Florian Hahn 6108d50aed [VPlan] Add ReductionStartVector VPInstruction. (#142290) ...

Add a new VPInstruction::ReductionStartVector opcode to create the start
values for wide reductions. This more accurately models the start value
creation in VPlan and simplifies VPReductionPHIRecipe::execute. Down the
line it also allows removing VPReductionPHIRecipe::RdxDesc.

PR: https://github.com/llvm/llvm-project/pull/142290

2025-06-09 20:59:12 +01:00

..

aarch64-predication.ll

[LoopVectorize] Don't replicate blocks with optsize (#129265)

2025-04-17 11:50:49 +01:00

aarch64-unroll.ll

…

arbitrary-induction-step.ll

…

arith-fp-frem-costs.ll

[LoopVectorize][NFC] Fix arith-fp-frem-costs.ll test to use new vplan cost model (#120742)

2025-01-06 10:26:51 +00:00

arm64-unroll.ll

…

backedge-overflow.ll

…

blend-costs.ll

[VPlan] Use VPlan operand order for VPBlendRecipes. (#139475)

2025-05-14 14:56:35 +01:00

call-costs.ll

[VPlan] Use InstSimplifyFolder instead of TargetFolder (#141222)

2025-05-28 11:00:14 +02:00

clamped-trip-count.ll

[VPlan] Add VPInstruction::StepVector and use it in VPWidenIntOrFpInductionRecipe (#129508)

2025-05-08 18:47:44 +08:00

conditional-branches-cost.ll

[VPlan] Don't rely on region check in isUniformAfterVectorization. (#137883)

2025-05-02 15:42:21 +01:00

cost-no-valid-vplans-built.ll

…

deterministic-type-shrinkage.ll

[VPlan] Use InstSimplifyFolder instead of TargetFolder (#141222)

2025-05-28 11:00:14 +02:00

divs-with-scalable-vfs.ll

[VPlan] Add VPInstruction::StepVector and use it in VPWidenIntOrFpInductionRecipe (#129508)

2025-05-08 18:47:44 +08:00

drop-poison-generating-flags.ll

[VPlan] Remove no-op SCALAR-STEPS after unrolling. (#123655)

2025-03-25 12:57:24 +00:00

early_exit_costs.ll

Reapply "[VPlan] Fold NOT into predicate of wide compares." (#130347)

2025-04-28 20:01:37 +01:00

eliminate-tail-predication.ll

[NFC][LLVM][Instrumentation][LoopVectorize] Regenerate test checks.

2025-06-05 11:38:30 +00:00

epilog-iv-select-cmp.ll

[VPlan] Add ReductionStartVector VPInstruction. (#142290)

2025-06-09 20:59:12 +01:00

epilog-vectorization-factors.ll

[VPlan] Generalize SCALAR-STEPS removal to any unroll factor.

2025-03-26 21:03:50 +00:00

epilog-vectorization-widen-inductions.ll

[VPlan] Generalize SCALAR-STEPS removal to any unroll factor.

2025-03-26 21:03:50 +00:00

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

…

extractvalue-no-scalarization-required.ll

[VPlan] Remove no-op SCALAR-STEPS after unrolling. (#123655)

2025-03-25 12:57:24 +00:00

f128-fmuladd-reduction.ll

[LV][AArch64] Add test for fp128 fmuladd reduction.(NFC) (#137576)

2025-04-29 09:18:07 +08:00

first-order-recurrence-fold-tail.ll

[VPlan] Add initial CFG simplification, removing BranchOnCond true. (#106748)

2025-04-04 15:44:26 +01:00

first-order-recurrence.ll

[LLVM][IR] Use splat syntax when printing ConstantExpr based splats. (#116856)

2024-11-21 11:21:12 +00:00

fixed-order-recurrence.ll

[VPlan] Generalize SCALAR-STEPS removal to any unroll factor.

2025-03-26 21:03:50 +00:00

fminimumnum.ll

[NFC][LV] Remove incorrect comment about lack of support (#142126)

2025-05-30 13:25:55 +02:00

force-target-instruction-cost.ll

[VPlan] Generalize SCALAR-STEPS removal to any unroll factor.

2025-03-26 21:03:50 +00:00

fully-unrolled-cost.ll

[LV] Make cost model tests independent of VPValue numbers.

2025-03-27 21:15:32 +00:00

gather-cost.ll

…

gather-do-not-vectorize-addressing.ll

[NFC][LLVM][Instrumentation][LoopVectorize] Regenerate test checks.

2025-06-05 11:38:30 +00:00

i1-reg-usage.ll

[LV] Move VPlan-based calculateRegisterUsage to VPlanAnalysis (NFC). (#135673)

2025-06-02 17:40:50 +01:00

induction-costs-sve.ll

[VPlan] Add initial CFG simplification, removing BranchOnCond true. (#106748)

2025-04-04 15:44:26 +01:00

induction-costs.ll

[VPlan] Generalize SCALAR-STEPS removal to any unroll factor.

2025-03-26 21:03:50 +00:00

induction-trunc.ll

[VPlan] Generalize SCALAR-STEPS removal to any unroll factor.

2025-03-26 21:03:50 +00:00

interleave_count_for_estimated_tc.ll

[LoopUtils] Don't wrap in getLoopEstimatedTripCount (#129080)

2025-03-04 08:43:08 +00:00

interleave_count_for_known_tc.ll

…

interleave-allocsize-not-equal-typesize.ll

[VPlan] Add incoming values for all predecessor to ResumePHI (NFCI).

2025-02-09 11:20:20 +00:00

interleaved_cost.ll

[LoopVectorize] Make needsExtract notice scalarized instructions (#119720)

2025-01-02 14:31:36 +00:00

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

[VPlan] Remove no-op SCALAR-STEPS after unrolling. (#123655)

2025-03-25 12:57:24 +00:00

interleaved-vs-scalar.ll

…

interleaving-load-store.ll

[VPlan] Generalize SCALAR-STEPS removal to any unroll factor.

2025-03-26 21:03:50 +00:00

interleaving-reduction.ll

[VPlan] Generalize SCALAR-STEPS removal to any unroll factor.

2025-03-26 21:03:50 +00:00

intrinsiccost.ll

[VPlan] Add incoming values for all predecessor to ResumePHI (NFCI).

2025-02-09 11:20:20 +00:00

invalid-costs.ll

[VPlan] Return cost of PHI for scalar VFs in computeCost for FORs.

2024-11-21 21:11:21 +00:00

invariant-replicate-region.ll

[VPlan] Use State.get to extract lane mask for BranchOnMask.

2025-01-27 21:35:36 +00:00

lit.local.cfg

…

loop-vectorization-factors.ll

[VPlan] Use InstSimplifyFolder instead of TargetFolder (#141222)

2025-05-28 11:00:14 +02:00

loopvectorize_pr33804_double.ll

[LV] Bail out early if BTC+1 wraps.

2025-01-14 22:07:38 +00:00

low_trip_count_predicates.ll

[VPlan] Add initial CFG simplification, removing BranchOnCond true. (#106748)

2025-04-04 15:44:26 +01:00

low_trip_memcheck_cost.ll

[LoopUtils] Saturate at INT_MAX when estimating TC (#129683)

2025-03-05 18:19:39 +00:00

masked-call-scalarize.ll

Reapply "[VPlan] Fold NOT into predicate of wide compares." (#130347)

2025-04-28 20:01:37 +01:00

masked-call.ll

[VPlan] Use VPlan operand order for VPBlendRecipes. (#139475)

2025-05-14 14:56:35 +01:00

masked-op-cost.ll

Reapply "[VPlan] Fold NOT into predicate of wide compares." (#130347)

2025-04-28 20:01:37 +01:00

max-vf-for-interleaved.ll

…

maximize-bandwidth-invalidate.ll

…

mul-simplification.ll

[VPlan] Only use SCEV for live-ins in tryToWiden. (#125436)

2025-02-03 17:01:02 +00:00

multiple-result-intrinsics.ll

[LV] Teach the vectorizer to cost and vectorize modf and sincospi intrinsics (#129064)

2025-02-28 12:56:12 +00:00

neon-gather-cost.ll

…

neoverse-epilogue-vect.ll

[AArch64][LV] Set MaxInterleaving to 4 for Neoverse V2 and V3 (#100385)

2024-11-20 09:33:39 +00:00

no_vector_instructions.ll

[LoopVectorize][NFC] Disable output for tests that don't need it (#124747)

2025-01-29 08:09:50 +00:00

nontemporal-load-store.ll

Fix regression tests with bad FileCheck checks (#140373)

2025-05-22 07:59:57 +03:00

optsize_minsize.ll

[VPlan] Use InstSimplifyFolder instead of TargetFolder (#141222)

2025-05-28 11:00:14 +02:00

outer_loop_prefer_scalable.ll

[VPlan] Omit zero add in VPWidenIntOrFpInductionRecipe (#119668)

2024-12-16 11:55:48 +08:00

outer_loop_test1_no_explicit_vect_width.ll

…

Oz-and-forced-vectorize.ll

…

partial-reduce-chained.ll

[VPlan] Remove no-op SCALAR-STEPS after unrolling. (#123655)

2025-03-25 12:57:24 +00:00

partial-reduce-dot-product-epilogue.ll

[VPlan] Add ReductionStartVector VPInstruction. (#142290)

2025-06-09 20:59:12 +01:00

partial-reduce-dot-product-mixed.ll

[AArch64] Don't allow mixed partial reductions without i8mm (#137602)

2025-05-01 16:06:37 +01:00

partial-reduce-dot-product-neon.ll

[LV] Reduce register usage for scaled reductions (#133090)

2025-04-11 14:31:08 +01:00

partial-reduce-dot-product.ll

[LoopVectorizer] Prune VFs based on plan register pressure (#132190)

2025-05-19 13:27:17 +01:00

partial-reduce-no-dotprod.ll

[LV] Fix crash when building partial reductions using types that aren't known scale factors (#136680)

2025-04-23 13:19:18 +01:00

partial-reduce-sub.ll

[VPlan] Generalize SCALAR-STEPS removal to any unroll factor.

2025-03-26 21:03:50 +00:00

pr31900.ll

…

pr33053.ll

…

pr36032.ll

…

pr46950-load-cast-context-crash.ll

…

pr56627.ll

…

pr60831-sve-inv-store-crash.ll

[VPlan] Use InstSimplifyFolder instead of TargetFolder (#141222)

2025-05-28 11:00:14 +02:00

pr73894.ll

[VPlan] Add initial CFG simplification, removing BranchOnCond true. (#106748)

2025-04-04 15:44:26 +01:00

predication_costs.ll

…

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

[AArch64] Enable UseFixedOverScalableIfEqualCost for more Cortex-x cpus. (#122807)

2025-01-20 15:05:15 +00:00

reduction-recurrence-costs-sve.ll

[VPlan] Replace VPRegionBlock with explicit CFG before execute (NFCI). (#117506)

2025-05-24 19:17:16 +01:00

reduction-small-size.ll

…

reg-usage.ll

[LV] Move VPlan-based calculateRegisterUsage to VPlanAnalysis (NFC). (#135673)

2025-06-02 17:40:50 +01:00

runtime-check-size-based-threshold.ll

…

runtime-check-trip-count-decisions.ll

…

scalable-alloca.ll

…

scalable-avoid-scalarization.ll

[VPlan] Add VPInstruction::StepVector and use it in VPWidenIntOrFpInductionRecipe (#129508)

2025-05-08 18:47:44 +08:00

scalable-call.ll

[LLVM][IR] Use splat syntax when printing ConstantExpr based splats. (#116856)

2024-11-21 11:21:12 +00:00

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

[VPlan] Remove no-op SCALAR-STEPS after unrolling. (#123655)

2025-03-25 12:57:24 +00:00

scalable-predicate-instruction.ll

…

scalable-reduction-inloop-cond.ll

[VPlan] Remove no-op SCALAR-STEPS after unrolling. (#123655)

2025-03-25 12:57:24 +00:00

scalable-reductions-tf.ll

…

scalable-reductions.ll

…

scalable-strict-fadd.ll

[NFC][LLVM][Instrumentation][LoopVectorize] Regenerate test checks.

2025-06-05 11:38:30 +00:00

scalable-struct-return.ll

[LV] Add initial support for vectorizing literal struct return values (#109833)

2025-02-17 09:51:35 +00:00

scalable-vectorization-cost-tuning.ll

[LoopVectorize][NFC] Disable output for tests that don't need it (#124747)

2025-01-29 08:09:50 +00:00

scalable-vectorization.ll

[LoopVectorize][NFC] Disable output for tests that don't need it (#124747)

2025-01-29 08:09:50 +00:00

scalable-vf-hint.ll

[AArch64] Change the default vscale-for-tuning to 1. (#117174)

2024-11-29 17:41:05 +00:00

scalar_interleave.ll

…

scalarize-store-with-predication.ll

…

sdiv-pow2.ll

…

select-costs.ll

Recommit "[LV][VPlan] Remove any-of reduction from precomputeCost. NFC (#117109)" (#117289)

2024-11-28 15:07:36 +08:00

select-index.ll

[LV] Reorganize index select tests (NFC).

2025-06-08 22:34:07 +01:00

simple_early_exit.ll

Reapply "[VPlan] Fold NOT into predicate of wide compares." (#130347)

2025-04-28 20:01:37 +01:00

smallest-and-widest-types.ll

[LV] Fix '-1U' bits for smallest type in getSmallestAndWidestTypes (#135783)

2025-04-17 13:26:15 +01:00

sme-vectorize.ll

…

store-costs-sve.ll

[VPlan] Manage noalias/alias_scope metadata in VPlan. (#136450)

2025-05-09 11:19:12 +01:00

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

[VPlan] Remove no-op SCALAR-STEPS after unrolling. (#123655)

2025-03-25 12:57:24 +00:00

streaming-vectorization.ll

[LoopVectorize][NFC] Disable output for tests that don't need it (#124747)

2025-01-29 08:09:50 +00:00

strict-fadd-cost.ll

…

strict-fadd-vf1.ll

…

strict-fadd.ll

[VPlan] Simplify BLEND %a, %b, NOT(%m) -> BLEND %b, %a, %m. (#128375)

2025-02-27 17:43:24 +00:00

struct-return-cost.ll

[LV] Add initial support for vectorizing literal struct return values (#109833)

2025-02-17 09:51:35 +00:00

sve2-histcnt-epilogue.ll

[LV][NFC] Regenerate some SVE tests using --filter-out-after option (#132174)

2025-03-31 12:40:41 +01:00

sve2-histcnt-no-scalar-interleave.ll

[InstCombine] Infer nusw + nneg -> nuw for getelementptr (#111144)

2024-12-05 14:36:40 +01:00

sve2-histcnt-outerloop-scevaddrec.ll

[LoopVectorize][NFC] Disable output for tests that don't need it (#124747)

2025-01-29 08:09:50 +00:00

sve2-histcnt-too-many-deps.ll

[LV][NFC] Regenerate some SVE tests using --filter-out-after option (#132174)

2025-03-31 12:40:41 +01:00

sve2-histcnt-vplan.ll

[VPlan] Use regular phi printing for resume phis.

2025-06-07 21:49:54 +01:00

sve2-histcnt.ll

[LV] Fix missing entry in willGenerateVectors (#136712)

2025-04-23 19:06:38 +01:00

sve-basic-vec.ll

[LLVM][IR] Use splat syntax when printing ConstantExpr based splats. (#116856)

2024-11-21 11:21:12 +00:00

sve-cond-inv-loads.ll

[LV][NFC] Regenerate some SVE tests using --filter-out-after option (#132174)

2025-03-31 12:40:41 +01:00

sve-epilog-vect-inloop-reductions.ll

[VPlan] Generalize SCALAR-STEPS removal to any unroll factor.

2025-03-26 21:03:50 +00:00

sve-epilog-vect-reductions.ll

[LV][NFC] Regenerate some SVE tests using --filter-out-after option (#132174)

2025-03-31 12:40:41 +01:00

sve-epilog-vect-strict-reductions.ll

[LV][NFC] Regenerate some SVE tests using --filter-out-after option (#132174)

2025-03-31 12:40:41 +01:00

sve-epilog-vect-vscale-tune.ll

[AArch64][LV] Set MaxInterleaving to 4 for Neoverse V2 and V3 (#100385)

2024-11-20 09:33:39 +00:00

sve-epilog-vect.ll

[LV][NFC] Regenerate some SVE tests using --filter-out-after option (#132174)

2025-03-31 12:40:41 +01:00

sve-extract-last-veclane.ll

…

sve-fixed-width-inorder-core.ll

Recommit [AArch64][SVE]Use FeatureUseFixedOverScalableIfEqualCost for A510/A520 (#134606)

2025-04-07 14:09:43 +01:00

sve-fneg.ll

[LV][NFC] Regenerate some SVE tests using --filter-out-after option (#132174)

2025-03-31 12:40:41 +01:00

sve-gather-scatter-cost.ll

…

sve-gather-scatter.ll

[LV][NFC] Regenerate some SVE tests using --filter-out-after option (#132174)

2025-03-31 12:40:41 +01:00

sve-illegal-type.ll

…

sve-inductions-unusual-types.ll

[VPlan] Add VPInstruction::StepVector and use it in VPWidenIntOrFpInductionRecipe (#129508)

2025-05-08 18:47:44 +08:00

sve-inductions.ll

[LV][NFC] Regenerate some SVE tests using --filter-out-after option (#132174)

2025-03-31 12:40:41 +01:00

sve-interleaved-accesses-cost.ll

[LV] Add test showing cost-model difference after 9491f75e1d.

2025-01-21 21:37:51 +00:00

sve-interleaved-accesses.ll

[LV] Add tests for more interleave group factors on AArch64 and RISC-V. NFC

2025-05-26 18:21:27 +01:00

sve-interleaved-masked-accesses.ll

[VPlan] Add VPInstruction::StepVector and use it in VPWidenIntOrFpInductionRecipe (#129508)

2025-05-08 18:47:44 +08:00

sve-inv-loads.ll

…

sve-inv-store.ll

[LV][NFC] Regenerate some SVE tests using --filter-out-after option (#132174)

2025-03-31 12:40:41 +01:00

sve-invalid-costs.ll

…

sve-large-strides.ll

[LLVM][IR] Use splat syntax when printing ConstantExpr based splats. (#116856)

2024-11-21 11:21:12 +00:00

sve-live-out-pointer-induction.ll

[VPlan] Generalize SCALAR-STEPS removal to any unroll factor.

2025-03-26 21:03:50 +00:00

sve-low-trip-count.ll

[LLVM][IR] Use splat syntax when printing ConstantExpr based splats. (#116856)

2024-11-21 11:21:12 +00:00

sve-masked-loadstore.ll

…

sve-multiexit.ll

[LV][NFC] Regenerate some SVE tests using --filter-out-after option (#132174)

2025-03-31 12:40:41 +01:00

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

[LV] Strip bad FIXME in test (#137142)

2025-04-25 09:47:47 +01:00

sve-scalable-load-in-loop.ll

…

sve-select-cmp.ll

Reapply "[VPlan] Fold NOT into predicate of wide compares." (#130347)

2025-04-28 20:01:37 +01:00

sve-strict-fadd-cost.ll

[VPlan] Implement VPlan-based cost model for VPReduction, VPExtendedReduction and VPMulAccumulateReduction. (#113903)

2025-05-29 11:15:16 +08:00

sve-tail-folding-cost.ll

[LoopVectorize] Add cost of generating tail-folding mask to the loop (#130565)

2025-03-21 09:24:56 +00:00

sve-tail-folding-forced.ll

[VPlan] Connect Entry to scalar preheader during initial construction. (#140132)

2025-05-27 16:07:56 +01:00

sve-tail-folding-option.ll

…

sve-tail-folding-optsize.ll

[VPlan] Add initial CFG simplification, removing BranchOnCond true. (#106748)

2025-04-04 15:44:26 +01:00

sve-tail-folding-overflow-checks.ll

[VPlan] Add initial CFG simplification, removing BranchOnCond true. (#106748)

2025-04-04 15:44:26 +01:00

sve-tail-folding-reductions.ll

[VPlan] Add initial CFG simplification, removing BranchOnCond true. (#106748)

2025-04-04 15:44:26 +01:00

sve-tail-folding-unroll.ll

[VPlan] Add initial CFG simplification, removing BranchOnCond true. (#106748)

2025-04-04 15:44:26 +01:00

sve-tail-folding.ll

Reapply "[VPlan] Fold NOT into predicate of wide compares." (#130347)

2025-04-28 20:01:37 +01:00

sve-type-conv.ll

…

sve-vector-reverse-mask4.ll

…

sve-vector-reverse.ll

[LV][NFC] Regenerate some SVE tests using --filter-out-after option (#132174)

2025-03-31 12:40:41 +01:00

sve-vfabi.ll

…

sve-vscale-based-trip-counts.ll

[NFC][LLVM] Tests for vectorisation of loops with vscale base trip counts.

2025-05-28 12:42:41 +00:00

sve-widen-extractvalue.ll

[VPlan] Restrict hoisting of broadcast operations using VPDominatorTree (#117138)

2025-03-13 07:16:04 -07:00

sve-widen-gep.ll

[NFC][LLVM][Instrumentation][LoopVectorize] Regenerate test checks.

2025-06-05 11:38:30 +00:00

sve-widen-phi.ll

[VPlan] Add VF as operand to VPScalarIVStepsRecipe.

2025-03-28 21:48:59 +00:00

synthesize-mask-for-call.ll

[VPlan] Use regular phi printing for resume phis.

2025-06-07 21:49:54 +01:00

tail-fold-uniform-memops.ll

Reapply "[VPlan] Fold NOT into predicate of wide compares." (#130347)

2025-04-28 20:01:37 +01:00

tail-folding-styles.ll

[VPlan] Add initial CFG simplification, removing BranchOnCond true. (#106748)

2025-04-04 15:44:26 +01:00

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

[VPlan] Generalize SCALAR-STEPS removal to any unroll factor.

2025-03-26 21:03:50 +00:00

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

[VPlan] Re-enable narrowing interleave groups with interleaving.

2025-03-29 20:14:10 +00:00

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

[VPlan] Manage noalias/alias_scope metadata in VPlan. (#136450)

2025-05-09 11:19:12 +01:00

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

[VPlan] Use InstSimplifyFolder instead of TargetFolder (#141222)

2025-05-28 11:00:14 +02:00

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

[VPlan] Don't narrow interleave groups if there are vector pointers.

2025-04-06 22:14:24 +01:00

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

[VPlan] Generalize SCALAR-STEPS removal to any unroll factor.

2025-03-26 21:03:50 +00:00

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

Reapply "[VPlan] Add transformation to narrow interleave groups. (#106441)"

2025-03-25 20:57:10 +00:00

type-shrinkage-insertelt.ll

…

type-shrinkage-zext-costs.ll

[IR] Convert from nocapture to captures(none) (#123181)

2025-01-29 16:56:47 +01:00

uniform-args-call-variants.ll

[InstCombine] Infer nusw + nneg -> nuw for getelementptr (#111144)

2024-12-05 14:36:40 +01:00

unsafe-vf-hint-remark.ll

…

veclib-calls-libsystem-darwin.ll

…

veclib-function-calls.ll

[LV] Use requested calling convention for vector math routines (#136122)

2025-04-22 09:33:52 +01:00

veclib-intrinsic-calls.ll

[LV] Use requested calling convention for vector math routines (#136122)

2025-04-22 09:33:52 +01:00

vector-call-linear-args.ll

…

vector-loop-backedge-elimination-epilogue.ll

[VPlan] Use InstSimplifyFolder instead of TargetFolder (#141222)

2025-05-28 11:00:14 +02:00

vector-reverse-mask4.ll

…

vector-reverse.ll

…

vplan-printing.ll

[VPlan] Add ReductionStartVector VPInstruction. (#142290)

2025-06-09 20:59:12 +01:00

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

[VPlan] Use regular phi printing for resume phis.

2025-06-07 21:49:54 +01:00

wider-VF-for-callinst.ll

[LLVM][IR] Use splat syntax when printing ConstantExpr based splats. (#116856)

2024-11-21 11:21:12 +00:00