maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

Adding simple cast cost to ARM 

Changing ARMBaseTargetMachine to return ARMTargetLowering intead of
the generic one (similar to x86 code).

Tests showing which instructions were added to cast when necessary
or cost zero when not. Downcast to 16 bits are not lowered in NEON,
so costs are not there yet.

llvm-svn: 173849
This commit is contained in:
Renato Golin 2013-01-29 23:31:38 +00:00
parent ae229d599b
commit 5e9d55eca0
3 changed files with 160 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
llvm/lib/Target/ARM/ARMTargetMachine.h
View File

@ -46,6 +46,10 @@ public:
virtual ARMJITInfo *getJITInfo() { return &JITInfo; }
virtual const ARMSubtarget *getSubtargetImpl() const { return &Subtarget; }
virtual const ARMTargetLowering *getTargetLowering() const {
// Implemented by derived classes
llvm_unreachable("getTargetLowering not implemented");
}
virtual const InstrItineraryData *getInstrItineraryData() const {
return &InstrItins;
}

44
llvm/lib/Target/ARM/ARMTargetTransformInfo.cpp
View File

@ -20,6 +20,7 @@
#include "llvm/Analysis/TargetTransformInfo.h"
#include "llvm/Support/Debug.h"
#include "llvm/Target/TargetLowering.h"
#include "llvm/Target/CostTable.h"
using namespace llvm;
// Declare the pass initialization routine locally as target-specific passes
@ -34,18 +35,20 @@ namespace {
class ARMTTI : public ImmutablePass, public TargetTransformInfo {
const ARMBaseTargetMachine *TM;
const ARMSubtarget *ST;
const ARMTargetLowering *TLI;
/// Estimate the overhead of scalarizing an instruction. Insert and Extract
/// are set if the result needs to be inserted and/or extracted from vectors.
unsigned getScalarizationOverhead(Type *Ty, bool Insert, bool Extract) const;
public:
ARMTTI() : ImmutablePass(ID), TM(0), ST(0) {
ARMTTI() : ImmutablePass(ID), TM(0), ST(0), TLI(0) {
llvm_unreachable("This pass cannot be directly constructed");
}
ARMTTI(const ARMBaseTargetMachine *TM)
: ImmutablePass(ID), TM(TM), ST(TM->getSubtargetImpl()) {
: ImmutablePass(ID), TM(TM), ST(TM->getSubtargetImpl()),
TLI(TM->getTargetLowering()) {
initializeARMTTIPass(*PassRegistry::getPassRegistry());
}
@ -111,6 +114,9 @@ public:
return 1;
}
unsigned getCastInstrCost(unsigned Opcode, Type *Dst,
Type *Src) const;
/// @}
};
@ -157,3 +163,37 @@ unsigned ARMTTI::getIntImmCost(const APInt &Imm, Type *Ty) const {
}
return 2;
}
unsigned ARMTTI::getCastInstrCost(unsigned Opcode, Type *Dst,
Type *Src) const {
int ISD = TLI->InstructionOpcodeToISD(Opcode);
assert(ISD && "Invalid opcode");
EVT SrcTy = TLI->getValueType(Src);
EVT DstTy = TLI->getValueType(Dst);
if (!SrcTy.isSimple() || !DstTy.isSimple())
return TargetTransformInfo::getCastInstrCost(Opcode, Dst, Src);
// Some arithmetic, load and store operations have specific instructions
// to cast up/down their types automatically at no extra cost
// TODO: Get these tables to know at least what the related operations are
static const TypeConversionCostTblEntry<MVT> NEONConversionTbl[] = {
{ ISD::SIGN_EXTEND, MVT::v4i32, MVT::v4i16, 0 },
{ ISD::ZERO_EXTEND, MVT::v4i32, MVT::v4i16, 0 },
{ ISD::SIGN_EXTEND, MVT::v2i64, MVT::v2i32, 1 },
{ ISD::ZERO_EXTEND, MVT::v2i64, MVT::v2i32, 1 },
{ ISD::TRUNCATE, MVT::v4i32, MVT::v4i64, 0 },
{ ISD::TRUNCATE, MVT::v4i16, MVT::v4i32, 1 },
};
if (ST->hasNEON()) {
int Idx = ConvertCostTableLookup<MVT>(NEONConversionTbl,
array_lengthof(NEONConversionTbl),
ISD, DstTy.getSimpleVT(), SrcTy.getSimpleVT());
if (Idx != -1)
return NEONConversionTbl[Idx].Cost;
}
return TargetTransformInfo::getCastInstrCost(Opcode, Dst, Src);
}

114
llvm/test/Transforms/LoopVectorize/ARM/mul-cast-vect.ll Normal file
View File

@ -0,0 +1,114 @@
; RUN: opt < %s -cost-model -analyze -mtriple=armv7-linux-gnueabihf -mcpu=cortex-a9 | FileCheck --check-prefix=COST %s
; To see the assembly output: llc -mcpu=cortex-a9 < %s | FileCheck --check-prefix=ASM %s
; ASM lines below are only for reference, tests on that direction should go to tests/CodeGen/ARM
; ModuleID = 'arm.ll'
target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:64:128-a0:0:64-n32-S64"
target triple = "armv7--linux-gnueabihf"
%T216 = type <2 x i16>
%T232 = type <2 x i32>
%T264 = type <2 x i64>
%T416 = type <4 x i16>
%T432 = type <4 x i32>
%T464 = type <4 x i64>
define void @direct(%T432* %loadaddr, %T432* %loadaddr2, %T432* %storeaddr) {
; COST: function 'direct':
%v0 = load %T432* %loadaddr
; ASM: vld1.64
%v1 = load %T432* %loadaddr2
; ASM: vld1.64
%r3 = mul %T432 %v0, %v1
; COST: cost of 2 for instruction: {{.*}} mul <4 x i32>
; ASM: vmul.i32
store %T432 %r3, %T432* %storeaddr
; ASM: vst1.64
ret void
}
define void @ups1632(%T416* %loadaddr, %T416* %loadaddr2, %T432* %storeaddr) {
; COST: function 'ups1632':
%v0 = load %T416* %loadaddr
; ASM: vldr
%v1 = load %T416* %loadaddr2
; ASM: vldr
%r1 = sext %T416 %v0 to %T432
%r2 = sext %T416 %v1 to %T432
; COST: cost of 0 for instruction: {{.*}} sext <4 x i16> {{.*}} to <4 x i32>
%r3 = mul %T432 %r1, %r2
; COST: cost of 2 for instruction: {{.*}} mul <4 x i32>
; ASM: vmull.s16
store %T432 %r3, %T432* %storeaddr
; ASM: vst1.64
ret void
}
define void @upu1632(%T416* %loadaddr, %T416* %loadaddr2, %T432* %storeaddr) {
; COST: function 'upu1632':
%v0 = load %T416* %loadaddr
; ASM: vldr
%v1 = load %T416* %loadaddr2
; ASM: vldr
%r1 = zext %T416 %v0 to %T432
%r2 = zext %T416 %v1 to %T432
; COST: cost of 0 for instruction: {{.*}} zext <4 x i16> {{.*}} to <4 x i32>
%r3 = mul %T432 %r1, %r2
; COST: cost of 2 for instruction: {{.*}} mul <4 x i32>
; ASM: vmull.u16
store %T432 %r3, %T432* %storeaddr
; ASM: vst1.64
ret void
}
define void @ups3264(%T232* %loadaddr, %T232* %loadaddr2, %T264* %storeaddr) {
; COST: function 'ups3264':
%v0 = load %T232* %loadaddr
; ASM: vldr
%v1 = load %T232* %loadaddr2
; ASM: vldr
%r3 = mul %T232 %v0, %v1
; ASM: vmul.i32
; COST: cost of 1 for instruction: {{.*}} mul <2 x i32>
%st = sext %T232 %r3 to %T264
; ASM: vmovl.s32
; COST: cost of 1 for instruction: {{.*}} sext <2 x i32> {{.*}} to <2 x i64>
store %T264 %st, %T264* %storeaddr
; ASM: vst1.64
ret void
}
define void @upu3264(%T232* %loadaddr, %T232* %loadaddr2, %T264* %storeaddr) {
; COST: function 'upu3264':
%v0 = load %T232* %loadaddr
; ASM: vldr
%v1 = load %T232* %loadaddr2
; ASM: vldr
%r3 = mul %T232 %v0, %v1
; ASM: vmul.i32
; COST: cost of 1 for instruction: {{.*}} mul <2 x i32>
%st = zext %T232 %r3 to %T264
; ASM: vmovl.u32
; COST: cost of 1 for instruction: {{.*}} zext <2 x i32> {{.*}} to <2 x i64>
store %T264 %st, %T264* %storeaddr
; ASM: vst1.64
ret void
}
define void @dn3216(%T432* %loadaddr, %T432* %loadaddr2, %T416* %storeaddr) {
; COST: function 'dn3216':
%v0 = load %T432* %loadaddr
; ASM: vld1.64
%v1 = load %T432* %loadaddr2
; ASM: vld1.64
%r3 = mul %T432 %v0, %v1
; ASM: vmul.i32
; COST: cost of 2 for instruction: {{.*}} mul <4 x i32>
%st = trunc %T432 %r3 to %T416
; ASM: vmovn.i32
; COST: cost of 1 for instruction: {{.*}} trunc <4 x i32> {{.*}} to <4 x i16>
store %T416 %st, %T416* %storeaddr
; ASM: vstr
ret void
}