Luke Lau 41f1b467a2

[RISCV] Account for zvfhmin and zvfbfmin promotion in register usage (#108370) ...

A half with only zvfhmin or bfloat will end up getting promoted to a f32
for most instructions.

Unless the loop consists only of memory ops and permutation instructions
which don't need promoted (is this common?), we'll end up using double
the LMUL than what's currently being returned by getRegUsageForType.

Since this is used by the loop vectorizer, it seems better to be
conservative and assume that any usage of a zvfhmin half/bfloat will end
up being widened to a f32

2024-09-17 13:50:19 +08:00

..

AArch64

[VPlan] Handle ForceTargetInstructionCost in during precomputeCosts.

2024-09-15 10:53:43 +01:00

AMDGPU

Prefer use of 0.0 over -0.0 for fadd reductions w/nsz (in IR) (#106770)

2024-09-03 09:16:37 -07:00

ARM

[LV] Assign cost to all interleave members when not interleaving.

2024-09-11 21:04:34 +01:00

Hexagon

LoopVectorize/test: fix opt invocations with -march (NFC) (#74462)

2023-12-08 09:56:55 +00:00

LoongArch

[LoongArch] Remove experimental auto-vec feature. (#100070)

2024-07-23 15:19:00 +08:00

PowerPC

[VPlan] Add VPValue for VF, use it for VPWidenIntOrFpInductionRecipe. (#95305)

2024-09-10 10:41:35 +01:00

RISCV

[RISCV] Account for zvfhmin and zvfbfmin promotion in register usage (#108370)

2024-09-17 13:50:19 +08:00

SystemZ

[LV] Assign cost to all interleave members when not interleaving.

2024-09-11 21:04:34 +01:00

VE

[NFC][Py Reformat] Reformat lit.local.cfg python files in llvm

2023-05-17 17:03:15 +02:00

WebAssembly

[LV] Add additional test coverage for cost modeling.

2024-06-26 10:18:01 +01:00

X86

Prefer use of 0.0 over -0.0 for fadd reductions w/nsz (in IR) (#106770)

2024-09-03 09:16:37 -07:00

XCore

[NFC][Py Reformat] Reformat lit.local.cfg python files in llvm

2023-05-17 17:03:15 +02:00

12-12-11-if-conv.ll

…

2012-10-20-infloop.ll

…

2012-10-22-isconsec.ll

…

2016-07-27-loop-vec.ll

…

alias-set-with-uncomputable-bounds.ll

…

align.ll

…

as_cast.ll

[VPlan] Add scalar inferencing support for addrspace cast (#92107)

2024-05-15 14:03:21 +01:00

assume.ll

…

blend-in-header.ll

[VPlan] Don't mark VPBlendRecipe as phi-like.

2024-04-16 21:24:25 +01:00

branch-weights.ll

[VPlan] Model branch cond to enter scalar epilogue in VPlan. (#92651)

2024-07-05 10:08:42 +01:00

bsd_regex.ll

…

bzip_reverse_loops.ll

…

calloc.ll

…

cast-induction.ll

[VPlan] Implement type inference for ICmp.

2024-02-05 15:42:07 +00:00

check-no-vectorize.ll

[LV] Fix emission of debug message in legality check (#101924)

2024-09-04 16:28:39 +05:30

check-prof-info.ll

…

conditional-assignment.ll

…

consec_no_gep.ll

[LoopVectorize] Convert most tests to opaque pointers (NFC)

2023-06-12 13:10:22 +02:00

consecutive-ptr-uniforms.ll

[VPlan] Explicitly handle scalar pointer inductions. (#83068)

2024-03-26 16:01:57 +01:00

control-flow.ll

…

cpp-new-array.ll

…

create-induction-resume.ll

[LV] Make create-induction-resume.ll more robust by adding store.

2024-06-25 11:14:13 +01:00

dbg-outer-loop-vect.ll

[VPlan] Run VPlan optimizations on plans in native path.

2024-08-15 13:05:51 +01:00

dbg.value.ll

…

dead_instructions.ll

[VPlan] Model branch cond to enter scalar epilogue in VPlan. (#92651)

2024-07-05 10:08:42 +01:00

debugloc.ll

[LV] Add test coverage for adding DebugLoc to vector select.

2023-09-04 12:01:14 +01:00

demanded-bits-of-pointer-instruction.ll

…

diag-missing-instr-debug-loc.ll

…

diag-with-hotness-info-2.ll

[LoopDist] Update the pragma info of loop distribute, NFC (#69825)

2023-10-28 17:47:46 +08:00

diag-with-hotness-info.ll

BlockFrequencyInfoImpl: Avoid big numbers, increase precision for small spreads

2023-10-24 20:27:39 -07:00

disable_nonforced_enable.ll

…

disable_nonforced.ll

…

discriminator.ll

[RemoveDIs] Print IR with debug records by default (#91724)

2024-06-14 15:07:27 +01:00

dont-fold-tail-for-const-TC.ll

[VPlan] Model address separately. (#72164)

2024-01-01 19:51:15 +00:00

dont-fold-tail-for-divisible-TC.ll

…

ee-crash.ll

…

epilog-vectorization-any-of-reductions.ll

[VPlan] Model branch cond to enter scalar epilogue in VPlan. (#92651)

2024-07-05 10:08:42 +01:00

epilog-vectorization-reductions.ll

Prefer use of 0.0 over -0.0 for fadd reductions w/nsz (in IR) (#106770)

2024-09-03 09:16:37 -07:00

epilog-vectorization-trunc-induction-steps.ll

[VPlan] Relax IV user assertion after 0ab539f for epilogue vec.

2024-01-26 13:19:25 +00:00

exact.ll

…

explicit_outer_detection.ll

…

explicit_outer_nonuniform_inner.ll

…

explicit_outer_uniform_diverg_branch.ll

…

extract-from-end-vector-constant.ll

[VPlan] Pass live-ins used as exit values straight to live-out.

2024-08-28 19:12:05 +01:00

extract-last-veclane.ll

[InstCombine] Remove some of the complexity-based canonicalization (#91185)

2024-08-21 12:02:54 +02:00

fcmp-vectorize.ll

…

first-order-recurrence-chains-vplan.ll

[VPlan] Only use selectVectorizationFactor for cross-check (NFCI). (#103033)

2024-08-21 13:09:01 +02:00

first-order-recurrence-chains.ll

[VPlan] Introduce explicit ExtractFromEnd recipes for live-outs. (#100658)

2024-08-21 10:06:44 +02:00

first-order-recurrence-complex.ll

[VPlan] Introduce explicit ExtractFromEnd recipes for live-outs. (#100658)

2024-08-21 10:06:44 +02:00

first-order-recurrence-multiply-recurrences.ll

[VPlan] Introduce ResumePhi VPInstruction, use to create phi for FOR. (#94760)

2024-07-11 16:08:04 +01:00

first-order-recurrence-scalable-vf1.ll

[LV] Update tests to not have dead interleave groups.

2024-07-21 14:03:40 +01:00

first-order-recurrence-sink-replicate-region.ll

[VPlan] Add VPIRInstruction, use for exit block live-outs. (#100735)

2024-09-14 21:21:55 +01:00

first-order-recurrence.ll

[VPlan] Introduce ResumePhi VPInstruction, use to create phi for FOR. (#94760)

2024-07-11 16:08:04 +01:00

fix-reduction-dbg.ll

[VPlan] Model branch cond to enter scalar epilogue in VPlan. (#92651)

2024-07-05 10:08:42 +01:00

fixed-order-recurrences-memory-instructions.ll

[LV] Extend recurrence test coverage for sinking memory instructions.

2023-04-17 13:08:15 +01:00

flags.ll

…

float-induction.ll

[InstCombine] Remove some of the complexity-based canonicalization (#91185)

2024-08-21 12:02:54 +02:00

float-minmax-instruction-flag.ll

[VPlan] Model branch cond to enter scalar epilogue in VPlan. (#92651)

2024-07-05 10:08:42 +01:00

float-reduction.ll

…

fneg.ll

…

followup.ll

…

forked-pointers.ll

[InstCombine] Set disjoint flag when turning Add into Or. (#72702)

2023-11-27 12:54:11 -08:00

fpsat.ll

…

funcall.ll

…

gcc-examples.ll

…

gep_with_bitcast.ll

…

global_alias.ll

Revert "[LAA] Remove loop-invariant check added in 234cc40adc61."

2024-08-27 11:55:47 +01:00

hints-trans.ll

…

hoist-loads.ll

…

i8-induction.ll

[DebugInfo][RemoveDIs] Make debugify pass convert to/from RemoveDIs mode (#73251)

2023-11-29 13:19:50 +00:00

icmp-uniforms.ll

[VPlan] Add VPValue for VF, use it for VPWidenIntOrFpInductionRecipe. (#95305)

2024-09-10 10:41:35 +01:00

if-conv-crash.ll

…

if-conversion-edgemasks.ll

…

if-conversion-nest.ll

[LLVM][VPlan] Pick more optimal initial value for VPBlend. (#104019)

2024-08-30 13:30:23 +01:00

if-conversion-reduction.ll

…

if-conversion.ll

…

if-pred-non-void.ll

[VPlan] Remove VPPredInstPHIRecipes without users after region merging.

2024-07-20 13:21:32 +01:00

if-pred-not-when-safe.ll

…

if-pred-stores.ll

[VPlan] Model branch cond to enter scalar epilogue in VPlan. (#92651)

2024-07-05 10:08:42 +01:00

if-reduction.ll

[LLVM][VPlan] Pick more optimal initial value for VPBlend. (#104019)

2024-08-30 13:30:23 +01:00

incorrect-dom-info.ll

…

increment.ll

…

induction_plus.ll

[LoopVectorize] Convert most tests to opaque pointers (NFC)

2023-06-12 13:10:22 +02:00

induction-multiple-uses-in-same-instruction.ll

[VPlan] Preserve original induction order when creating scalar steps.

2024-01-31 13:31:28 +00:00

induction-ptrcasts.ll

…

induction-step.ll

…

induction-unroll-novec.ll

[VPlan] Preserve original induction order when creating scalar steps.

2024-01-31 13:31:28 +00:00

induction.ll

Prefer use of 0.0 over -0.0 for fadd reductions w/nsz (in IR) (#106770)

2024-09-03 09:16:37 -07:00

infiniteloop.ll

…

instruction-only-used-outside-of-loop.ll

[VPlan] Introduce explicit ExtractFromEnd recipes for live-outs. (#100658)

2024-08-21 10:06:44 +02:00

int_sideeffect.ll

…

interleave-and-scalarize-only.ll

[VPlan] Remove VPPredInstPHIRecipes without users after region merging.

2024-07-20 13:21:32 +01:00

interleaved-accesses-1.ll

…

interleaved-accesses-2.ll

…

interleaved-accesses-3.ll

…

interleaved-accesses-alias.ll

…

interleaved-accesses-different-insert-position.ll

[LV] Add extra tests with interleave groups and different insert pos.

2024-08-28 19:35:31 +01:00

interleaved-accesses-masked-group.ll

[Tests] Add disjoint flag to some tests (NFC)

2023-12-05 14:09:36 +01:00

interleaved-accesses-max-dependences.ll

[LV] Complete load groups and release store groups. Try 2.

2023-08-08 18:10:23 -04:00

interleaved-accesses-pred-stores.ll

[InstCombine] Simplify select using KnownBits of condition (#95923)

2024-07-01 09:26:01 +02:00

interleaved-accesses-uniform-load.ll

…

interleaved-accesses.ll

Prefer use of 0.0 over -0.0 for fadd reductions w/nsz (in IR) (#106770)

2024-09-03 09:16:37 -07:00

interleaved-acess-with-remarks.ll

…

intrinsic.ll

[CodeGen] Support vectors across all backends (#95518)

2024-06-14 17:18:20 -04:00

invariant-store-vectorization-2.ll

[InstCombine] Remove some of the complexity-based canonicalization (#91185)

2024-08-21 12:02:54 +02:00

invariant-store-vectorization.ll

[InstCombine] Remove some of the complexity-based canonicalization (#91185)

2024-08-21 12:02:54 +02:00

irregular_type.ll

…

is_fpclass.ll

[LV] Use IRBuilder to create and optimize middle-block compare.

2023-08-29 11:42:18 +01:00

iv_outside_user.ll

[VPlan] Don't add live-outs for IV phis.

2024-07-14 20:49:03 +01:00

iv-select-cmp-no-wrap.ll

[LV][NFC] Remove unnecessary parameter attributes from the test cases. (#67630)

2023-09-28 21:15:34 +08:00

iv-select-cmp-trunc.ll

[LV][NFC] Move and add truncated-related FindLastIV reduction test cases. (#67674)

2023-09-29 22:18:32 +08:00

iv-select-cmp.ll

[LV][NFC] Move and add truncated-related FindLastIV reduction test cases. (#67674)

2023-09-29 22:18:32 +08:00

lcssa-crashes.ll

[Transforms] Convert tests to opaque pointers (NFC)

2024-02-05 11:57:34 +01:00

libcall-remark.ll

…

lifetime.ll

…

load-deref-pred-align.ll

[Analysis] Bail out for negative offsets in isDereferenceableAndAlignedInLoop (#99490)

2024-07-22 11:31:50 +01:00

load-of-struct-deref-pred.ll

[LV] Create block in mask up-front if needed. (#76635)

2024-01-09 10:50:08 +00:00

loop-form.ll

[VPlan] Model branch cond to enter scalar epilogue in VPlan. (#92651)

2024-07-05 10:08:42 +01:00

loop-legality-checks.ll

…

loop-scalars.ll

[InstCombine] Revert the signed icmp -> unsigned icmp canonicalization when folding icmp Pred min|max(X, Y), Z (#76685)

2024-01-05 14:39:16 +08:00

loop-vect-memdep.ll

…

loop-vect-option.ll

…

memdep-fold-tail.ll

…

memdep.ll

…

memory-dep-remarks.ll

[LoopDist] Update the pragma info of loop distribute, NFC (#69825)

2023-10-28 17:47:46 +08:00

metadata-unroll.ll

…

metadata-width.ll

…

metadata.ll

…

middle-block-dbg.ll

…

miniters.ll

…

minmax_reduction.ll

[LV] Add support for minimum/maximum intrinsics

2023-06-20 13:17:28 -04:00

mixed-precision-remarks.ll

…

multi-use-reduction-bug.ll

…

multiple-address-spaces.ll

[InferAlignment] Enable InferAlignment pass by default

2023-09-20 12:08:52 +05:30

multiple-exits-versioning.ll

…

multiple-strides-vectorization.ll

[Tests] Regenerate test checks (NFC)

2024-08-06 12:59:55 +02:00

no_array_bounds_scalable.ll

…

no_array_bounds.ll

…

no_idiv_reduction.ll

…

no_int_induction.ll

…

no_outside_user.ll

[LoopVectorize] Convert most tests to opaque pointers (NFC)

2023-06-12 13:10:22 +02:00

no_switch_disable_vectorization.ll

…

no_switch.ll

[LV] Support generating masks for switch terminators. (#99808)

2024-08-11 20:38:36 +02:00

no-fold-tail-by-masking-iv-external-uses.ll

[VPlan] Don't add live-outs for IV phis.

2024-07-14 20:49:03 +01:00

no-interleave-up-front.ll

…

noalias-md-licm.ll

…

noalias-md.ll

…

noalias-scope-decl.ll

…

nofloat-report.ll

…

nofloat.ll

…

non-const-n.ll

[InferAlignment] Enable InferAlignment pass by default

2023-09-20 12:08:52 +05:30

nontemporal.ll

…

nounroll.ll

…

novect-lcssa-cfg-invalidation.ll

[LV] Preserve LAA in LoopVectorize (NFCI).

2024-07-05 21:41:31 +01:00

nsw-crash.ll

…

nuw.ll

…

opaque-ptr.ll

[LV] Add pointer induction test variant with inbounds, remove TODO.

2024-09-15 21:48:18 +01:00

opt.ll

…

optimal-epilog-vectorization-limitations.ll

…

optimal-epilog-vectorization-liveout.ll

…

optimal-epilog-vectorization-scalable.ll

…

optimal-epilog-vectorization.ll

[VPlan] Preserve original induction order when creating scalar steps.

2024-01-31 13:31:28 +00:00

optsize.ll

…

outer_loop_hcfg_construction.ll

[VPlan] Run VPlan optimizations on plans in native path.

2024-08-15 13:05:51 +01:00

outer_loop_scalable.ll

[VPlan] Add VPValue for VF, use it for VPWidenIntOrFpInductionRecipe. (#95305)

2024-09-10 10:41:35 +01:00

outer_loop_test1.ll

[VPlan] Preserve DT (and SCEV) in VPlan-native path (#93287)

2024-05-27 17:03:53 -07:00

outer_loop_test2.ll

…

outer-loop-vec-phi-predecessor-order.ll

[VPlan] Run VPlan optimizations on plans in native path.

2024-08-15 13:05:51 +01:00

partial-lcssa.ll

…

phi-cost.ll

[LLVM][VPlan] Pick more optimal initial value for VPBlend. (#104019)

2024-08-30 13:30:23 +01:00

phi-hang.ll

…

pointer-induction-unroll.ll

[VPlan] Explicitly handle scalar pointer inductions. (#83068)

2024-03-26 16:01:57 +01:00

pointer-induction.ll

[VPlan] Explicitly handle scalar pointer inductions. (#83068)

2024-03-26 16:01:57 +01:00

pointer-select-runtime-checks.ll

[LoopUtils] Freeze compare results for diff checks instead of pointers.

2023-11-21 10:54:36 +00:00

pr25281.ll

…

pr28541.ll

…

pr30654-phiscev-sext-trunc.ll

[LV] Refresh some auto-gen tests to reduce diff [nfc]

2023-05-01 13:55:11 -07:00

pr30806.ll

…

pr31098.ll

…

pr31190.ll

…

pr32859.ll

[LV] Move check if any vector insts will be generated to VPlan. (#96622)

2024-07-07 20:08:01 +01:00

pr33706.ll

[LV] Regenreate check lines fr pr33706.ll

2023-04-17 13:49:49 +01:00

pr34681.ll

…

pr35743.ll

…

pr35773.ll

[LoopVectorize] Convert most tests to opaque pointers (NFC)

2023-06-12 13:10:22 +02:00

pr36311.ll

…

pr36983.ll

[VPlan] Add VPIRInstruction, use for exit block live-outs. (#100735)

2024-09-14 21:21:55 +01:00

pr37248.ll

[VPlan] Mark some VPInstruction opcodes as not having side effects.

2023-08-22 20:05:57 +01:00

pr37515.ll

…

pr38697.ll

Revert "[test] Autogenerate a test in advance of an upcoming change"

2024-07-01 09:52:56 -07:00

pr38800.ll

…

pr39099.ll

[Tests] Add disjoint flag to some tests (NFC)

2023-12-05 14:09:36 +01:00

pr39417-optsize-scevchecks.ll

[LV] Use IRBuilder to create and optimize middle-block compare.

2023-08-29 11:42:18 +01:00

pr43166-fold-tail-by-masking.ll

…

pr44488-predication.ll

[LV] Use IRBuilder to create and optimize middle-block compare.

2023-08-29 11:42:18 +01:00

pr45259.ll

[VPlan] Add VPIRInstruction, use for exit block live-outs. (#100735)

2024-09-14 21:21:55 +01:00

pr45525.ll

…

pr45679-fold-tail-by-masking.ll

[VPlan] Remove VPPredInstPHIRecipes without users after region merging.

2024-07-20 13:21:32 +01:00

pr46525-expander-insertpoint.ll

[VPlan] Add new VPScalarCastRecipe, use for IV & step trunc. (#78113)

2024-01-26 11:13:05 +00:00

pr47343-expander-lcssa-after-cfg-update.ll

[ConstantFolding] Canonicalize constexpr GEPs to i8 (#89872)

2024-05-20 11:47:30 +02:00

pr48832.ll

…

pr50686.ll

[LV] Use IRBuilder to create and optimize middle-block compare.

2023-08-29 11:42:18 +01:00

pr51614-fold-tail-by-masking.ll

[VPlan] Model branch cond to enter scalar epilogue in VPlan. (#92651)

2024-07-05 10:08:42 +01:00

pr55100-expand-scev-predicate-used.ll

[SCEV] Strengthen nowrap flags via ranges for ARs on construction.

2023-03-07 17:10:34 +01:00

pr55167-fold-tail-live-out.ll

[VPlan] Introduce explicit ExtractFromEnd recipes for live-outs. (#100658)

2024-08-21 10:06:44 +02:00

pr58811-scev-expansion.ll

[VPlan] Don't add live-outs for IV phis.

2024-07-14 20:49:03 +01:00

pr59319-loop-access-info-invalidation.ll

[VPlan] Don't add live-outs for IV phis.

2024-07-14 20:49:03 +01:00

pr66616.ll

[SCEV][LV] Invalidate LCSSA exit phis more thoroughly (#69909)

2023-11-17 09:34:24 +01:00

predicate-switch.ll

[LV] Only OR unique edges when creating block-in masks.

2024-08-12 10:17:40 +01:00

preserve-dbg-loc-and-loop-metadata.ll

[DebugInfo][RemoveDIs] Make debugify pass convert to/from RemoveDIs mode (#73251)

2023-11-29 13:19:50 +00:00

preserve-or-disjoint.ll

[VPlan] Add disjoint flag to VPRecipeWithIRFlags. (#74364)

2023-12-05 15:21:59 +00:00

pseudoprobe.ll

…

ptr_loops.ll

…

ptr-induction.ll

…

read-only.ll

…

reduction-align.ll

[VPlan] Model branch cond to enter scalar epilogue in VPlan. (#92651)

2024-07-05 10:08:42 +01:00

reduction-inloop-cond.ll

[LV] Prefer FLT_MIN/MAX for fmin/fmax reductions with ninf (#107141)

2024-09-03 12:21:54 -07:00

reduction-inloop-min-max.ll

[LV] Reorganize and extend in-loop reduction tests.

2023-07-26 23:23:14 +01:00

reduction-inloop-pred.ll

Prefer use of 0.0 over -0.0 for fadd reductions w/nsz (in IR) (#106770)

2024-09-03 09:16:37 -07:00

reduction-inloop-uf4.ll

[InstCombine] Canonicalize constant GEPs to i8 source element type (#68882)

2024-01-24 15:25:29 +01:00

reduction-inloop.ll

Prefer use of 0.0 over -0.0 for fadd reductions w/nsz (in IR) (#106770)

2024-09-03 09:16:37 -07:00

reduction-odd-interleave-counts.ll

[VPlan] Model branch cond to enter scalar epilogue in VPlan. (#92651)

2024-07-05 10:08:42 +01:00

reduction-order.ll

…

reduction-predselect.ll

Prefer use of 0.0 over -0.0 for fadd reductions w/nsz (in IR) (#106770)

2024-09-03 09:16:37 -07:00

reduction-ptr.ll

…

reduction-small-size.ll

[VPlan] Model branch cond to enter scalar epilogue in VPlan. (#92651)

2024-07-05 10:08:42 +01:00

reduction-with-invariant-store.ll

[LV,LAA] Don't vectorize loops with load and store to invar address.

2024-05-04 20:53:54 +01:00

reduction.ll

Prefer use of 0.0 over -0.0 for fadd reductions w/nsz (in IR) (#106770)

2024-09-03 09:16:37 -07:00

remarks-multi-exit-loops.ll

…

remove_metadata.ll

…

reverse_induction.ll

…

reverse_iter.ll

…

runtime-check-address-space.ll

[AMDGPU,test] Change llc -march= to -mtriple= (#75982)

2024-01-16 21:54:58 -08:00

runtime-check-needed-but-empty.ll

[VPlan] Preserve original induction order when creating scalar steps.

2024-01-31 13:31:28 +00:00

runtime-check-pointer-element-type.ll

…

runtime-check-readonly-address-space.ll

[AMDGPU,test] Change llc -march= to -mtriple= (#75982)

2024-01-16 21:54:58 -08:00

runtime-check-readonly.ll

…

runtime-check-small-clamped-bounds.ll

[LV] Use SCEV for subtraction of src/sink for diff runtime checks.

2023-11-22 12:48:04 +00:00

runtime-check.ll

[InstCombine] Remove some of the complexity-based canonicalization (#91185)

2024-08-21 12:02:54 +02:00

runtime-checks-difference-simplifications.ll

[LAA] Also clear DiffChecks in LAI::reset().

2024-08-14 10:19:29 +01:00

runtime-checks-difference.ll

[LAA] Also reset CanUseDiffCheck in RTPointerChecking::reset().

2024-09-12 09:31:59 +01:00

runtime-checks-hoist.ll

LoopInfo: introduce Loop::getLocStr; unify debug output (#93051)

2024-06-25 13:12:15 +01:00

runtime-drop-crash.ll

…

safegep.ll

…

same-base-access.ll

…

scalable-assume.ll

…

scalable-first-order-recurrence.ll

[VPlan] Add VPValue for VF, use it for VPWidenIntOrFpInductionRecipe. (#95305)

2024-09-10 10:41:35 +01:00

scalable-inductions.ll

[VPlan] Add VPValue for VF, use it for VPWidenIntOrFpInductionRecipe. (#95305)

2024-09-10 10:41:35 +01:00

scalable-lifetime.ll

[VPlan] Compute scalable VF in preheader for induction increment. (#74762)

2023-12-08 12:18:31 +00:00

scalable-loop-unpredicated-body-scalar-tail.ll

[InstCombine] Canonicalize non-i8 gep of mul to i8 (#96606)

2024-06-26 14:25:54 +01:00

scalable-noalias-scope-decl.ll

…

scalable-reduction-inloop.ll

[VPlan] Model branch cond to enter scalar epilogue in VPlan. (#92651)

2024-07-05 10:08:42 +01:00

scalable-trunc-min-bitwidth.ll

[VPlan] Initial modeling of VF * UF as VPValue. (#74761)

2023-12-08 18:30:30 +00:00

scalable-vf-hint.ll

…

scalar_after_vectorization.ll

[InstCombine] Canonicalize constant GEPs to i8 source element type (#68882)

2024-01-24 15:25:29 +01:00

scalar-select.ll

…

scalarize-masked-call.ll

[LV] Use available masked vector function variants when required

2023-04-05 11:18:38 +01:00

scalarized-bitcast.ll

[LoopVectorize] Convert most tests to opaque pointers (NFC)

2023-06-12 13:10:22 +02:00

scev-during-mutation.ll

…

scev-exit-phi-invalidation.ll

[LV] Use IRBuilder to create and optimize middle-block compare.

2023-08-29 11:42:18 +01:00

scev-exitlim-crash.ll

…

scev-invalidation.ll

[LV] Invalidate disposition of SCEV values after loop vectorization (#69230)

2023-10-17 03:49:39 +08:00

scev-predicate-reasoning.ll

[SCEV] Don't add predicates already implied by UnionPredicate. (#93397)

2024-05-26 18:31:36 -07:00

select-cmp-multiuse.ll

[VPlan] Introduce explicit ExtractFromEnd recipes for live-outs. (#100658)

2024-08-21 10:06:44 +02:00

select-cmp-predicated.ll

[VPlan] Model branch cond to enter scalar epilogue in VPlan. (#92651)

2024-07-05 10:08:42 +01:00

select-cmp.ll

[LoopVectorize] LLVM fails to vectorise loops with multi-bool varables (#89226)

2024-07-15 20:21:50 +01:00

select-min-index.ll

[LV] Change the test cases to ensure that the trip count is not zero. (NFC)

2023-07-11 19:12:59 -07:00

select-reduction-start-value-may-be-undef-or-poison.ll

[VPlan] Model branch cond to enter scalar epilogue in VPlan. (#92651)

2024-07-05 10:08:42 +01:00

select-reduction.ll

[VPlan] Model branch cond to enter scalar epilogue in VPlan. (#92651)

2024-07-05 10:08:42 +01:00

simple-unroll.ll

…

single-value-blend-phis.ll

[LLVM][VPlan] Pick more optimal initial value for VPBlend. (#104019)

2024-08-30 13:30:23 +01:00

skeleton-lcssa-crash.ll

[SCEV] Handle more add/addrec mixes in computeConstantDifference() (#101999)

2024-08-13 11:01:39 +02:00

skip-iterations.ll

…

small-loop.ll

…

smax-idx.ll

[LV] Rename the Select[I|F]Cmp reduction pattern to [I|F]AnyOf. (NFC)

2023-08-03 00:37:19 -07:00

start-non-zero.ll

…

store-reduction-results-in-tail-folded-loop.ll

[VPlan] Model branch cond to enter scalar epilogue in VPlan. (#92651)

2024-07-05 10:08:42 +01:00

store-shuffle-bug.ll

…

strict-fadd-interleave-only.ll

[VPlan] Model branch cond to enter scalar epilogue in VPlan. (#92651)

2024-07-05 10:08:42 +01:00

strided-accesses-interleave-only.ll

[LV] Use IRBuilder to create and optimize middle-block compare.

2023-08-29 11:42:18 +01:00

struct_access.ll

…

tail-folding-alloca-in-loop.ll

[LV]Process alloca in isPredicatedInst for tail-folded analysis.

2024-08-05 14:04:54 -04:00

tail-folding-counting-down.ll

…

tail-folding-switch.ll

[LV] Handle SwitchInst in ::isPredicatedInst.

2024-08-11 20:56:58 +01:00

tail-folding-vectorization-factor-1.ll

[VPlan] Explicitly handle scalar pointer inductions. (#83068)

2024-03-26 16:01:57 +01:00

tbaa-nodep.ll

…

trip-count-expansion-may-introduce-ub.ll

[SCEVExpander] Recognize urem idiom during expansion (#96005)

2024-06-19 08:40:04 -07:00

tripcount.ll

…

trunc-extended-icmps.ll

[VPlan] Skip extending ICmp results in trunateToMinimalBitwidth.

2024-04-23 11:50:26 +01:00

trunc-loads-p16.ll

[VPlan] Support narrowing widened loads in truncateToMinimimalBitwidths.

2024-01-12 13:14:13 +00:00

trunc-reductions.ll

[VPlan] Model branch cond to enter scalar epilogue in VPlan. (#92651)

2024-07-05 10:08:42 +01:00

trunc-shifts.ll

[VPlan] Replace IR based truncateToMinimalBitwidths with VPlan version.

2023-12-02 16:12:38 +00:00

undef-inst-bug.ll

…

uniform_across_vf_induction1_and.ll

[LV] Use IRBuilder to create and optimize middle-block compare.

2023-08-29 11:42:18 +01:00

uniform_across_vf_induction1_div_urem.ll

[LV] Use IRBuilder to create and optimize middle-block compare.

2023-08-29 11:42:18 +01:00

uniform_across_vf_induction1_lshr.ll

[LV] Use IRBuilder to create and optimize middle-block compare.

2023-08-29 11:42:18 +01:00

uniform_across_vf_induction1.ll

[LV] Use IRBuilder to create and optimize middle-block compare.

2023-08-29 11:42:18 +01:00

uniform_across_vf_induction2.ll

[VPlan] Preserve original induction order when creating scalar steps.

2024-01-31 13:31:28 +00:00

uniform-args-call-variants.ll

[InstCombine] Remove some of the complexity-based canonicalization (#91185)

2024-08-21 12:02:54 +02:00

uniform-blend.ll

[LoopVectorize] Generate test checks (NFC)

2024-06-25 14:46:12 +02:00

unroll_nonlatch.ll

[Tests] Add disjoint flag to some tests (NFC)

2023-12-05 14:09:36 +01:00

unroll_novec.ll

…

unroll-novec-memcheck-metadata.ll

…

unroll.ll

…

unsafe-dep-remark.ll

[LoopDist] Update the pragma info of loop distribute, NFC (#69825)

2023-10-28 17:47:46 +08:00

unsafe-vf-hint-remark.ll

[VPlan] Emit note when UserVF > MaxUserVF (NFCI).

2024-08-19 12:40:20 +01:00

unused-blend-mask-for-first-operand.ll

[VPlan] Simplify (X && Y) || (X && !Y) -> X. (#89386)

2024-05-19 15:45:23 +00:00

use-iv-start-value.ll

[LV] Amend check for IV increments in collectUsersInEntryBlock (#108020)

2024-09-11 16:43:34 +01:00

use-scalar-epilogue-if-tp-fails.ll

…

value-ptr-bug.ll

…

vect-phiscev-sext-trunc.ll

[VPlan] Preserve original induction order when creating scalar steps.

2024-01-31 13:31:28 +00:00

vect.omp.persistence.ll

…

vect.stats.ll

…

vector-freeze.ll

…

vector-geps.ll

[InstCombine] Canonicalize constant GEPs to i8 source element type (#68882)

2024-01-24 15:25:29 +01:00

vector-intrinsic-call-cost.ll

[LV] Update tests to replace some code with loop varying instructions.

2024-09-09 14:10:12 +01:00

vector-loop-backedge-elimination.ll

…

vector-no-scevcheck.ll

[SCEV] Do not plant SCEV checks unnecessarily

2023-04-25 21:47:14 +01:00

vector-to-scalar-cast.ll

[LV] Check for vector-to-scalar casts in legalizer (#106244)

2024-09-06 11:20:14 +02:00

vectorize-force-tail-with-evl.ll

[LV][NFCI]Use integer for cost/trip count calculations instead of double, fix possible UB.

2024-04-16 09:48:13 -04:00

vectorize-once.ll

…

vectorize-pointer-phis.ll

…

vectorizeVFone.ll

…

version-mem-access.ll

…

version-stride-with-integer-casts.ll

[VPlan] Don't create live-outs for induction increments.

2024-07-25 21:34:55 +01:00

vplan_hcfg_stress_test.ll

[VPlan] Merge main VPlan verifer with HCFG verifier.

2024-02-20 16:43:57 +00:00

vplan-dot-printing.ll

[VPlan] Use ir-bb prefix for VPIRBasicBlock.

2024-05-30 17:43:40 -07:00

vplan-force-tail-with-evl.ll

[LV, VP]VP intrinsics support for the Loop Vectorizer + adding new tail-folding mode using EVL. (#76172)

2024-04-04 18:30:17 -04:00

vplan-incomplete-cases.ll

[LV] Move check if any vector insts will be generated to VPlan. (#96622)

2024-07-07 20:08:01 +01:00

vplan-iv-transforms.ll

[VPlan] Add VPValue for VF, use it for VPWidenIntOrFpInductionRecipe. (#95305)

2024-09-10 10:41:35 +01:00

vplan-outer-loop-uncomputable-trip-count.ll

…

vplan-predicate-switch.ll

[LV] Only OR unique edges when creating block-in masks.

2024-08-12 10:17:40 +01:00

vplan-printing-before-execute.ll

[VPlan] Add VPIRInstruction, use for exit block live-outs. (#100735)

2024-09-14 21:21:55 +01:00

vplan-printing-outer-loop.ll

[VPlan] Update HCFG builder after 72937203dd3b to fix leak.

2024-07-09 15:28:43 +01:00

vplan-printing.ll

[VPlan] Add VPIRInstruction, use for exit block live-outs. (#100735)

2024-09-14 21:21:55 +01:00

vplan-sink-scalars-and-merge-vf1.ll

[VPlan] Model branch cond to enter scalar epilogue in VPlan. (#92651)

2024-07-05 10:08:42 +01:00

vplan-sink-scalars-and-merge.ll

[VPlan] Add VPValue for VF, use it for VPWidenIntOrFpInductionRecipe. (#95305)

2024-09-10 10:41:35 +01:00

vplan-stress-test-no-explict-vf.ll

…

vplan-unused-interleave-group.ll

[VPlan] Implement mayHaveSideEffects/mayWriteToMemory for VPInterleav… (#71360)

2023-12-15 00:23:14 +08:00

vplan-vectorize-inner-loop-reduction.ll

[VPlan] Run VPlan optimizations on plans in native path.

2024-08-15 13:05:51 +01:00

vplan-widen-call-instruction.ll

[VPlan] Run VPlan optimizations on plans in native path.

2024-08-15 13:05:51 +01:00

vplan-widen-select-instruction.ll

…

widen-gep-all-indices-invariant.ll

[LV] Use IRBuilder to create and optimize middle-block compare.

2023-08-29 11:42:18 +01:00

write-only.ll

…