1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-10-20 11:33:24 +02:00

[ARM] Inline callee if its target-features are a subset of the caller

Summary:
Similar to X86, it should be safe to inline callees if their
target-features are a subset of the caller. As some subtarget features
provide different instructions depending on whether they are set or
unset (e.g. ThumbMode and ModeSoftFloat), we use a whitelist of
target-features describing hardware capabilities only.

Reviewers: kristof.beyls, rengolin, t.p.northover, SjoerdMeijer, peter.smith, silviu.baranga, efriedma

Reviewed By: SjoerdMeijer, efriedma

Subscribers: dschuff, efriedma, aemerson, sdardis, javed.absar, arichardson, eraman, llvm-commits

Differential Revision: https://reviews.llvm.org/D34697

llvm-svn: 307889
This commit is contained in:
Florian Hahn 2017-07-13 08:26:17 +00:00
parent dcba8216a6
commit 17accd7982
4 changed files with 116 additions and 0 deletions

View File

@ -15,6 +15,24 @@ using namespace llvm;
#define DEBUG_TYPE "armtti"
bool ARMTTIImpl::areInlineCompatible(const Function *Caller,
const Function *Callee) const {
const TargetMachine &TM = getTLI()->getTargetMachine();
const FeatureBitset &CallerBits =
TM.getSubtargetImpl(*Caller)->getFeatureBits();
const FeatureBitset &CalleeBits =
TM.getSubtargetImpl(*Callee)->getFeatureBits();
// To inline a callee, all features not in the whitelist must match exactly.
bool MatchExact = (CallerBits & ~InlineFeatureWhitelist) ==
(CalleeBits & ~InlineFeatureWhitelist);
// For features in the whitelist, the callee's features must be a subset of
// the callers'.
bool MatchSubset = ((CallerBits & CalleeBits) & InlineFeatureWhitelist) ==
(CalleeBits & InlineFeatureWhitelist);
return MatchExact && MatchSubset;
}
int ARMTTIImpl::getIntImmCost(const APInt &Imm, Type *Ty) {
assert(Ty->isIntegerTy());

View File

@ -33,6 +33,39 @@ class ARMTTIImpl : public BasicTTIImplBase<ARMTTIImpl> {
const ARMSubtarget *ST;
const ARMTargetLowering *TLI;
// Currently the following features are excluded from InlineFeatureWhitelist.
// ModeThumb, FeatureNoARM, ModeSoftFloat, FeatureVFPOnlySP, FeatureD16
// Depending on whether they are set or unset, different
// instructions/registers are available. For example, inlining a callee with
// -thumb-mode in a caller with +thumb-mode, may cause the assembler to
// fail if the callee uses ARM only instructions, e.g. in inline asm.
const FeatureBitset InlineFeatureWhitelist = {
ARM::FeatureVFP2, ARM::FeatureVFP3, ARM::FeatureNEON, ARM::FeatureThumb2,
ARM::FeatureFP16, ARM::FeatureVFP4, ARM::FeatureFPARMv8,
ARM::FeatureFullFP16, ARM::FeatureHWDivThumb,
ARM::FeatureHWDivARM, ARM::FeatureDB, ARM::FeatureV7Clrex,
ARM::FeatureAcquireRelease, ARM::FeatureSlowFPBrcc,
ARM::FeaturePerfMon, ARM::FeatureTrustZone, ARM::Feature8MSecExt,
ARM::FeatureCrypto, ARM::FeatureCRC, ARM::FeatureRAS,
ARM::FeatureFPAO, ARM::FeatureFuseAES, ARM::FeatureZCZeroing,
ARM::FeatureProfUnpredicate, ARM::FeatureSlowVGETLNi32,
ARM::FeatureSlowVDUP32, ARM::FeaturePreferVMOVSR,
ARM::FeaturePrefISHSTBarrier, ARM::FeatureMuxedUnits,
ARM::FeatureSlowOddRegister, ARM::FeatureSlowLoadDSubreg,
ARM::FeatureDontWidenVMOVS, ARM::FeatureExpandMLx,
ARM::FeatureHasVMLxHazards, ARM::FeatureNEONForFPMovs,
ARM::FeatureNEONForFP, ARM::FeatureCheckVLDnAlign,
ARM::FeatureHasSlowFPVMLx, ARM::FeatureVMLxForwarding,
ARM::FeaturePref32BitThumb, ARM::FeatureAvoidPartialCPSR,
ARM::FeatureCheapPredicableCPSR, ARM::FeatureAvoidMOVsShOp,
ARM::FeatureHasRetAddrStack, ARM::FeatureHasNoBranchPredictor,
ARM::FeatureDSP, ARM::FeatureMP, ARM::FeatureVirtualization,
ARM::FeatureMClass, ARM::FeatureRClass, ARM::FeatureAClass,
ARM::FeatureNaClTrap, ARM::FeatureStrictAlign, ARM::FeatureLongCalls,
ARM::FeatureExecuteOnly, ARM::FeatureReserveR9, ARM::FeatureNoMovt,
ARM::FeatureNoNegativeImmediates
};
const ARMSubtarget *getST() const { return ST; }
const ARMTargetLowering *getTLI() const { return TLI; }
@ -41,6 +74,9 @@ public:
: BaseT(TM, F.getParent()->getDataLayout()), ST(TM->getSubtargetImpl(F)),
TLI(ST->getTargetLowering()) {}
bool areInlineCompatible(const Function *Caller,
const Function *Callee) const;
bool enableInterleavedAccessVectorization() { return true; }
/// Floating-point computation using ARMv8 AArch32 Advanced

View File

@ -0,0 +1,60 @@
; RUN: opt < %s -mtriple=arm-unknown-linux-gnu -S -inline | FileCheck %s
; RUN: opt < %s -mtriple=arm-unknown-linux-gnu -S -passes='cgscc(inline)' | FileCheck %s
; Check that we only inline when we have compatible target attributes.
; ARM has implemented a target attribute that will verify that the attribute
; sets are compatible.
define i32 @foo() #0 {
entry:
%call = call i32 (...) @baz()
ret i32 %call
; CHECK-LABEL: foo
; CHECK: call i32 (...) @baz()
}
declare i32 @baz(...) #0
define i32 @bar() #1 {
entry:
%call = call i32 @foo()
ret i32 %call
; CHECK-LABEL: bar
; CHECK: call i32 (...) @baz()
}
define i32 @qux() #0 {
entry:
%call = call i32 @bar()
ret i32 %call
; CHECK-LABEL: qux
; CHECK: call i32 @bar()
}
define i32 @thumb_fn() #2 {
entry:
%call = call i32 @foo()
ret i32 %call
; CHECK-LABEL: thumb_fn
; CHECK: call i32 @foo
}
define i32 @strict_align() #3 {
entry:
%call = call i32 @foo()
ret i32 %call
; CHECK-LABEL: strict_align
; CHECK: call i32 (...) @baz()
}
define i32 @soft_float_fn() #4 {
entry:
%call = call i32 @foo()
ret i32 %call
; CHECK-LABEL: thumb_fn
; CHECK: call i32 @foo
}
attributes #0 = { "target-cpu"="generic" "target-features"="+dsp,+neon" }
attributes #1 = { "target-cpu"="generic" "target-features"="+dsp,+neon,+fp16" }
attributes #2 = { "target-cpu"="generic" "target-features"="+dsp,+neon,+fp16,+thumb-mode" }
attributes #3 = { "target-cpu"="generic" "target-features"="+dsp,+neon,+strict-align" }
attributes #4 = { "target-cpu"="generic" "target-features"="+dsp,+neon,+fp16,+soft-float" }

View File

@ -0,0 +1,2 @@
if not 'ARM' in config.root.targets:
config.unsupported = True