diff options
| author | Florian Hahn <flo@fhahn.com> | 2025-10-06 22:16:08 +0100 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2025-10-06 22:16:08 +0100 |
| commit | 74af5784a570914271a258618bf6f7cb06c50241 (patch) | |
| tree | a90a4425e1bcf342595ebaee050875fd57f1f6a0 /llvm/lib/Transforms/Vectorize/LoopVectorize.cpp | |
| parent | c830c843ab249940811f0bb15924ec94a7b01538 (diff) | |
Reapply "[VPlan] Compute cost of more replicating loads/stores in ::computeCost. (#160053)" (#162157)
This reverts commit f80c0baf058dbdc5 and 94eade61a02ae5.
Recommit a small fix for targets using prefersVectorizedAddressing.
Original message:
Update VPReplicateRecipe::computeCost to compute costs of more
replicating loads/stores.
There are 2 cases that require extra checks to match the legacy cost
model:
1. If the pointer is based on an induction, the legacy cost model passes
its SCEV to getAddressComputationCost. In those cases, still fall back
to the legacy cost. SCEV computations will be added as follow-up
2. If a load is used as part of an address of another load, the legacy
cost model skips the scalarization overhead. Those cases are currently
handled by a usedByLoadOrStore helper.
Note that getScalarizationOverhead also needs updating, because when the
legacy cost model computes the scalarization overhead, scalars have not
been collected yet, so we can't each for replicating recipes to skip
their cost, except other loads. This again can be further improved by
modeling inserts/extracts explicitly and consistently, and compute costs
for those operations directly where needed.
PR: https://github.com/llvm/llvm-project/pull/160053
Diffstat (limited to 'llvm/lib/Transforms/Vectorize/LoopVectorize.cpp')
| -rw-r--r-- | llvm/lib/Transforms/Vectorize/LoopVectorize.cpp | 16 |
1 files changed, 10 insertions, 6 deletions
diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp index d393a9c1506d..cee08ef94aeb 100644 --- a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp +++ b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp @@ -3903,7 +3903,8 @@ void LoopVectorizationPlanner::emitInvalidCostRemarks( if (VF.isScalar()) continue; - VPCostContext CostCtx(CM.TTI, *CM.TLI, *Plan, CM, CM.CostKind); + VPCostContext CostCtx(CM.TTI, *CM.TLI, *Plan, CM, CM.CostKind, + *CM.PSE.getSE()); precomputeCosts(*Plan, VF, CostCtx); auto Iter = vp_depth_first_deep(Plan->getVectorLoopRegion()->getEntry()); for (VPBasicBlock *VPBB : VPBlockUtils::blocksOnly<VPBasicBlock>(Iter)) { @@ -4160,7 +4161,8 @@ VectorizationFactor LoopVectorizationPlanner::selectVectorizationFactor() { // Add on other costs that are modelled in VPlan, but not in the legacy // cost model. - VPCostContext CostCtx(CM.TTI, *CM.TLI, *P, CM, CM.CostKind); + VPCostContext CostCtx(CM.TTI, *CM.TLI, *P, CM, CM.CostKind, + *CM.PSE.getSE()); VPRegionBlock *VectorRegion = P->getVectorLoopRegion(); assert(VectorRegion && "Expected to have a vector region!"); for (VPBasicBlock *VPBB : VPBlockUtils::blocksOnly<VPBasicBlock>( @@ -6852,7 +6854,7 @@ LoopVectorizationPlanner::precomputeCosts(VPlan &Plan, ElementCount VF, InstructionCost LoopVectorizationPlanner::cost(VPlan &Plan, ElementCount VF) const { - VPCostContext CostCtx(CM.TTI, *CM.TLI, Plan, CM, CM.CostKind); + VPCostContext CostCtx(CM.TTI, *CM.TLI, Plan, CM, CM.CostKind, *PSE.getSE()); InstructionCost Cost = precomputeCosts(Plan, VF, CostCtx); // Now compute and add the VPlan-based cost. @@ -7085,7 +7087,8 @@ VectorizationFactor LoopVectorizationPlanner::computeBestVF() { // simplifications not accounted for in the legacy cost model. If that's the // case, don't trigger the assertion, as the extra simplifications may cause a // different VF to be picked by the VPlan-based cost model. - VPCostContext CostCtx(CM.TTI, *CM.TLI, BestPlan, CM, CM.CostKind); + VPCostContext CostCtx(CM.TTI, *CM.TLI, BestPlan, CM, CM.CostKind, + *CM.PSE.getSE()); precomputeCosts(BestPlan, BestFactor.Width, CostCtx); // Verify that the VPlan-based and legacy cost models agree, except for VPlans // with early exits and plans with additional VPlan simplifications. The @@ -8418,7 +8421,8 @@ VPlanPtr LoopVectorizationPlanner::tryToBuildVPlanWithVPRecipes( // TODO: Enable following transform when the EVL-version of extended-reduction // and mulacc-reduction are implemented. if (!CM.foldTailWithEVL()) { - VPCostContext CostCtx(CM.TTI, *CM.TLI, *Plan, CM, CM.CostKind); + VPCostContext CostCtx(CM.TTI, *CM.TLI, *Plan, CM, CM.CostKind, + *CM.PSE.getSE()); VPlanTransforms::runPass(VPlanTransforms::convertToAbstractRecipes, *Plan, CostCtx, Range); } @@ -9874,7 +9878,7 @@ bool LoopVectorizePass::processLoop(Loop *L) { bool ForceVectorization = Hints.getForce() == LoopVectorizeHints::FK_Enabled; VPCostContext CostCtx(CM.TTI, *CM.TLI, LVP.getPlanFor(VF.Width), CM, - CM.CostKind); + CM.CostKind, *CM.PSE.getSE()); if (!ForceVectorization && !isOutsideLoopWorkProfitable(Checks, VF, L, PSE, CostCtx, LVP.getPlanFor(VF.Width), SEL, |
