///
//===----------------------------------------------------------------------===//
-#define DEBUG_TYPE "basictti"
#include "llvm/CodeGen/Passes.h"
+#include "llvm/Analysis/LoopInfo.h"
#include "llvm/Analysis/TargetTransformInfo.h"
+#include "llvm/Support/CommandLine.h"
#include "llvm/Target/TargetLowering.h"
+#include "llvm/Target/TargetSubtargetInfo.h"
#include <utility>
-
using namespace llvm;
+static cl::opt<unsigned>
+PartialUnrollingThreshold("partial-unrolling-threshold", cl::init(0),
+ cl::desc("Threshold for partial unrolling"), cl::Hidden);
+
+#define DEBUG_TYPE "basictti"
+
namespace {
class BasicTTI final : public ImmutablePass, public TargetTransformInfo {
/// are set if the result needs to be inserted and/or extracted from vectors.
unsigned getScalarizationOverhead(Type *Ty, bool Insert, bool Extract) const;
+ /// Estimate the cost overhead of SK_Alternate shuffle.
+ unsigned getAltShuffleOverhead(Type *Ty) const;
+
const TargetLoweringBase *getTLI() const { return TM->getTargetLowering(); }
public:
- BasicTTI() : ImmutablePass(ID), TM(0) {
+ BasicTTI() : ImmutablePass(ID), TM(nullptr) {
llvm_unreachable("This pass cannot be directly constructed");
}
return TLI->isTypeLegal(VT) && TLI->isOperationLegalOrCustom(ISD::FSQRT, VT);
}
-void BasicTTI::getUnrollingPreferences(Loop *, UnrollingPreferences &) const { }
+void BasicTTI::getUnrollingPreferences(Loop *L,
+ UnrollingPreferences &UP) const {
+ // This unrolling functionality is target independent, but to provide some
+ // motivation for its intended use, for x86:
+
+ // According to the Intel 64 and IA-32 Architectures Optimization Reference
+ // Manual, Intel Core models and later have a loop stream detector
+ // (and associated uop queue) that can benefit from partial unrolling.
+ // The relevant requirements are:
+ // - The loop must have no more than 4 (8 for Nehalem and later) branches
+ // taken, and none of them may be calls.
+ // - The loop can have no more than 18 (28 for Nehalem and later) uops.
+
+ // According to the Software Optimization Guide for AMD Family 15h Processors,
+ // models 30h-4fh (Steamroller and later) have a loop predictor and loop
+ // buffer which can benefit from partial unrolling.
+ // The relevant requirements are:
+ // - The loop must have fewer than 16 branches
+ // - The loop must have less than 40 uops in all executed loop branches
+
+ // The number of taken branches in a loop is hard to estimate here, and
+ // benchmarking has revealed that it is better not to be conservative when
+ // estimating the branch count. As a result, we'll ignore the branch limits
+ // until someone finds a case where it matters in practice.
+
+ unsigned MaxOps;
+ const TargetSubtargetInfo *ST = &TM->getSubtarget<TargetSubtargetInfo>();
+ if (PartialUnrollingThreshold.getNumOccurrences() > 0)
+ MaxOps = PartialUnrollingThreshold;
+ else if (ST->getSchedModel()->LoopMicroOpBufferSize > 0)
+ MaxOps = ST->getSchedModel()->LoopMicroOpBufferSize;
+ else
+ return;
+
+ // Scan the loop: don't unroll loops with calls.
+ for (Loop::block_iterator I = L->block_begin(), E = L->block_end();
+ I != E; ++I) {
+ BasicBlock *BB = *I;
+
+ for (BasicBlock::iterator J = BB->begin(), JE = BB->end(); J != JE; ++J)
+ if (isa<CallInst>(J) || isa<InvokeInst>(J)) {
+ ImmutableCallSite CS(J);
+ if (const Function *F = CS.getCalledFunction()) {
+ if (!TopTTI->isLoweredToCall(F))
+ continue;
+ }
+
+ return;
+ }
+ }
+
+ // Enable runtime and partial unrolling up to the specified size.
+ UP.Partial = UP.Runtime = true;
+ UP.PartialThreshold = UP.PartialOptSizeThreshold = MaxOps;
+}
//===----------------------------------------------------------------------===//
//
return OpCost;
}
+unsigned BasicTTI::getAltShuffleOverhead(Type *Ty) const {
+ assert(Ty->isVectorTy() && "Can only shuffle vectors");
+ unsigned Cost = 0;
+ // Shuffle cost is equal to the cost of extracting element from its argument
+ // plus the cost of inserting them onto the result vector.
+
+ // e.g. <4 x float> has a mask of <0,5,2,7> i.e we need to extract from index
+ // 0 of first vector, index 1 of second vector,index 2 of first vector and
+ // finally index 3 of second vector and insert them at index <0,1,2,3> of
+ // result vector.
+ for (int i = 0, e = Ty->getVectorNumElements(); i < e; ++i) {
+ Cost += TopTTI->getVectorInstrCost(Instruction::InsertElement, Ty, i);
+ Cost += TopTTI->getVectorInstrCost(Instruction::ExtractElement, Ty, i);
+ }
+ return Cost;
+}
+
unsigned BasicTTI::getShuffleCost(ShuffleKind Kind, Type *Tp, int Index,
Type *SubTp) const {
+ if (Kind == SK_Alternate) {
+ return getAltShuffleOverhead(Tp);
+ }
return 1;
}
return 0;
// If the cast is marked as legal (or promote) then assume low cost.
- if (TLI->isOperationLegalOrPromote(ISD, DstLT.second))
+ if (SrcLT.first == DstLT.first &&
+ TLI->isOperationLegalOrPromote(ISD, DstLT.second))
return 1;
// Handle scalar conversions.
unsigned BasicTTI::getVectorInstrCost(unsigned Opcode, Type *Val,
unsigned Index) const {
- return 1;
+ std::pair<unsigned, MVT> LT = getTLI()->getTypeLegalizationCost(Val->getScalarType());
+
+ return LT.first;
}
unsigned BasicTTI::getMemoryOpCost(unsigned Opcode, Type *Src,
assert(!Src->isVoidTy() && "Invalid type");
std::pair<unsigned, MVT> LT = getTLI()->getTypeLegalizationCost(Src);
- // Assume that all loads of legal types cost 1.
- return LT.first;
+ // Assuming that all loads of legal types cost 1.
+ unsigned Cost = LT.first;
+
+ if (Src->isVectorTy() &&
+ Src->getPrimitiveSizeInBits() < LT.second.getSizeInBits()) {
+ // This is a vector load that legalizes to a larger type than the vector
+ // itself. Unless the corresponding extending load or truncating store is
+ // legal, then this will scalarize.
+ TargetLowering::LegalizeAction LA = TargetLowering::Expand;
+ EVT MemVT = getTLI()->getValueType(Src, true);
+ if (MemVT.isSimple() && MemVT != MVT::Other) {
+ if (Opcode == Instruction::Store)
+ LA = getTLI()->getTruncStoreAction(LT.second, MemVT.getSimpleVT());
+ else
+ LA = getTLI()->getLoadExtAction(ISD::EXTLOAD, MemVT.getSimpleVT());
+ }
+
+ if (LA != TargetLowering::Legal && LA != TargetLowering::Custom) {
+ // This is a vector load/store for some illegal type that is scalarized.
+ // We must account for the cost of building or decomposing the vector.
+ Cost += getScalarizationOverhead(Src, Opcode != Instruction::Store,
+ Opcode == Instruction::Store);
+ }
+ }
+
+ return Cost;
}
unsigned BasicTTI::getIntrinsicInstrCost(Intrinsic::ID IID, Type *RetTy,
case Intrinsic::round: ISD = ISD::FROUND; break;
case Intrinsic::pow: ISD = ISD::FPOW; break;
case Intrinsic::fma: ISD = ISD::FMA; break;
- case Intrinsic::fmuladd: ISD = ISD::FMA; break; // FIXME: mul + add?
+ case Intrinsic::fmuladd: ISD = ISD::FMA; break;
case Intrinsic::lifetime_start:
case Intrinsic::lifetime_end:
return 0;
return LT.first * 2;
}
+ // If we can't lower fmuladd into an FMA estimate the cost as a floating
+ // point mul followed by an add.
+ if (IID == Intrinsic::fmuladd)
+ return TopTTI->getArithmeticInstrCost(BinaryOperator::FMul, RetTy) +
+ TopTTI->getArithmeticInstrCost(BinaryOperator::FAdd, RetTy);
+
// Else, assume that we need to scalarize this intrinsic. For math builtins
// this will emit a costly libcall, adding call overhead and spills. Make it
// very expensive.
projects / oota-llvm.git / blobdiff