RPCS3/llvm
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm.git synced 2025-02-14 15:57:47 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

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

Browse Source 
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/trunk@275866 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Tim Northover 2016-07-18 18:28:52 +00:00
parent ee8657416e
commit d7c16ef558
2 changed files with 10 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
lib/CodeGen/CodeGenPrepare.cpp
View File

@ -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);

9
test/CodeGen/ARM/memfunc.ll
View File

@ -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