Experiments show this to be a small speedup for modern ARM cores.
llvm-svn: 147689
using namespace llvm;
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"));
static MachineBasicBlock::iterator
define void @aaa(%quuz* %this, i8* %block) {
; CHECK: aaa:
-; CHECK: bic sp, sp, #15
+; CHECK: bic {{.*}}, #15
; CHECK: vst1.64 {{.*}}sp, :128
; CHECK: vld1.64 {{.*}}sp, :128
entry:
-; RUN: llc < %s -mcpu=cortex-a8 | 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=0 | FileCheck %s
+; 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 triple = "thumbv7-apple-ios"