Elvis Wang a068b974b1

[VPlan] Implement VPWidenLoad/StoreEVLRecipe::computeCost(). (#109644) ...

Currently the EVL recipes transfer the tail masking to the EVL.
But in the legacy cost model, the mask exist and will calculate the
instruction cost of the mask.
To fix the difference between the VPlan-based cost model and the legacy
cost model, we always calculate the instruction cost for the mask in the
EVL recipes.

Note that we should remove the mask cost in the EVL recipes when we
don't need to compare to the legacy cost model.

This patch also fixes #109468.

2024-09-26 07:10:25 +08:00

..

blocks-with-dead-instructions.ll

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

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

dead-ops-cost.ll

[VPlan] Implement unrolling as VPlan-to-VPlan transform. (#95842)

2024-09-21 19:47:37 +01:00

defaults.ll

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

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

divrem.ll

[VPlan] Run DCE after unrolling.

2024-09-22 22:08:46 +01:00

evl-compatible-loops.ll

[LV, VPlan] Check if plan is compatible to EVL transform (#92092)

2024-05-25 08:22:49 +08:00

first-order-recurrence-scalable-vf1.ll

[VPlan] Run DCE after unrolling.

2024-09-22 22:08:46 +01:00

force-vect-msg.ll

…

illegal-type.ll

[RISCV][TTI] Scale the cost of ICmp with LMUL (#88235)

2024-04-16 09:37:32 +08:00

induction-costs.ll

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

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

inloop-reduction.ll

[LV] Support binary and unary operations with EVL-vectorization (#93854)

2024-09-06 11:41:36 -04:00

interleaved-accesses-zve32x.ll

[opt] Infer DataLayout from triple if not specified

2023-10-26 12:07:37 -07:00

interleaved-accesses.ll

[VPlan] Run DCE after unrolling.

2024-09-22 22:08:46 +01:00

interleaved-cost.ll

[RISCV] Pass subvector type to isLegalInterleavedAccessType in getInterleavedMemoryOpCost. (#91825)

2024-05-15 21:47:29 -07:00

lit.local.cfg

…

lmul.ll

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

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

low-trip-count.ll

[LV] Remove unnecessary getRuntimeVF call when computing vector TC.

2024-06-12 14:35:37 +01:00

mask-index-type.ll

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

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

masked_gather_scatter.ll

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

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

only-compute-cost-for-vplan-vfs.ll

[VPlan] Don't compute costs if there are no vector VPlans.

2024-06-24 08:38:31 +01:00

ordered-reduction.ll

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

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

pr87378-vpinstruction-or-drop-poison-generating-flags.ll

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

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

pr88802.ll

[VPlan] Generalize VPValue::isDefinedOutsideLoopRegions.

2024-09-20 15:34:00 +01:00

reg-usage-bf16.ll

[RISCV] Add asserts requirement to loop vectorizer tests

2024-09-17 14:18:36 +08:00

reg-usage-f16.ll

[RISCV] Add asserts requirement to loop vectorizer tests

2024-09-17 14:18:36 +08:00

reg-usage.ll

…

riscv-interleaved.ll

…

riscv-unroll.ll

…

riscv-vector-reverse.ll

[VPlan] Implement unrolling as VPlan-to-VPlan transform. (#95842)

2024-09-21 19:47:37 +01:00

safe-dep-distance.ll

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

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

scalable-basics.ll

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

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

scalable-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

scalable-tailfold.ll

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

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

scalable-vf-hint.ll

…

select-cmp-reduction.ll

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

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

short-trip-count.ll

[RISCV][TTI] Properly model odd vector sized LD/ST operations (#100436)

2024-07-26 12:52:20 -07:00

strided-accesses.ll

[VPlan][NFC] Fix the value name of VECTOR_GEP (#107544)

2024-09-18 19:22:36 +08:00

truncate-to-minimal-bitwidth-cost.ll

[VPlan] Generalize VPValue::isDefinedOutsideLoopRegions.

2024-09-20 15:34:00 +01:00

uniform-load-store.ll

[VPlan] Run DCE after unrolling.

2024-09-22 22:08:46 +01:00

unroll-in-loop-vectorizer.ll

…

vectorize-force-tail-with-evl-bin-unary-ops-args.ll

[LV] Support binary and unary operations with EVL-vectorization (#93854)

2024-09-06 11:41:36 -04:00

vectorize-force-tail-with-evl-cond-reduction.ll

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

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

vectorize-force-tail-with-evl-gather-scatter.ll

[LV, VPlan] Check if plan is compatible to EVL transform (#92092)

2024-05-25 08:22:49 +08:00

vectorize-force-tail-with-evl-inloop-reduction.ll

[VPlan] Run DCE after unrolling.

2024-09-22 22:08:46 +01:00

vectorize-force-tail-with-evl-interleave.ll

[VPlan] Run DCE after unrolling.

2024-09-22 22:08:46 +01:00

vectorize-force-tail-with-evl-intermediate-store.ll

[LV][EVL] Support in-loop reduction using tail folding with EVL. (#90184)

2024-07-16 16:15:24 +08:00

vectorize-force-tail-with-evl-iv32.ll

[LV] Remove unnecessary getRuntimeVF call when computing vector TC.

2024-06-12 14:35:37 +01:00

vectorize-force-tail-with-evl-masked-loadstore.ll

[LV] Support binary and unary operations with EVL-vectorization (#93854)

2024-09-06 11:41:36 -04:00

vectorize-force-tail-with-evl-no-masking.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

vectorize-force-tail-with-evl-ordered-reduction.ll

[LV][EVL] Support in-loop reduction using tail folding with EVL. (#90184)

2024-07-16 16:15:24 +08:00

vectorize-force-tail-with-evl-reduction.ll

[VPlan] Run DCE after unrolling.

2024-09-22 22:08:46 +01:00

vectorize-force-tail-with-evl-reverse-load-store.ll

[LV] Support binary and unary operations with EVL-vectorization (#93854)

2024-09-06 11:41:36 -04:00

vectorize-force-tail-with-evl-safe-dep-distance.ll

[LV][VP][NFC]Add tests for safe store/load forwarding/dependence distance.

2024-07-25 19:55:37 -04:00

vectorize-force-tail-with-evl-uniform-store.ll

[VPlan] Implement VPWidenLoad/StoreEVLRecipe::computeCost(). (#109644)

2024-09-26 07:10:25 +08:00

vectorize-vp-intrinsics.ll

[LV] Support binary and unary operations with EVL-vectorization (#93854)

2024-09-06 11:41:36 -04:00

vf-will-not-generate-any-vector-insts.ll

[LV] Add additional test coverage for cost modeling.

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

vplan-vp-intrinsics-reduction.ll

[LV][EVL]Explicitly model AVL as sub, original TC, EVL_PHI.

2024-09-25 08:58:29 -04:00

vplan-vp-intrinsics.ll

[LV][EVL]Explicitly model AVL as sub, original TC, EVL_PHI.

2024-09-25 08:58:29 -04:00

zvl32b.ll

[RISCV] Disable fixed length vectors with Zve32* without Zvl64b. (#102405)

2024-08-08 09:17:43 -07:00