forked from OSchip/llvm-project
use hte new pred cache to speed up the new non-local memdep
queries. This speeds up GVN using the new queries (not yet checked in) by just over 10%. llvm-svn: 60743
This commit is contained in:
parent
4c9bb5336a
commit
768e5bcafc
|
@ -18,6 +18,7 @@
|
|||
#include "llvm/Pass.h"
|
||||
#include "llvm/ADT/DenseMap.h"
|
||||
#include "llvm/ADT/SmallPtrSet.h"
|
||||
#include "llvm/ADT/OwningPtr.h"
|
||||
#include "llvm/ADT/PointerIntPair.h"
|
||||
|
||||
namespace llvm {
|
||||
|
@ -28,6 +29,7 @@ namespace llvm {
|
|||
class AliasAnalysis;
|
||||
class TargetData;
|
||||
class MemoryDependenceAnalysis;
|
||||
class PredIteratorCache;
|
||||
|
||||
/// MemDepResult - A memory dependence query can return one of three different
|
||||
/// answers, described below.
|
||||
|
@ -193,23 +195,18 @@ namespace llvm {
|
|||
/// Current AA implementation, just a cache.
|
||||
AliasAnalysis *AA;
|
||||
TargetData *TD;
|
||||
OwningPtr<PredIteratorCache> PredCache;
|
||||
public:
|
||||
MemoryDependenceAnalysis() : FunctionPass(&ID) {}
|
||||
MemoryDependenceAnalysis();
|
||||
~MemoryDependenceAnalysis();
|
||||
static char ID;
|
||||
|
||||
/// Pass Implementation stuff. This doesn't do any analysis eagerly.
|
||||
bool runOnFunction(Function &);
|
||||
|
||||
/// Clean up memory in between runs
|
||||
void releaseMemory() {
|
||||
LocalDeps.clear();
|
||||
NonLocalDeps.clear();
|
||||
NonLocalPointerDeps.clear();
|
||||
ReverseLocalDeps.clear();
|
||||
ReverseNonLocalDeps.clear();
|
||||
ReverseNonLocalPtrDeps.clear();
|
||||
}
|
||||
|
||||
void releaseMemory();
|
||||
|
||||
/// getAnalysisUsage - Does not modify anything. It uses Value Numbering
|
||||
/// and Alias Analysis.
|
||||
///
|
||||
|
|
|
@ -21,7 +21,7 @@
|
|||
#include "llvm/Function.h"
|
||||
#include "llvm/Analysis/AliasAnalysis.h"
|
||||
#include "llvm/ADT/Statistic.h"
|
||||
#include "llvm/Support/CFG.h"
|
||||
#include "llvm/Support/PredIteratorCache.h"
|
||||
#include "llvm/Support/Debug.h"
|
||||
#include "llvm/Target/TargetData.h"
|
||||
using namespace llvm;
|
||||
|
@ -45,6 +45,25 @@ char MemoryDependenceAnalysis::ID = 0;
|
|||
static RegisterPass<MemoryDependenceAnalysis> X("memdep",
|
||||
"Memory Dependence Analysis", false, true);
|
||||
|
||||
MemoryDependenceAnalysis::MemoryDependenceAnalysis()
|
||||
: FunctionPass(&ID), PredCache(0) {
|
||||
}
|
||||
MemoryDependenceAnalysis::~MemoryDependenceAnalysis() {
|
||||
}
|
||||
|
||||
/// Clean up memory in between runs
|
||||
void MemoryDependenceAnalysis::releaseMemory() {
|
||||
LocalDeps.clear();
|
||||
NonLocalDeps.clear();
|
||||
NonLocalPointerDeps.clear();
|
||||
ReverseLocalDeps.clear();
|
||||
ReverseNonLocalDeps.clear();
|
||||
ReverseNonLocalPtrDeps.clear();
|
||||
PredCache->clear();
|
||||
}
|
||||
|
||||
|
||||
|
||||
/// getAnalysisUsage - Does not modify anything. It uses Alias Analysis.
|
||||
///
|
||||
void MemoryDependenceAnalysis::getAnalysisUsage(AnalysisUsage &AU) const {
|
||||
|
@ -56,6 +75,8 @@ void MemoryDependenceAnalysis::getAnalysisUsage(AnalysisUsage &AU) const {
|
|||
bool MemoryDependenceAnalysis::runOnFunction(Function &) {
|
||||
AA = &getAnalysis<AliasAnalysis>();
|
||||
TD = &getAnalysis<TargetData>();
|
||||
if (PredCache == 0)
|
||||
PredCache.reset(new PredIteratorCache());
|
||||
return false;
|
||||
}
|
||||
|
||||
|
@ -468,8 +489,7 @@ getNonLocalPointerDependency(Value *Pointer, bool isLoad, BasicBlock *FromBB,
|
|||
// While we have blocks to analyze, get their values.
|
||||
SmallPtrSet<BasicBlock*, 64> Visited;
|
||||
|
||||
for (pred_iterator PI = pred_begin(FromBB), E = pred_end(FromBB); PI != E;
|
||||
++PI) {
|
||||
for (BasicBlock **PI = PredCache->GetPreds(FromBB); *PI; ++PI) {
|
||||
// TODO: PHI TRANSLATE.
|
||||
getNonLocalPointerDepInternal(Pointer, PointeeSize, isLoad, *PI,
|
||||
Result, Visited);
|
||||
|
@ -592,7 +612,7 @@ getNonLocalPointerDepInternal(Value *Pointer, uint64_t PointeeSize,
|
|||
|
||||
// Otherwise, we have to process all the predecessors of this block to scan
|
||||
// them as well.
|
||||
for (pred_iterator PI = pred_begin(BB), E = pred_end(BB); PI != E; ++PI) {
|
||||
for (BasicBlock **PI = PredCache->GetPreds(BB); *PI; ++PI) {
|
||||
// TODO: PHI TRANSLATE.
|
||||
Worklist.push_back(*PI);
|
||||
}
|
||||
|
|
Loading…
Reference in New Issue