llvm-project/llvm/lib/Analysis/CodeMetrics.cpp

188 lines
6.4 KiB
C++
Raw Normal View History

//===- CodeMetrics.cpp - Code cost measurements ---------------------------===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This file implements code cost measurement utilities.
//
//===----------------------------------------------------------------------===//
#include "llvm/Analysis/AssumptionCache.h"
#include "llvm/Analysis/CodeMetrics.h"
#include "llvm/Analysis/LoopInfo.h"
#include "llvm/Analysis/TargetTransformInfo.h"
#include "llvm/Analysis/ValueTracking.h"
#include "llvm/IR/CallSite.h"
#include "llvm/IR/DataLayout.h"
#include "llvm/IR/Function.h"
#include "llvm/IR/IntrinsicInst.h"
#include "llvm/Support/Debug.h"
#include "llvm/Support/raw_ostream.h"
#define DEBUG_TYPE "code-metrics"
using namespace llvm;
static void completeEphemeralValues(SmallVector<const Value *, 16> &WorkSet,
SmallPtrSetImpl<const Value*> &EphValues) {
SmallPtrSet<const Value *, 32> Visited;
// Make sure that all of the items in WorkSet are in our EphValues set.
EphValues.insert(WorkSet.begin(), WorkSet.end());
// Note: We don't speculate PHIs here, so we'll miss instruction chains kept
// alive only by ephemeral values.
while (!WorkSet.empty()) {
const Value *V = WorkSet.front();
WorkSet.erase(WorkSet.begin());
if (!Visited.insert(V).second)
continue;
// If all uses of this value are ephemeral, then so is this value.
if (!std::all_of(V->user_begin(), V->user_end(),
[&](const User *U) { return EphValues.count(U); }))
continue;
EphValues.insert(V);
DEBUG(dbgs() << "Ephemeral Value: " << *V << "\n");
if (const User *U = dyn_cast<User>(V))
for (const Value *J : U->operands()) {
if (isSafeToSpeculativelyExecute(J))
WorkSet.push_back(J);
}
}
}
// Find all ephemeral values.
void CodeMetrics::collectEphemeralValues(
const Loop *L, AssumptionCache *AC,
SmallPtrSetImpl<const Value *> &EphValues) {
SmallVector<const Value *, 16> WorkSet;
for (auto &AssumeVH : AC->assumptions()) {
if (!AssumeVH)
continue;
Instruction *I = cast<Instruction>(AssumeVH);
// Filter out call sites outside of the loop so we don't to a function's
// worth of work for each of its loops (and, in the common case, ephemeral
// values in the loop are likely due to @llvm.assume calls in the loop).
if (!L->contains(I->getParent()))
continue;
WorkSet.push_back(I);
}
completeEphemeralValues(WorkSet, EphValues);
}
void CodeMetrics::collectEphemeralValues(
const Function *F, AssumptionCache *AC,
SmallPtrSetImpl<const Value *> &EphValues) {
SmallVector<const Value *, 16> WorkSet;
for (auto &AssumeVH : AC->assumptions()) {
if (!AssumeVH)
continue;
Instruction *I = cast<Instruction>(AssumeVH);
assert(I->getParent()->getParent() == F &&
"Found assumption for the wrong function!");
WorkSet.push_back(I);
}
completeEphemeralValues(WorkSet, EphValues);
}
/// analyzeBasicBlock - Fill in the current structure with information gleaned
/// from the specified block.
void CodeMetrics::analyzeBasicBlock(const BasicBlock *BB,
const TargetTransformInfo &TTI,
SmallPtrSetImpl<const Value*> &EphValues) {
++NumBlocks;
unsigned NumInstsBeforeThisBB = NumInsts;
for (BasicBlock::const_iterator II = BB->begin(), E = BB->end();
II != E; ++II) {
// Skip ephemeral values.
Analysis: Remove implicit ilist iterator conversions Remove implicit ilist iterator conversions from LLVMAnalysis. I came across something really scary in `llvm::isKnownNotFullPoison()` which relied on `Instruction::getNextNode()` being completely broken (not surprising, but scary nevertheless). This function is documented (and coded to) return `nullptr` when it gets to the sentinel, but with an `ilist_half_node` as a sentinel, the sentinel check looks into some other memory and we don't recognize we've hit the end. Rooting out these scary cases is the reason I'm removing the implicit conversions before doing anything else with `ilist`; I'm not at all surprised that clients rely on badness. I found another scary case -- this time, not relying on badness, just bad (but I guess getting lucky so far) -- in `ObjectSizeOffsetEvaluator::compute_()`. Here, we save out the insertion point, do some things, and then restore it. Previously, we let the iterator auto-convert to `Instruction*`, and then set it back using the `Instruction*` version: Instruction *PrevInsertPoint = Builder.GetInsertPoint(); /* Logic that may change insert point */ if (PrevInsertPoint) Builder.SetInsertPoint(PrevInsertPoint); The check for `PrevInsertPoint` doesn't protect correctly against bad accesses. If the insertion point has been set to the end of a basic block (i.e., `SetInsertPoint(SomeBB)`), then `GetInsertPoint()` returns an iterator pointing at the list sentinel. The version of `SetInsertPoint()` that's getting called will then call `PrevInsertPoint->getParent()`, which explodes horribly. The only reason this hasn't blown up is that it's fairly unlikely the builder is adding to the end of the block; usually, we're adding instructions somewhere before the terminator. llvm-svn: 249925
2015-10-10 08:53:03 +08:00
if (EphValues.count(&*II))
continue;
// Special handling for calls.
if (isa<CallInst>(II) || isa<InvokeInst>(II)) {
ImmutableCallSite CS(cast<Instruction>(II));
if (const Function *F = CS.getCalledFunction()) {
// If a function is both internal and has a single use, then it is
// extremely likely to get inlined in the future (it was probably
// exposed by an interleaved devirtualization pass).
if (!CS.isNoInline() && F->hasInternalLinkage() && F->hasOneUse())
++NumInlineCandidates;
// If this call is to function itself, then the function is recursive.
// Inlining it into other functions is a bad idea, because this is
// basically just a form of loop peeling, and our metrics aren't useful
// for that case.
if (F == BB->getParent())
isRecursive = true;
if (TTI.isLoweredToCall(F))
++NumCalls;
} else {
// We don't want inline asm to count as a call - that would prevent loop
// unrolling. The argument setup cost is still real, though.
if (!isa<InlineAsm>(CS.getCalledValue()))
++NumCalls;
}
}
if (const AllocaInst *AI = dyn_cast<AllocaInst>(II)) {
if (!AI->isStaticAlloca())
this->usesDynamicAlloca = true;
}
if (isa<ExtractElementInst>(II) || II->getType()->isVectorTy())
++NumVectorInsts;
[IR] Add token types This introduces the basic functionality to support "token types". The motivation stems from the need to perform operations on a Value whose provenance cannot be obscured. There are several applications for such a type but my immediate motivation stems from WinEH. Our personality routine enforces a single-entry - single-exit regime for cleanups. After several rounds of optimizations, we may be left with a terminator whose "cleanup-entry block" is not entirely clear because control flow has merged two cleanups together. We have experimented with using labels as operands inside of instructions which are not terminators to indicate where we came from but found that LLVM does not expect such exotic uses of BasicBlocks. Instead, we can use this new type to clearly associate the "entry point" and "exit point" of our cleanup. This is done by having the cleanuppad yield a Token and consuming it at the cleanupret. The token type makes it impossible to obscure or otherwise hide the Value, making it trivial to track the relationship between the two points. What is the burden to the optimizer? Well, it turns out we have already paid down this cost by accepting that there are certain calls that we are not permitted to duplicate, optimizations have to watch out for such instructions anyway. There are additional places in the optimizer that we will probably have to update but early examination has given me the impression that this will not be heroic. Differential Revision: http://reviews.llvm.org/D11861 llvm-svn: 245029
2015-08-14 13:09:07 +08:00
if (II->getType()->isTokenTy() && II->isUsedOutsideOfBlock(BB))
notDuplicatable = true;
if (const CallInst *CI = dyn_cast<CallInst>(II)) {
if (CI->cannotDuplicate())
notDuplicatable = true;
if (CI->isConvergent())
convergent = true;
}
if (const InvokeInst *InvI = dyn_cast<InvokeInst>(II))
if (InvI->cannotDuplicate())
notDuplicatable = true;
NumInsts += TTI.getUserCost(&*II);
}
if (isa<ReturnInst>(BB->getTerminator()))
++NumRets;
// We never want to inline functions that contain an indirectbr. This is
// incorrect because all the blockaddress's (in static global initializers
// for example) would be referring to the original function, and this indirect
// jump would jump from the inlined copy of the function into the original
// function which is extremely undefined behavior.
// FIXME: This logic isn't really right; we can safely inline functions
// with indirectbr's as long as no other function or global references the
// blockaddress of a block within the current function. And as a QOI issue,
// if someone is using a blockaddress without an indirectbr, and that
// reference somehow ends up in another function or global, we probably
// don't want to inline this function.
notDuplicatable |= isa<IndirectBrInst>(BB->getTerminator());
// Remember NumInsts for this BB.
NumBBInsts[BB] = NumInsts - NumInstsBeforeThisBB;
}