1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-25 04:02:41 +01:00
llvm-mirror/test/CodeGen/ARM/2011-10-26-memset-with-neon.ll
Evan Cheng 86dd733bc8 Some enhancements for memcpy / memset inline expansion.
1. Teach it to use overlapping unaligned load / store to copy / set the trailing
   bytes. e.g. On 86, use two pairs of movups / movaps for 17 - 31 byte copies.
2. Use f64 for memcpy / memset on targets where i64 is not legal but f64 is. e.g.
   x86 and ARM.
3. When memcpy from a constant string, do *not* replace the load with a constant
   if it's not possible to materialize an integer immediate with a single
   instruction (required a new target hook: TLI.isIntImmLegal()).
4. Use unaligned load / stores more aggressively if target hooks indicates they
   are "fast".
5. Update ARM target hooks to use unaligned load / stores. e.g. vld1.8 / vst1.8.
   Also increase the threshold to something reasonable (8 for memset, 4 pairs
   for memcpy).

This significantly improves Dhrystone, up to 50% on ARM iOS devices.

rdar://12760078

llvm-svn: 169791
2012-12-10 23:21:26 +00:00

13 lines
364 B
LLVM

; RUN: llc -march=arm -mcpu=cortex-a8 < %s | FileCheck %s
; Trigger multiple NEON stores.
; CHECK: vst1.64
; CHECK-NEXT: vst1.64
define void @f_0_40(i8* nocapture %c) nounwind optsize {
entry:
call void @llvm.memset.p0i8.i64(i8* %c, i8 0, i64 40, i32 16, i1 false)
ret void
}
declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i32, i1) nounwind