[LV] Change getSmallBestKnownTC to return an ElementCount (NFC) #141793
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…ementCount. This is prep work for enabling better UF calculations when using vscale based VFs to vectorise loops with vscale based tripcounts. NOTE: NFC because All uses remain fixed-length until a following PR changes getSmallConstantRuntimeTripCount().
|
@llvm/pr-subscribers-llvm-analysis @llvm/pr-subscribers-llvm-transforms Author: Paul Walker (paulwalker-arm) ChangesThis is prep work for enabling better UF calculations when using vscale based VFs to vectorise loops with vscale based tripcounts. NOTE: NFC because All uses remain fixed-length until a following PR changes getSmallConstantRuntimeTripCount(). Full diff: https://github.com/llvm/llvm-project/pull/141793.diff 3 Files Affected:
diff --git a/llvm/include/llvm/Analysis/ScalarEvolution.h b/llvm/include/llvm/Analysis/ScalarEvolution.h
index 167845ce646b9..b5faa4c479afd 100644
--- a/llvm/include/llvm/Analysis/ScalarEvolution.h
+++ b/llvm/include/llvm/Analysis/ScalarEvolution.h
@@ -823,6 +823,10 @@ class ScalarEvolution {
/// than the backedge taken count for the loop.
LLVM_ABI unsigned getSmallConstantTripCount(const Loop *L);
+ /// A version of getSmallConstantTripCount that returns as an ElementCount to
+ /// include loops whose trip count is a function of llvm.vscale().
+ ElementCount getSmallConstantRuntimeTripCount(const Loop *L);
+
/// Return the exact trip count for this loop if we exit through ExitingBlock.
/// '0' is used to represent an unknown or non-constant trip count. Note
/// that a trip count is simply one more than the backedge taken count for
diff --git a/llvm/lib/Analysis/ScalarEvolution.cpp b/llvm/lib/Analysis/ScalarEvolution.cpp
index 4bd5a4c3ab75c..5542bf2a8fc38 100644
--- a/llvm/lib/Analysis/ScalarEvolution.cpp
+++ b/llvm/lib/Analysis/ScalarEvolution.cpp
@@ -8217,6 +8217,10 @@ unsigned ScalarEvolution::getSmallConstantTripCount(const Loop *L) {
return getConstantTripCount(ExitCount);
}
+ElementCount ScalarEvolution::getSmallConstantRuntimeTripCount(const Loop *L) {
+ return ElementCount::getFixed(getSmallConstantTripCount(L));
+}
+
unsigned
ScalarEvolution::getSmallConstantTripCount(const Loop *L,
const BasicBlock *ExitingBlock) {
diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
index 2fe59a464457f..ad1c698f96f82 100644
--- a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -427,24 +427,24 @@ static bool hasIrregularType(Type *Ty, const DataLayout &DL) {
/// 2) Returns expected trip count according to profile data if any.
/// 3) Returns upper bound estimate if known, and if \p CanUseConstantMax.
/// 4) Returns std::nullopt if all of the above failed.
-static std::optional<unsigned>
+static std::optional<ElementCount>
getSmallBestKnownTC(PredicatedScalarEvolution &PSE, Loop *L,
bool CanUseConstantMax = true) {
// Check if exact trip count is known.
- if (unsigned ExpectedTC = PSE.getSE()->getSmallConstantTripCount(L))
+ if (auto ExpectedTC = PSE.getSE()->getSmallConstantRuntimeTripCount(L))
return ExpectedTC;
// Check if there is an expected trip count available from profile data.
if (LoopVectorizeWithBlockFrequency)
if (auto EstimatedTC = getLoopEstimatedTripCount(L))
- return *EstimatedTC;
+ return ElementCount::getFixed(*EstimatedTC);
if (!CanUseConstantMax)
return std::nullopt;
// Check if upper bound estimate is known.
if (unsigned ExpectedTC = PSE.getSmallConstantMaxTripCount())
- return ExpectedTC;
+ return ElementCount::getFixed(ExpectedTC);
return std::nullopt;
}
@@ -1977,7 +1977,8 @@ class GeneratedRTChecks {
// Get the best known TC estimate.
if (auto EstimatedTC = getSmallBestKnownTC(
PSE, OuterLoop, /* CanUseConstantMax = */ false))
- BestTripCount = *EstimatedTC;
+ if (EstimatedTC->isFixed())
+ BestTripCount = EstimatedTC->getFixedValue();
InstructionCost NewMemCheckCost = MemCheckCost / BestTripCount;
@@ -3751,12 +3752,12 @@ LoopVectorizationCostModel::computeMaxVF(ElementCount UserVF, unsigned UserIC) {
}
ScalarEvolution *SE = PSE.getSE();
- unsigned TC = SE->getSmallConstantTripCount(TheLoop);
+ ElementCount TC = SE->getSmallConstantRuntimeTripCount(TheLoop);
unsigned MaxTC = PSE.getSmallConstantMaxTripCount();
LLVM_DEBUG(dbgs() << "LV: Found trip count: " << TC << '\n');
- if (TC != MaxTC)
+ if (TC != ElementCount::getFixed(MaxTC))
LLVM_DEBUG(dbgs() << "LV: Found maximum trip count: " << MaxTC << '\n');
- if (TC == 1) {
+ if (TC.isScalar()) {
reportVectorizationFailure("Single iteration (non) loop",
"loop trip count is one, irrelevant for vectorization",
"SingleIterationLoop", ORE, TheLoop);
@@ -3870,7 +3871,9 @@ LoopVectorizationCostModel::computeMaxVF(ElementCount UserVF, unsigned UserIC) {
}
auto ExpectedTC = getSmallBestKnownTC(PSE, TheLoop);
- if (ExpectedTC && ExpectedTC <= TTI.getMinTripCountTailFoldingThreshold()) {
+ if (ExpectedTC && ExpectedTC->isFixed() &&
+ ExpectedTC->getFixedValue() <=
+ TTI.getMinTripCountTailFoldingThreshold()) {
if (MaxPowerOf2RuntimeVF > 0u) {
// If we have a low-trip-count, and the fixed-width VF is known to divide
// the trip count but the scalable factor does not, use the fixed-width
@@ -3928,7 +3931,7 @@ LoopVectorizationCostModel::computeMaxVF(ElementCount UserVF, unsigned UserIC) {
return FixedScalableVFPair::getNone();
}
- if (TC == 0) {
+ if (TC.isZero()) {
reportVectorizationFailure(
"unable to calculate the loop count due to complex control flow",
"UnknownLoopCountComplexCFG", ORE, TheLoop);
@@ -5071,13 +5074,13 @@ LoopVectorizationCostModel::selectInterleaveCount(VPlan &Plan, ElementCount VF,
// At least one iteration must be scalar when this constraint holds. So the
// maximum available iterations for interleaving is one less.
unsigned AvailableTC = requiresScalarEpilogue(VF.isVector())
- ? (*BestKnownTC) - 1
- : *BestKnownTC;
+ ? BestKnownTC->getFixedValue() - 1
+ : BestKnownTC->getFixedValue();
unsigned InterleaveCountLB = bit_floor(std::max(
1u, std::min(AvailableTC / (EstimatedVF * 2), MaxInterleaveCount)));
- if (PSE.getSE()->getSmallConstantTripCount(TheLoop) > 0) {
+ if (PSE.getSE()->getSmallConstantRuntimeTripCount(TheLoop).isNonZero()) {
// If the best known trip count is exact, we select between two
// prospective ICs, where
//
@@ -5437,8 +5440,8 @@ InstructionCost LoopVectorizationCostModel::expectedCost(ElementCount VF) {
// costs of comparison and induction instructions, as they'll get simplified
// away.
SmallPtrSet<Instruction *, 2> ValuesToIgnoreForVF;
- auto TC = PSE.getSE()->getSmallConstantTripCount(TheLoop);
- if (VF.isFixed() && TC == VF.getFixedValue() && !foldTailByMasking())
+ auto TC = PSE.getSE()->getSmallConstantRuntimeTripCount(TheLoop);
+ if (TC == VF && !foldTailByMasking())
addFullyUnrolledInstructionsToIgnore(TheLoop, Legal->getInductionVars(),
ValuesToIgnoreForVF);
@@ -7134,8 +7137,8 @@ LoopVectorizationPlanner::precomputeCosts(VPlan &Plan, ElementCount VF,
// simplified away.
// TODO: Remove this code after stepping away from the legacy cost model and
// adding code to simplify VPlans before calculating their costs.
- auto TC = PSE.getSE()->getSmallConstantTripCount(OrigLoop);
- if (VF.isFixed() && TC == VF.getFixedValue() && !CM.foldTailByMasking())
+ auto TC = PSE.getSE()->getSmallConstantRuntimeTripCount(OrigLoop);
+ if (TC == VF && !CM.foldTailByMasking())
addFullyUnrolledInstructionsToIgnore(OrigLoop, Legal->getInductionVars(),
CostCtx.SkipCostComputation);
@@ -9942,8 +9945,7 @@ static bool isOutsideLoopWorkProfitable(GeneratedRTChecks &Checks,
// Skip vectorization if the expected trip count is less than the minimum
// required trip count.
if (auto ExpectedTC = getSmallBestKnownTC(PSE, L)) {
- if (ElementCount::isKnownLT(ElementCount::getFixed(*ExpectedTC),
- VF.MinProfitableTripCount)) {
+ if (ElementCount::isKnownLT(*ExpectedTC, VF.MinProfitableTripCount)) {
LLVM_DEBUG(dbgs() << "LV: Vectorization is not beneficial: expected "
"trip count < minimum profitable VF ("
<< *ExpectedTC << " < " << VF.MinProfitableTripCount
@@ -10300,7 +10302,8 @@ bool LoopVectorizePass::processLoop(Loop *L) {
// Check the loop for a trip count threshold: vectorize loops with a tiny trip
// count by optimizing for size, to minimize overheads.
auto ExpectedTC = getSmallBestKnownTC(PSE, L);
- if (ExpectedTC && *ExpectedTC < TinyTripCountVectorThreshold) {
+ if (ExpectedTC && ExpectedTC->isFixed() &&
+ ExpectedTC->getFixedValue() < TinyTripCountVectorThreshold) {
LLVM_DEBUG(dbgs() << "LV: Found a loop with a very small trip count. "
<< "This loop is worth vectorizing only if no scalar "
<< "iteration overheads are incurred.");
|
|
@llvm/pr-subscribers-vectorizers Author: Paul Walker (paulwalker-arm) ChangesThis is prep work for enabling better UF calculations when using vscale based VFs to vectorise loops with vscale based tripcounts. NOTE: NFC because All uses remain fixed-length until a following PR changes getSmallConstantRuntimeTripCount(). Full diff: https://github.com/llvm/llvm-project/pull/141793.diff 3 Files Affected:
diff --git a/llvm/include/llvm/Analysis/ScalarEvolution.h b/llvm/include/llvm/Analysis/ScalarEvolution.h
index 167845ce646b9..b5faa4c479afd 100644
--- a/llvm/include/llvm/Analysis/ScalarEvolution.h
+++ b/llvm/include/llvm/Analysis/ScalarEvolution.h
@@ -823,6 +823,10 @@ class ScalarEvolution {
/// than the backedge taken count for the loop.
LLVM_ABI unsigned getSmallConstantTripCount(const Loop *L);
+ /// A version of getSmallConstantTripCount that returns as an ElementCount to
+ /// include loops whose trip count is a function of llvm.vscale().
+ ElementCount getSmallConstantRuntimeTripCount(const Loop *L);
+
/// Return the exact trip count for this loop if we exit through ExitingBlock.
/// '0' is used to represent an unknown or non-constant trip count. Note
/// that a trip count is simply one more than the backedge taken count for
diff --git a/llvm/lib/Analysis/ScalarEvolution.cpp b/llvm/lib/Analysis/ScalarEvolution.cpp
index 4bd5a4c3ab75c..5542bf2a8fc38 100644
--- a/llvm/lib/Analysis/ScalarEvolution.cpp
+++ b/llvm/lib/Analysis/ScalarEvolution.cpp
@@ -8217,6 +8217,10 @@ unsigned ScalarEvolution::getSmallConstantTripCount(const Loop *L) {
return getConstantTripCount(ExitCount);
}
+ElementCount ScalarEvolution::getSmallConstantRuntimeTripCount(const Loop *L) {
+ return ElementCount::getFixed(getSmallConstantTripCount(L));
+}
+
unsigned
ScalarEvolution::getSmallConstantTripCount(const Loop *L,
const BasicBlock *ExitingBlock) {
diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
index 2fe59a464457f..ad1c698f96f82 100644
--- a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -427,24 +427,24 @@ static bool hasIrregularType(Type *Ty, const DataLayout &DL) {
/// 2) Returns expected trip count according to profile data if any.
/// 3) Returns upper bound estimate if known, and if \p CanUseConstantMax.
/// 4) Returns std::nullopt if all of the above failed.
-static std::optional<unsigned>
+static std::optional<ElementCount>
getSmallBestKnownTC(PredicatedScalarEvolution &PSE, Loop *L,
bool CanUseConstantMax = true) {
// Check if exact trip count is known.
- if (unsigned ExpectedTC = PSE.getSE()->getSmallConstantTripCount(L))
+ if (auto ExpectedTC = PSE.getSE()->getSmallConstantRuntimeTripCount(L))
return ExpectedTC;
// Check if there is an expected trip count available from profile data.
if (LoopVectorizeWithBlockFrequency)
if (auto EstimatedTC = getLoopEstimatedTripCount(L))
- return *EstimatedTC;
+ return ElementCount::getFixed(*EstimatedTC);
if (!CanUseConstantMax)
return std::nullopt;
// Check if upper bound estimate is known.
if (unsigned ExpectedTC = PSE.getSmallConstantMaxTripCount())
- return ExpectedTC;
+ return ElementCount::getFixed(ExpectedTC);
return std::nullopt;
}
@@ -1977,7 +1977,8 @@ class GeneratedRTChecks {
// Get the best known TC estimate.
if (auto EstimatedTC = getSmallBestKnownTC(
PSE, OuterLoop, /* CanUseConstantMax = */ false))
- BestTripCount = *EstimatedTC;
+ if (EstimatedTC->isFixed())
+ BestTripCount = EstimatedTC->getFixedValue();
InstructionCost NewMemCheckCost = MemCheckCost / BestTripCount;
@@ -3751,12 +3752,12 @@ LoopVectorizationCostModel::computeMaxVF(ElementCount UserVF, unsigned UserIC) {
}
ScalarEvolution *SE = PSE.getSE();
- unsigned TC = SE->getSmallConstantTripCount(TheLoop);
+ ElementCount TC = SE->getSmallConstantRuntimeTripCount(TheLoop);
unsigned MaxTC = PSE.getSmallConstantMaxTripCount();
LLVM_DEBUG(dbgs() << "LV: Found trip count: " << TC << '\n');
- if (TC != MaxTC)
+ if (TC != ElementCount::getFixed(MaxTC))
LLVM_DEBUG(dbgs() << "LV: Found maximum trip count: " << MaxTC << '\n');
- if (TC == 1) {
+ if (TC.isScalar()) {
reportVectorizationFailure("Single iteration (non) loop",
"loop trip count is one, irrelevant for vectorization",
"SingleIterationLoop", ORE, TheLoop);
@@ -3870,7 +3871,9 @@ LoopVectorizationCostModel::computeMaxVF(ElementCount UserVF, unsigned UserIC) {
}
auto ExpectedTC = getSmallBestKnownTC(PSE, TheLoop);
- if (ExpectedTC && ExpectedTC <= TTI.getMinTripCountTailFoldingThreshold()) {
+ if (ExpectedTC && ExpectedTC->isFixed() &&
+ ExpectedTC->getFixedValue() <=
+ TTI.getMinTripCountTailFoldingThreshold()) {
if (MaxPowerOf2RuntimeVF > 0u) {
// If we have a low-trip-count, and the fixed-width VF is known to divide
// the trip count but the scalable factor does not, use the fixed-width
@@ -3928,7 +3931,7 @@ LoopVectorizationCostModel::computeMaxVF(ElementCount UserVF, unsigned UserIC) {
return FixedScalableVFPair::getNone();
}
- if (TC == 0) {
+ if (TC.isZero()) {
reportVectorizationFailure(
"unable to calculate the loop count due to complex control flow",
"UnknownLoopCountComplexCFG", ORE, TheLoop);
@@ -5071,13 +5074,13 @@ LoopVectorizationCostModel::selectInterleaveCount(VPlan &Plan, ElementCount VF,
// At least one iteration must be scalar when this constraint holds. So the
// maximum available iterations for interleaving is one less.
unsigned AvailableTC = requiresScalarEpilogue(VF.isVector())
- ? (*BestKnownTC) - 1
- : *BestKnownTC;
+ ? BestKnownTC->getFixedValue() - 1
+ : BestKnownTC->getFixedValue();
unsigned InterleaveCountLB = bit_floor(std::max(
1u, std::min(AvailableTC / (EstimatedVF * 2), MaxInterleaveCount)));
- if (PSE.getSE()->getSmallConstantTripCount(TheLoop) > 0) {
+ if (PSE.getSE()->getSmallConstantRuntimeTripCount(TheLoop).isNonZero()) {
// If the best known trip count is exact, we select between two
// prospective ICs, where
//
@@ -5437,8 +5440,8 @@ InstructionCost LoopVectorizationCostModel::expectedCost(ElementCount VF) {
// costs of comparison and induction instructions, as they'll get simplified
// away.
SmallPtrSet<Instruction *, 2> ValuesToIgnoreForVF;
- auto TC = PSE.getSE()->getSmallConstantTripCount(TheLoop);
- if (VF.isFixed() && TC == VF.getFixedValue() && !foldTailByMasking())
+ auto TC = PSE.getSE()->getSmallConstantRuntimeTripCount(TheLoop);
+ if (TC == VF && !foldTailByMasking())
addFullyUnrolledInstructionsToIgnore(TheLoop, Legal->getInductionVars(),
ValuesToIgnoreForVF);
@@ -7134,8 +7137,8 @@ LoopVectorizationPlanner::precomputeCosts(VPlan &Plan, ElementCount VF,
// simplified away.
// TODO: Remove this code after stepping away from the legacy cost model and
// adding code to simplify VPlans before calculating their costs.
- auto TC = PSE.getSE()->getSmallConstantTripCount(OrigLoop);
- if (VF.isFixed() && TC == VF.getFixedValue() && !CM.foldTailByMasking())
+ auto TC = PSE.getSE()->getSmallConstantRuntimeTripCount(OrigLoop);
+ if (TC == VF && !CM.foldTailByMasking())
addFullyUnrolledInstructionsToIgnore(OrigLoop, Legal->getInductionVars(),
CostCtx.SkipCostComputation);
@@ -9942,8 +9945,7 @@ static bool isOutsideLoopWorkProfitable(GeneratedRTChecks &Checks,
// Skip vectorization if the expected trip count is less than the minimum
// required trip count.
if (auto ExpectedTC = getSmallBestKnownTC(PSE, L)) {
- if (ElementCount::isKnownLT(ElementCount::getFixed(*ExpectedTC),
- VF.MinProfitableTripCount)) {
+ if (ElementCount::isKnownLT(*ExpectedTC, VF.MinProfitableTripCount)) {
LLVM_DEBUG(dbgs() << "LV: Vectorization is not beneficial: expected "
"trip count < minimum profitable VF ("
<< *ExpectedTC << " < " << VF.MinProfitableTripCount
@@ -10300,7 +10302,8 @@ bool LoopVectorizePass::processLoop(Loop *L) {
// Check the loop for a trip count threshold: vectorize loops with a tiny trip
// count by optimizing for size, to minimize overheads.
auto ExpectedTC = getSmallBestKnownTC(PSE, L);
- if (ExpectedTC && *ExpectedTC < TinyTripCountVectorThreshold) {
+ if (ExpectedTC && ExpectedTC->isFixed() &&
+ ExpectedTC->getFixedValue() < TinyTripCountVectorThreshold) {
LLVM_DEBUG(dbgs() << "LV: Found a loop with a very small trip count. "
<< "This loop is worth vectorizing only if no scalar "
<< "iteration overheads are incurred.");
|
david-arm
approved these changes
Jun 2, 2025
| @@ -823,6 +823,10 @@ class ScalarEvolution { | |||
| /// than the backedge taken count for the loop. | |||
| LLVM_ABI unsigned getSmallConstantTripCount(const Loop *L); | |||
|
|
|||
| /// A version of getSmallConstantTripCount that returns as an ElementCount to | |||
| /// include loops whose trip count is a function of llvm.vscale(). | |||
| ElementCount getSmallConstantRuntimeTripCount(const Loop *L); | |||
There was a problem hiding this comment.
I think this need the same LLVM_ABI prefix as above.
artagnon
changed the title
artagnon
reviewed
Jun 3, 2025
Comment on lines
431
to
432
| getSmallBestKnownTC(PredicatedScalarEvolution &PSE, Loop *L, | ||
| bool CanUseConstantMax = true) { |
There was a problem hiding this comment.
Is it sufficient to change getSmallBestKnownTC to return ElementCount, and not touch SCEV?
There was a problem hiding this comment.
I don't think so because there are other places within LoopVectorize where getSmallConstantTripCount is called that also require the ElementCount returning variant.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This is prep work for enabling better UF calculations when using vscale based VFs to vectorise loops with vscale based tripcounts.
NOTE: NFC because All uses remain fixed-length until a following PR changes getSmallConstantRuntimeTripCount().