RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-26 12:43:36 +01:00
Code Issues Projects Releases Wiki Activity

[SDAG] Use ABI type alignment for constant pools when optimizing for size

Browse Source 
SelectionDAG::getConstantPool will automatically determine an appropriate alignment if one is not specified. It does this by querying the type's preferred alignment. This can end up creating quite a lot of padding when the preferred alignment for vectors is 128.

In optimize-for-size mode, it makes sense to instead query the ABI type alignment which is often smaller and causes less padding.

llvm-svn: 284381
This commit is contained in:
James Molloy 2016-10-17 12:54:07 +00:00
parent f39706c65a
commit c6be02fbf0
2 changed files with 22 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
lib/CodeGen/SelectionDAG/SelectionDAG.cpp
View File

@ -1315,7 +1315,9 @@ SDValue SelectionDAG::getConstantPool(const Constant *C, EVT VT,
assert((TargetFlags == 0 || isTarget) &&
"Cannot set target flags on target-independent globals");
if (Alignment == 0)
Alignment = getDataLayout().getPrefTypeAlignment(C->getType());
Alignment = MF->getFunction()->optForSize()
? getDataLayout().getABITypeAlignment(C->getType())
: getDataLayout().getPrefTypeAlignment(C->getType());
unsigned Opc = isTarget ? ISD::TargetConstantPool : ISD::ConstantPool;
FoldingSetNodeID ID;
AddNodeIDNode(ID, Opc, getVTList(VT), None);

19
test/CodeGen/ARM/constantpool-align.ll Normal file
View File

@ -0,0 +1,19 @@
; RUN: llc < %s | FileCheck %s
target datalayout = "e-m:e-p:32:32-i64:64-v128:64:128-a:0:32-n32-S64"
target triple = "thumbv7-arm-none-eabi"
; CHECK-LABEL: f:
; CHECK: vld1.64 {{.*}}, [r1:128]
; CHECK: .p2align 4
define void @f(<4 x i32>* %p) {
store <4 x i32> <i32 -1, i32 0, i32 0, i32 -1>, <4 x i32>* %p, align 4
ret void
}
; CHECK-LABEL: f_optsize:
; CHECK: vld1.64 {{.*}}, [r1]
; CHECK: .p2align 3
define void @f_optsize(<4 x i32>* %p) optsize {
store <4 x i32> <i32 -1, i32 0, i32 0, i32 -1>, <4 x i32>* %p, align 4
ret void
}