Matt Arsenault 54015f36c6 AMDGPU: Cost model for minimumnum/maximumnum (#141946)

2025-06-18 08:19:06 +09:00

..

add_sub_sat-inseltpoison.ll

[InstCombine] Fold shuffles through all trivially vectorizable intrinsics (#141979)

2025-06-13 18:25:07 +01:00

add_sub_sat.ll

[InstCombine] Fold shuffles through all trivially vectorizable intrinsics (#141979)

2025-06-13 18:25:07 +01:00

address-space-ptr-sze-gep-index-assert.ll

[AMDGPU] Remove explicit datalayout from tests where not needed

2025-04-30 10:58:17 -07:00

bswap-inseltpoison.ll

…

bswap.ll

…

crash_extract_subvector_cost.ll

…

external-shuffle.ll

[SLPVectorizer] Use accurate cost for external users of resize shuffles (#137419)

2025-06-17 08:14:05 -07:00

extract-ordering.ll

[SLP] Sort PHIs by ExtractElements when relevant (#131229)

2025-03-17 14:19:46 -07:00

horizontal-store.ll

…

lit.local.cfg

…

min_max.ll

Revert "[SLP] getSpillCost - fully populate IntrinsicCostAttributes to improve cost analysis." (#124962)

2025-01-29 22:17:53 +00:00

packed-math.ll

AMDGPU: Improve cost handling of canonicalize (#101479)

2024-08-01 19:02:20 +04:00

phi-result-use-order.ll

[SLP] Sort PHIs by ExtractElements when relevant (#131229)

2025-03-17 14:19:46 -07:00

reduction.ll

[SLP]Improved reduction cost/codegen

2025-02-14 11:03:33 -08:00

round-inseltpoison.ll

…

round.ll

[test][SLPVectorizer] Use -passes syntax in RUN lines. NFC

2022-10-13 10:44:38 +02:00

slp-v2f16.ll

AMDGPU: Cost model for minimumnum/maximumnum (#141946)

2025-06-18 08:19:06 +09:00

slp-v2f32.ll

…

vectorize-i8.ll

[AMDGPU][NFC] Add tests in preparation for i8 vectorization (#138801)

2025-05-09 10:32:49 -04:00