llvm-6502/include/llvm/Analysis/InlineCost.h

144 lines
4.8 KiB
C
Raw Normal View History

//===- InlineCost.h - Cost analysis for inliner -----------------*- C++ -*-===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This file implements heuristics for inlining decisions.
//
//===----------------------------------------------------------------------===//
#ifndef LLVM_ANALYSIS_INLINECOST_H
#define LLVM_ANALYSIS_INLINECOST_H
#include "llvm/Analysis/CodeMetrics.h"
#include "llvm/Analysis/CallGraphSCCPass.h"
#include <cassert>
#include <climits>
namespace llvm {
class CallSite;
class DataLayout;
class Function;
class TargetTransformInfo;
namespace InlineConstants {
// Various magic constants used to adjust heuristics.
const int InstrCost = 5;
const int IndirectCallThreshold = 100;
const int CallPenalty = 25;
const int LastCallToStaticBonus = -15000;
const int ColdccPenalty = 2000;
const int NoreturnPenalty = 10000;
/// Do not inline functions which allocate this many bytes on the stack
/// when the caller is recursive.
const unsigned TotalAllocaSizeRecursiveCaller = 1024;
}
/// \brief Represents the cost of inlining a function.
///
/// This supports special values for functions which should "always" or
/// "never" be inlined. Otherwise, the cost represents a unitless amount;
/// smaller values increase the likelihood of the function being inlined.
///
/// Objects of this type also provide the adjusted threshold for inlining
/// based on the information available for a particular callsite. They can be
/// directly tested to determine if inlining should occur given the cost and
/// threshold for this cost metric.
class InlineCost {
enum SentinelValues {
AlwaysInlineCost = INT_MIN,
NeverInlineCost = INT_MAX
};
/// \brief The estimated cost of inlining this callsite.
const int Cost;
/// \brief The adjusted threshold against which this cost was computed.
const int Threshold;
// Trivial constructor, interesting logic in the factory functions below.
InlineCost(int Cost, int Threshold) : Cost(Cost), Threshold(Threshold) {}
public:
static InlineCost get(int Cost, int Threshold) {
assert(Cost > AlwaysInlineCost && "Cost crosses sentinel value");
assert(Cost < NeverInlineCost && "Cost crosses sentinel value");
return InlineCost(Cost, Threshold);
}
static InlineCost getAlways() {
return InlineCost(AlwaysInlineCost, 0);
}
static InlineCost getNever() {
return InlineCost(NeverInlineCost, 0);
}
/// \brief Test whether the inline cost is low enough for inlining.
operator bool() const {
return Cost < Threshold;
}
bool isAlways() const { return Cost == AlwaysInlineCost; }
bool isNever() const { return Cost == NeverInlineCost; }
bool isVariable() const { return !isAlways() && !isNever(); }
/// \brief Get the inline cost estimate.
/// It is an error to call this on an "always" or "never" InlineCost.
int getCost() const {
assert(isVariable() && "Invalid access of InlineCost");
return Cost;
}
/// \brief Get the cost delta from the threshold for inlining.
/// Only valid if the cost is of the variable kind. Returns a negative
/// value if the cost is too high to inline.
int getCostDelta() const { return Threshold - getCost(); }
};
/// \brief Cost analyzer used by inliner.
class InlineCostAnalysis : public CallGraphSCCPass {
const DataLayout *TD;
const TargetTransformInfo *TTI;
public:
static char ID;
InlineCostAnalysis();
~InlineCostAnalysis();
// Pass interface implementation.
void getAnalysisUsage(AnalysisUsage &AU) const;
bool runOnSCC(CallGraphSCC &SCC);
/// \brief Get an InlineCost object representing the cost of inlining this
/// callsite.
Initial commit for the rewrite of the inline cost analysis to operate on a per-callsite walk of the called function's instructions, in breadth-first order over the potentially reachable set of basic blocks. This is a major shift in how inline cost analysis works to improve the accuracy and rationality of inlining decisions. A brief outline of the algorithm this moves to: - Build a simplification mapping based on the callsite arguments to the function arguments. - Push the entry block onto a worklist of potentially-live basic blocks. - Pop the first block off of the *front* of the worklist (for breadth-first ordering) and walk its instructions using a custom InstVisitor. - For each instruction's operands, re-map them based on the simplification mappings available for the given callsite. - Compute any simplification possible of the instruction after re-mapping, and store that back int othe simplification mapping. - Compute any bonuses, costs, or other impacts of the instruction on the cost metric. - When the terminator is reached, replace any conditional value in the terminator with any simplifications from the mapping we have, and add any successors which are not proven to be dead from these simplifications to the worklist. - Pop the next block off of the front of the worklist, and repeat. - As soon as the cost of inlining exceeds the threshold for the callsite, stop analyzing the function in order to bound cost. The primary goal of this algorithm is to perfectly handle dead code paths. We do not want any code in trivially dead code paths to impact inlining decisions. The previous metric was *extremely* flawed here, and would always subtract the average cost of two successors of a conditional branch when it was proven to become an unconditional branch at the callsite. There was no handling of wildly different costs between the two successors, which would cause inlining when the path actually taken was too large, and no inlining when the path actually taken was trivially simple. There was also no handling of the code *path*, only the immediate successors. These problems vanish completely now. See the added regression tests for the shiny new features -- we skip recursive function calls, SROA-killing instructions, and high cost complex CFG structures when dead at the callsite being analyzed. Switching to this algorithm required refactoring the inline cost interface to accept the actual threshold rather than simply returning a single cost. The resulting interface is pretty bad, and I'm planning to do lots of interface cleanup after this patch. Several other refactorings fell out of this, but I've tried to minimize them for this patch. =/ There is still more cleanup that can be done here. Please point out anything that you see in review. I've worked really hard to try to mirror at least the spirit of all of the previous heuristics in the new model. It's not clear that they are all correct any more, but I wanted to minimize the change in this single patch, it's already a bit ridiculous. One heuristic that is *not* yet mirrored is to allow inlining of functions with a dynamic alloca *if* the caller has a dynamic alloca. I will add this back, but I think the most reasonable way requires changes to the inliner itself rather than just the cost metric, and so I've deferred this for a subsequent patch. The test case is XFAIL-ed until then. As mentioned in the review mail, this seems to make Clang run about 1% to 2% faster in -O0, but makes its binary size grow by just under 4%. I've looked into the 4% growth, and it can be fixed, but requires changes to other parts of the inliner. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@153812 91177308-0d34-0410-b5e6-96231b3b80d8
2012-03-31 12:42:41 +00:00
///
/// Note that threshold is passed into this function. Only costs below the
/// threshold are computed with any accuracy. The threshold can be used to
/// bound the computation necessary to determine whether the cost is
/// sufficiently low to warrant inlining.
///
/// Also note that calling this function *dynamically* computes the cost of
/// inlining the callsite. It is an expensive, heavyweight call.
InlineCost getInlineCost(CallSite CS, int Threshold);
/// \brief Get an InlineCost with the callee explicitly specified.
/// This allows you to calculate the cost of inlining a function via a
/// pointer. This behaves exactly as the version with no explicit callee
/// parameter in all other respects.
//
// Note: This is used by out-of-tree passes, please do not remove without
// adding a replacement API.
InlineCost getInlineCost(CallSite CS, Function *Callee, int Threshold);
/// \brief Minimal filter to detect invalid constructs for inlining.
bool isInlineViable(Function &Callee);
};
}
#endif