ([7 x i8], [7 x i8]* @arr1, i32 0, i32 0), i32 %n, i32 1, i1 false)
@@ -395,6 +397,8 @@ entry:
   call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* getelementptr inbounds ([7 x i8], [7 x i8]* @arr5, i32 0, i32 0), i32 %n, i32 1, i1 false)
   call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* getelementptr inbounds ([7 x i8], [7 x i8]* @arr6, i32 0, i32 0), i32 %n, i32 1, i1 false)
   call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* getelementptr inbounds ([7 x i8], [7 x i8]* @arr7, i32 0, i32 0), i32 %n, i32 1, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* getelementptr inbounds ([128 x i8], [128 x i8]* @arr8, i32 0, i32 0), i32 %n, i32 1, i1 false)
+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* getelementptr inbounds ([128 x i8], [128 x i8]* @arr9, i32 0, i32 0), i32 %n, i32 1, i1 false)
 
   unreachable
 }
@@ -417,6 +421,11 @@ entry:
 ; CHECK: arr5:
 ; CHECK-NOT: .p2align
 ; CHECK: arr6:
+; CHECK: .p2align 4
+; CHECK: arr8:
+; CHECK: .p2align 4
+; CHECK: arr9:
+
 ; CHECK-NOT: arr7:
 
 declare void @llvm.memmove.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i32, i1) nounwind