maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

Enable aligned NEON spilling by default. 

Experiments show this to be a small speedup for modern ARM cores.

llvm-svn: 147689
This commit is contained in:
Jakob Stoklund Olesen 2012-01-06 22:19:37 +00:00
parent 632e3b7ee2
commit 68a922c0e9
3 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
llvm/lib/Target/ARM/ARMFrameLowering.cpp
View File

@ -28,7 +28,7 @@
using namespace llvm; using namespace llvm;
cl::opt<bool> cl::opt<bool>
SpillAlignedNEONRegs("align-neon-spills", cl::Hidden, SpillAlignedNEONRegs("align-neon-spills", cl::Hidden, cl::init(true),
cl::desc("Align ARM NEON spills in prolog and epilog")); cl::desc("Align ARM NEON spills in prolog and epilog"));
static MachineBasicBlock::iterator static MachineBasicBlock::iterator

2
llvm/test/CodeGen/ARM/spill-q.ll
View File

@ -11,7 +11,7 @@ declare <4 x float> @llvm.arm.neon.vld1.v4f32(i8*, i32) nounwind readonly
define void @aaa(%quuz* %this, i8* %block) { define void @aaa(%quuz* %this, i8* %block) {
; CHECK: aaa: ; CHECK: aaa:
; CHECK: bic sp, sp, #15 ; CHECK: bic {{.*}}, #15
; CHECK: vst1.64 {{.*}}sp, :128 ; CHECK: vst1.64 {{.*}}sp, :128
; CHECK: vld1.64 {{.*}}sp, :128 ; CHECK: vld1.64 {{.*}}sp, :128
entry: entry:

4
llvm/test/CodeGen/Thumb2/aligned-spill.ll
View File

@ -1,5 +1,5 @@
; RUN: llc < %s -mcpu=cortex-a8 | FileCheck %s ; RUN: llc < %s -mcpu=cortex-a8 -align-neon-spills=0 | FileCheck %s
; RUN: llc < %s -mcpu=cortex-a8 -align-neon-spills | FileCheck %s --check-prefix=NEON ; RUN: llc < %s -mcpu=cortex-a8 -align-neon-spills=1 | FileCheck %s --check-prefix=NEON
target datalayout = "e-p:32:32:32-i1:8:32-i8:8:32-i16:16:32-i32:32:32-i64:32:64-f32:32:32-f64:32:64-v64:32:64-v128:32:128-a0:0:32-n32-S32" target datalayout = "e-p:32:32:32-i1:8:32-i8:8:32-i16:16:32-i32:32:32-i64:32:64-f32:32:32-f64:32:64-v64:32:64-v128:32:128-a0:0:32-n32-S32"
target triple = "thumbv7-apple-ios" target triple = "thumbv7-apple-ios"