RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-23 11:13:28 +01:00
Code Issues Projects Releases Wiki Activity

Code size optimisation: do not inline memcpy if this expansion results

Browse Source 
in more instructions than the libary call.

Differential Revision: http://reviews.llvm.org/D20958

llvm-svn: 271678
This commit is contained in:
Sjoerd Meijer 2016-06-03 15:38:55 +00:00
parent 1fa884d6ab
commit 3d4cf26cf6
2 changed files with 39 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
lib/Target/ARM/ARMSelectionDAGInfo.cpp
View File

@ -176,6 +176,12 @@ ARMSelectionDAGInfo::EmitTargetCodeForMemcpy(SelectionDAG &DAG, SDLoc dl,
// emit. // emit.
unsigned NumMEMCPYs = (NumMemOps + MaxLoadsInLDM - 1) / MaxLoadsInLDM; unsigned NumMEMCPYs = (NumMemOps + MaxLoadsInLDM - 1) / MaxLoadsInLDM;
// Code size optimisation: do not inline memcpy if expansion results in
// more instructions than the libary call.
if (NumMEMCPYs > 1 && DAG.getMachineFunction().getFunction()->optForMinSize()) {
return SDValue();
}
SDVTList VTs = DAG.getVTList(MVT::i32, MVT::i32, MVT::Other, MVT::Glue); SDVTList VTs = DAG.getVTList(MVT::i32, MVT::i32, MVT::Other, MVT::Glue);
for (unsigned I = 0; I != NumMEMCPYs; ++I) { for (unsigned I = 0; I != NumMEMCPYs; ++I) {

33
test/CodeGen/ARM/memcpy-no-inline.ll Normal file
View File

@ -0,0 +1,33 @@
; RUN: llc -mtriple=thumbv7m-arm-none-eabi -mcpu=cortex-m3 < %s | FileCheck %s
%struct.mystruct = type { [31 x i8] }
@.str = private unnamed_addr constant [31 x i8] c"012345678901234567890123456789\00", align 1
@.str.1 = private unnamed_addr constant [21 x i8] c"01234567890123456789\00", align 1
@myglobal = common global %struct.mystruct zeroinitializer, align 1
define void @foo() #0 {
entry:
; CHECK-LABEL: foo:
; CHECK: __aeabi_memcpy
; CHECK-NOT: ldm
%mystring = alloca [31 x i8], align 1
%0 = getelementptr inbounds [31 x i8], [31 x i8]* %mystring, i32 0, i32 0
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %0, i8* getelementptr inbounds ([31 x i8], [31 x i8]* @.str, i32 0, i32 0), i32 31, i32 1, i1 false)
ret void
}
define void @bar() #0 {
entry:
; CHECK-LABEL: bar:
; CHECK-NOT: __aeabi_memcpy
%mystring = alloca [31 x i8], align 1
%0 = getelementptr inbounds [31 x i8], [31 x i8]* %mystring, i32 0, i32 0
call void @llvm.memcpy.p0i8.p0i8.i32(i8* %0, i8* getelementptr inbounds ([21 x i8], [21 x i8]* @.str.1, i32 0, i32 0), i32 21, i32 1, i1 false)
ret void
}
declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture readonly, i32, i32, i1) #1
attributes #0 = { minsize noinline nounwind optsize }