llvm-6502/test/CodeGen/ARM/memset-inline.ll
Evan Cheng 376642ed62 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


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@169791 91177308-0d34-0410-b5e6-96231b3b80d8
2012-12-10 23:21:26 +00:00

31 lines
998 B
LLVM

; RUN: llc < %s -mtriple=thumbv7-apple-ios -mcpu=cortex-a8 -pre-RA-sched=source -disable-post-ra | FileCheck %s
define void @t1(i8* nocapture %c) nounwind optsize {
entry:
; CHECK: t1:
; CHECK: movs r1, #0
; CHECK: str r1, [r0]
; CHECK: str r1, [r0, #4]
; CHECK: str r1, [r0, #8]
call void @llvm.memset.p0i8.i64(i8* %c, i8 0, i64 12, i32 8, i1 false)
ret void
}
define void @t2() nounwind ssp {
entry:
; CHECK: t2:
; CHECK: add.w r1, r0, #10
; CHECK: vmov.i32 {{q[0-9]+}}, #0x0
; CHECK: vst1.16 {d{{[0-9]+}}, d{{[0-9]+}}}, [r1]
; CHECK: vst1.32 {d{{[0-9]+}}, d{{[0-9]+}}}, [r0]
%buf = alloca [26 x i8], align 1
%0 = getelementptr inbounds [26 x i8]* %buf, i32 0, i32 0
call void @llvm.memset.p0i8.i32(i8* %0, i8 0, i32 26, i32 1, i1 false)
call void @something(i8* %0) nounwind
ret void
}
declare void @something(i8*) nounwind
declare void @llvm.memset.p0i8.i32(i8* nocapture, i8, i32, i32, i1) nounwind
declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i32, i1) nounwind