RPCS3/llvm
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm.git synced 2025-02-01 08:12:12 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

The alignment of the pointer part of the store instruction may have an

Browse Source 
alignment. If that's the case, then we want to make sure that we don't increase
the alignment of the store instruction. Because if we increase it to be "more
aligned" than the pointer, code-gen may use instructions which require a greater
alignment than the pointer guarantees.
<rdar://problem/11043589>


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@152907 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Bill Wendling 2012-03-16 07:40:08 +00:00
parent 5a4c790c06
commit ff030fd300
2 changed files with 27 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
lib/Transforms/InstCombine/InstCombineLoadStoreAlloca.cpp
View File

@ -379,10 +379,22 @@ Instruction *InstCombiner::visitStoreInst(StoreInst &SI) {
unsigned EffectiveStoreAlign = StoreAlign != 0 ? StoreAlign :
TD->getABITypeAlignment(Val->getType());
if (KnownAlign > EffectiveStoreAlign)
if (KnownAlign > EffectiveStoreAlign) {
SI.setAlignment(KnownAlign);
else if (StoreAlign == 0)
SI.setAlignment(EffectiveStoreAlign);
} else if (StoreAlign == 0) {
unsigned PtrAlign = 0;
if (GlobalValue *GV = dyn_cast<GlobalValue>(Ptr->stripPointerCasts()))
PtrAlign = GV->getAlignment();
if (PtrAlign != 0 && PtrAlign < EffectiveStoreAlign)
// The pointer alignment may be less than the effective store
// alignment. If so, then we don't want to increase the alignment here,
// since that could lead to code-gen using instructions which require a
// higher alignment than the pointer guarantees.
SI.setAlignment(PtrAlign);
else
SI.setAlignment(EffectiveStoreAlign);
}
}
// Don't hack volatile/atomic stores.

12
test/Transforms/InstCombine/2012-03-16-StoreAlignment.ll Normal file
View File

@ -0,0 +1,12 @@
; RUN: opt < %s -S -instcombine | FileCheck %s
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
%0 = type { i32, i8, i8, i8 }
@G = external hidden global %0, align 4
define void @f1(i64 %a1) nounwind ssp align 2 {
; CHECK: store i64 %a1, i64* bitcast (%0* @G to i64*), align 4
store i64 %a1, i64* bitcast (%0* @G to i64*)
ret void
}