1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-10-21 03:53:04 +02:00
llvm-mirror/lib/Transforms/Scalar/LoopInstSimplify.cpp

209 lines
7.4 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/LoopInstSimplify.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/Analysis/TargetLibraryInfo.h"
#include "llvm/IR/DataLayout.h"
#include "llvm/IR/Dominators.h"
#include "llvm/IR/Instructions.h"
#include "llvm/Support/Debug.h"
#include "llvm/Transforms/Scalar.h"
#include "llvm/Transforms/Scalar/LoopPassManager.h"
#include "llvm/Transforms/Utils/Local.h"
[LPM] Factor all of the loop analysis usage updates into a common helper routine. We were getting this wrong in small ways and generally being very inconsistent about it across loop passes. Instead, let's have a common place where we do this. One minor downside is that this will require some analyses like SCEV in more places than they are strictly needed. However, this seems benign as these analyses are complete no-ops, and without this consistency we can in many cases end up with the legacy pass manager scheduling deciding to split up a loop pass pipeline in order to run the function analysis half-way through. It is very, very annoying to fix these without just being very pedantic across the board. The only loop passes I've not updated here are ones that use AU.setPreservesAll() such as IVUsers (an analysis) and the pass printer. They seemed less relevant. With this patch, almost all of the problems in PR24804 around loop pass pipelines are fixed. The one remaining issue is that we run simplify-cfg and instcombine in the middle of the loop pass pipeline. We've recently added some loop variants of these passes that would seem substantially cleaner to use, but this at least gets us much closer to the previous state. Notably, the seven loop pass managers is down to three. I've not updated the loop passes using LoopAccessAnalysis because that analysis hasn't been fully wired into LoopSimplify/LCSSA, and it isn't clear that those transforms want to support those forms anyways. They all run late anyways, so this is harmless. Similarly, LSR is left alone because it already carefully manages its forms and doesn't need to get fused into a single loop pass manager with a bunch of other loop passes. LoopReroll didn't use loop simplified form previously, and I've updated the test case to match the trivially different output. Finally, I've also factored all the pass initialization for the passes that use this technique as well, so that should be done regularly and reliably. Thanks to James for the help reviewing and thinking about this stuff, and Ben for help thinking about it as well! Differential Revision: http://reviews.llvm.org/D17435 llvm-svn: 261316
2016-02-19 11:45:18 +01:00
#include "llvm/Transforms/Utils/LoopUtils.h"
using namespace llvm;
#define DEBUG_TYPE "loop-instsimplify"
STATISTIC(NumSimplified, "Number of redundant instructions simplified");
static bool SimplifyLoopInst(Loop *L, DominatorTree *DT, LoopInfo *LI,
AssumptionCache *AC,
const TargetLibraryInfo *TLI) {
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 04:16:01 +01:00
for (User *U : I->users())
Next->insert(cast<Instruction>(U));
I->replaceAllUsesWith(V);
LocalChanged = true;
++NumSimplified;
}
}
2016-04-06 15:27:13 +02:00
if (RecursivelyDeleteTriviallyDeadInstructions(I, TLI)) {
// 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();
2016-04-06 15:27:13 +02:00
LocalChanged = true;
}
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;
}
namespace {
class LoopInstSimplifyLegacyPass : public LoopPass {
public:
static char ID; // Pass ID, replacement for typeid
LoopInstSimplifyLegacyPass() : LoopPass(ID) {
initializeLoopInstSimplifyLegacyPassPass(*PassRegistry::getPassRegistry());
}
bool runOnLoop(Loop *L, LPPassManager &LPM) override {
if (skipLoop(L))
return false;
DominatorTreeWrapperPass *DTWP =
getAnalysisIfAvailable<DominatorTreeWrapperPass>();
DominatorTree *DT = DTWP ? &DTWP->getDomTree() : nullptr;
LoopInfo *LI = &getAnalysis<LoopInfoWrapperPass>().getLoopInfo();
AssumptionCache *AC =
&getAnalysis<AssumptionCacheTracker>().getAssumptionCache(
*L->getHeader()->getParent());
const TargetLibraryInfo *TLI =
&getAnalysis<TargetLibraryInfoWrapperPass>().getTLI();
return SimplifyLoopInst(L, DT, LI, AC, TLI);
}
void getAnalysisUsage(AnalysisUsage &AU) const override {
AU.addRequired<AssumptionCacheTracker>();
AU.addRequired<TargetLibraryInfoWrapperPass>();
AU.setPreservesCFG();
getLoopAnalysisUsage(AU);
}
};
}
[PM] Rewrite the loop pass manager to use a worklist and augmented run arguments much like the CGSCC pass manager. This is a major redesign following the pattern establish for the CGSCC layer to support updates to the set of loops during the traversal of the loop nest and to support invalidation of analyses. An additional significant burden in the loop PM is that so many passes require access to a large number of function analyses. Manually ensuring these are cached, available, and preserved has been a long-standing burden in LLVM even with the help of the automatic scheduling in the old pass manager. And it made the new pass manager extremely unweildy. With this design, we can package the common analyses up while in a function pass and make them immediately available to all the loop passes. While in some cases this is unnecessary, I think the simplicity afforded is worth it. This does not (yet) address loop simplified form or LCSSA form, but those are the next things on my radar and I have a clear plan for them. While the patch is very large, most of it is either mechanically updating loop passes to the new API or the new testing for the loop PM. The code for it is reasonably compact. I have not yet updated all of the loop passes to correctly leverage the update mechanisms demonstrated in the unittests. I'll do that in follow-up patches along with improved FileCheck tests for those passes that ensure things work in more realistic scenarios. In many cases, there isn't much we can do with these until the loop simplified form and LCSSA form are in place. Differential Revision: https://reviews.llvm.org/D28292 llvm-svn: 291651
2017-01-11 07:23:21 +01:00
PreservedAnalyses LoopInstSimplifyPass::run(Loop &L, LoopAnalysisManager &AM,
LoopStandardAnalysisResults &AR,
LPMUpdater &) {
if (!SimplifyLoopInst(&L, &AR.DT, &AR.LI, &AR.AC, &AR.TLI))
return PreservedAnalyses::all();
auto PA = getLoopPassPreservedAnalyses();
PA.preserveSet<CFGAnalyses>();
return PA;
}
char LoopInstSimplifyLegacyPass::ID = 0;
INITIALIZE_PASS_BEGIN(LoopInstSimplifyLegacyPass, "loop-instsimplify",
"Simplify instructions in loops", false, false)
INITIALIZE_PASS_DEPENDENCY(AssumptionCacheTracker)
INITIALIZE_PASS_DEPENDENCY(LoopPass)
INITIALIZE_PASS_DEPENDENCY(TargetLibraryInfoWrapperPass)
INITIALIZE_PASS_END(LoopInstSimplifyLegacyPass, "loop-instsimplify",
"Simplify instructions in loops", false, false)
Pass *llvm::createLoopInstSimplifyPass() {
return new LoopInstSimplifyLegacyPass();
}