SLOTHY-OPT: Run poly_decompose_32_asm.S through SLOTHY

[willieyz]

• according to Run poly_caddq through SLOTHY #509 (comment), this PR add Makefile and run the poly_decompose_32_asm.S through SLOTHY,
• Similar with PR Run Neon NTT+iNTT through SLOTHY #221 , this PR follow its structure.

[github-actions]

Mac Mini (M1, 2020) benchmarks (opt)

Benchmark suite	Current: e237512	Previous: d6f0aff	Ratio
ML-DSA-44 keypair	47880 cycles	47864 cycles	1.00
ML-DSA-44 sign	157684 cycles	157629 cycles	1.00
ML-DSA-44 verify	52386 cycles	52369 cycles	1.00
ML-DSA-65 keypair	83676 cycles	83696 cycles	1.00
ML-DSA-65 sign	255450 cycles	255541 cycles	1.00
ML-DSA-65 verify	85607 cycles	85600 cycles	1.00
ML-DSA-87 keypair	135664 cycles	135671 cycles	1.00
ML-DSA-87 sign	320963 cycles	321128 cycles	1.00
ML-DSA-87 verify	137891 cycles	137903 cycles	1.00

This comment was automatically generated by workflow using github-action-benchmark.

[github-actions]

Mac Mini (M1, 2020) benchmarks (no-opt)

Benchmark suite	Current: e237512	Previous: d6f0aff	Ratio
ML-DSA-44 keypair	115031 cycles	115043 cycles	1.00
ML-DSA-44 sign	431563 cycles	431544 cycles	1.00
ML-DSA-44 verify	122125 cycles	122136 cycles	1.00
ML-DSA-65 keypair	197007 cycles	197016 cycles	1.00
ML-DSA-65 sign	701163 cycles	701195 cycles	1.00
ML-DSA-65 verify	197636 cycles	197645 cycles	1.00
ML-DSA-87 keypair	325315 cycles	325246 cycles	1.00
ML-DSA-87 sign	884560 cycles	884528 cycles	1.00
ML-DSA-87 verify	328924 cycles	328866 cycles	1.00

This comment was automatically generated by workflow using github-action-benchmark.

[github-actions]

Arm Cortex-A76 (Raspberry Pi 5) benchmarks (opt)

Benchmark suite	Current: e237512	Previous: d6f0aff	Ratio
ML-DSA-44 keypair	115389 cycles	115401 cycles	1.00
ML-DSA-44 sign	391656 cycles	392073 cycles	1.00
ML-DSA-44 verify	123912 cycles	123591 cycles	1.00
ML-DSA-65 keypair	200047 cycles	199999 cycles	1.00
ML-DSA-65 sign	647348 cycles	647924 cycles	1.00
ML-DSA-65 verify	202825 cycles	202810 cycles	1.00
ML-DSA-87 keypair	327751 cycles	327090 cycles	1.00
ML-DSA-87 sign	818922 cycles	819493 cycles	1.00
ML-DSA-87 verify	331920 cycles	331094 cycles	1.00

This comment was automatically generated by workflow using github-action-benchmark.

[github-actions]

Arm Cortex-A76 (Raspberry Pi 5) benchmarks (no-opt)

Benchmark suite	Current: e237512	Previous: d6f0aff	Ratio
ML-DSA-44 keypair	213230 cycles	213140 cycles	1.00
ML-DSA-44 sign	780518 cycles	781344 cycles	1.00
ML-DSA-44 verify	229917 cycles	230250 cycles	1.00
ML-DSA-65 keypair	380882 cycles	381133 cycles	1.00
ML-DSA-65 sign	1303784 cycles	1291739 cycles	1.01
ML-DSA-65 verify	372469 cycles	373008 cycles	1.00
ML-DSA-87 keypair	609772 cycles	608751 cycles	1.00
ML-DSA-87 sign	1641790 cycles	1641995 cycles	1.00
ML-DSA-87 verify	621954 cycles	621106 cycles	1.00

This comment was automatically generated by workflow using github-action-benchmark.

[oqs-bot]

Intel Xeon 4th gen (c7i)

Benchmark suite	Current: e237512	Previous: d6f0aff	Ratio
ML-DSA-44 keypair	35506 cycles	35788 cycles	0.99
ML-DSA-44 sign	132499 cycles	131795 cycles	1.01
ML-DSA-44 verify	40992 cycles	40749 cycles	1.01
ML-DSA-65 keypair	63685 cycles	63833 cycles	1.00
ML-DSA-65 sign	220272 cycles	220628 cycles	1.00
ML-DSA-65 verify	65992 cycles	66289 cycles	1.00
ML-DSA-87 keypair	96369 cycles	96556 cycles	1.00
ML-DSA-87 sign	262921 cycles	263782 cycles	1.00
ML-DSA-87 verify	99444 cycles	100913 cycles	0.99

This comment was automatically generated by workflow using github-action-benchmark.

[github-actions]

Arm Cortex-A72 (Raspberry Pi 4) benchmarks (opt)

Benchmark suite	Current: e237512	Previous: d6f0aff	Ratio
ML-DSA-44 keypair	231258 cycles	226299 cycles	1.02
ML-DSA-44 sign	684337 cycles	685209 cycles	1.00
ML-DSA-44 verify	231750 cycles	233852 cycles	0.99
ML-DSA-65 keypair	389858 cycles	392853 cycles	0.99
ML-DSA-65 sign	1110644 cycles	1104283 cycles	1.01
ML-DSA-65 verify	378467 cycles	385283 cycles	0.98
ML-DSA-87 keypair	663723 cycles	660528 cycles	1.00
ML-DSA-87 sign	1465558 cycles	1507365 cycles	0.97
ML-DSA-87 verify	645894 cycles	653714 cycles	0.99

This comment was automatically generated by workflow using github-action-benchmark.

[github-actions]

⚠️ Performance Alert ⚠️

Possible performance regression was detected for benchmark 'Arm Cortex-A72 (Raspberry Pi 4) benchmarks (opt)'.
Benchmark result of this commit is worse than the previous benchmark result exceeding threshold 1.03.

Benchmark suite	Current: e237512	Previous: d6f0aff	Ratio
ML-DSA-44 keypair	240088 cycles	226299 cycles	1.06
ML-DSA-65 keypair	414233 cycles	392853 cycles	1.05
ML-DSA-65 sign	1151909 cycles	1104283 cycles	1.04

This comment was automatically generated by workflow using github-action-benchmark.

[oqs-bot]

Intel Xeon 4th gen (c7i) (no-opt)

Benchmark suite	Current: e237512	Previous: d6f0aff	Ratio
ML-DSA-44 keypair	95956 cycles	95950 cycles	1.00
ML-DSA-44 sign	346065 cycles	345418 cycles	1.00
ML-DSA-44 verify	101754 cycles	101652 cycles	1.00
ML-DSA-65 keypair	164751 cycles	164915 cycles	1.00
ML-DSA-65 sign	568315 cycles	567873 cycles	1.00
ML-DSA-65 verify	165933 cycles	165321 cycles	1.00
ML-DSA-87 keypair	270070 cycles	270539 cycles	1.00
ML-DSA-87 sign	724125 cycles	725041 cycles	1.00
ML-DSA-87 verify	273271 cycles	273150 cycles	1.00

This comment was automatically generated by workflow using github-action-benchmark.

[oqs-bot]

AMD EPYC 3rd gen (c6a)

Benchmark suite	Current: e237512	Previous: d6f0aff	Ratio
ML-DSA-44 keypair	71440 cycles	71449 cycles	1.00
ML-DSA-44 sign	213333 cycles	213021 cycles	1.00
ML-DSA-44 verify	74915 cycles	75043 cycles	1.00
ML-DSA-65 keypair	123105 cycles	122715 cycles	1.00
ML-DSA-65 sign	343569 cycles	343373 cycles	1.00
ML-DSA-65 verify	123293 cycles	123319 cycles	1.00
ML-DSA-87 keypair	206699 cycles	206387 cycles	1.00
ML-DSA-87 sign	448270 cycles	446324 cycles	1.00
ML-DSA-87 verify	204807 cycles	205034 cycles	1.00

This comment was automatically generated by workflow using github-action-benchmark.

[oqs-bot]

Intel Xeon 3rd gen (c6i)

Benchmark suite	Current: e237512	Previous: d6f0aff	Ratio
ML-DSA-44 keypair	57630 cycles	58197 cycles	0.99
ML-DSA-44 sign	200945 cycles	201370 cycles	1.00
ML-DSA-44 verify	65793 cycles	65969 cycles	1.00
ML-DSA-65 keypair	102498 cycles	102122 cycles	1.00
ML-DSA-65 sign	332789 cycles	333005 cycles	1.00
ML-DSA-65 verify	106674 cycles	107174 cycles	1.00
ML-DSA-87 keypair	157375 cycles	157277 cycles	1.00
ML-DSA-87 sign	400696 cycles	399982 cycles	1.00
ML-DSA-87 verify	162667 cycles	163575 cycles	0.99

This comment was automatically generated by workflow using github-action-benchmark.

[oqs-bot]

Graviton4

Benchmark suite	Current: e237512	Previous: d6f0aff	Ratio
ML-DSA-44 keypair	69466 cycles	69482 cycles	1.00
ML-DSA-44 sign	222700 cycles	222985 cycles	1.00
ML-DSA-44 verify	74540 cycles	74674 cycles	1.00
ML-DSA-65 keypair	123225 cycles	123364 cycles	1.00
ML-DSA-65 sign	365869 cycles	366286 cycles	1.00
ML-DSA-65 verify	123247 cycles	123391 cycles	1.00
ML-DSA-87 keypair	201308 cycles	200567 cycles	1.00
ML-DSA-87 sign	466683 cycles	467051 cycles	1.00
ML-DSA-87 verify	201738 cycles	201926 cycles	1.00

This comment was automatically generated by workflow using github-action-benchmark.

[oqs-bot]

AMD EPYC 3rd gen (c6a) (no-opt)

Benchmark suite	Current: e237512	Previous: d6f0aff	Ratio
ML-DSA-44 keypair	135675 cycles	136615 cycles	0.99
ML-DSA-44 sign	542002 cycles	542816 cycles	1.00
ML-DSA-44 verify	148557 cycles	148510 cycles	1.00
ML-DSA-65 keypair	227888 cycles	227149 cycles	1.00
ML-DSA-65 sign	881584 cycles	880505 cycles	1.00
ML-DSA-65 verify	236356 cycles	235629 cycles	1.00
ML-DSA-87 keypair	375380 cycles	375182 cycles	1.00
ML-DSA-87 sign	1101424 cycles	1097816 cycles	1.00
ML-DSA-87 verify	387800 cycles	387755 cycles	1.00

This comment was automatically generated by workflow using github-action-benchmark.

[oqs-bot]

Graviton3

Benchmark suite	Current: e237512	Previous: d6f0aff	Ratio
ML-DSA-44 keypair	73952 cycles	73984 cycles	1.00
ML-DSA-44 sign	235620 cycles	236046 cycles	1.00
ML-DSA-44 verify	80067 cycles	79934 cycles	1.00
ML-DSA-65 keypair	129915 cycles	129596 cycles	1.00
ML-DSA-65 sign	388796 cycles	388386 cycles	1.00
ML-DSA-65 verify	131188 cycles	130906 cycles	1.00
ML-DSA-87 keypair	210697 cycles	209997 cycles	1.00
ML-DSA-87 sign	492590 cycles	492315 cycles	1.00
ML-DSA-87 verify	213203 cycles	212609 cycles	1.00

This comment was automatically generated by workflow using github-action-benchmark.

[oqs-bot]

Intel Xeon 3rd gen (c6i) (no-opt)

Benchmark suite	Current: e237512	Previous: d6f0aff	Ratio
ML-DSA-44 keypair	157920 cycles	158063 cycles	1.00
ML-DSA-44 sign	562926 cycles	563792 cycles	1.00
ML-DSA-44 verify	169279 cycles	169142 cycles	1.00
ML-DSA-65 keypair	269217 cycles	270178 cycles	1.00
ML-DSA-65 sign	927071 cycles	928301 cycles	1.00
ML-DSA-65 verify	274379 cycles	274880 cycles	1.00
ML-DSA-87 keypair	450858 cycles	451079 cycles	1.00
ML-DSA-87 sign	1178012 cycles	1178223 cycles	1.00
ML-DSA-87 verify	459398 cycles	459001 cycles	1.00

This comment was automatically generated by workflow using github-action-benchmark.

[oqs-bot]

Graviton2

Benchmark suite	Current: e237512	Previous: d6f0aff	Ratio
ML-DSA-44 keypair	116624 cycles	115590 cycles	1.01
ML-DSA-44 sign	395508 cycles	392399 cycles	1.01
ML-DSA-44 verify	125349 cycles	123668 cycles	1.01
ML-DSA-65 keypair	200078 cycles	200149 cycles	1.00
ML-DSA-65 sign	647776 cycles	648318 cycles	1.00
ML-DSA-65 verify	202723 cycles	202806 cycles	1.00
ML-DSA-87 keypair	328043 cycles	329010 cycles	1.00
ML-DSA-87 sign	820543 cycles	824159 cycles	1.00
ML-DSA-87 verify	331940 cycles	332809 cycles	1.00

This comment was automatically generated by workflow using github-action-benchmark.

[oqs-bot]

Graviton4 (no-opt)

Benchmark suite	Current: e237512	Previous: d6f0aff	Ratio
ML-DSA-44 keypair	132656 cycles	132742 cycles	1.00
ML-DSA-44 sign	498638 cycles	498277 cycles	1.00
ML-DSA-44 verify	144908 cycles	144925 cycles	1.00
ML-DSA-65 keypair	227219 cycles	227487 cycles	1.00
ML-DSA-65 sign	813837 cycles	813779 cycles	1.00
ML-DSA-65 verify	232216 cycles	231472 cycles	1.00
ML-DSA-87 keypair	374426 cycles	374674 cycles	1.00
ML-DSA-87 sign	1021492 cycles	1021533 cycles	1.00
ML-DSA-87 verify	383805 cycles	383781 cycles	1.00

This comment was automatically generated by workflow using github-action-benchmark.

[oqs-bot]

AMD EPYC 4th gen (c7a)

Benchmark suite	Current: e237512	Previous: d6f0aff	Ratio
ML-DSA-44 keypair	42976 cycles	41586 cycles	1.03
ML-DSA-44 sign	148402 cycles	144052 cycles	1.03
ML-DSA-44 verify	48658 cycles	47065 cycles	1.03
ML-DSA-65 keypair	73494 cycles	75266 cycles	0.98
ML-DSA-65 sign	236353 cycles	241080 cycles	0.98
ML-DSA-65 verify	77688 cycles	78595 cycles	0.99
ML-DSA-87 keypair	111624 cycles	111245 cycles	1.00
ML-DSA-87 sign	278761 cycles	278009 cycles	1.00
ML-DSA-87 verify	117685 cycles	116719 cycles	1.01

This comment was automatically generated by workflow using github-action-benchmark.

[oqs-bot]

⚠️ Performance Alert ⚠️

Possible performance regression was detected for benchmark 'AMD EPYC 4th gen (c7a)'.
Benchmark result of this commit is worse than the previous benchmark result exceeding threshold 1.03.

Benchmark suite	Current: e237512	Previous: d6f0aff	Ratio
ML-DSA-44 keypair	42976 cycles	41586 cycles	1.03
ML-DSA-44 sign	148402 cycles	144052 cycles	1.03
ML-DSA-44 verify	48658 cycles	47065 cycles	1.03

This comment was automatically generated by workflow using github-action-benchmark.

[oqs-bot]

Graviton3 (no-opt)

Benchmark suite	Current: e237512	Previous: d6f0aff	Ratio
ML-DSA-44 keypair	138592 cycles	138584 cycles	1.00
ML-DSA-44 sign	494895 cycles	495374 cycles	1.00
ML-DSA-44 verify	148746 cycles	148755 cycles	1.00
ML-DSA-65 keypair	241448 cycles	241271 cycles	1.00
ML-DSA-65 sign	809853 cycles	809938 cycles	1.00
ML-DSA-65 verify	240968 cycles	240917 cycles	1.00
ML-DSA-87 keypair	396530 cycles	396435 cycles	1.00
ML-DSA-87 sign	1031874 cycles	1031484 cycles	1.00
ML-DSA-87 verify	402484 cycles	402258 cycles	1.00

This comment was automatically generated by workflow using github-action-benchmark.

[oqs-bot]

AMD EPYC 4th gen (c7a) (no-opt)

Benchmark suite	Current: e237512	Previous: d6f0aff	Ratio
ML-DSA-44 keypair	120505 cycles	120449 cycles	1.00
ML-DSA-44 sign	453001 cycles	453415 cycles	1.00
ML-DSA-44 verify	131694 cycles	131953 cycles	1.00
ML-DSA-65 keypair	205050 cycles	205323 cycles	1.00
ML-DSA-65 sign	738715 cycles	738545 cycles	1.00
ML-DSA-65 verify	209801 cycles	209892 cycles	1.00
ML-DSA-87 keypair	340062 cycles	339821 cycles	1.00
ML-DSA-87 sign	944440 cycles	940263 cycles	1.00
ML-DSA-87 verify	349936 cycles	348851 cycles	1.00

This comment was automatically generated by workflow using github-action-benchmark.

[oqs-bot]

Graviton2 (no-opt)

Benchmark suite	Current: e237512	Previous: d6f0aff	Ratio
ML-DSA-44 keypair	213554 cycles	213361 cycles	1.00
ML-DSA-44 sign	781026 cycles	793921 cycles	0.98
ML-DSA-44 verify	230163 cycles	229839 cycles	1.00
ML-DSA-65 keypair	381231 cycles	381829 cycles	1.00
ML-DSA-65 sign	1287176 cycles	1286726 cycles	1.00
ML-DSA-65 verify	372989 cycles	373869 cycles	1.00
ML-DSA-87 keypair	609791 cycles	609570 cycles	1.00
ML-DSA-87 sign	1643649 cycles	1645233 cycles	1.00
ML-DSA-87 verify	621462 cycles	621509 cycles	1.00

This comment was automatically generated by workflow using github-action-benchmark.

[github-actions]

Arm Cortex-A72 (Raspberry Pi 4) benchmarks (no-opt)

Benchmark suite	Current: e237512	Previous: d6f0aff	Ratio
ML-DSA-44 keypair	313471 cycles	311190 cycles	1.01
ML-DSA-44 sign	1207074 cycles	1212315 cycles	1.00
ML-DSA-44 verify	339304 cycles	340736 cycles	1.00
ML-DSA-65 keypair	579570 cycles	571742 cycles	1.01
ML-DSA-65 sign	1972598 cycles	1991218 cycles	0.99
ML-DSA-65 verify	549704 cycles	548869 cycles	1.00
ML-DSA-87 keypair	879411 cycles	887392 cycles	0.99
ML-DSA-87 sign	2514858 cycles	2524414 cycles	1.00
ML-DSA-87 verify	900041 cycles	911995 cycles	0.99

This comment was automatically generated by workflow using github-action-benchmark.

[github-actions]

SpacemiT K1 8 (Banana Pi F3) benchmarks (no-opt)

Benchmark suite	Current: e237512	Previous: d6f0aff	Ratio
ML-DSA-44 keypair	822598 cycles	822538 cycles	1.00
ML-DSA-44 sign	3329124 cycles	3328040 cycles	1.00
ML-DSA-44 verify	919233 cycles	919478 cycles	1.00
ML-DSA-65 keypair	1394757 cycles	1397190 cycles	1.00
ML-DSA-65 sign	5424797 cycles	5444263 cycles	1.00
ML-DSA-65 verify	1462282 cycles	1464822 cycles	1.00
ML-DSA-87 keypair	2301463 cycles	2297219 cycles	1.00
ML-DSA-87 sign	6813371 cycles	6806027 cycles	1.00
ML-DSA-87 verify	2397935 cycles	2402236 cycles	1.00

This comment was automatically generated by workflow using github-action-benchmark.

[github-actions]

Arm Cortex-A55 (Snapdragon 888) benchmarks (opt)

Benchmark suite	Current: e237512	Previous: d6f0aff	Ratio
ML-DSA-44 keypair	288777 cycles	287865 cycles	1.00
ML-DSA-44 sign	973349 cycles	972680 cycles	1.00
ML-DSA-44 verify	306008 cycles	306215 cycles	1.00
ML-DSA-65 keypair	488752 cycles	484999 cycles	1.01
ML-DSA-65 sign	1623660 cycles	1597132 cycles	1.02
ML-DSA-65 verify	494660 cycles	490629 cycles	1.01
ML-DSA-87 keypair	843914 cycles	830211 cycles	1.02
ML-DSA-87 sign	2177225 cycles	2167209 cycles	1.00
ML-DSA-87 verify	845327 cycles	839232 cycles	1.01

This comment was automatically generated by workflow using github-action-benchmark.

[github-actions]

Arm Cortex-A55 (Snapdragon 888) benchmarks (no-opt)

Benchmark suite	Current: e237512	Previous: d6f0aff	Ratio
ML-DSA-44 keypair	466422 cycles	466586 cycles	1.00
ML-DSA-44 sign	2214549 cycles	2214626 cycles	1.00
ML-DSA-44 verify	550875 cycles	550223 cycles	1.00
ML-DSA-65 keypair	778138 cycles	779087 cycles	1.00
ML-DSA-65 sign	3634604 cycles	3627200 cycles	1.00
ML-DSA-65 verify	853443 cycles	853807 cycles	1.00
ML-DSA-87 keypair	1258651 cycles	1257068 cycles	1.00
ML-DSA-87 sign	4468779 cycles	4493954 cycles	0.99
ML-DSA-87 verify	1370671 cycles	1368680 cycles	1.00

This comment was automatically generated by workflow using github-action-benchmark.

[github-actions]

⚠️ Performance Alert ⚠️

Possible performance regression was detected for benchmark 'Mac Mini (M1, 2020) benchmarks (opt)'.
Benchmark result of this commit is worse than the previous benchmark result exceeding threshold 1.03.

Benchmark suite	Current: 0c90841	Previous: 47831f0	Ratio
ML-DSA-44 keypair	47878 cycles	0 cycles	+∞
ML-DSA-44 sign	157577 cycles	0 cycles	+∞
ML-DSA-44 verify	52377 cycles	0 cycles	+∞

This comment was automatically generated by workflow using github-action-benchmark.

[github-actions]

⚠️ Performance Alert ⚠️

Possible performance regression was detected for benchmark 'Arm Cortex-A72 (Raspberry Pi 4) benchmarks (no-opt)'.
Benchmark result of this commit is worse than the previous benchmark result exceeding threshold 1.03.

Benchmark suite	Current: 0c90841	Previous: 47831f0	Ratio
ML-DSA-65 keypair	592759 cycles	567906 cycles	1.04
ML-DSA-65 verify	561983 cycles	537553 cycles	1.05

This comment was automatically generated by workflow using github-action-benchmark.