[BENCH] x86_64: Benchmark alternative Keccak (#2)

[hanno-becker]

Copy of @manastasova's PR #1480 to allow benchmarking to run.

[oqs-bot]

Mac Mini (M1, 2020) benchmarks

Details

Benchmark suite	Current: 85f5c74	Previous: 70d3b1b	Ratio
ML-KEM-512 keypair	12315 cycles	12315 cycles	1
ML-KEM-512 encaps	14989 cycles	14989 cycles	1
ML-KEM-512 decaps	19558 cycles	19557 cycles	1.00
ML-KEM-768 keypair	21084 cycles	21084 cycles	1
ML-KEM-768 encaps	23868 cycles	23867 cycles	1.00
ML-KEM-768 decaps	30436 cycles	30436 cycles	1
ML-KEM-1024 keypair	30380 cycles	30378 cycles	1.00
ML-KEM-1024 encaps	34656 cycles	34654 cycles	1.00
ML-KEM-1024 decaps	44268 cycles	44268 cycles	1

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

[oqs-bot]

Intel Xeon 4th gen (c7i)

Details

Benchmark suite	Current: 85f5c74	Previous: 70d3b1b	Ratio
ML-KEM-512 keypair	12318 cycles	9625 cycles	1.28
ML-KEM-512 encaps	14281 cycles	11261 cycles	1.27
ML-KEM-512 decaps	17975 cycles	15164 cycles	1.19
ML-KEM-768 keypair	21073 cycles	16379 cycles	1.29
ML-KEM-768 encaps	21903 cycles	17876 cycles	1.23
ML-KEM-768 decaps	27848 cycles	23467 cycles	1.19
ML-KEM-1024 keypair	30157 cycles	22351 cycles	1.35
ML-KEM-1024 encaps	32101 cycles	24490 cycles	1.31
ML-KEM-1024 decaps	39896 cycles	32226 cycles	1.24

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

[oqs-bot]

⚠️ Performance Alert ⚠️

Possible performance regression was detected for benchmark 'Intel Xeon 4th gen (c7i)'.
Benchmark result of this commit is worse than the previous benchmark result exceeding threshold 1.03.

Benchmark suite	Current: 85f5c74	Previous: 70d3b1b	Ratio
ML-KEM-512 keypair	12318 cycles	9625 cycles	1.28
ML-KEM-512 encaps	14281 cycles	11261 cycles	1.27
ML-KEM-512 decaps	17975 cycles	15164 cycles	1.19
ML-KEM-768 keypair	21073 cycles	16379 cycles	1.29
ML-KEM-768 encaps	21903 cycles	17876 cycles	1.23
ML-KEM-768 decaps	27848 cycles	23467 cycles	1.19
ML-KEM-1024 keypair	30157 cycles	22351 cycles	1.35
ML-KEM-1024 encaps	32101 cycles	24490 cycles	1.31
ML-KEM-1024 decaps	39896 cycles	32226 cycles	1.24

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

[oqs-bot]

AMD EPYC 3rd gen (c6a)

Details

Benchmark suite	Current: 85f5c74	Previous: 70d3b1b	Ratio
ML-KEM-512 keypair	14745 cycles	16898 cycles	0.87
ML-KEM-512 encaps	16514 cycles	18592 cycles	0.89
ML-KEM-512 decaps	22010 cycles	24064 cycles	0.91
ML-KEM-768 keypair	25052 cycles	28520 cycles	0.88
ML-KEM-768 encaps	26403 cycles	29608 cycles	0.89
ML-KEM-768 decaps	34250 cycles	37440 cycles	0.91
ML-KEM-1024 keypair	36485 cycles	42905 cycles	0.85
ML-KEM-1024 encaps	38094 cycles	44084 cycles	0.86
ML-KEM-1024 decaps	48527 cycles	54546 cycles	0.89

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

[oqs-bot]

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

Details

Benchmark suite	Current: 85f5c74	Previous: 70d3b1b	Ratio
ML-KEM-512 keypair	29174 cycles	29267 cycles	1.00
ML-KEM-512 encaps	36377 cycles	36676 cycles	0.99
ML-KEM-512 decaps	45066 cycles	45180 cycles	1.00
ML-KEM-768 keypair	45999 cycles	45976 cycles	1.00
ML-KEM-768 encaps	55596 cycles	55681 cycles	1.00
ML-KEM-768 decaps	69275 cycles	69239 cycles	1.00
ML-KEM-1024 keypair	72863 cycles	72724 cycles	1.00
ML-KEM-1024 encaps	84841 cycles	84820 cycles	1.00
ML-KEM-1024 decaps	102849 cycles	102767 cycles	1.00

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

[oqs-bot]

Intel Xeon 3rd gen (c6i)

Details

Benchmark suite	Current: 85f5c74	Previous: 70d3b1b	Ratio
ML-KEM-512 keypair	18202 cycles	16250 cycles	1.12
ML-KEM-512 encaps	20451 cycles	18593 cycles	1.10
ML-KEM-512 decaps	27396 cycles	25256 cycles	1.08
ML-KEM-768 keypair	30968 cycles	28059 cycles	1.10
ML-KEM-768 encaps	33578 cycles	31904 cycles	1.05
ML-KEM-768 decaps	42427 cycles	39398 cycles	1.08
ML-KEM-1024 keypair	42758 cycles	37797 cycles	1.13
ML-KEM-1024 encaps	45779 cycles	40503 cycles	1.13
ML-KEM-1024 decaps	59528 cycles	54261 cycles	1.10

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

[oqs-bot]

⚠️ Performance Alert ⚠️

Possible performance regression was detected for benchmark 'Intel Xeon 3rd gen (c6i)'.
Benchmark result of this commit is worse than the previous benchmark result exceeding threshold 1.03.

Benchmark suite	Current: 85f5c74	Previous: 70d3b1b	Ratio
ML-KEM-512 keypair	18202 cycles	16250 cycles	1.12
ML-KEM-512 encaps	20451 cycles	18593 cycles	1.10
ML-KEM-512 decaps	27396 cycles	25256 cycles	1.08
ML-KEM-768 keypair	30968 cycles	28059 cycles	1.10
ML-KEM-768 encaps	33578 cycles	31904 cycles	1.05
ML-KEM-768 decaps	42427 cycles	39398 cycles	1.08
ML-KEM-1024 keypair	42758 cycles	37797 cycles	1.13
ML-KEM-1024 encaps	45779 cycles	40503 cycles	1.13
ML-KEM-1024 decaps	59528 cycles	54261 cycles	1.10

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

[oqs-bot]

AMD EPYC 4th gen (c7a)

Details

Benchmark suite	Current: 85f5c74	Previous: 70d3b1b	Ratio
ML-KEM-512 keypair	13362 cycles	11911 cycles	1.12
ML-KEM-512 encaps	14910 cycles	13470 cycles	1.11
ML-KEM-512 decaps	19836 cycles	18367 cycles	1.08
ML-KEM-768 keypair	22912 cycles	20274 cycles	1.13
ML-KEM-768 encaps	23998 cycles	21295 cycles	1.13
ML-KEM-768 decaps	31155 cycles	28322 cycles	1.10
ML-KEM-1024 keypair	32630 cycles	27571 cycles	1.18
ML-KEM-1024 encaps	34850 cycles	29429 cycles	1.18
ML-KEM-1024 decaps	44182 cycles	38939 cycles	1.13

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: 85f5c74	Previous: 70d3b1b	Ratio
ML-KEM-512 keypair	13362 cycles	11911 cycles	1.12
ML-KEM-512 encaps	14910 cycles	13470 cycles	1.11
ML-KEM-512 decaps	19836 cycles	18367 cycles	1.08
ML-KEM-768 keypair	22912 cycles	20274 cycles	1.13
ML-KEM-768 encaps	23998 cycles	21295 cycles	1.13
ML-KEM-768 decaps	31155 cycles	28322 cycles	1.10
ML-KEM-1024 keypair	32630 cycles	27571 cycles	1.18
ML-KEM-1024 encaps	34850 cycles	29429 cycles	1.18
ML-KEM-1024 decaps	44182 cycles	38939 cycles	1.13

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

[oqs-bot]

Graviton4

Details

Benchmark suite	Current: 85f5c74	Previous: 70d3b1b	Ratio
ML-KEM-512 keypair	17663 cycles	17664 cycles	1.00
ML-KEM-512 encaps	20538 cycles	20522 cycles	1.00
ML-KEM-512 decaps	26966 cycles	26962 cycles	1.00
ML-KEM-768 keypair	29978 cycles	29976 cycles	1.00
ML-KEM-768 encaps	32779 cycles	32769 cycles	1.00
ML-KEM-768 decaps	41934 cycles	41949 cycles	1.00
ML-KEM-1024 keypair	43840 cycles	43864 cycles	1.00
ML-KEM-1024 encaps	48792 cycles	48797 cycles	1.00
ML-KEM-1024 decaps	61395 cycles	61312 cycles	1.00

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

[oqs-bot]

Graviton3

Details

Benchmark suite	Current: 85f5c74	Previous: 70d3b1b	Ratio
ML-KEM-512 keypair	18726 cycles	18726 cycles	1
ML-KEM-512 encaps	21994 cycles	21990 cycles	1.00
ML-KEM-512 decaps	28929 cycles	28926 cycles	1.00
ML-KEM-768 keypair	31697 cycles	31695 cycles	1.00
ML-KEM-768 encaps	34910 cycles	34897 cycles	1.00
ML-KEM-768 decaps	44903 cycles	44904 cycles	1.00
ML-KEM-1024 keypair	46304 cycles	46310 cycles	1.00
ML-KEM-1024 encaps	51614 cycles	51631 cycles	1.00
ML-KEM-1024 decaps	65126 cycles	65063 cycles	1.00

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

[oqs-bot]

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

Details

Benchmark suite	Current: 85f5c74	Previous: 70d3b1b	Ratio
ML-KEM-512 keypair	40128 cycles	40063 cycles	1.00
ML-KEM-512 encaps	48501 cycles	48449 cycles	1.00
ML-KEM-512 decaps	62844 cycles	62704 cycles	1.00
ML-KEM-768 keypair	63572 cycles	63580 cycles	1.00
ML-KEM-768 encaps	74834 cycles	74811 cycles	1.00
ML-KEM-768 decaps	93416 cycles	93436 cycles	1.00
ML-KEM-1024 keypair	95199 cycles	95232 cycles	1.00
ML-KEM-1024 encaps	109410 cycles	109437 cycles	1.00
ML-KEM-1024 decaps	132370 cycles	132545 cycles	1.00

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

[oqs-bot]

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

Details

Benchmark suite	Current: 85f5c74	Previous: 70d3b1b	Ratio
ML-KEM-512 keypair	36843 cycles	36858 cycles	1.00
ML-KEM-512 encaps	43417 cycles	43499 cycles	1.00
ML-KEM-512 decaps	56479 cycles	56468 cycles	1.00
ML-KEM-768 keypair	58872 cycles	58994 cycles	1.00
ML-KEM-768 encaps	67919 cycles	67944 cycles	1.00
ML-KEM-768 decaps	85270 cycles	85324 cycles	1.00
ML-KEM-1024 keypair	89116 cycles	89191 cycles	1.00
ML-KEM-1024 encaps	99475 cycles	99540 cycles	1.00
ML-KEM-1024 decaps	121686 cycles	121698 cycles	1.00

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

[oqs-bot]

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

Details

Benchmark suite	Current: 85f5c74	Previous: 70d3b1b	Ratio
ML-KEM-512 keypair	47151 cycles	47179 cycles	1.00
ML-KEM-512 encaps	55598 cycles	55651 cycles	1.00
ML-KEM-512 decaps	70987 cycles	71018 cycles	1.00
ML-KEM-768 keypair	73261 cycles	73292 cycles	1.00
ML-KEM-768 encaps	85084 cycles	85170 cycles	1.00
ML-KEM-768 decaps	105452 cycles	105463 cycles	1.00
ML-KEM-1024 keypair	112637 cycles	112706 cycles	1.00
ML-KEM-1024 encaps	125505 cycles	125595 cycles	1.00
ML-KEM-1024 decaps	151648 cycles	151812 cycles	1.00

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

[oqs-bot]

Graviton2

Details

Benchmark suite	Current: 85f5c74	Previous: 70d3b1b	Ratio
ML-KEM-512 keypair	28324 cycles	28264 cycles	1.00
ML-KEM-512 encaps	34244 cycles	34161 cycles	1.00
ML-KEM-512 decaps	44502 cycles	44402 cycles	1.00
ML-KEM-768 keypair	47755 cycles	47752 cycles	1.00
ML-KEM-768 encaps	54100 cycles	54108 cycles	1.00
ML-KEM-768 decaps	68455 cycles	68467 cycles	1.00
ML-KEM-1024 keypair	70410 cycles	70508 cycles	1.00
ML-KEM-1024 encaps	78879 cycles	78973 cycles	1.00
ML-KEM-1024 decaps	98594 cycles	98511 cycles	1.00

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

[oqs-bot]

Graviton4 (no-opt)

Details

Benchmark suite	Current: 85f5c74	Previous: 70d3b1b	Ratio
ML-KEM-512 keypair	35473 cycles	35452 cycles	1.00
ML-KEM-512 encaps	40556 cycles	40519 cycles	1.00
ML-KEM-512 decaps	51257 cycles	51291 cycles	1.00
ML-KEM-768 keypair	57112 cycles	57158 cycles	1.00
ML-KEM-768 encaps	64702 cycles	65307 cycles	0.99
ML-KEM-768 decaps	79334 cycles	79757 cycles	0.99
ML-KEM-1024 keypair	88039 cycles	88019 cycles	1.00
ML-KEM-1024 encaps	97529 cycles	97622 cycles	1.00
ML-KEM-1024 decaps	116470 cycles	116481 cycles	1.00

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

[oqs-bot]

Graviton3 (no-opt)

Details

Benchmark suite	Current: 85f5c74	Previous: 70d3b1b	Ratio
ML-KEM-512 keypair	39066 cycles	39044 cycles	1.00
ML-KEM-512 encaps	44901 cycles	44876 cycles	1.00
ML-KEM-512 decaps	56804 cycles	56828 cycles	1.00
ML-KEM-768 keypair	62479 cycles	62544 cycles	1.00
ML-KEM-768 encaps	71085 cycles	71848 cycles	0.99
ML-KEM-768 decaps	87243 cycles	88231 cycles	0.99
ML-KEM-1024 keypair	96278 cycles	96222 cycles	1.00
ML-KEM-1024 encaps	106597 cycles	106760 cycles	1.00
ML-KEM-1024 decaps	127088 cycles	127083 cycles	1.00

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

[oqs-bot]

ppc64le (POWER10) benchmarks

Details

Benchmark suite	Current: 85f5c74	Previous: 70d3b1b	Ratio
ML-KEM-512 keypair	58468 cycles	58609 cycles	1.00
ML-KEM-512 encaps	71320 cycles	71470 cycles	1.00
ML-KEM-512 decaps	90857 cycles	91062 cycles	1.00
ML-KEM-768 keypair	102230 cycles	95061 cycles	1.08
ML-KEM-768 encaps	118571 cycles	110883 cycles	1.07
ML-KEM-768 decaps	145304 cycles	136318 cycles	1.07
ML-KEM-1024 keypair	154111 cycles	154856 cycles	1.00
ML-KEM-1024 encaps	172730 cycles	173402 cycles	1.00
ML-KEM-1024 decaps	203878 cycles	204939 cycles	0.99

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

[oqs-bot]

⚠️ Performance Alert ⚠️

Possible performance regression was detected for benchmark 'ppc64le (POWER10) benchmarks'.
Benchmark result of this commit is worse than the previous benchmark result exceeding threshold 1.03.

Benchmark suite	Current: 85f5c74	Previous: 70d3b1b	Ratio
ML-KEM-768 keypair	102230 cycles	95061 cycles	1.08
ML-KEM-768 encaps	118571 cycles	110883 cycles	1.07
ML-KEM-768 decaps	145304 cycles	136318 cycles	1.07

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

[oqs-bot]

Graviton2 (no-opt)

Details

Benchmark suite	Current: 85f5c74	Previous: 70d3b1b	Ratio
ML-KEM-512 keypair	59123 cycles	59151 cycles	1.00
ML-KEM-512 encaps	68486 cycles	68489 cycles	1.00
ML-KEM-512 decaps	87106 cycles	87126 cycles	1.00
ML-KEM-768 keypair	95671 cycles	95579 cycles	1.00
ML-KEM-768 encaps	109314 cycles	109395 cycles	1.00
ML-KEM-768 decaps	135477 cycles	134650 cycles	1.01
ML-KEM-1024 keypair	147888 cycles	147999 cycles	1.00
ML-KEM-1024 encaps	163830 cycles	163660 cycles	1.00
ML-KEM-1024 decaps	195469 cycles	195255 cycles	1.00

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

[oqs-bot]

SpacemiT K1 8 (Banana Pi F3) benchmarks

Details

Benchmark suite	Current: 85f5c74	Previous: 70d3b1b	Ratio
ML-KEM-512 keypair	154997 cycles	154986 cycles	1.00
ML-KEM-512 encaps	163004 cycles	162936 cycles	1.00
ML-KEM-512 decaps	206190 cycles	206098 cycles	1.00
ML-KEM-768 keypair	249988 cycles	249874 cycles	1.00
ML-KEM-768 encaps	269333 cycles	269171 cycles	1.00
ML-KEM-768 decaps	332721 cycles	332517 cycles	1.00
ML-KEM-1024 keypair	395576 cycles	395324 cycles	1.00
ML-KEM-1024 encaps	422925 cycles	423158 cycles	1.00
ML-KEM-1024 decaps	506594 cycles	505518 cycles	1.00

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

[oqs-bot]

Arm Cortex-A55 (Snapdragon 888) benchmarks

Details

Benchmark suite	Current: 85f5c74	Previous: 70d3b1b	Ratio
ML-KEM-512 keypair	59470 cycles	59417 cycles	1.00
ML-KEM-512 encaps	67164 cycles	67139 cycles	1.00
ML-KEM-512 decaps	85763 cycles	85868 cycles	1.00
ML-KEM-768 keypair	96952 cycles	96902 cycles	1.00
ML-KEM-768 encaps	110487 cycles	110211 cycles	1.00
ML-KEM-768 decaps	137233 cycles	137410 cycles	1.00
ML-KEM-1024 keypair	153992 cycles	153909 cycles	1.00
ML-KEM-1024 encaps	170580 cycles	170400 cycles	1.00
ML-KEM-1024 decaps	206720 cycles	206601 cycles	1.00

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

[oqs-bot]

Arm Cortex-A76 (Raspberry Pi 5) benchmarks

Details

Benchmark suite	Current: 85f5c74	Previous: 70d3b1b	Ratio
ML-KEM-512 keypair	28298 cycles	28271 cycles	1.00
ML-KEM-512 encaps	34131 cycles	34173 cycles	1.00
ML-KEM-512 decaps	44364 cycles	44385 cycles	1.00
ML-KEM-768 keypair	47773 cycles	47761 cycles	1.00
ML-KEM-768 encaps	54074 cycles	54100 cycles	1.00
ML-KEM-768 decaps	68473 cycles	68455 cycles	1.00
ML-KEM-1024 keypair	70400 cycles	70462 cycles	1.00
ML-KEM-1024 encaps	78892 cycles	78930 cycles	1.00
ML-KEM-1024 decaps	98579 cycles	98530 cycles	1.00

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

[oqs-bot]

Arm Cortex-A72 (Raspberry Pi 4) benchmarks

Details

Benchmark suite	Current: 85f5c74	Previous: 70d3b1b	Ratio
ML-KEM-512 keypair	50713 cycles	51720 cycles	0.98
ML-KEM-512 encaps	58962 cycles	60244 cycles	0.98
ML-KEM-512 decaps	75559 cycles	75279 cycles	1.00
ML-KEM-768 keypair	86616 cycles	87370 cycles	0.99
ML-KEM-768 encaps	94687 cycles	96230 cycles	0.98
ML-KEM-768 decaps	116946 cycles	118439 cycles	0.99
ML-KEM-1024 keypair	130797 cycles	130623 cycles	1.00
ML-KEM-1024 encaps	142440 cycles	143260 cycles	0.99
ML-KEM-1024 decaps	173812 cycles	174116 cycles	1.00

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