Alireza Torabian 9bc38df587

[LoopFusion] Simplifying the legality checks (#171889) ...

Considering that the current loop fusion only supports adjacent loops,
we are able to simplify the checks in this pass. By removing
`isControlFlowEquivalent` check, this patch fixes multiple issues
including #166560, #166535, #165031, #80301 and #168263.

Now only the sequential/adjacent candidates are collected in the same
list. This patch is the implementation of approach 2 discussed in post
#171207.

2025-12-12 15:09:34 -05:00

..

ADCE.cpp

…

AlignmentFromAssumptions.cpp

[LLVMContext] Add OB_align assume bundle op ID. (#158078)

2025-09-24 16:03:46 +00:00

AnnotationRemarks.cpp

…

BDCE.cpp

…

CallSiteSplitting.cpp

…

CMakeLists.txt

[DropUnnecessaryAssumes] Add pass for dropping assumes (#159403)

2025-09-18 14:44:04 +00:00

ConstantHoisting.cpp

…

ConstraintElimination.cpp

[ConstraintElim] Apply add with neg constant first during decomp. (#164791)

2025-10-23 12:50:12 +01:00

CorrelatedValuePropagation.cpp

…

DCE.cpp

…

DeadStoreElimination.cpp

[IR] Replace alignment argument with attribute on masked intrinsics (#163802)

2025-10-20 08:50:09 +00:00

DFAJumpThreading.cpp

[DFAJumpThreading] Try harder to avoid cycles in paths. (#169151)

2025-11-22 10:59:27 -08:00

DivRemPairs.cpp

…

DropUnnecessaryAssumes.cpp

[DropAssumes] Drop dereferenceable assumptions after vectorization. (#166947)

2025-11-10 10:50:15 +00:00

EarlyCSE.cpp

[IR] Replace alignment argument with attribute on masked intrinsics (#163802)

2025-10-20 08:50:09 +00:00

FlattenCFGPass.cpp

[NFC][LLVM] Namespace cleanup in FlattenCFGPass.cpp (#163304)

2025-10-14 07:57:09 -07:00

Float2Int.cpp

[Float2Int] Make sure the CFP can be represented in the integer type (#167699)

2025-11-13 20:54:32 +08:00

GuardWidening.cpp

[NFC][LLVM] Namespace cleanup in GuardWidening (#163585)

2025-10-15 17:16:20 -07:00

GVN.cpp

[IR] Replace alignment argument with attribute on masked intrinsics (#163802)

2025-10-20 08:50:09 +00:00

GVNHoist.cpp

…

GVNSink.cpp

[Scalar] Avoid deep copies of DenseMap (NFC) (#168012)

2025-11-13 21:54:16 -08:00

InductiveRangeCheckElimination.cpp

[IRCE] Use function_ref<> instead of optional<function_ref<>> (NFC) (#151308)

2025-07-31 07:56:05 +01:00

IndVarSimplify.cpp

[SCEVExp] Get DL from SE, strip constructor arg (NFC) (#171823)

2025-12-11 14:26:47 +00:00

InferAddressSpaces.cpp

[InferAddressSpaces] Fix bad addrspacecast insertion for phinode (#163528)

2025-11-14 18:55:05 +08:00

InferAlignment.cpp

[InferAlign] Eliminate and ptr, -align pattern (#171147)

2025-12-09 08:04:30 +01:00

InstSimplifyPass.cpp

…

IVUsersPrinter.cpp

…

JumpTableToSwitch.cpp

[NFC][LLVM] Namespace cleanup in JumpTableToSwitch (#163586)

2025-10-15 17:16:44 -07:00

JumpThreading.cpp

[JumpThread] Fix JumpThreading pass to skip merging when both blocks contain convergence loop/entry intrinsics. (#170247)

2025-12-05 02:53:56 +09:00

LICM.cpp

Revert "[LICM] Sink unused l-invariant loads in preheader. #157559"

2025-11-14 14:51:33 +01:00

LoopAccessAnalysisPrinter.cpp

…

LoopBoundSplit.cpp

[SCEVExp] Get DL from SE, strip constructor arg (NFC) (#171823)

2025-12-11 14:26:47 +00:00

LoopDataPrefetch.cpp

[SCEVExp] Get DL from SE, strip constructor arg (NFC) (#171823)

2025-12-11 14:26:47 +00:00

LoopDeletion.cpp

…

LoopDistribute.cpp

[Scalar] Remove a redaundant cast (NFC) (#168284)

2025-11-16 14:06:10 -08:00

LoopFlatten.cpp

[SCEVExp] Get DL from SE, strip constructor arg (NFC) (#171823)

2025-12-11 14:26:47 +00:00

LoopFuse.cpp

[LoopFusion] Simplifying the legality checks (#171889)

2025-12-12 15:09:34 -05:00

LoopIdiomRecognize.cpp

[SCEVExp] Get DL from SE, strip constructor arg (NFC) (#171823)

2025-12-11 14:26:47 +00:00

LoopInstSimplify.cpp

…

LoopInterchange.cpp

[LoopInterchange] Don't consider loops with BTC=0 (#167113)

2025-11-19 13:13:35 +00:00

LoopLoadElimination.cpp

[SCEVExp] Get DL from SE, strip constructor arg (NFC) (#171823)

2025-12-11 14:26:47 +00:00

LoopPassManager.cpp

[SimpleLoopUnswitch] Don't use BlockFrequencyInfo to skip cold loops (#159522)

2025-10-17 23:33:49 +00:00

LoopPredication.cpp

[SCEVExp] Get DL from SE, strip constructor arg (NFC) (#171823)

2025-12-11 14:26:47 +00:00

LoopRotation.cpp

…

LoopSimplifyCFG.cpp

[LSCFG][profcheck] Add dummy branch weights for the dummy switch to dead exits (#164714)

2025-11-05 17:14:03 -08:00

LoopSink.cpp

…

LoopStrengthReduce.cpp

[SCEVExp] Get DL from SE, strip constructor arg (NFC) (#171823)

2025-12-11 14:26:47 +00:00

LoopTermFold.cpp

[SCEVExp] Get DL from SE, strip constructor arg (NFC) (#171823)

2025-12-11 14:26:47 +00:00

LoopUnrollAndJamPass.cpp

…

LoopUnrollPass.cpp

[LoopUnroll] Prevent LoopFullUnrollPass from performing partial unrolling when trip counts are unknown (#165013)

2025-11-04 09:20:01 -08:00

LoopVersioningLICM.cpp

[Polly] Introduce PhaseManager and remove LPM support (#125442) (#167560)

2025-11-14 00:45:54 +01:00

LowerAtomicPass.cpp

…

LowerConstantIntrinsics.cpp

…

LowerExpectIntrinsic.cpp

…

LowerGuardIntrinsic.cpp

…

LowerMatrixIntrinsics.cpp

[Matrix] (NFC) Refactor sharing of shape information (#164774)

2025-11-02 09:44:34 +00:00

LowerWidenableCondition.cpp

…

MakeGuardsExplicit.cpp

…

MemCpyOptimizer.cpp

[MemCpyOpt][profcheck] Set unknown branch weights for certain selects (#167597)

2025-11-14 10:36:50 -08:00

MergedLoadStoreMotion.cpp

…

MergeICmps.cpp

[MergeICmp][profcheck] Propagate profile info (#167594)

2025-11-14 09:29:41 -08:00

NaryReassociate.cpp

[SCEVExp] Get DL from SE, strip constructor arg (NFC) (#171823)

2025-12-11 14:26:47 +00:00

NewGVN.cpp

[NFC][LLVM] Namespace cleanup in NewGVN (#163763)

2025-10-16 10:14:27 -07:00

PartiallyInlineLibCalls.cpp

[PILC][profcheck] Bias branch weights when optimizing sqrt (#167742)

2025-11-13 12:46:22 -08:00

PlaceSafepoints.cpp

…

Reassociate.cpp

[NFC][LLVM] Fix indentation of ReassociateLegacyPass in Reassociate.cpp (#163764)

2025-10-16 10:15:21 -07:00

Reg2Mem.cpp

[NFC][LLVM] Namespace cleanup in Reg2Mem.cpp (#163765)

2025-10-17 13:20:43 +02:00

RewriteStatepointsForGC.cpp

[llvm] Remove unused includes of SmallSet.h (NFC) (#154893)

2025-08-22 10:33:46 -07:00

Scalar.cpp

[DirectX] Remove lifetime intrinsics and run Dead Store Elimination (#152636)

2025-08-12 12:42:08 -04:00

ScalarizeMaskedMemIntrin.cpp

[NVPTX] Lower LLVM masked vector loads and stores to PTX (#159387)

2025-11-25 10:26:15 -06:00

Scalarizer.cpp

Scalarizer : Fix vector shuffle issue when can't aligned to customized minBits. (#163912)

2025-12-08 18:06:39 +00:00

SCCP.cpp

[SCCP] Enable PredicateInfo for non-interprocedural SCCP (#153003)

2025-08-19 10:59:38 +02:00

SeparateConstOffsetFromGEP.cpp

[SeparateConstOffsetFromGEP] Check if non-extracted indices may be negative when preserving inbounds (#159515)

2025-09-19 09:01:14 +02:00

SimpleLoopUnswitch.cpp

[llvm] Use llvm::size (NFC) (#168675)

2025-11-19 07:29:57 -08:00

SimplifyCFGPass.cpp

[SimplifyCFG] Allow some switch optimizations early in the pipeline (#158242)

2025-10-08 14:24:29 +02:00

Sink.cpp

…

SpeculativeExecution.cpp

[SpeculativeExecution] Add support for ptrtoaddr

2025-10-20 16:56:11 +02:00

SROA.cpp

SROA: Recognize llvm.protected.field.ptr intrinsics.

2025-12-11 18:22:05 -08:00

StraightLineStrengthReduce.cpp

Reland "Redesign Straight-Line Strength Reduction (SLSR) (#162930)" (#169614)

2025-12-08 16:07:27 -06:00

StructurizeCFG.cpp

Reapply: [AMDGPU][UnifyDivergentExitNodes][StructurizeCFG] Add support for callbr instruction with inline-asm (#152161) (#166195)

2025-11-03 20:59:48 +01:00

TailRecursionElimination.cpp

[NFC][LLVM] Add end namespace comments to TailRecursionElimination (#163771)

2025-10-16 10:17:23 -07:00

WarnMissedTransforms.cpp

…