Add functions for finding ephemeral values

This adds a set of utility functions for collecting 'ephemeral' values. These
are LLVM IR values that are used only by @llvm.assume intrinsics (directly or
indirectly), and thus will be removed prior to code generation, implying that
they should be considered free for certain purposes (like inlining). The
inliner's cost analysis, and a few other passes, have been updated to account
for ephemeral values using the provided functionality.

This functionality is important for the usability of @llvm.assume, because it
limits the "non-local" side-effects of adding llvm.assume on inlining, loop
unrolling, etc. (these are hints, and do not generate code, so they should not
directly contribute to estimates of execution cost).

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@217335 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Hal Finkel
2014-09-07 13:49:57 +00:00
parent 3666e7f4c1
commit 3d03d60ca8
9 changed files with 222 additions and 17 deletions

View File

@@ -13,6 +13,7 @@
#include "llvm/Transforms/Scalar.h"
#include "llvm/ADT/Statistic.h"
#include "llvm/Analysis/AssumptionTracker.h"
#include "llvm/Analysis/CodeMetrics.h"
#include "llvm/Analysis/InstructionSimplify.h"
#include "llvm/Analysis/LoopPass.h"
@@ -53,6 +54,7 @@ namespace {
// LCSSA form makes instruction renaming easier.
void getAnalysisUsage(AnalysisUsage &AU) const override {
AU.addRequired<AssumptionTracker>();
AU.addPreserved<DominatorTreeWrapperPass>();
AU.addRequired<LoopInfo>();
AU.addPreserved<LoopInfo>();
@@ -72,12 +74,14 @@ namespace {
unsigned MaxHeaderSize;
LoopInfo *LI;
const TargetTransformInfo *TTI;
AssumptionTracker *AT;
};
}
char LoopRotate::ID = 0;
INITIALIZE_PASS_BEGIN(LoopRotate, "loop-rotate", "Rotate Loops", false, false)
INITIALIZE_AG_DEPENDENCY(TargetTransformInfo)
INITIALIZE_PASS_DEPENDENCY(AssumptionTracker)
INITIALIZE_PASS_DEPENDENCY(LoopInfo)
INITIALIZE_PASS_DEPENDENCY(LoopSimplify)
INITIALIZE_PASS_DEPENDENCY(LCSSA)
@@ -98,6 +102,7 @@ bool LoopRotate::runOnLoop(Loop *L, LPPassManager &LPM) {
LI = &getAnalysis<LoopInfo>();
TTI = &getAnalysis<TargetTransformInfo>();
AT = &getAnalysis<AssumptionTracker>();
// Simplify the loop latch before attempting to rotate the header
// upward. Rotation may not be needed if the loop tail can be folded into the
@@ -323,8 +328,11 @@ bool LoopRotate::rotateLoop(Loop *L, bool SimplifiedLatch) {
// Check size of original header and reject loop if it is very big or we can't
// duplicate blocks inside it.
{
SmallPtrSet<const Value *, 32> EphValues;
CodeMetrics::collectEphemeralValues(L, AT, EphValues);
CodeMetrics Metrics;
Metrics.analyzeBasicBlock(OrigHeader, *TTI);
Metrics.analyzeBasicBlock(OrigHeader, *TTI, EphValues);
if (Metrics.notDuplicatable) {
DEBUG(dbgs() << "LoopRotation: NOT rotating - contains non-duplicatable"
<< " instructions: "; L->dump());

View File

@@ -203,11 +203,15 @@ Pass *llvm::createSimpleLoopUnrollPass() {
/// ApproximateLoopSize - Approximate the size of the loop.
static unsigned ApproximateLoopSize(const Loop *L, unsigned &NumCalls,
bool &NotDuplicatable,
const TargetTransformInfo &TTI) {
const TargetTransformInfo &TTI,
AssumptionTracker *AT) {
SmallPtrSet<const Value *, 32> EphValues;
CodeMetrics::collectEphemeralValues(L, AT, EphValues);
CodeMetrics Metrics;
for (Loop::block_iterator I = L->block_begin(), E = L->block_end();
I != E; ++I)
Metrics.analyzeBasicBlock(*I, TTI);
Metrics.analyzeBasicBlock(*I, TTI, EphValues);
NumCalls = Metrics.NumInlineCandidates;
NotDuplicatable = Metrics.notDuplicatable;
@@ -391,7 +395,7 @@ bool LoopUnroll::runOnLoop(Loop *L, LPPassManager &LPM) {
unsigned NumInlineCandidates;
bool notDuplicatable;
unsigned LoopSize =
ApproximateLoopSize(L, NumInlineCandidates, notDuplicatable, TTI);
ApproximateLoopSize(L, NumInlineCandidates, notDuplicatable, TTI, AT);
DEBUG(dbgs() << " Loop Size = " << LoopSize << "\n");
uint64_t UnrolledSize = (uint64_t)LoopSize * Count;
if (notDuplicatable) {

View File

@@ -104,7 +104,8 @@ namespace {
// Analyze loop. Check its size, calculate is it possible to unswitch
// it. Returns true if we can unswitch this loop.
bool countLoop(const Loop *L, const TargetTransformInfo &TTI);
bool countLoop(const Loop *L, const TargetTransformInfo &TTI,
AssumptionTracker *AT);
// Clean all data related to given loop.
void forgetLoop(const Loop *L);
@@ -215,7 +216,8 @@ namespace {
// Analyze loop. Check its size, calculate is it possible to unswitch
// it. Returns true if we can unswitch this loop.
bool LUAnalysisCache::countLoop(const Loop *L, const TargetTransformInfo &TTI) {
bool LUAnalysisCache::countLoop(const Loop *L, const TargetTransformInfo &TTI,
AssumptionTracker *AT) {
LoopPropsMapIt PropsIt;
bool Inserted;
@@ -232,13 +234,16 @@ bool LUAnalysisCache::countLoop(const Loop *L, const TargetTransformInfo &TTI) {
// large numbers of branches which cause loop unswitching to go crazy.
// This is a very ad-hoc heuristic.
SmallPtrSet<const Value *, 32> EphValues;
CodeMetrics::collectEphemeralValues(L, AT, EphValues);
// FIXME: This is overly conservative because it does not take into
// consideration code simplification opportunities and code that can
// be shared by the resultant unswitched loops.
CodeMetrics Metrics;
for (Loop::block_iterator I = L->block_begin(), E = L->block_end();
I != E; ++I)
Metrics.analyzeBasicBlock(*I, TTI);
Metrics.analyzeBasicBlock(*I, TTI, EphValues);
Props.SizeEstimation = std::min(Metrics.NumInsts, Metrics.NumBlocks * 5);
Props.CanBeUnswitchedCount = MaxSize / (Props.SizeEstimation);
@@ -426,7 +431,8 @@ bool LoopUnswitch::processCurrentLoop() {
// Probably we reach the quota of branches for this loop. If so
// stop unswitching.
if (!BranchesInfo.countLoop(currentLoop, getAnalysis<TargetTransformInfo>()))
if (!BranchesInfo.countLoop(currentLoop, getAnalysis<TargetTransformInfo>(),
AT))
return false;
// Loop over all of the basic blocks in the loop. If we find an interior