6502/llvm-6502
1
0
Fork 0
mirror of https://github.com/c64scene-ar/llvm-6502.git synced 2024-07-21 18:29:45 +00:00
Code Issues Projects Releases Wiki Activity

[AArch64] Teach AArch64TargetLowering::getOptimalMemOpType to consider alignment

Browse Source 
restrictions when choosing a type for small-memcpy inlining in
SelectionDAGBuilder.

This ensures that the loads and stores output for the memcpy won't be further
expanded during legalization, which would cause the total number of instructions
for the memcpy to exceed (often significantly) the inlining thresholds.

<rdar://problem/17829180>



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@234462 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Lang Hames 2015-04-09 03:40:33 +00:00
parent 23295f613b
commit 174f04eefb
2 changed files with 25 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
lib/Target/AArch64/AArch64ISelLowering.cpp
View File

@ -6664,7 +6664,17 @@ EVT AArch64TargetLowering::getOptimalMemOpType(uint64_t Size, unsigned DstAlign,
(allowsMisalignedMemoryAccesses(MVT::f128, 0, 1, &Fast) && Fast)))
return MVT::f128;
return Size >= 8 ? MVT::i64 : MVT::i32;
if (Size >= 8 &&
(memOpAlign(SrcAlign, DstAlign, 8) ||
(allowsMisalignedMemoryAccesses(MVT::i64, 0, 1, &Fast) && Fast)))
return MVT::i64;
if (Size >= 4 &&
(memOpAlign(SrcAlign, DstAlign, 4) ||
(allowsMisalignedMemoryAccesses(MVT::i32, 0, 1, &Fast) && Fast)))
return MVT::i64;
return MVT::Other;
}
// 12-bit optionally shifted immediates are legal for adds.

14
test/CodeGen/AArch64/arm64-misaligned-memcpy-inline.ll Normal file
View File

@ -0,0 +1,14 @@
; RUN: llc -march=arm64 -aarch64-strict-align < %s | FileCheck %s
; Small (16-bytes here) unaligned memcpys should stay memcpy calls if
; strict-alignment is turned on.
define void @t0(i8* %out, i8* %in) {
; CHECK-LABEL: t0:
; CHECK: orr w2, wzr, #0x10
; CHECK-NEXT: bl _memcpy
entry:
call void @llvm.memcpy.p0i8.p0i8.i64(i8* %out, i8* %in, i64 16, i32 1, i1 false)
ret void
}
declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture readonly, i64, i32, i1)