[LoopVectorize] Move checking for OptForSize into the cost model (NFC) #130752
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
Move OptForSizeBasedOnProfile into the cost model and rename it to OptForSize, as shouldOptimizeForSize checks both the function attribute and profile. This being done in preparation for OptForSize being used in the cost model.
john-brawn-arm
requested review from
david-arm,
fhahn,
nikic and
paulwalker-arm
Member
|
@llvm/pr-subscribers-llvm-transforms Author: John Brawn (john-brawn-arm) ChangesMove OptForSizeBasedOnProfile into the cost model and rename it to OptForSize, as shouldOptimizeForSize checks both the function attribute and profile. This being done in preparation for OptForSize being used in the cost model. Full diff: https://github.com/llvm/llvm-project/pull/130752.diff 1 Files Affected:
diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
index 02aa21e33bf4f..f0f85c706866b 100644
--- a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -494,12 +494,7 @@ class InnerLoopVectorizer {
MinProfitableTripCount(MinProfitableTripCount), UF(UnrollFactor),
Builder(PSE.getSE()->getContext()), Legal(LVL), Cost(CM), BFI(BFI),
PSI(PSI), RTChecks(RTChecks), Plan(Plan),
- VectorPHVPB(Plan.getEntry()->getSingleSuccessor()) {
- // Query this against the original loop and save it here because the profile
- // of the original loop header may change as the transformation happens.
- OptForSizeBasedOnProfile = llvm::shouldOptimizeForSize(
- OrigLoop->getHeader(), PSI, BFI, PGSOQueryType::IRPass);
- }
+ VectorPHVPB(Plan.getEntry()->getSingleSuccessor()) {}
virtual ~InnerLoopVectorizer() = default;
@@ -672,10 +667,6 @@ class InnerLoopVectorizer {
BlockFrequencyInfo *BFI;
ProfileSummaryInfo *PSI;
- // Whether this loop should be optimized for size based on profile guided size
- // optimizatios.
- bool OptForSizeBasedOnProfile;
-
/// Structure to hold information about generated runtime checks, responsible
/// for cleaning the checks, if vectorization turns out unprofitable.
GeneratedRTChecks &RTChecks;
@@ -987,13 +978,18 @@ class LoopVectorizationCostModel {
AssumptionCache *AC,
OptimizationRemarkEmitter *ORE, const Function *F,
const LoopVectorizeHints *Hints,
- InterleavedAccessInfo &IAI)
+ InterleavedAccessInfo &IAI,
+ ProfileSummaryInfo *PSI, BlockFrequencyInfo *BFI)
: ScalarEpilogueStatus(SEL), TheLoop(L), PSE(PSE), LI(LI), Legal(Legal),
TTI(TTI), TLI(TLI), DB(DB), AC(AC), ORE(ORE), TheFunction(F),
Hints(Hints), InterleaveInfo(IAI) {
if (TTI.supportsScalableVectors() || ForceTargetSupportsScalableVectors)
initializeVScaleForTuning();
CostKind = F->hasMinSize() ? TTI::TCK_CodeSize : TTI::TCK_RecipThroughput;
+ // Query this against the original loop and save it here because the profile
+ // of the original loop header may change as the transformation happens.
+ OptForSize = llvm::shouldOptimizeForSize(L->getHeader(), PSI, BFI,
+ PGSOQueryType::IRPass);
}
/// \return An upper bound for the vectorization factors (both fixed and
@@ -1830,6 +1826,10 @@ class LoopVectorizationCostModel {
/// The kind of cost that we are calculating
TTI::TargetCostKind CostKind;
+
+ /// Whether this loop should be optimized for size based on function attribute
+ /// or profile information.
+ bool OptForSize;
};
} // end namespace llvm
@@ -2602,9 +2602,8 @@ BasicBlock *InnerLoopVectorizer::emitSCEVChecks(BasicBlock *Bypass) {
if (!SCEVCheckBlock)
return nullptr;
- assert(!(SCEVCheckBlock->getParent()->hasOptSize() ||
- (OptForSizeBasedOnProfile &&
- Cost->Hints->getForce() != LoopVectorizeHints::FK_Enabled)) &&
+ assert((!Cost->OptForSize ||
+ Cost->Hints->getForce() == LoopVectorizeHints::FK_Enabled) &&
"Cannot SCEV check stride or overflow when optimizing for size");
assert(!LoopBypassBlocks.empty() &&
"Should already be a bypass block due to iteration count check");
@@ -2629,7 +2628,7 @@ BasicBlock *InnerLoopVectorizer::emitMemRuntimeChecks(BasicBlock *Bypass) {
assert((!EnableVPlanNativePath || OrigLoop->begin() == OrigLoop->end()) &&
"Runtime checks are not supported for outer loops yet");
- if (MemCheckBlock->getParent()->hasOptSize() || OptForSizeBasedOnProfile) {
+ if (Cost->OptForSize) {
assert(Cost->Hints->getForce() == LoopVectorizeHints::FK_Enabled &&
"Cannot emit memory checks when optimizing for size, unless forced "
"to vectorize.");
@@ -10083,7 +10082,7 @@ static bool processLoopInVPlanNativePath(
getScalarEpilogueLowering(F, L, Hints, PSI, BFI, TTI, TLI, *LVL, &IAI);
LoopVectorizationCostModel CM(SEL, L, PSE, LI, LVL, *TTI, TLI, DB, AC, ORE, F,
- &Hints, IAI);
+ &Hints, IAI, PSI, BFI);
// Use the planner for outer loop vectorization.
// TODO: CM is not used at this point inside the planner. Turn CM into an
// optional argument if we don't need it in the future.
@@ -10620,7 +10619,7 @@ bool LoopVectorizePass::processLoop(Loop *L) {
// Use the cost model.
LoopVectorizationCostModel CM(SEL, L, PSE, LI, &LVL, *TTI, TLI, DB, AC, ORE,
- F, &Hints, IAI);
+ F, &Hints, IAI, PSI, BFI);
// Use the planner for vectorization.
LoopVectorizationPlanner LVP(L, LI, DT, TLI, *TTI, &LVL, CM, IAI, PSE, Hints,
ORE);
|
Member
|
@llvm/pr-subscribers-vectorizers Author: John Brawn (john-brawn-arm) ChangesMove OptForSizeBasedOnProfile into the cost model and rename it to OptForSize, as shouldOptimizeForSize checks both the function attribute and profile. This being done in preparation for OptForSize being used in the cost model. Full diff: https://github.com/llvm/llvm-project/pull/130752.diff 1 Files Affected:
diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
index 02aa21e33bf4f..f0f85c706866b 100644
--- a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -494,12 +494,7 @@ class InnerLoopVectorizer {
MinProfitableTripCount(MinProfitableTripCount), UF(UnrollFactor),
Builder(PSE.getSE()->getContext()), Legal(LVL), Cost(CM), BFI(BFI),
PSI(PSI), RTChecks(RTChecks), Plan(Plan),
- VectorPHVPB(Plan.getEntry()->getSingleSuccessor()) {
- // Query this against the original loop and save it here because the profile
- // of the original loop header may change as the transformation happens.
- OptForSizeBasedOnProfile = llvm::shouldOptimizeForSize(
- OrigLoop->getHeader(), PSI, BFI, PGSOQueryType::IRPass);
- }
+ VectorPHVPB(Plan.getEntry()->getSingleSuccessor()) {}
virtual ~InnerLoopVectorizer() = default;
@@ -672,10 +667,6 @@ class InnerLoopVectorizer {
BlockFrequencyInfo *BFI;
ProfileSummaryInfo *PSI;
- // Whether this loop should be optimized for size based on profile guided size
- // optimizatios.
- bool OptForSizeBasedOnProfile;
-
/// Structure to hold information about generated runtime checks, responsible
/// for cleaning the checks, if vectorization turns out unprofitable.
GeneratedRTChecks &RTChecks;
@@ -987,13 +978,18 @@ class LoopVectorizationCostModel {
AssumptionCache *AC,
OptimizationRemarkEmitter *ORE, const Function *F,
const LoopVectorizeHints *Hints,
- InterleavedAccessInfo &IAI)
+ InterleavedAccessInfo &IAI,
+ ProfileSummaryInfo *PSI, BlockFrequencyInfo *BFI)
: ScalarEpilogueStatus(SEL), TheLoop(L), PSE(PSE), LI(LI), Legal(Legal),
TTI(TTI), TLI(TLI), DB(DB), AC(AC), ORE(ORE), TheFunction(F),
Hints(Hints), InterleaveInfo(IAI) {
if (TTI.supportsScalableVectors() || ForceTargetSupportsScalableVectors)
initializeVScaleForTuning();
CostKind = F->hasMinSize() ? TTI::TCK_CodeSize : TTI::TCK_RecipThroughput;
+ // Query this against the original loop and save it here because the profile
+ // of the original loop header may change as the transformation happens.
+ OptForSize = llvm::shouldOptimizeForSize(L->getHeader(), PSI, BFI,
+ PGSOQueryType::IRPass);
}
/// \return An upper bound for the vectorization factors (both fixed and
@@ -1830,6 +1826,10 @@ class LoopVectorizationCostModel {
/// The kind of cost that we are calculating
TTI::TargetCostKind CostKind;
+
+ /// Whether this loop should be optimized for size based on function attribute
+ /// or profile information.
+ bool OptForSize;
};
} // end namespace llvm
@@ -2602,9 +2602,8 @@ BasicBlock *InnerLoopVectorizer::emitSCEVChecks(BasicBlock *Bypass) {
if (!SCEVCheckBlock)
return nullptr;
- assert(!(SCEVCheckBlock->getParent()->hasOptSize() ||
- (OptForSizeBasedOnProfile &&
- Cost->Hints->getForce() != LoopVectorizeHints::FK_Enabled)) &&
+ assert((!Cost->OptForSize ||
+ Cost->Hints->getForce() == LoopVectorizeHints::FK_Enabled) &&
"Cannot SCEV check stride or overflow when optimizing for size");
assert(!LoopBypassBlocks.empty() &&
"Should already be a bypass block due to iteration count check");
@@ -2629,7 +2628,7 @@ BasicBlock *InnerLoopVectorizer::emitMemRuntimeChecks(BasicBlock *Bypass) {
assert((!EnableVPlanNativePath || OrigLoop->begin() == OrigLoop->end()) &&
"Runtime checks are not supported for outer loops yet");
- if (MemCheckBlock->getParent()->hasOptSize() || OptForSizeBasedOnProfile) {
+ if (Cost->OptForSize) {
assert(Cost->Hints->getForce() == LoopVectorizeHints::FK_Enabled &&
"Cannot emit memory checks when optimizing for size, unless forced "
"to vectorize.");
@@ -10083,7 +10082,7 @@ static bool processLoopInVPlanNativePath(
getScalarEpilogueLowering(F, L, Hints, PSI, BFI, TTI, TLI, *LVL, &IAI);
LoopVectorizationCostModel CM(SEL, L, PSE, LI, LVL, *TTI, TLI, DB, AC, ORE, F,
- &Hints, IAI);
+ &Hints, IAI, PSI, BFI);
// Use the planner for outer loop vectorization.
// TODO: CM is not used at this point inside the planner. Turn CM into an
// optional argument if we don't need it in the future.
@@ -10620,7 +10619,7 @@ bool LoopVectorizePass::processLoop(Loop *L) {
// Use the cost model.
LoopVectorizationCostModel CM(SEL, L, PSE, LI, &LVL, *TTI, TLI, DB, AC, ORE,
- F, &Hints, IAI);
+ F, &Hints, IAI, PSI, BFI);
// Use the planner for vectorization.
LoopVectorizationPlanner LVP(L, LI, DT, TLI, *TTI, &LVL, CM, IAI, PSE, Hints,
ORE);
|
david-arm
approved these changes
Mar 11, 2025
Contributor
david-arm
left a comment
david-arm
left a comment
There was a problem hiding this comment.
LGTM! Thanks for splitting this off.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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.
Move OptForSizeBasedOnProfile into the cost model and rename it to OptForSize, as shouldOptimizeForSize checks both the function attribute and profile. This being done in preparation for OptForSize being used in the cost model.