Mikhail R. Gadelha e78be31639 [RISCV] Added cost model for fmuladd (#125683) ...

This patch updates the cost model for fmuladd on vector types to scale with LMUL. This was found when analyzing a hot loop in 519.lbm_r that was unprofitably vectorized, but doesn't directly impact that case and is split off so it doesn't get forgotten.

Unlike other FP arithmetic ops, it's not scaled by 2 because the scalar cost isn't scaled by 2.

2025-02-05 09:33:24 -03:00

..

bf16.ll

[RISCV] Added cost model for fmuladd (#125683)

2025-02-05 09:33:24 -03:00

blend-any-of-reduction-cost.ll

[llvm-project] Fix typos mutli and mutliple. NFC. (#122880)

2025-01-14 11:59:41 +00:00

blocks-with-dead-instructions.ll

[VPlan] Compute induction end values in VPlan. (#112145)

2024-12-29 19:05:08 +00:00

dead-ops-cost.ll

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

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

defaults.ll

…

divrem.ll

[VPlan] Handle some VPInstructions in may{Read,Write}FromMemory (#120058)

2025-01-08 15:17:26 +08:00

evl-compatible-loops.ll

…

f16.ll

[RISCV] Enable scalable loop vectorization for zvfhmin/zvfbfmin (#115272)

2024-11-11 13:29:48 +08:00

first-order-recurrence-scalable-vf1.ll

[VPlan] Compute induction end values in VPlan. (#112145)

2024-12-29 19:05:08 +00:00

force-vect-msg.ll

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

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

illegal-type.ll

…

induction-costs.ll

[VPlan] Compute induction end values in VPlan. (#112145)

2024-12-29 19:05:08 +00:00

inloop-reduction.ll

[LV][EVL] Support cast instruction with EVL-vectorization (#108351)

2024-12-11 10:01:41 +08:00

interleaved-accesses-zve32x.ll

…

interleaved-accesses.ll

Revert "[LV]: Teach LV to recursively (de)interleave. (#122989)"

2025-01-21 21:36:16 +00:00

interleaved-cost.ll

[RISCV] Add +optimized-nfN-segment-load-store (#114414)

2024-11-04 06:43:58 +08:00

lit.local.cfg

…

lmul.ll

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

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

low-trip-count.ll

[VPlan] Remove loop region in optimizeForVFAndUF. (#108378)

2025-01-05 15:50:42 +00:00

mask-index-type.ll

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

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

masked_gather_scatter.ll

[VPlan] Compute induction end values in VPlan. (#112145)

2024-12-29 19:05:08 +00:00

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

…

ordered-reduction.ll

…

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

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

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

pr88802.ll

[LV] Use IVUpdateMayOverflow to set HasNUW. (#111758)

2024-11-28 10:12:41 +00:00

preserve-dbg-loc.ll

[VPlan] Set debug location for VPReduction/VPWidenIntrinsicRecipe. (#120054)

2024-12-27 10:37:21 +08:00

reg-usage-bf16.ll

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

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

reg-usage-f16.ll

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

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

reg-usage.ll

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

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

riscv-interleaved.ll

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

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

riscv-unroll.ll

…

riscv-vector-reverse.ll

Reapply "[VPlan] Update final IV exit value via VPlan. (#112147)"

2025-01-19 19:32:03 +00:00

safe-dep-distance.ll

…

scalable-basics.ll

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

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

scalable-reductions.ll

[RISCV] Enable scalable loop vectorization for zvfhmin/zvfbfmin (#115272)

2024-11-11 13:29:48 +08:00

scalable-tailfold.ll

[LV] Use IVUpdateMayOverflow to set HasNUW. (#111758)

2024-11-28 10:12:41 +00:00

scalable-vf-hint.ll

…

select-cmp-reduction.ll

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

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

select-invariant-cond-cost.ll

[VPlan] Also check if plan for best legacy VF contains simplifications.

2024-11-08 20:53:03 +00:00

short-trip-count.ll

[VPlan] Remove loop region in optimizeForVFAndUF. (#108378)

2025-01-05 15:50:42 +00:00

strided-accesses.ll

[VPlan] Compute induction end values in VPlan. (#112145)

2024-12-29 19:05:08 +00:00

truncate-to-minimal-bitwidth-cost.ll

[VPlan] Remove loop region in optimizeForVFAndUF. (#108378)

2025-01-05 15:50:42 +00:00

truncate-to-minimal-bitwidth-evl-crash.ll

[VPlan] Handle VPWidenCastRecipe without underlying value in EVL transform (#120194)

2024-12-18 11:28:07 +08:00

type-info-cache-evl-crash.ll

[LV] Update failing test with middle block. NFC

2024-12-18 11:51:48 +08:00

uniform-load-store.ll

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

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

unroll-in-loop-vectorizer.ll

…

veclib-function-calls.ll

[RISCV][SLEEF]: Support SLEEF vector library for RISC-V target. (#114014)

2024-11-26 12:25:54 +03:00

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

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

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

vectorize-force-tail-with-evl-call-intrinsics.ll

[VPlan] Fix crash with EVL tail folding intrinsic with no corresponding VP (#121542)

2025-01-05 11:41:56 +08:00

vectorize-force-tail-with-evl-cast-intrinsics.ll

[VPlan] Remove reverse() of predecessors from VPInstruction::generate.

2024-12-17 20:44:32 +00:00

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

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

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

vectorize-force-tail-with-evl-fixed-order-recurrence.ll

[LV][EVL] Address post-commit comments for 9720be9. (NFC) (#123311)

2025-01-20 14:20:40 +08:00

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

…

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

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

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

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

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

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

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

[VPlan] Remove reverse() of predecessors from VPInstruction::generate.

2024-12-17 20:44:32 +00:00

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

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

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

vectorize-force-tail-with-evl-known-no-overflow.ll

[LV] Use IVUpdateMayOverflow to set HasNUW. (#111758)

2024-11-28 10:12:41 +00:00

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

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

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

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

…

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

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

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

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

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

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

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

[LV][VPlan] Use opcode to retrieve the VPID of the CallRecipe, rather than underlying instruction (#120816)

2024-12-22 10:28:20 +08:00

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

[VPlan] Fix mutating whilst iterating over users in EVL transform (#122885)

2025-01-14 22:17:51 +08:00

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

[LV] Use IVUpdateMayOverflow to set HasNUW. (#111758)

2024-11-28 10:12:41 +00:00

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

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

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

vectorize-vp-intrinsics.ll

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

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

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

[VPlan] Remove reverse() of predecessors from VPInstruction::generate.

2024-12-17 20:44:32 +00:00

vplan-vp-call-intrinsics.ll

[LV][EVL] Skip tryAddExplicitVectorLength for plans with scalar VF. (#125497)

2025-02-05 15:02:33 +08:00

vplan-vp-cast-intrinsics.ll

[LV][EVL] Skip tryAddExplicitVectorLength for plans with scalar VF. (#125497)

2025-02-05 15:02:33 +08:00

vplan-vp-intrinsics-reduction.ll

[LV][EVL] Skip tryAddExplicitVectorLength for plans with scalar VF. (#125497)

2025-02-05 15:02:33 +08:00

vplan-vp-intrinsics.ll

[LV][EVL] Skip tryAddExplicitVectorLength for plans with scalar VF. (#125497)

2025-02-05 15:02:33 +08:00

vplan-vp-select-intrinsics.ll

[LV][EVL] Skip tryAddExplicitVectorLength for plans with scalar VF. (#125497)

2025-02-05 15:02:33 +08:00

zvl32b.ll

…