llvm-project/llvm/lib/Transforms/Scalar/LoopInstSimplify.cpp

196 lines
6.9 KiB
C++
Raw Normal View History

//===- LoopInstSimplify.cpp - Loop Instruction Simplification Pass --------===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This pass performs lightweight instruction simplification on loop bodies.
//
//===----------------------------------------------------------------------===//
#include "llvm/Transforms/Scalar.h"
#include "llvm/ADT/STLExtras.h"
#include "llvm/ADT/Statistic.h"
#include "llvm/Analysis/AssumptionCache.h"
#include "llvm/Analysis/InstructionSimplify.h"
#include "llvm/Analysis/LoopInfo.h"
#include "llvm/Analysis/LoopPass.h"
#include "llvm/Analysis/ScalarEvolution.h"
#include "llvm/IR/DataLayout.h"
#include "llvm/IR/Dominators.h"
#include "llvm/IR/Instructions.h"
#include "llvm/Support/Debug.h"
#include "llvm/Analysis/TargetLibraryInfo.h"
#include "llvm/Transforms/Utils/Local.h"
using namespace llvm;
#define DEBUG_TYPE "loop-instsimplify"
STATISTIC(NumSimplified, "Number of redundant instructions simplified");
namespace {
class LoopInstSimplify : public LoopPass {
public:
static char ID; // Pass ID, replacement for typeid
LoopInstSimplify() : LoopPass(ID) {
initializeLoopInstSimplifyPass(*PassRegistry::getPassRegistry());
}
bool runOnLoop(Loop*, LPPassManager&) override;
void getAnalysisUsage(AnalysisUsage &AU) const override {
AU.setPreservesCFG();
AU.addRequired<AssumptionCacheTracker>();
AU.addRequired<LoopInfoWrapperPass>();
AU.addRequiredID(LoopSimplifyID);
AU.addPreservedID(LoopSimplifyID);
AU.addPreservedID(LCSSAID);
[PM] Port ScalarEvolution to the new pass manager. This change makes ScalarEvolution a stand-alone object and just produces one from a pass as needed. Making this work well requires making the object movable, using references instead of overwritten pointers in a number of places, and other refactorings. I've also wired it up to the new pass manager and added a RUN line to a test to exercise it under the new pass manager. This includes basic printing support much like with other analyses. But there is a big and somewhat scary change here. Prior to this patch ScalarEvolution was never *actually* invalidated!!! Re-running the pass just re-wired up the various other analyses and didn't remove any of the existing entries in the SCEV caches or clear out anything at all. This might seem OK as everything in SCEV that can uses ValueHandles to track updates to the values that serve as SCEV keys. However, this still means that as we ran SCEV over each function in the module, we kept accumulating more and more SCEVs into the cache. At the end, we would have a SCEV cache with every value that we ever needed a SCEV for in the entire module!!! Yowzers. The releaseMemory routine would dump all of this, but that isn't realy called during normal runs of the pipeline as far as I can see. To make matters worse, there *is* actually a key that we don't update with value handles -- there is a map keyed off of Loop*s. Because LoopInfo *does* release its memory from run to run, it is entirely possible to run SCEV over one function, then over another function, and then lookup a Loop* from the second function but find an entry inserted for the first function! Ouch. To make matters still worse, there are plenty of updates that *don't* trip a value handle. It seems incredibly unlikely that today GVN or another pass that invalidates SCEV can update values in *just* such a way that a subsequent run of SCEV will incorrectly find lookups in a cache, but it is theoretically possible and would be a nightmare to debug. With this refactoring, I've fixed all this by actually destroying and recreating the ScalarEvolution object from run to run. Technically, this could increase the amount of malloc traffic we see, but then again it is also technically correct. ;] I don't actually think we're suffering from tons of malloc traffic from SCEV because if we were, the fact that we never clear the memory would seem more likely to have come up as an actual problem before now. So, I've made the simple fix here. If in fact there are serious issues with too much allocation and deallocation, I can work on a clever fix that preserves the allocations (while clearing the data) between each run, but I'd prefer to do that kind of optimization with a test case / benchmark that shows why we need such cleverness (and that can test that we actually make it faster). It's possible that this will make some things faster by making the SCEV caches have higher locality (due to being significantly smaller) so until there is a clear benchmark, I think the simple change is best. Differential Revision: http://reviews.llvm.org/D12063 llvm-svn: 245193
2015-08-17 10:08:17 +08:00
AU.addPreserved<ScalarEvolutionWrapperPass>();
AU.addRequired<TargetLibraryInfoWrapperPass>();
}
};
}
2012-07-24 18:51:42 +08:00
char LoopInstSimplify::ID = 0;
INITIALIZE_PASS_BEGIN(LoopInstSimplify, "loop-instsimplify",
"Simplify instructions in loops", false, false)
INITIALIZE_PASS_DEPENDENCY(AssumptionCacheTracker)
INITIALIZE_PASS_DEPENDENCY(TargetLibraryInfoWrapperPass)
INITIALIZE_PASS_DEPENDENCY(DominatorTreeWrapperPass)
INITIALIZE_PASS_DEPENDENCY(LoopInfoWrapperPass)
INITIALIZE_PASS_DEPENDENCY(LCSSA)
INITIALIZE_PASS_END(LoopInstSimplify, "loop-instsimplify",
"Simplify instructions in loops", false, false)
Pass *llvm::createLoopInstSimplifyPass() {
return new LoopInstSimplify();
}
bool LoopInstSimplify::runOnLoop(Loop *L, LPPassManager &LPM) {
if (skipOptnoneFunction(L))
return false;
DominatorTreeWrapperPass *DTWP =
getAnalysisIfAvailable<DominatorTreeWrapperPass>();
DominatorTree *DT = DTWP ? &DTWP->getDomTree() : nullptr;
LoopInfo *LI = &getAnalysis<LoopInfoWrapperPass>().getLoopInfo();
const TargetLibraryInfo *TLI =
&getAnalysis<TargetLibraryInfoWrapperPass>().getTLI();
auto &AC = getAnalysis<AssumptionCacheTracker>().getAssumptionCache(
*L->getHeader()->getParent());
SmallVector<BasicBlock*, 8> ExitBlocks;
L->getUniqueExitBlocks(ExitBlocks);
array_pod_sort(ExitBlocks.begin(), ExitBlocks.end());
SmallPtrSet<const Instruction*, 8> S1, S2, *ToSimplify = &S1, *Next = &S2;
// The bit we are stealing from the pointer represents whether this basic
// block is the header of a subloop, in which case we only process its phis.
typedef PointerIntPair<BasicBlock*, 1> WorklistItem;
SmallVector<WorklistItem, 16> VisitStack;
SmallPtrSet<BasicBlock*, 32> Visited;
bool Changed = false;
bool LocalChanged;
do {
LocalChanged = false;
VisitStack.clear();
Visited.clear();
VisitStack.push_back(WorklistItem(L->getHeader(), false));
while (!VisitStack.empty()) {
WorklistItem Item = VisitStack.pop_back_val();
BasicBlock *BB = Item.getPointer();
bool IsSubloopHeader = Item.getInt();
const DataLayout &DL = L->getHeader()->getModule()->getDataLayout();
// Simplify instructions in the current basic block.
for (BasicBlock::iterator BI = BB->begin(), BE = BB->end(); BI != BE;) {
Instruction *I = &*BI++;
// The first time through the loop ToSimplify is empty and we try to
// simplify all instructions. On later iterations ToSimplify is not
// empty and we only bother simplifying instructions that are in it.
if (!ToSimplify->empty() && !ToSimplify->count(I))
continue;
// Don't bother simplifying unused instructions.
if (!I->use_empty()) {
Value *V = SimplifyInstruction(I, DL, TLI, DT, &AC);
if (V && LI->replacementPreservesLCSSAForm(I, V)) {
// Mark all uses for resimplification next time round the loop.
[C++11] Add range based accessors for the Use-Def chain of a Value. This requires a number of steps. 1) Move value_use_iterator into the Value class as an implementation detail 2) Change it to actually be a *Use* iterator rather than a *User* iterator. 3) Add an adaptor which is a User iterator that always looks through the Use to the User. 4) Wrap these in Value::use_iterator and Value::user_iterator typedefs. 5) Add the range adaptors as Value::uses() and Value::users(). 6) Update *all* of the callers to correctly distinguish between whether they wanted a use_iterator (and to explicitly dig out the User when needed), or a user_iterator which makes the Use itself totally opaque. Because #6 requires churning essentially everything that walked the Use-Def chains, I went ahead and added all of the range adaptors and switched them to range-based loops where appropriate. Also because the renaming requires at least churning every line of code, it didn't make any sense to split these up into multiple commits -- all of which would touch all of the same lies of code. The result is still not quite optimal. The Value::use_iterator is a nice regular iterator, but Value::user_iterator is an iterator over User*s rather than over the User objects themselves. As a consequence, it fits a bit awkwardly into the range-based world and it has the weird extra-dereferencing 'operator->' that so many of our iterators have. I think this could be fixed by providing something which transforms a range of T&s into a range of T*s, but that *can* be separated into another patch, and it isn't yet 100% clear whether this is the right move. However, this change gets us most of the benefit and cleans up a substantial amount of code around Use and User. =] llvm-svn: 203364
2014-03-09 11:16:01 +08:00
for (User *U : I->users())
Next->insert(cast<Instruction>(U));
I->replaceAllUsesWith(V);
LocalChanged = true;
++NumSimplified;
}
}
bool res = RecursivelyDeleteTriviallyDeadInstructions(I, TLI);
if (res) {
// RecursivelyDeleteTriviallyDeadInstruction can remove
// more than one instruction, so simply incrementing the
// iterator does not work. When instructions get deleted
// re-iterate instead.
BI = BB->begin(); BE = BB->end();
LocalChanged |= res;
}
if (IsSubloopHeader && !isa<PHINode>(I))
break;
}
// Add all successors to the worklist, except for loop exit blocks and the
// bodies of subloops. We visit the headers of loops so that we can process
// their phis, but we contract the rest of the subloop body and only follow
// edges leading back to the original loop.
for (succ_iterator SI = succ_begin(BB), SE = succ_end(BB); SI != SE;
++SI) {
BasicBlock *SuccBB = *SI;
if (!Visited.insert(SuccBB).second)
continue;
const Loop *SuccLoop = LI->getLoopFor(SuccBB);
if (SuccLoop && SuccLoop->getHeader() == SuccBB
&& L->contains(SuccLoop)) {
VisitStack.push_back(WorklistItem(SuccBB, true));
SmallVector<BasicBlock*, 8> SubLoopExitBlocks;
SuccLoop->getExitBlocks(SubLoopExitBlocks);
for (unsigned i = 0; i < SubLoopExitBlocks.size(); ++i) {
BasicBlock *ExitBB = SubLoopExitBlocks[i];
if (LI->getLoopFor(ExitBB) == L && Visited.insert(ExitBB).second)
VisitStack.push_back(WorklistItem(ExitBB, false));
}
continue;
}
bool IsExitBlock = std::binary_search(ExitBlocks.begin(),
ExitBlocks.end(), SuccBB);
if (IsExitBlock)
continue;
VisitStack.push_back(WorklistItem(SuccBB, false));
}
}
// Place the list of instructions to simplify on the next loop iteration
// into ToSimplify.
std::swap(ToSimplify, Next);
Next->clear();
Changed |= LocalChanged;
} while (LocalChanged);
return Changed;
}