Florian Hahn 2dcf858ba0 [LAA] Use SCEVPtrToAddr in tryToCreateDiffChecks. (#178861) ...

The checks created by LAA only compute a pointer difference and do not
need to capture provenance. Use SCEVPtrToAddr instead of SCEVPtrToInt
for computations.

To avoid regressions while parts of SCEV are migrated to use PtrToAddr
this adds logic to rewrite all PtrToInt to PtrToAddr if possible in the
created expressions. This is needed to avoid regressions.

Similarly, if in the original IR we have a PtrToInt, SCEVExpander tries
to re-use it if possible when expanding PtrToAddr.

Depends on https://github.com/llvm/llvm-project/pull/178727.

Fixes https://github.com/llvm/llvm-project/issues/156978.

PR: https://github.com/llvm/llvm-project/pull/178861

2026-02-11 11:51:51 +00:00

..

aarch64-predication.ll

…

aarch64-unroll.ll

…

arbitrary-induction-step.ll

…

arith-fp-frem-costs.ll

…

arm64-unroll.ll

…

backedge-overflow.ll

…

blend-costs.ll

Reapply "[VPlan] Remove legacy costing inside VPBlendRecipe::computeCost (#171846)" (#172261)

2025-12-16 06:30:54 +00:00

bug165359.ll

[LV] Update LoopVectorizationPlanner::emitInvalidCostRemarks to handle reduction plans (#165913)

2025-11-13 06:12:40 -10:00

call-costs.ll

[VPlan] Use DL index type consistently for GEPs (#169396)

2025-11-26 12:25:55 +00:00

check-prof-info.ll

[profcheck] Fix encoding of 0 loopEstimatedTrip count (#174896)

2026-01-12 17:12:35 -08:00

clamped-trip-count.ll

[LV] Teach m_One, m_ZeroInt patterns to look through broadcasts (#170159)

2026-01-07 10:35:08 +00:00

conditional-branches-cost.ll

[LAA] Use SCEVPtrToAddr in tryToCreateDiffChecks. (#178861)

2026-02-11 11:51:51 +00:00

conditional-scalar-assignment.ll

Reland "[LV] Support conditional scalar assignments of masked operations" (#180708)

2026-02-10 09:57:48 +00:00

cost-no-valid-vplans-built.ll

…

deterministic-type-shrinkage.ll

[VPlan] Use DL index type consistently for GEPs (#169396)

2025-11-26 12:25:55 +00:00

divs-with-scalable-vfs.ll

[LV] Teach m_One, m_ZeroInt patterns to look through broadcasts (#170159)

2026-01-07 10:35:08 +00:00

drop-poison-generating-flags.ll

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

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

early_exit_cost.ll

[LV] Add additional tests for early-exit loops loads not known deref.

2026-01-25 23:09:58 +00:00

early_exit_costs.ll

[LV] Separate runtime check cost from total overhead in profitability check (#176754)

2026-01-23 07:29:56 +00:00

eliminate-tail-predication.ll

Reland [VPlan] Simplify pow-of-2 (mul|udiv) -> (shl|lshr) (#174581)

2026-01-06 20:36:26 +00:00

epilog-iv-select-cmp.ll

[VPlan] Use DL index type consistently for GEPs (#169396)

2025-11-26 12:25:55 +00:00

epilog-vectorization-factors.ll

[LAA] Use SCEVPtrToAddr in tryToCreateDiffChecks. (#178861)

2026-02-11 11:51:51 +00:00

epilog-vectorization-widen-inductions.ll

[VPlan] Use DL index type consistently for GEPs (#169396)

2025-11-26 12:25:55 +00:00

epilogue-vectorization-fix-scalar-resume-values.ll

[SCEV] Handle URem pattern in getRangeRef. (#174456)

2026-01-07 11:32:43 +00:00

extend-vectorization-factor-for-unprofitable-memops.ll

…

extractvalue-no-scalarization-required.ll

[VPlan] Permit more users in narrowToSingleScalars (#166559)

2025-11-10 17:03:14 +00:00

f128-fmuladd-reduction.ll

[VPlan] Use DL index type consistently for GEPs (#169396)

2025-11-26 12:25:55 +00:00

findlast-epilogue-loop.ll

[LV] Vectorize conditional scalar assignments (#158088)

2026-01-14 14:59:18 +00:00

first-order-recurrence-fold-tail.ll

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

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

first-order-recurrence.ll

[IR] Split vector.splice into vector.splice.left and vector.splice.right (#170796)

2026-01-06 15:41:26 +08:00

fixed-order-recurrence.ll

[VPlan] Use DL index type consistently for GEPs (#169396)

2025-11-26 12:25:55 +00:00

fixed-wide-lane-mask.ll

[VPlan] Use DL index type consistently for GEPs (#169396)

2025-11-26 12:25:55 +00:00

fmax-without-fast-math-flags.ll

[VPlan] Use DL index type consistently for GEPs (#169396)

2025-11-26 12:25:55 +00:00

fmin-without-fast-math-flags.ll

[VPlan] Use DL index type consistently for GEPs (#169396)

2025-11-26 12:25:55 +00:00

fminimumnum.ll

[LAA] Use SCEVPtrToAddr in tryToCreateDiffChecks. (#178861)

2026-02-11 11:51:51 +00:00

fold-tail-low-trip-count.ll

[LV][NFC] Update low trip count tail-folding tests (#176898)

2026-01-20 12:15:50 +00:00

force-target-instruction-cost.ll

[VPlan] Skip applying InstsToScalarize with forced instr costs. (#168269)

2026-02-09 13:20:44 +00:00

fully-unrolled-cost.ll

[AArch64] Enable maximising scalable vector bandwidth (#166748)

2025-11-26 16:36:54 +00:00

gather-cost.ll

[LV] Check Addr in getAddressAccessSCEV in terms of SCEV expressions. (#171204)

2025-12-19 22:05:27 +00:00

gather-do-not-vectorize-addressing.ll

Reland [VPlan] Simplify pow-of-2 (mul|udiv) -> (shl|lshr) (#174581)

2026-01-06 20:36:26 +00:00

hoist-predicated-loads-scalable.ll

[LV] Add additional cost and folding test coverage. (NFC)

2026-01-14 22:19:11 +00:00

i1-reg-usage.ll

…

induction-costs-sve.ll

[LAA] Use SCEVPtrToAddr in tryToCreateDiffChecks. (#178861)

2026-02-11 11:51:51 +00:00

induction-costs.ll

[VPlan] Sink recipes from the vector loop region in licm. (#168031)

2026-02-03 07:57:15 +00:00

induction-trunc.ll

…

interleave_count_for_estimated_tc.ll

…

interleave_count_for_known_tc.ll

…

interleave-allocsize-not-equal-typesize.ll

…

interleave-with-gaps.ll

[AArch64] Enable maximising scalable vector bandwidth (#166748)

2025-11-26 16:36:54 +00:00

interleave-with-runtime-checks.ll

…

interleaved_cost.ll

…

interleaved-store-of-first-order-recurrence.ll

…

interleaved-vs-scalar.ll

…

interleaving-load-store.ll

[LAA] Use SCEVPtrToAddr in tryToCreateDiffChecks. (#178861)

2026-02-11 11:51:51 +00:00

interleaving-reduction.ll

[AArch64] Add FeatureUseFixedOverScalableIfEqualCost to Neoverse-V3 and Neoverse-V3ae (#179903)

2026-02-05 17:55:49 +00:00

intrinsiccost.ll

[VPlan] Use DL index type consistently for GEPs (#169396)

2025-11-26 12:25:55 +00:00

invalid-costs.ll

Reland [VPlan] Simplify pow-of-2 (mul|udiv) -> (shl|lshr) (#174581)

2026-01-06 20:36:26 +00:00

invariant-replicate-region.ll

[VPlan] Sink recipes from the vector loop region in licm. (#168031)

2026-02-03 07:57:15 +00:00

licm-calls.ll

[VPlan] Use DL index type consistently for GEPs (#169396)

2025-11-26 12:25:55 +00:00

lit.local.cfg

…

load-cast-context.ll

Reland [VPlan] Simplify pow-of-2 (mul|udiv) -> (shl|lshr) (#174581)

2026-01-06 20:36:26 +00:00

loop-vectorization-factors.ll

…

loopvectorize_pr33804_double.ll

…

low_trip_count_predicates.ll

Reland [VPlan] Simplify pow-of-2 (mul|udiv) -> (shl|lshr) (#174581)

2026-01-06 20:36:26 +00:00

low_trip_memcheck_cost.ll

[LV] Always include middle block cost in isOutsideLoopWorkProfitable. (#171102)

2025-12-11 21:41:47 +00:00

masked_ldst_sme.ll

Reland [VPlan] Simplify pow-of-2 (mul|udiv) -> (shl|lshr) (#174581)

2026-01-06 20:36:26 +00:00

masked-call-scalarize.ll

[VPlan] Handle single-scalar conds in VPWidenSelectRecipe. (#165506)

2025-11-05 22:11:29 +00:00

masked-call.ll

Reland [VPlan] Simplify pow-of-2 (mul|udiv) -> (shl|lshr) (#174581)

2026-01-06 20:36:26 +00:00

masked-op-cost.ll

…

max-vf-for-interleaved.ll

…

maxbandwidth-regpressure.ll

[LV] Bundle partial reductions inside VPExpressionRecipe (#147302)

2025-10-23 11:18:55 +00:00

maximize-bandwidth-invalidate.ll

…

mul-simplification.ll

[VPlan] Simplify x + 0 -> x (#169394)

2025-11-25 05:58:41 +00:00

multiple-result-intrinsics.ll

Reland "[LoopVectorize] Support vectorization of overflow intrinsics" (#180526)

2026-02-09 15:32:04 +00:00

neon-gather-cost.ll

…

neon-inloop-reductions.ll

…

neoverse-epilogue-vect.ll

[AArch64] Add FeatureUseFixedOverScalableIfEqualCost to Neoverse-V3 and Neoverse-V3ae (#179903)

2026-02-05 17:55:49 +00:00

no_vector_instructions.ll

…

nontemporal-load-store.ll

[AArch64] Align nontemporal store/load little-endian checks (#177468)

2026-01-27 21:37:21 +02:00

optsize_minsize.ll

[LV] Teach m_One, m_ZeroInt patterns to look through broadcasts (#170159)

2026-01-07 10:35:08 +00:00

outer_loop_prefer_scalable.ll

[VPlan] Simplify single-entry VPWidenPHIRecipe.

2026-02-09 22:10:13 +00:00

outer_loop_test1_no_explicit_vect_width.ll

Reland [VPlan] Expand WidenInt inductions with nuw/nsw (#168354)

2025-11-17 13:44:25 +00:00

Oz-and-forced-vectorize.ll

…

partial-reduce-add-sdot-i16-i32.ll

[AArch64] Define cost of i16->i32 udot/sdot instructions (#174102)

2026-01-12 16:46:25 +00:00

partial-reduce-chained.ll

[LV] Handle partial sub-reductions with sub in middle block. (#178919)

2026-02-10 11:00:32 +00:00

partial-reduce-constant-ops.ll

Reland [VPlan] Simplify pow-of-2 (mul|udiv) -> (shl|lshr) (#174581)

2026-01-06 20:36:26 +00:00

partial-reduce-dot-product-epilogue.ll

Reland [VPlan] Simplify pow-of-2 (mul|udiv) -> (shl|lshr) (#174581)

2026-01-06 20:36:26 +00:00

partial-reduce-dot-product-mixed.ll

Reland [VPlan] Simplify pow-of-2 (mul|udiv) -> (shl|lshr) (#174581)

2026-01-06 20:36:26 +00:00

partial-reduce-dot-product-neon.ll

[VPlan] Sink recipes from the vector loop region in licm. (#168031)

2026-02-03 07:57:15 +00:00

partial-reduce-dot-product.ll

[VPlan] Sink recipes from the vector loop region in licm. (#168031)

2026-02-03 07:57:15 +00:00

partial-reduce-fdot-product.ll

[VPlan] Refine exit select check in transformtoPartialReduction.

2026-02-03 21:07:02 +00:00

partial-reduce-incomplete-chains.ll

[VPlan] Reject partial reductions with invalid costs in getScaledReds. (#180438)

2026-02-10 21:16:21 +00:00

partial-reduce-interleave.ll

[VPlan] Use DL index type consistently for GEPs (#169396)

2025-11-26 12:25:55 +00:00

partial-reduce-no-dotprod.ll

[VPlan] Use DL index type consistently for GEPs (#169396)

2025-11-26 12:25:55 +00:00

partial-reduce-sub-sdot.ll

[LV] Handle partial sub-reductions with sub in middle block. (#178919)

2026-02-10 11:00:32 +00:00

partial-reduce-sub.ll

[LV] Handle partial sub-reductions with sub in middle block. (#178919)

2026-02-10 11:00:32 +00:00

partial-reduce-with-invariant-stores.ll

[LV] Add additional tests for reductions with intermediate stores. (NFC)

2026-02-09 23:14:26 +00:00

partial-reduce.ll

Reland [VPlan] Simplify pow-of-2 (mul|udiv) -> (shl|lshr) (#174581)

2026-01-06 20:36:26 +00:00

pr31900.ll

…

pr33053.ll

[test][Transforms] Remove unsafe-fp-math uses part 2 (NFC) (#164786)

2025-10-23 20:31:31 +08:00

pr36032.ll

[LV][NFC] Remove undef from phi incoming values (#163762)

2025-10-21 10:49:27 +01:00

pr56627.ll

…

pr60831-sve-inv-store-crash.ll

[LV] Teach m_One, m_ZeroInt patterns to look through broadcasts (#170159)

2026-01-07 10:35:08 +00:00

pr73894.ll

…

pr151664-cost-hoisted-vector-scalable.ll

[VPlan] Use DL index type consistently for GEPs (#169396)

2025-11-26 12:25:55 +00:00

pr162009.ll

…

predicated-costs.ll

[VPlan] Mark VPActiveLaneMaskPHIRecipe as readnone. (#177886)

2026-01-30 16:12:30 +00:00

predication_costs.ll

…

prefer-fixed-if-equal-to-scalable.ll

…

reduction-cost.ll

[VPlan] Sink recipes from the vector loop region in licm. (#168031)

2026-02-03 07:57:15 +00:00

reduction-recurrence-costs-sve.ll

Reland [VPlan] Simplify pow-of-2 (mul|udiv) -> (shl|lshr) (#174581)

2026-01-06 20:36:26 +00:00

reduction-small-size.ll

…

reg-usage.ll

[LV] Add register pressure test for #164124.

2025-11-08 21:59:38 +00:00

replicating-load-store-costs-apple.ll

[LV] Add replicating load/store cost tests for Apple CPUs.

2026-01-21 16:37:12 +00:00

replicating-load-store-costs.ll

[VPlan] Use DL index type consistently for GEPs (#169396)

2025-11-26 12:25:55 +00:00

runtime-check-size-based-threshold.ll

…

runtime-check-trip-count-decisions.ll

…

scalable-alloca.ll

…

scalable-avoid-scalarization.ll

[LV] Separate runtime check cost from total overhead in profitability check (#176754)

2026-01-23 07:29:56 +00:00

scalable-call.ll

…

scalable-fp-ext-trunc-illegal-type.ll

…

scalable-predicate-instruction.ll

…

scalable-reduction-inloop-cond.ll

Reland [VPlan] Simplify pow-of-2 (mul|udiv) -> (shl|lshr) (#174581)

2026-01-06 20:36:26 +00:00

scalable-reductions-tf.ll

…

scalable-reductions.ll

[LV] Ignore user-specified interleave count when unsafe. (#153009)

2025-10-22 15:21:27 +01:00

scalable-strict-fadd.ll

Reland [VPlan] Simplify pow-of-2 (mul|udiv) -> (shl|lshr) (#174581)

2026-01-06 20:36:26 +00:00

scalable-struct-return.ll

[LAA] Use SCEVPtrToAddr in tryToCreateDiffChecks. (#178861)

2026-02-11 11:51:51 +00:00

scalable-vectorization-cost-tuning.ll

…

scalable-vectorization.ll

[AArch64] Enable maximising scalable vector bandwidth (#166748)

2025-11-26 16:36:54 +00:00

scalable-vf-hint.ll

…

scalar_interleave.ll

…

scalarize-store-with-predication.ll

…

sdiv-pow2.ll

…

select-costs.ll

Recommit "[VPlan] Only use isAddressSCEVForCost in legacy getAddressAccSCEV"

2026-01-18 19:55:46 +00:00

select-index.ll

[LV] Precommit extra argmin/argmax tests for #170223.

2026-01-26 21:32:50 +00:00

simple_early_exit.ll

[VPlan] Optimize BranchOnTwoConds to chain of 2 simple branches. (#174016)

2026-01-13 20:14:15 +00:00

single-early-exit-interleave.ll

[VPlan] Optimize BranchOnTwoConds to chain of 2 simple branches. (#174016)

2026-01-13 20:14:15 +00:00

smallest-and-widest-types.ll

…

sme-vectorize.ll

…

store-costs-sve.ll

[VPlan] Mark VPActiveLaneMaskPHIRecipe as readnone. (#177886)

2026-01-30 16:12:30 +00:00

streaming-compatible-sve-no-maximize-bandwidth.ll

[VPlan] Drop poison-generating flags on induction trunc (#168922)

2025-11-21 08:14:46 +00:00

streaming-vectorization.ll

…

strict-fadd-cost.ll

…

strict-fadd-vf1.ll

…

strict-fadd.ll

[VPlan] Sink recipes from the vector loop region in licm. (#168031)

2026-02-03 07:57:15 +00:00

struct-return-cost.ll

[VPlan] Directly unroll VectorPointerRecipe (#168886)

2025-12-15 10:54:06 +00:00

sve2-histcnt-epilogue.ll

…

sve2-histcnt-no-scalar-interleave.ll

…

sve2-histcnt-outerloop-scevaddrec.ll

…

sve2-histcnt-too-many-deps.ll

[VPlan] Drop poison-generating flags on induction trunc (#168922)

2025-11-21 08:14:46 +00:00

sve2-histcnt-vplan.ll

[VPlan] Include flags in VectorPointerRecipe::printRecipe (#169466)

2025-11-25 10:26:51 +00:00

sve2-histcnt.ll

[LAA] Use SCEVPtrToAddr in tryToCreateDiffChecks. (#178861)

2026-02-11 11:51:51 +00:00

sve-basic-vec.ll

…

sve-cond-inv-loads.ll

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

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

sve-epilog-vect-inloop-reductions.ll

Reland [VPlan] Simplify pow-of-2 (mul|udiv) -> (shl|lshr) (#174581)

2026-01-06 20:36:26 +00:00

sve-epilog-vect-reductions.ll

Reland [VPlan] Simplify pow-of-2 (mul|udiv) -> (shl|lshr) (#174581)

2026-01-06 20:36:26 +00:00

sve-epilog-vect-strict-reductions.ll

Reland [VPlan] Simplify pow-of-2 (mul|udiv) -> (shl|lshr) (#174581)

2026-01-06 20:36:26 +00:00

sve-epilog-vect-vscale-tune.ll

…

sve-epilog-vect.ll

Reland [VPlan] Simplify pow-of-2 (mul|udiv) -> (shl|lshr) (#174581)

2026-01-06 20:36:26 +00:00

sve-epilog-vscale-fixed.ll

Reland [VPlan] Simplify pow-of-2 (mul|udiv) -> (shl|lshr) (#174581)

2026-01-06 20:36:26 +00:00

sve-extract-last-veclane.ll

…

sve-fixed-width-inorder-core.ll

[LAA] Use SCEVPtrToAddr in tryToCreateDiffChecks. (#178861)

2026-02-11 11:51:51 +00:00

sve-fneg.ll

[LAA] Use SCEVPtrToAddr in tryToCreateDiffChecks. (#178861)

2026-02-11 11:51:51 +00:00

sve-gather-scatter-cost.ll

…

sve-gather-scatter.ll

[VPlan] Directly unroll VectorPointerRecipe (#168886)

2025-12-15 10:54:06 +00:00

sve-illegal-type.ll

…

sve-inductions-unusual-types.ll

[LV] Teach m_One, m_ZeroInt patterns to look through broadcasts (#170159)

2026-01-07 10:35:08 +00:00

sve-inductions.ll

Reland [VPlan] Expand WidenInt inductions with nuw/nsw (#168354)

2025-11-17 13:44:25 +00:00

sve-interleaved-accesses-cost.ll

…

sve-interleaved-accesses.ll

Reland [VPlan] Simplify pow-of-2 (mul|udiv) -> (shl|lshr) (#174581)

2026-01-06 20:36:26 +00:00

sve-interleaved-masked-accesses.ll

Reland [VPlan] Expand WidenInt inductions with nuw/nsw (#168354)

2025-11-17 13:44:25 +00:00

sve-inv-loads.ll

…

sve-inv-store.ll

Reland [VPlan] Simplify pow-of-2 (mul|udiv) -> (shl|lshr) (#174581)

2026-01-06 20:36:26 +00:00

sve-invalid-costs.ll

…

sve-large-strides.ll

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

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

sve-live-out-pointer-induction.ll

Reland [VPlan] Simplify pow-of-2 (mul|udiv) -> (shl|lshr) (#174581)

2026-01-06 20:36:26 +00:00

sve-low-trip-count.ll

Reland [VPlan] Simplify pow-of-2 (mul|udiv) -> (shl|lshr) (#174581)

2026-01-06 20:36:26 +00:00

sve-masked-loadstore.ll

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

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

sve-multiexit.ll

[LAA] Use SCEVPtrToAddr in tryToCreateDiffChecks. (#178861)

2026-02-11 11:51:51 +00:00

sve-predicated-costs.ll

Reland [VPlan] Simplify pow-of-2 (mul|udiv) -> (shl|lshr) (#174581)

2026-01-06 20:36:26 +00:00

sve-runtime-check-size-based-threshold.ll

[LAA] Use SCEVPtrToAddr in tryToCreateDiffChecks. (#178861)

2026-02-11 11:51:51 +00:00

sve-scalable-load-in-loop.ll

…

sve-select-cmp.ll

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

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

sve-strict-fadd-cost.ll

…

sve-tail-folding-cost.ll

…

sve-tail-folding-forced.ll

Reland [VPlan] Simplify pow-of-2 (mul|udiv) -> (shl|lshr) (#174581)

2026-01-06 20:36:26 +00:00

sve-tail-folding-option.ll

[IR] Split vector.splice into vector.splice.left and vector.splice.right (#170796)

2026-01-06 15:41:26 +08:00

sve-tail-folding-optsize.ll

Reland [VPlan] Simplify pow-of-2 (mul|udiv) -> (shl|lshr) (#174581)

2026-01-06 20:36:26 +00:00

sve-tail-folding-overflow-checks.ll

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

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

sve-tail-folding-reductions.ll

Reland [VPlan] Simplify pow-of-2 (mul|udiv) -> (shl|lshr) (#174581)

2026-01-06 20:36:26 +00:00

sve-tail-folding-unroll.ll

Reland [VPlan] Simplify pow-of-2 (mul|udiv) -> (shl|lshr) (#174581)

2026-01-06 20:36:26 +00:00

sve-tail-folding.ll

[LV] Teach m_One, m_ZeroInt patterns to look through broadcasts (#170159)

2026-01-07 10:35:08 +00:00

sve-type-conv.ll

…

sve-vector-reverse-mask4.ll

[VPlan] Extract reverse operation for reverse accesses (#146525)

2025-12-18 14:57:48 +00:00

sve-vector-reverse.ll

[LAA] Use SCEVPtrToAddr in tryToCreateDiffChecks. (#178861)

2026-02-11 11:51:51 +00:00

sve-vfabi.ll

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

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

sve-vscale-based-trip-counts.ll

Reland [VPlan] Simplify pow-of-2 (mul|udiv) -> (shl|lshr) (#174581)

2026-01-06 20:36:26 +00:00

sve-wide-lane-mask.ll

Reland [VPlan] Simplify pow-of-2 (mul|udiv) -> (shl|lshr) (#174581)

2026-01-06 20:36:26 +00:00

sve-widen-extractvalue.ll

Reland [VPlan] Simplify pow-of-2 (mul|udiv) -> (shl|lshr) (#174581)

2026-01-06 20:36:26 +00:00

sve-widen-gep.ll

Reland [VPlan] Simplify pow-of-2 (mul|udiv) -> (shl|lshr) (#174581)

2026-01-06 20:36:26 +00:00

sve-widen-phi.ll

Reland [VPlan] Simplify pow-of-2 (mul|udiv) -> (shl|lshr) (#174581)

2026-01-06 20:36:26 +00:00

synthesize-mask-for-call.ll

[VPlan] Include flags in VectorPointerRecipe::printRecipe (#169466)

2025-11-25 10:26:51 +00:00

tail-fold-uniform-memops.ll

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

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

tail-folding-styles.ll

Reland [VPlan] Simplify pow-of-2 (mul|udiv) -> (shl|lshr) (#174581)

2026-01-06 20:36:26 +00:00

transform-narrow-interleave-to-widen-memory-constant-ops.ll

Revert "[VPlan] Run narrowInterleaveGroups during general VPlan optimizations. (#149706)"

2025-10-22 21:27:11 +01:00

transform-narrow-interleave-to-widen-memory-cost.ll

[VPlan] Use DL index type consistently for GEPs (#169396)

2025-11-26 12:25:55 +00:00

transform-narrow-interleave-to-widen-memory-derived-ivs.ll

[VPlan] Simplify x + 0 -> x (#169394)

2025-11-25 05:58:41 +00:00

transform-narrow-interleave-to-widen-memory-metadata.ll

…

transform-narrow-interleave-to-widen-memory-multi-block.ll

[VPlan] Use DL index type consistently for GEPs (#169396)

2025-11-26 12:25:55 +00:00

transform-narrow-interleave-to-widen-memory-remove-loop-region.ll

Revert "[VPlan] Run narrowInterleaveGroups during general VPlan optimizations. (#149706)"

2025-10-22 21:27:11 +01:00

transform-narrow-interleave-to-widen-memory-scalable.ll

Reland [VPlan] Simplify pow-of-2 (mul|udiv) -> (shl|lshr) (#174581)

2026-01-06 20:36:26 +00:00

transform-narrow-interleave-to-widen-memory-unroll.ll

[VPlan] Use DL index type consistently for GEPs (#169396)

2025-11-26 12:25:55 +00:00

transform-narrow-interleave-to-widen-memory-with-wide-ops-and-casts.ll

[LV] Add tests for narrowing interleave groups with casts.

2025-11-05 20:57:52 +00:00

transform-narrow-interleave-to-widen-memory-with-wide-ops-chained.ll

Reland [VPlan] Simplify pow-of-2 (mul|udiv) -> (shl|lshr) (#174581)

2026-01-06 20:36:26 +00:00

transform-narrow-interleave-to-widen-memory-with-wide-ops.ll

[VPlan] Add VPInstruction to unpack vector values to scalars. (#155670)

2025-10-19 18:49:05 +00:00

transform-narrow-interleave-to-widen-memory.ll

Revert "[VPlan] Run narrowInterleaveGroups during general VPlan optimizations. (#149706)"

2025-10-22 21:27:11 +01:00

type-shrinkage-insertelt.ll

[VPlan] Add VPInstruction to unpack vector values to scalars. (#155670)

2025-10-19 18:49:05 +00:00

type-shrinkage-zext-costs.ll

Reland [VPlan] Simplify pow-of-2 (mul|udiv) -> (shl|lshr) (#174581)

2026-01-06 20:36:26 +00:00

uniform-args-call-variants.ll

[VPlan] Directly unroll VectorPointerRecipe (#168886)

2025-12-15 10:54:06 +00:00

unsafe-vf-hint-remark.ll

…

veclib-calls-libsystem-darwin.ll

…

veclib-function-calls.ll

…

veclib-intrinsic-calls.ll

[AArch64][VecLib] Add vector function mappings for the modf, sincos, sincospi vector intrinsics (#175098)

2026-01-09 18:08:16 +00:00

vector-call-linear-args.ll

…

vector-loop-backedge-elimination-epilogue.ll

[VPlan] Use DL index type consistently for GEPs (#169396)

2025-11-26 12:25:55 +00:00

vector-reverse-mask4.ll

[VPlan] Extract reverse operation for reverse accesses (#146525)

2025-12-18 14:57:48 +00:00

vector-reverse.ll

[LAA] Use SCEVPtrToAddr in tryToCreateDiffChecks. (#178861)

2026-02-11 11:51:51 +00:00

vplan-printing.ll

[VPlan] Replace PhiR operand of ComputeRdxResult with VPIRFlags. (#174026)

2026-01-14 07:45:44 +00:00

widen-call-with-intrinsic-or-libfunc.ll

[VPlan] Include flags in VectorPointerRecipe::printRecipe (#169466)

2025-11-25 10:26:51 +00:00

widen-gep-all-indices-invariant.ll

[LV] Prevent extract-lane generate unused IRs with single vector operand. (#172798)

2026-01-16 13:59:51 +08:00

wider-VF-for-callinst.ll

Reland [VPlan] Simplify pow-of-2 (mul|udiv) -> (shl|lshr) (#174581)

2026-01-06 20:36:26 +00:00