SLOTHY: Superoptimize AArch64 INTT #748

mkannwischer · 2025-11-28T03:55:01Z

Resolves Run Neon NTT/iNTT through SLOTHY #206
Depends on AArch64: Add d-form ldr slothy-optimizer/slothy#363
Depends on CI: Switch from pqcp-arm64 to Github Arm runners #749

iNTT speed-ups:

Platform	Before (main)	After	Speedup
Mac Mini (M1)	434	427	1.016x
Graviton2	1970	1745	1.129x
Graviton3	876	690	1.270x
Graviton4	785	657	1.195x
Cortex-A76 (RPi 5)	1970	1744	1.130x
Cortex-A72 (RPi 4)	2441	1902	1.283x
Cortex-A55 (Snapdragon)	3519	2428	1.449x

github-actions

Mac Mini (M1, 2020) benchmarks (opt)

Details

Benchmark suite	Current: `308107d`	Previous: `2948ece`	Ratio
`ML-DSA-44 keypair`	`46398` cycles	`46414` cycles	`1.00`
`ML-DSA-44 sign`	`131854` cycles	`132001` cycles	`1.00`
`ML-DSA-44 verify`	`47791` cycles	`47801` cycles	`1.00`
`ML-DSA-65 keypair`	`81320` cycles	`81338` cycles	`1.00`
`ML-DSA-65 sign`	`218021` cycles	`218252` cycles	`1.00`
`ML-DSA-65 verify`	`80057` cycles	`80072` cycles	`1.00`
`ML-DSA-87 keypair`	`132433` cycles	`132477` cycles	`1.00`
`ML-DSA-87 sign`	`279539` cycles	`279832` cycles	`1.00`
`ML-DSA-87 verify`	`130404` cycles	`130427` cycles	`1.00`

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

github-actions

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

Details

Benchmark suite	Current: `308107d`	Previous: `2948ece`	Ratio
`ML-DSA-44 keypair`	`114369` cycles	`114382` cycles	`1.00`
`ML-DSA-44 sign`	`428771` cycles	`428727` cycles	`1.00`
`ML-DSA-44 verify`	`121521` cycles	`121527` cycles	`1.00`
`ML-DSA-65 keypair`	`196266` cycles	`196236` cycles	`1.00`
`ML-DSA-65 sign`	`697624` cycles	`697597` cycles	`1.00`
`ML-DSA-65 verify`	`196490` cycles	`196451` cycles	`1.00`
`ML-DSA-87 keypair`	`323099` cycles	`323068` cycles	`1.00`
`ML-DSA-87 sign`	`880192` cycles	`880149` cycles	`1.00`
`ML-DSA-87 verify`	`327024` cycles	`326950` cycles	`1.00`

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

oqs-bot

Intel Xeon 4th gen (c7i)

Details

Benchmark suite	Current: `308107d`	Previous: `2948ece`	Ratio
`ML-DSA-44 keypair`	`35497` cycles	`35143` cycles	`1.01`
`ML-DSA-44 sign`	`121073` cycles	`121147` cycles	`1.00`
`ML-DSA-44 verify`	`38211` cycles	`38343` cycles	`1.00`
`ML-DSA-65 keypair`	`63058` cycles	`62033` cycles	`1.02`
`ML-DSA-65 sign`	`201564` cycles	`200225` cycles	`1.01`
`ML-DSA-65 verify`	`63214` cycles	`62992` cycles	`1.00`
`ML-DSA-87 keypair`	`95083` cycles	`94071` cycles	`1.01`
`ML-DSA-87 sign`	`234938` cycles	`230071` cycles	`1.02`
`ML-DSA-87 verify`	`94549` cycles	`95065` cycles	`0.99`

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

oqs-bot

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

Details

Benchmark suite	Current: `308107d`	Previous: `2948ece`	Ratio
`ML-DSA-44 keypair`	`95910` cycles	`95749` cycles	`1.00`
`ML-DSA-44 sign`	`349210` cycles	`348923` cycles	`1.00`
`ML-DSA-44 verify`	`101723` cycles	`101599` cycles	`1.00`
`ML-DSA-65 keypair`	`163623` cycles	`163400` cycles	`1.00`
`ML-DSA-65 sign`	`565612` cycles	`564714` cycles	`1.00`
`ML-DSA-65 verify`	`166016` cycles	`165902` cycles	`1.00`
`ML-DSA-87 keypair`	`267621` cycles	`267773` cycles	`1.00`
`ML-DSA-87 sign`	`723411` cycles	`723169` cycles	`1.00`
`ML-DSA-87 verify`	`273113` cycles	`272914` cycles	`1.00`

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

github-actions

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

Details

Benchmark suite	Current: `308107d`	Previous: `2948ece`	Ratio
`ML-DSA-44 keypair`	`276121` cycles	`285745` cycles	`0.97`
`ML-DSA-44 sign`	`825067` cycles	`894122` cycles	`0.92`
`ML-DSA-44 verify`	`273925` cycles	`280893` cycles	`0.98`
`ML-DSA-65 keypair`	`475121` cycles	`486508` cycles	`0.98`
`ML-DSA-65 sign`	`1365693` cycles	`1463974` cycles	`0.93`
`ML-DSA-65 verify`	`451767` cycles	`465274` cycles	`0.97`
`ML-DSA-87 keypair`	`805587` cycles	`832477` cycles	`0.97`
`ML-DSA-87 sign`	`1835576` cycles	`2000183` cycles	`0.92`
`ML-DSA-87 verify`	`773596` cycles	`798546` cycles	`0.97`

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

oqs-bot

AMD EPYC 3rd gen (c6a)

Details

Benchmark suite	Current: `308107d`	Previous: `2948ece`	Ratio
`ML-DSA-44 keypair`	`69206` cycles	`69206` cycles	`1`
`ML-DSA-44 sign`	`184245` cycles	`184387` cycles	`1.00`
`ML-DSA-44 verify`	`69151` cycles	`69106` cycles	`1.00`
`ML-DSA-65 keypair`	`119169` cycles	`119372` cycles	`1.00`
`ML-DSA-65 sign`	`294909` cycles	`295603` cycles	`1.00`
`ML-DSA-65 verify`	`115188` cycles	`115375` cycles	`1.00`
`ML-DSA-87 keypair`	`203578` cycles	`203802` cycles	`1.00`
`ML-DSA-87 sign`	`388167` cycles	`387905` cycles	`1.00`
`ML-DSA-87 verify`	`195857` cycles	`195698` cycles	`1.00`

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

oqs-bot

Graviton4

Details

Benchmark suite	Current: `308107d`	Previous: `2948ece`	Ratio
`ML-DSA-44 keypair`	`68739` cycles	`69152` cycles	`0.99`
`ML-DSA-44 sign`	`202889` cycles	`208483` cycles	`0.97`
`ML-DSA-44 verify`	`70765` cycles	`71242` cycles	`0.99`
`ML-DSA-65 keypair`	`121544` cycles	`122178` cycles	`0.99`
`ML-DSA-65 sign`	`331812` cycles	`342020` cycles	`0.97`
`ML-DSA-65 verify`	`117588` cycles	`118474` cycles	`0.99`
`ML-DSA-87 keypair`	`198973` cycles	`199864` cycles	`1.00`
`ML-DSA-87 sign`	`428789` cycles	`439835` cycles	`0.97`
`ML-DSA-87 verify`	`194463` cycles	`195400` 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: `308107d`	Previous: `2948ece`	Ratio
`ML-DSA-44 keypair`	`57596` cycles	`57148` cycles	`1.01`
`ML-DSA-44 sign`	`180276` cycles	`179819` cycles	`1.00`
`ML-DSA-44 verify`	`61330` cycles	`61125` cycles	`1.00`
`ML-DSA-65 keypair`	`99552` cycles	`99980` cycles	`1.00`
`ML-DSA-65 sign`	`295981` cycles	`297406` cycles	`1.00`
`ML-DSA-65 verify`	`101064` cycles	`101235` cycles	`1.00`
`ML-DSA-87 keypair`	`154022` cycles	`154320` cycles	`1.00`
`ML-DSA-87 sign`	`353635` cycles	`354598` cycles	`1.00`
`ML-DSA-87 verify`	`153339` cycles	`153733` cycles	`1.00`

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

oqs-bot

Graviton2

Details

Benchmark suite	Current: `308107d`	Previous: `2948ece`	Ratio
`ML-DSA-44 keypair`	`115425` cycles	`115728` cycles	`1.00`
`ML-DSA-44 sign`	`364333` cycles	`373939` cycles	`0.97`
`ML-DSA-44 verify`	`119521` cycles	`119966` cycles	`1.00`
`ML-DSA-65 keypair`	`198063` cycles	`199386` cycles	`0.99`
`ML-DSA-65 sign`	`597460` cycles	`615426` cycles	`0.97`
`ML-DSA-65 verify`	`194953` cycles	`196625` cycles	`0.99`
`ML-DSA-87 keypair`	`324508` cycles	`326647` cycles	`0.99`
`ML-DSA-87 sign`	`761477` cycles	`784067` cycles	`0.97`
`ML-DSA-87 verify`	`320619` cycles	`322593` cycles	`0.99`

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

oqs-bot

Graviton4 (no-opt)

Details

Benchmark suite	Current: `308107d`	Previous: `2948ece`	Ratio
`ML-DSA-44 keypair`	`128248` cycles	`128410` cycles	`1.00`
`ML-DSA-44 sign`	`457074` cycles	`456811` cycles	`1.00`
`ML-DSA-44 verify`	`136266` cycles	`136364` cycles	`1.00`
`ML-DSA-65 keypair`	`220925` cycles	`220811` cycles	`1.00`
`ML-DSA-65 sign`	`745590` cycles	`746754` cycles	`1.00`
`ML-DSA-65 verify`	`220422` cycles	`220734` cycles	`1.00`
`ML-DSA-87 keypair`	`365098` cycles	`365323` cycles	`1.00`
`ML-DSA-87 sign`	`944236` cycles	`943162` cycles	`1.00`
`ML-DSA-87 verify`	`369008` cycles	`369319` 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: `308107d`	Previous: `2948ece`	Ratio
`ML-DSA-44 keypair`	`135820` cycles	`135683` cycles	`1.00`
`ML-DSA-44 sign`	`540804` cycles	`540540` cycles	`1.00`
`ML-DSA-44 verify`	`148978` cycles	`148890` cycles	`1.00`
`ML-DSA-65 keypair`	`229064` cycles	`228278` cycles	`1.00`
`ML-DSA-65 sign`	`891984` cycles	`889005` cycles	`1.00`
`ML-DSA-65 verify`	`238549` cycles	`237556` cycles	`1.00`
`ML-DSA-87 keypair`	`373012` cycles	`374889` cycles	`0.99`
`ML-DSA-87 sign`	`1104955` cycles	`1108915` cycles	`1.00`
`ML-DSA-87 verify`	`387383` cycles	`388708` cycles	`1.00`

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

oqs-bot

Graviton3

Details

Benchmark suite	Current: `308107d`	Previous: `2948ece`	Ratio
`ML-DSA-44 keypair`	`72610` cycles	`73277` cycles	`0.99`
`ML-DSA-44 sign`	`213227` cycles	`221350` cycles	`0.96`
`ML-DSA-44 verify`	`75647` cycles	`76289` cycles	`0.99`
`ML-DSA-65 keypair`	`128411` cycles	`129514` cycles	`0.99`
`ML-DSA-65 sign`	`353239` cycles	`367951` cycles	`0.96`
`ML-DSA-65 verify`	`125610` cycles	`126662` cycles	`0.99`
`ML-DSA-87 keypair`	`206984` cycles	`210841` cycles	`0.98`
`ML-DSA-87 sign`	`445951` cycles	`467821` cycles	`0.95`
`ML-DSA-87 verify`	`205858` cycles	`206335` 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: `308107d`	Previous: `2948ece`	Ratio
`ML-DSA-44 keypair`	`158807` cycles	`159036` cycles	`1.00`
`ML-DSA-44 sign`	`565120` cycles	`565513` cycles	`1.00`
`ML-DSA-44 verify`	`170104` cycles	`170189` cycles	`1.00`
`ML-DSA-65 keypair`	`270096` cycles	`270337` cycles	`1.00`
`ML-DSA-65 sign`	`925021` cycles	`926558` cycles	`1.00`
`ML-DSA-65 verify`	`276337` cycles	`276745` cycles	`1.00`
`ML-DSA-87 keypair`	`451464` cycles	`451390` cycles	`1.00`
`ML-DSA-87 sign`	`1182648` cycles	`1184163` cycles	`1.00`
`ML-DSA-87 verify`	`461290` cycles	`461812` cycles	`1.00`

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

oqs-bot

Graviton2 (no-opt)

Details

Benchmark suite	Current: `308107d`	Previous: `2948ece`	Ratio
`ML-DSA-44 keypair`	`214615` cycles	`214703` cycles	`1.00`
`ML-DSA-44 sign`	`782904` cycles	`782961` cycles	`1.00`
`ML-DSA-44 verify`	`230602` cycles	`230723` cycles	`1.00`
`ML-DSA-65 keypair`	`385499` cycles	`385351` cycles	`1.00`
`ML-DSA-65 sign`	`1309947` cycles	`1310117` cycles	`1.00`
`ML-DSA-65 verify`	`376028` cycles	`376231` cycles	`1.00`
`ML-DSA-87 keypair`	`607490` cycles	`607560` cycles	`1.00`
`ML-DSA-87 sign`	`1655444` cycles	`1656700` cycles	`1.00`
`ML-DSA-87 verify`	`618074` cycles	`618424` cycles	`1.00`

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

oqs-bot

AMD EPYC 4th gen (c7a)

Details

Benchmark suite	Current: `308107d`	Previous: `2948ece`	Ratio
`ML-DSA-44 keypair`	`40979` cycles	`41813` cycles	`0.98`
`ML-DSA-44 sign`	`129104` cycles	`129629` cycles	`1.00`
`ML-DSA-44 verify`	`43279` cycles	`43610` cycles	`0.99`
`ML-DSA-65 keypair`	`72204` cycles	`72392` cycles	`1.00`
`ML-DSA-65 sign`	`211025` cycles	`212110` cycles	`0.99`
`ML-DSA-65 verify`	`73573` cycles	`73873` cycles	`1.00`
`ML-DSA-87 keypair`	`109362` cycles	`109524` cycles	`1.00`
`ML-DSA-87 sign`	`247835` cycles	`249633` cycles	`0.99`
`ML-DSA-87 verify`	`112117` cycles	`110170` cycles	`1.02`

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

oqs-bot

Graviton3 (no-opt)

Details

Benchmark suite	Current: `308107d`	Previous: `2948ece`	Ratio
`ML-DSA-44 keypair`	`138756` cycles	`138845` cycles	`1.00`
`ML-DSA-44 sign`	`493651` cycles	`493534` cycles	`1.00`
`ML-DSA-44 verify`	`148309` cycles	`148510` cycles	`1.00`
`ML-DSA-65 keypair`	`242702` cycles	`242325` cycles	`1.00`
`ML-DSA-65 sign`	`808721` cycles	`808829` cycles	`1.00`
`ML-DSA-65 verify`	`240717` cycles	`240967` cycles	`1.00`
`ML-DSA-87 keypair`	`396445` cycles	`396798` cycles	`1.00`
`ML-DSA-87 sign`	`1027156` cycles	`1026810` cycles	`1.00`
`ML-DSA-87 verify`	`401766` cycles	`402035` 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: `308107d`	Previous: `2948ece`	Ratio
`ML-DSA-44 keypair`	`120131` cycles	`121135` cycles	`0.99`
`ML-DSA-44 sign`	`455762` cycles	`455691` cycles	`1.00`
`ML-DSA-44 verify`	`130384` cycles	`130171` cycles	`1.00`
`ML-DSA-65 keypair`	`204342` cycles	`206078` cycles	`0.99`
`ML-DSA-65 sign`	`734962` cycles	`734493` cycles	`1.00`
`ML-DSA-65 verify`	`208973` cycles	`210555` cycles	`0.99`
`ML-DSA-87 keypair`	`337202` cycles	`337989` cycles	`1.00`
`ML-DSA-87 sign`	`924298` cycles	`922942` cycles	`1.00`
`ML-DSA-87 verify`	`344714` cycles	`345245` cycles	`1.00`

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

github-actions

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

Details

Benchmark suite	Current: `308107d`	Previous: `2948ece`	Ratio
`ML-DSA-44 keypair`	`827587` cycles	`827337` cycles	`1.00`
`ML-DSA-44 sign`	`3333337` cycles	`3331425` cycles	`1.00`
`ML-DSA-44 verify`	`920188` cycles	`919913` cycles	`1.00`
`ML-DSA-65 keypair`	`1402437` cycles	`1404508` cycles	`1.00`
`ML-DSA-65 sign`	`5443872` cycles	`5442876` cycles	`1.00`
`ML-DSA-65 verify`	`1470631` cycles	`1469680` cycles	`1.00`
`ML-DSA-87 keypair`	`2304223` cycles	`2306569` cycles	`1.00`
`ML-DSA-87 sign`	`6818211` cycles	`6817332` cycles	`1.00`
`ML-DSA-87 verify`	`2407130` cycles	`2402780` cycles	`1.00`

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

github-actions

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

Details

Benchmark suite	Current: `308107d`	Previous: `2948ece`	Ratio
`ML-DSA-44 keypair`	`464921` cycles	`464556` cycles	`1.00`
`ML-DSA-44 sign`	`2212617` cycles	`2208657` cycles	`1.00`
`ML-DSA-44 verify`	`546747` cycles	`545962` cycles	`1.00`
`ML-DSA-65 keypair`	`779753` cycles	`777602` cycles	`1.00`
`ML-DSA-65 sign`	`3629690` cycles	`3608012` cycles	`1.01`
`ML-DSA-65 verify`	`850546` cycles	`847136` cycles	`1.00`
`ML-DSA-87 keypair`	`1255823` cycles	`1253990` cycles	`1.00`
`ML-DSA-87 sign`	`4472890` cycles	`4443324` cycles	`1.01`
`ML-DSA-87 verify`	`1361597` cycles	`1361371` cycles	`1.00`

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

github-actions

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

Details

Benchmark suite	Current: `308107d`	Previous: `2948ece`	Ratio
`ML-DSA-44 keypair`	`114069` cycles	`114842` cycles	`0.99`
`ML-DSA-44 sign`	`361125` cycles	`371794` cycles	`0.97`
`ML-DSA-44 verify`	`118214` cycles	`119310` cycles	`0.99`
`ML-DSA-65 keypair`	`197806` cycles	`199034` cycles	`0.99`
`ML-DSA-65 sign`	`597002` cycles	`614739` cycles	`0.97`
`ML-DSA-65 verify`	`194692` cycles	`196379` cycles	`0.99`
`ML-DSA-87 keypair`	`323963` cycles	`326202` cycles	`0.99`
`ML-DSA-87 sign`	`760578` cycles	`783241` cycles	`0.97`
`ML-DSA-87 verify`	`320320` cycles	`322445` cycles	`0.99`

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

github-actions

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

Details

Benchmark suite	Current: `308107d`	Previous: `2948ece`	Ratio
`ML-DSA-44 keypair`	`214154` cycles	`213868` cycles	`1.00`
`ML-DSA-44 sign`	`782106` cycles	`784182` cycles	`1.00`
`ML-DSA-44 verify`	`230079` cycles	`230054` cycles	`1.00`
`ML-DSA-65 keypair`	`384873` cycles	`384979` cycles	`1.00`
`ML-DSA-65 sign`	`1326370` cycles	`1314553` cycles	`1.01`
`ML-DSA-65 verify`	`375442` cycles	`375792` cycles	`1.00`
`ML-DSA-87 keypair`	`606660` cycles	`606983` cycles	`1.00`
`ML-DSA-87 sign`	`1652718` cycles	`1654364` cycles	`1.00`
`ML-DSA-87 verify`	`617702` cycles	`618211` cycles	`1.00`

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

github-actions

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

Details

Benchmark suite	Current: `308107d`	Previous: `2948ece`	Ratio
`ML-DSA-44 keypair`	`227884` cycles	`229441` cycles	`0.99`
`ML-DSA-44 sign`	`640944` cycles	`675710` cycles	`0.95`
`ML-DSA-44 verify`	`231954` cycles	`238273` cycles	`0.97`
`ML-DSA-65 keypair`	`389453` cycles	`405551` cycles	`0.96`
`ML-DSA-65 sign`	`1045279` cycles	`1085789` cycles	`0.96`
`ML-DSA-65 verify`	`379960` cycles	`383505` cycles	`0.99`
`ML-DSA-87 keypair`	`655079` cycles	`677320` cycles	`0.97`
`ML-DSA-87 sign`	`1347200` cycles	`1446952` cycles	`0.93`
`ML-DSA-87 verify`	`633744` cycles	`643185` cycles	`0.99`

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

github-actions

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

Details

Benchmark suite	Current: `308107d`	Previous: `2948ece`	Ratio
`ML-DSA-44 keypair`	`308894` cycles	`313340` cycles	`0.99`
`ML-DSA-44 sign`	`1203258` cycles	`1210106` cycles	`0.99`
`ML-DSA-44 verify`	`332723` cycles	`345251` cycles	`0.96`
`ML-DSA-65 keypair`	`581830` cycles	`573758` cycles	`1.01`
`ML-DSA-65 sign`	`1985838` cycles	`2022886` cycles	`0.98`
`ML-DSA-65 verify`	`547594` cycles	`546429` cycles	`1.00`
`ML-DSA-87 keypair`	`891983` cycles	`880785` cycles	`1.01`
`ML-DSA-87 sign`	`2521635` cycles	`2523515` cycles	`1.00`
`ML-DSA-87 verify`	`903880` cycles	`908652` cycles	`0.99`

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

mkannwischer · 2025-11-29T05:01:21Z

We first need to merge slothy-optimizer/slothy#363 and then update the SLOTHY commit.

mkannwischer · 2025-12-01T02:42:52Z

We first need to merge slothy-optimizer/slothy#363 and then update the SLOTHY commit.

It has been merged and I updated the SLOTHY commit.

Resolves #206 Signed-off-by: Matthias J. Kannwischer <[email protected]>

mkannwischer force-pushed the slothy-intt branch 2 times, most recently from b99e917 to 308107d Compare November 28, 2025 05:11

mkannwischer added the benchmark label Nov 28, 2025

github-actions bot reviewed Nov 28, 2025

View reviewed changes

oqs-bot reviewed Nov 28, 2025

View reviewed changes

github-actions bot reviewed Nov 28, 2025

View reviewed changes

oqs-bot reviewed Nov 28, 2025

View reviewed changes

github-actions bot reviewed Nov 28, 2025

View reviewed changes

mkannwischer marked this pull request as ready for review November 28, 2025 05:45

mkannwischer requested a review from a team as a code owner November 28, 2025 05:45

mkannwischer force-pushed the slothy-intt branch from 308107d to 770940b Compare November 28, 2025 06:06

hanno-becker approved these changes Nov 29, 2025

View reviewed changes

mkannwischer added the DO-NOT-MERGE label Nov 29, 2025

mkannwischer force-pushed the slothy-intt branch from 770940b to 1001650 Compare December 1, 2025 02:42

mkannwischer removed the DO-NOT-MERGE label Dec 1, 2025

SLOTHY: Superoptimize AArch64 INTT

3efff95

Resolves #206 Signed-off-by: Matthias J. Kannwischer <[email protected]>

mkannwischer force-pushed the slothy-intt branch from 1001650 to 3efff95 Compare December 1, 2025 03:03

mkannwischer mentioned this pull request Dec 1, 2025

SLOTHY: Superoptimize polyvecl_pointwise_acc_montgomery #761

Closed

mkannwischer merged commit 1915e47 into main Dec 1, 2025
332 checks passed

mkannwischer deleted the slothy-intt branch December 1, 2025 03:53

SLOTHY: Superoptimize AArch64 INTT #748

SLOTHY: Superoptimize AArch64 INTT #748

Uh oh!

Conversation

mkannwischer commented Nov 28, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

github-actions bot left a comment

Choose a reason for hiding this comment

Mac Mini (M1, 2020) benchmarks (opt)

Uh oh!

github-actions bot left a comment

Choose a reason for hiding this comment

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

Uh oh!

oqs-bot left a comment

Choose a reason for hiding this comment

Intel Xeon 4th gen (c7i)

Uh oh!

oqs-bot left a comment

Choose a reason for hiding this comment

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

Uh oh!

github-actions bot left a comment

Choose a reason for hiding this comment

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

Uh oh!

oqs-bot left a comment

Choose a reason for hiding this comment

AMD EPYC 3rd gen (c6a)

Uh oh!

oqs-bot left a comment

Choose a reason for hiding this comment

Graviton4

Uh oh!

oqs-bot left a comment

Choose a reason for hiding this comment

Intel Xeon 3rd gen (c6i)

Uh oh!

oqs-bot left a comment

Choose a reason for hiding this comment

Graviton2

Uh oh!

oqs-bot left a comment

Choose a reason for hiding this comment

Graviton4 (no-opt)

Uh oh!

oqs-bot left a comment

Choose a reason for hiding this comment

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

Uh oh!

oqs-bot left a comment

Choose a reason for hiding this comment

Graviton3

Uh oh!

oqs-bot left a comment

Choose a reason for hiding this comment

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

Uh oh!

oqs-bot left a comment

Choose a reason for hiding this comment

Graviton2 (no-opt)

Uh oh!

oqs-bot left a comment

Choose a reason for hiding this comment

AMD EPYC 4th gen (c7a)

Uh oh!

oqs-bot left a comment

Choose a reason for hiding this comment

Graviton3 (no-opt)

Uh oh!

oqs-bot left a comment

Choose a reason for hiding this comment

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

Uh oh!

github-actions bot left a comment

Choose a reason for hiding this comment

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

Uh oh!

github-actions bot left a comment

mkannwischer commented Nov 28, 2025 •

edited

Loading