RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-10-18 18:42:46 +02:00
Code Issues Projects Releases Wiki Activity

[AArch64] Expand bcmp() for small block lengths

Browse Source 
Patch D56593 by @courbet results in calls to `bcmp()` in some cases, should
the target support the it.  Unless `TTI::MemCmpExpansionOptions()`
is overridden by the target.

In a proprietary benchmark we see a performance drop of about 12% on PNG
compression before this patch, though it passes all tests.

This patch mirrors X86 for AArch64 and initializes
`TTI::MemCmpExpansionOptions()` to then expand calls to `bcmp()` when
appropriate.  No tuning of the parameters was performed, but, at this point,
it's enough to recover the performance drop above.

This problem also exists on ARM.  Once a consensus is reached for AArch64, we
can work to fix ARM as well.

Authors:
- Evandro Menezes (@evandro) <e.menezes@samsung.com>
- Brian Rzycki (@brzycki) <b.rzycki@samsung.com>

Differential revision: https://reviews.llvm.org/D64805

llvm-svn: 367898
This commit is contained in:
Evandro Menezes 2019-08-05 18:09:14 +00:00
parent 0492dd709d
commit 66a85dd4d4
4 changed files with 64 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
lib/Target/AArch64/AArch64ISelLowering.cpp
View File

@ -629,6 +629,10 @@ AArch64TargetLowering::AArch64TargetLowering(const TargetMachine &TM,
MaxStoresPerMemmoveOptSize = MaxStoresPerMemmove = 4;
MaxLoadsPerMemcmpOptSize = 4;
MaxLoadsPerMemcmp = Subtarget->requiresStrictAlign()
? MaxLoadsPerMemcmpOptSize : 8;
setStackPointerRegisterToSaveRestore(AArch64::SP);
setSchedulingPreference(Sched::Hybrid);

13
lib/Target/AArch64/AArch64TargetTransformInfo.cpp
View File

@ -618,6 +618,19 @@ int AArch64TTIImpl::getCmpSelInstrCost(unsigned Opcode, Type *ValTy,
return BaseT::getCmpSelInstrCost(Opcode, ValTy, CondTy, I);
}
AArch64TTIImpl::TTI::MemCmpExpansionOptions
AArch64TTIImpl::enableMemCmpExpansion(bool OptSize, bool IsZeroCmp) const {
TTI::MemCmpExpansionOptions Options;
Options.AllowOverlappingLoads = !ST->requiresStrictAlign();
Options.MaxNumLoads = TLI->getMaxExpandSizeMemcmp(OptSize);
Options.NumLoadsPerBlock = Options.MaxNumLoads;
// TODO: Though vector loads usually perform well on AArch64, in some targets
// they may wake up the FP unit, which raises the power consumption. Perhaps
// they could be used with no holds barred (-O3).
Options.LoadSizes = {8, 4, 2, 1};
return Options;
}
int AArch64TTIImpl::getMemoryOpCost(unsigned Opcode, Type *Ty,
unsigned Alignment, unsigned AddressSpace,
const Instruction *I) {

3
lib/Target/AArch64/AArch64TargetTransformInfo.h
View File

@ -130,6 +130,9 @@ public:
int getCmpSelInstrCost(unsigned Opcode, Type *ValTy, Type *CondTy,
const Instruction *I = nullptr);
TTI::MemCmpExpansionOptions enableMemCmpExpansion(bool OptSize,
bool IsZeroCmp) const;
int getMemoryOpCost(unsigned Opcode, Type *Src, unsigned Alignment,
unsigned AddressSpace, const Instruction *I = nullptr);

44
test/CodeGen/AArch64/bcmp-inline-small.ll Normal file
View File

@ -0,0 +1,44 @@
; RUN: llc -O2 < %s -mtriple=aarch64-linux-gnu | FileCheck %s --check-prefixes=CHECK,CHECKN
; RUN: llc -O2 < %s -mtriple=aarch64-linux-gnu -mattr=strict-align | FileCheck %s --check-prefixes=CHECK,CHECKS
declare i32 @bcmp(i8*, i8*, i64) nounwind readonly
declare i32 @memcmp(i8*, i8*, i64) nounwind readonly
define i1 @bcmp_b2(i8* %s1, i8* %s2) {
entry:
%bcmp = call i32 @bcmp(i8* %s1, i8* %s2, i64 15)
%ret = icmp eq i32 %bcmp, 0
ret i1 %ret
; CHECK-LABEL: bcmp_b2:
; CHECK-NOT: bl bcmp
; CHECKN: ldr x
; CHECKN-NEXT: ldr x
; CHECKN-NEXT: ldur x
; CHECKN-NEXT: ldur x
; CHECKS: ldr x
; CHECKS-NEXT: ldr x
; CHECKS-NEXT: ldr w
; CHECKS-NEXT: ldr w
; CHECKS-NEXT: ldrh w
; CHECKS-NEXT: ldrh w
; CHECKS-NEXT: ldrb w
; CHECKS-NEXT: ldrb w
}
define i1 @bcmp_bs(i8* %s1, i8* %s2) optsize {
entry:
%memcmp = call i32 @memcmp(i8* %s1, i8* %s2, i64 31)
%ret = icmp eq i32 %memcmp, 0
ret i1 %ret
; CHECK-LABEL: bcmp_bs:
; CHECKN-NOT: bl memcmp
; CHECKN: ldp x
; CHECKN-NEXT: ldp x
; CHECKN-NEXT: ldr x
; CHECKN-NEXT: ldr x
; CHECKN-NEXT: ldur x
; CHECKN-NEXT: ldur x
; CHECKS: bl memcmp
}