Faster INTT on AArch64 by more efficient reduction #773

rod-chapman · 2025-02-14T18:53:43Z

This PR introduces a small change in AArch64 intt_clean.S that reduces the number of intermediate
reduction steps from 4 to 3, through more thorough tracking of coefficient bounds.

TODO

Applicatioin of SLOTHY to this code to also update intt_opt.S
Re-proof of both Clean and Opt versions with HOL-Light
Benchmarks

oqs-bot

Intel Xeon 4th gen (c7i)

Benchmark suite	Current: `2b96f0c`	Previous: `c1cd91f`	Ratio
`ML-KEM-512 keypair`	`9680` cycles	`9594` cycles	`1.01`
`ML-KEM-512 encaps`	`11253` cycles	`11228` cycles	`1.00`
`ML-KEM-512 decaps`	`15808` cycles	`15296` cycles	`1.03`
`ML-KEM-768 keypair`	`16653` cycles	`16378` cycles	`1.02`
`ML-KEM-768 encaps`	`18007` cycles	`17908` cycles	`1.01`
`ML-KEM-768 decaps`	`23510` cycles	`23636` cycles	`0.99`
`ML-KEM-1024 keypair`	`22248` cycles	`22233` cycles	`1.00`
`ML-KEM-1024 encaps`	`24101` cycles	`24083` cycles	`1.00`
`ML-KEM-1024 decaps`	`31967` cycles	`31905` cycles	`1.00`

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

oqs-bot

Arm Cortex-A76 (Raspberry Pi 5) benchmarks

Benchmark suite	Current: `2b96f0c`	Previous: `c1cd91f`	Ratio
`ML-KEM-512 keypair`	`29500` cycles	`29453` cycles	`1.00`
`ML-KEM-512 encaps`	`34717` cycles	`35071` cycles	`0.99`
`ML-KEM-512 decaps`	`45263` cycles	`45674` cycles	`0.99`
`ML-KEM-768 keypair`	`50213` cycles	`50349` cycles	`1.00`
`ML-KEM-768 encaps`	`55526` cycles	`55719` cycles	`1.00`
`ML-KEM-768 decaps`	`70330` cycles	`70756` cycles	`0.99`
`ML-KEM-1024 keypair`	`73206` cycles	`73199` cycles	`1.00`
`ML-KEM-1024 encaps`	`81647` cycles	`82250` cycles	`0.99`
`ML-KEM-1024 decaps`	`101738` cycles	`102458` cycles	`0.99`

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

oqs-bot

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

Benchmark suite	Current: `2b96f0c`	Previous: `c1cd91f`	Ratio
`ML-KEM-512 keypair`	`29398` cycles	`29311` cycles	`1.00`
`ML-KEM-512 encaps`	`34683` cycles	`34724` cycles	`1.00`
`ML-KEM-512 decaps`	`44967` cycles	`45050` cycles	`1.00`
`ML-KEM-768 keypair`	`48655` cycles	`48655` cycles	`1`
`ML-KEM-768 encaps`	`55658` cycles	`55747` cycles	`1.00`
`ML-KEM-768 decaps`	`67588` cycles	`67507` cycles	`1.00`
`ML-KEM-1024 keypair`	`72636` cycles	`72600` cycles	`1.00`
`ML-KEM-1024 encaps`	`84691` cycles	`84719` cycles	`1.00`
`ML-KEM-1024 decaps`	`101753` cycles	`101613` cycles	`1.00`

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

oqs-bot

Intel Xeon 3rd gen (c6i)

Benchmark suite	Current: `2b96f0c`	Previous: `c1cd91f`	Ratio
`ML-KEM-512 keypair`	`16150` cycles	`16161` cycles	`1.00`
`ML-KEM-512 encaps`	`18798` cycles	`18387` cycles	`1.02`
`ML-KEM-512 decaps`	`24983` cycles	`24935` cycles	`1.00`
`ML-KEM-768 keypair`	`27836` cycles	`27810` cycles	`1.00`
`ML-KEM-768 encaps`	`29540` cycles	`29529` cycles	`1.00`
`ML-KEM-768 decaps`	`38906` cycles	`38947` cycles	`1.00`
`ML-KEM-1024 keypair`	`38262` cycles	`37715` cycles	`1.01`
`ML-KEM-1024 encaps`	`40720` cycles	`40713` cycles	`1.00`
`ML-KEM-1024 decaps`	`53236` cycles	`53246` cycles	`1.00`

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

oqs-bot

AMD EPYC 3rd gen (c6a)

Benchmark suite	Current: `2b96f0c`	Previous: `c1cd91f`	Ratio
`ML-KEM-512 keypair`	`17260` cycles	`17271` cycles	`1.00`
`ML-KEM-512 encaps`	`19051` cycles	`19067` cycles	`1.00`
`ML-KEM-512 decaps`	`24630` cycles	`24503` cycles	`1.01`
`ML-KEM-768 keypair`	`29411` cycles	`29400` cycles	`1.00`
`ML-KEM-768 encaps`	`30812` cycles	`30641` cycles	`1.01`
`ML-KEM-768 decaps`	`38582` cycles	`38593` cycles	`1.00`
`ML-KEM-1024 keypair`	`43743` cycles	`43347` cycles	`1.01`
`ML-KEM-1024 encaps`	`45090` cycles	`44937` cycles	`1.00`
`ML-KEM-1024 decaps`	`55593` cycles	`55416` cycles	`1.00`

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

oqs-bot

AMD EPYC 4th gen (c7a)

Benchmark suite	Current: `2b96f0c`	Previous: `c1cd91f`	Ratio
`ML-KEM-512 keypair`	`11648` cycles	`11633` cycles	`1.00`
`ML-KEM-512 encaps`	`13328` cycles	`13296` cycles	`1.00`
`ML-KEM-512 decaps`	`18237` cycles	`18216` cycles	`1.00`
`ML-KEM-768 keypair`	`20184` cycles	`20515` cycles	`0.98`
`ML-KEM-768 encaps`	`21209` cycles	`21177` cycles	`1.00`
`ML-KEM-768 decaps`	`28439` cycles	`28411` cycles	`1.00`
`ML-KEM-1024 keypair`	`26971` cycles	`27039` cycles	`1.00`
`ML-KEM-1024 encaps`	`29009` cycles	`29022` cycles	`1.00`
`ML-KEM-1024 decaps`	`38524` cycles	`38526` cycles	`1.00`

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

oqs-bot

Graviton4

Benchmark suite	Current: `2b96f0c`	Previous: `c1cd91f`	Ratio
`ML-KEM-512 keypair`	`17879` cycles	`17886` cycles	`1.00`
`ML-KEM-512 encaps`	`21105` cycles	`21242` cycles	`0.99`
`ML-KEM-512 decaps`	`27750` cycles	`27950` cycles	`0.99`
`ML-KEM-768 keypair`	`30812` cycles	`30850` cycles	`1.00`
`ML-KEM-768 encaps`	`33710` cycles	`33938` cycles	`0.99`
`ML-KEM-768 decaps`	`43292` cycles	`43591` cycles	`0.99`
`ML-KEM-1024 keypair`	`44386` cycles	`44447` cycles	`1.00`
`ML-KEM-1024 encaps`	`49670` cycles	`49886` cycles	`1.00`
`ML-KEM-1024 decaps`	`62606` cycles	`62820` 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: `2b96f0c`	Previous: `c1cd91f`	Ratio
`ML-KEM-512 keypair`	`47709` cycles	`47710` cycles	`1.00`
`ML-KEM-512 encaps`	`55617` cycles	`55544` cycles	`1.00`
`ML-KEM-512 decaps`	`71793` cycles	`71776` cycles	`1.00`
`ML-KEM-768 keypair`	`76884` cycles	`76906` cycles	`1.00`
`ML-KEM-768 encaps`	`87284` cycles	`87347` cycles	`1.00`
`ML-KEM-768 decaps`	`108142` cycles	`108373` cycles	`1.00`
`ML-KEM-1024 keypair`	`112878` cycles	`112725` cycles	`1.00`
`ML-KEM-1024 encaps`	`126444` cycles	`126316` cycles	`1.00`
`ML-KEM-1024 decaps`	`153142` cycles	`152984` 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: `2b96f0c`	Previous: `c1cd91f`	Ratio
`ML-KEM-512 keypair`	`39050` cycles	`39065` cycles	`1.00`
`ML-KEM-512 encaps`	`47207` cycles	`47268` cycles	`1.00`
`ML-KEM-512 decaps`	`60795` cycles	`60849` cycles	`1.00`
`ML-KEM-768 keypair`	`63600` cycles	`63516` cycles	`1.00`
`ML-KEM-768 encaps`	`74265` cycles	`74236` cycles	`1.00`
`ML-KEM-768 decaps`	`92145` cycles	`92578` cycles	`1.00`
`ML-KEM-1024 keypair`	`94298` cycles	`94265` cycles	`1.00`
`ML-KEM-1024 encaps`	`107212` cycles	`107467` cycles	`1.00`
`ML-KEM-1024 decaps`	`129676` cycles	`129805` 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: `2b96f0c`	Previous: `c1cd91f`	Ratio
`ML-KEM-512 keypair`	`36725` cycles	`36492` cycles	`1.01`
`ML-KEM-512 encaps`	`43090` cycles	`43065` cycles	`1.00`
`ML-KEM-512 decaps`	`56132` cycles	`56111` cycles	`1.00`
`ML-KEM-768 keypair`	`59542` cycles	`59492` cycles	`1.00`
`ML-KEM-768 encaps`	`67987` cycles	`67953` cycles	`1.00`
`ML-KEM-768 decaps`	`85141` cycles	`85220` cycles	`1.00`
`ML-KEM-1024 keypair`	`88081` cycles	`88107` cycles	`1.00`
`ML-KEM-1024 encaps`	`98826` cycles	`98850` cycles	`1.00`
`ML-KEM-1024 decaps`	`120598` cycles	`120601` cycles	`1.00`

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

oqs-bot

Graviton3

Benchmark suite	Current: `2b96f0c`	Previous: `c1cd91f`	Ratio
`ML-KEM-512 keypair`	`18959` cycles	`18916` cycles	`1.00`
`ML-KEM-512 encaps`	`22421` cycles	`22691` cycles	`0.99`
`ML-KEM-512 decaps`	`29652` cycles	`29998` cycles	`0.99`
`ML-KEM-768 keypair`	`32341` cycles	`32374` cycles	`1.00`
`ML-KEM-768 encaps`	`35738` cycles	`36074` cycles	`0.99`
`ML-KEM-768 decaps`	`46039` cycles	`46507` cycles	`0.99`
`ML-KEM-1024 keypair`	`46651` cycles	`46587` cycles	`1.00`
`ML-KEM-1024 encaps`	`52263` cycles	`52649` cycles	`0.99`
`ML-KEM-1024 decaps`	`66119` cycles	`66591` cycles	`0.99`

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

oqs-bot

Graviton4 (no-opt)

Benchmark suite	Current: `2b96f0c`	Previous: `c1cd91f`	Ratio
`ML-KEM-512 keypair`	`35973` cycles	`35951` cycles	`1.00`
`ML-KEM-512 encaps`	`41664` cycles	`40871` cycles	`1.02`
`ML-KEM-512 decaps`	`52289` cycles	`52315` cycles	`1.00`
`ML-KEM-768 keypair`	`59972` cycles	`63503` cycles	`0.94`
`ML-KEM-768 encaps`	`67073` cycles	`67650` cycles	`0.99`
`ML-KEM-768 decaps`	`81836` cycles	`81530` cycles	`1.00`
`ML-KEM-1024 keypair`	`89258` cycles	`89213` cycles	`1.00`
`ML-KEM-1024 encaps`	`98967` cycles	`99057` cycles	`1.00`
`ML-KEM-1024 decaps`	`117887` cycles	`117883` cycles	`1.00`

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

oqs-bot

Graviton2

Benchmark suite	Current: `2b96f0c`	Previous: `c1cd91f`	Ratio
`ML-KEM-512 keypair`	`29506` cycles	`29483` cycles	`1.00`
`ML-KEM-512 encaps`	`34722` cycles	`35063` cycles	`0.99`
`ML-KEM-512 decaps`	`45269` cycles	`45743` cycles	`0.99`
`ML-KEM-768 keypair`	`50227` cycles	`50361` cycles	`1.00`
`ML-KEM-768 encaps`	`55528` cycles	`55821` cycles	`0.99`
`ML-KEM-768 decaps`	`70343` cycles	`70723` cycles	`0.99`
`ML-KEM-1024 keypair`	`73340` cycles	`73216` cycles	`1.00`
`ML-KEM-1024 encaps`	`81677` cycles	`82269` cycles	`0.99`
`ML-KEM-1024 decaps`	`101671` cycles	`102486` cycles	`0.99`

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

oqs-bot

Graviton3 (no-opt)

Benchmark suite	Current: `2b96f0c`	Previous: `c1cd91f`	Ratio
`ML-KEM-512 keypair`	`39099` cycles	`39101` cycles	`1.00`
`ML-KEM-512 encaps`	`45001` cycles	`44970` cycles	`1.00`
`ML-KEM-512 decaps`	`56876` cycles	`56873` cycles	`1.00`
`ML-KEM-768 keypair`	`64515` cycles	`64576` cycles	`1.00`
`ML-KEM-768 encaps`	`72112` cycles	`72801` cycles	`0.99`
`ML-KEM-768 decaps`	`88232` cycles	`88137` cycles	`1.00`
`ML-KEM-1024 keypair`	`96335` cycles	`96248` cycles	`1.00`
`ML-KEM-1024 encaps`	`106445` cycles	`106349` cycles	`1.00`
`ML-KEM-1024 decaps`	`127105` cycles	`127373` cycles	`1.00`

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

oqs-bot

Graviton2 (no-opt)

Benchmark suite	Current: `2b96f0c`	Previous: `c1cd91f`	Ratio
`ML-KEM-512 keypair`	`59518` cycles	`59546` cycles	`1.00`
`ML-KEM-512 encaps`	`68123` cycles	`68085` cycles	`1.00`
`ML-KEM-512 decaps`	`86773` cycles	`86727` cycles	`1.00`
`ML-KEM-768 keypair`	`99655` cycles	`99248` cycles	`1.00`
`ML-KEM-768 encaps`	`111282` cycles	`110660` cycles	`1.01`
`ML-KEM-768 decaps`	`134682` cycles	`134859` cycles	`1.00`
`ML-KEM-1024 keypair`	`148868` cycles	`149034` cycles	`1.00`
`ML-KEM-1024 encaps`	`164066` cycles	`164405` cycles	`1.00`
`ML-KEM-1024 decaps`	`195925` cycles	`195634` cycles	`1.00`

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

oqs-bot

SpacemiT K1 8 (Banana Pi F3) benchmarks

Benchmark suite	Current: `2b96f0c`	Previous: `c1cd91f`	Ratio
`ML-KEM-512 keypair`	`225295` cycles	`225269` cycles	`1.00`
`ML-KEM-512 encaps`	`271065` cycles	`271025` cycles	`1.00`
`ML-KEM-512 decaps`	`345546` cycles	`345491` cycles	`1.00`
`ML-KEM-768 keypair`	`372892` cycles	`372949` cycles	`1.00`
`ML-KEM-768 encaps`	`433575` cycles	`433538` cycles	`1.00`
`ML-KEM-768 decaps`	`531199` cycles	`531315` cycles	`1.00`
`ML-KEM-1024 keypair`	`554548` cycles	`554640` cycles	`1.00`
`ML-KEM-1024 encaps`	`633794` cycles	`633914` cycles	`1.00`
`ML-KEM-1024 decaps`	`755414` cycles	`756120` cycles	`1.00`

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

oqs-bot

Arm Cortex-A72 (Raspberry Pi 4) benchmarks

Benchmark suite	Current: `2b96f0c`	Previous: `c1cd91f`	Ratio
`ML-KEM-512 keypair`	`52882` cycles	`53629` cycles	`0.99`
`ML-KEM-512 encaps`	`61052` cycles	`61642` cycles	`0.99`
`ML-KEM-512 decaps`	`77703` cycles	`79021` cycles	`0.98`
`ML-KEM-768 keypair`	`89960` cycles	`91270` cycles	`0.99`
`ML-KEM-768 encaps`	`98109` cycles	`99862` cycles	`0.98`
`ML-KEM-768 decaps`	`122537` cycles	`124565` cycles	`0.98`
`ML-KEM-1024 keypair`	`135820` cycles	`135453` cycles	`1.00`
`ML-KEM-1024 encaps`	`148661` cycles	`148361` cycles	`1.00`
`ML-KEM-1024 decaps`	`181617` cycles	`181489` cycles	`1.00`

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

oqs-bot

⚠️ Performance Alert ⚠️

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

Benchmark suite	Current: `9145809`	Previous: `10cccc5`	Ratio
`ML-KEM-512 keypair`	`54741` cycles	`52947` cycles	`1.03`

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

oqs-bot

Arm Cortex-A55 (Snapdragon 888) benchmarks

Benchmark suite	Current: `2b96f0c`	Previous: `c1cd91f`	Ratio
`ML-KEM-512 keypair`	`59569` cycles	`59512` cycles	`1.00`
`ML-KEM-512 encaps`	`67172` cycles	`67193` cycles	`1.00`
`ML-KEM-512 decaps`	`86262` cycles	`86365` cycles	`1.00`
`ML-KEM-768 keypair`	`101414` cycles	`101280` cycles	`1.00`
`ML-KEM-768 encaps`	`112349` cycles	`112488` cycles	`1.00`
`ML-KEM-768 decaps`	`139650` cycles	`139807` cycles	`1.00`
`ML-KEM-1024 keypair`	`153548` cycles	`153796` cycles	`1.00`
`ML-KEM-1024 encaps`	`171375` cycles	`171232` cycles	`1.00`
`ML-KEM-1024 decaps`	`207531` cycles	`210029` cycles	`0.99`

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

hanno-becker

@rod-chapman Good catch, this may indeed be a little improvement, but there's more work to do in this PR?

rod-chapman · 2025-02-16T03:30:09Z

Yes... is "slothy-cli" installed by the NIX environment? If not, then what platform should I be running SLOTHY on?

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: `2b96f0c`	Previous: `c1cd91f`	Ratio
`ML-KEM-512 decaps`	`15808` cycles	`15296` cycles	`1.03`

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

Signed-off-by: Rod Chapman <[email protected]>

Updated HOL proof remains TBD. Signed-off-by: Rod Chapman <[email protected]>

rod-chapman added benchmark this PR should be benchmarked in CI aarch64 labels Feb 14, 2025

rod-chapman requested a review from a team as a code owner February 14, 2025 18:53

oqs-bot reviewed Feb 14, 2025

View reviewed changes

rod-chapman requested a review from hanno-becker February 14, 2025 20:43

hanno-becker removed request for a team and hanno-becker February 15, 2025 12:55

hanno-becker reviewed Feb 15, 2025

View reviewed changes

rod-chapman force-pushed the faster_aarch64_intt branch 3 times, most recently from cee0db3 to 918d5b2 Compare February 19, 2025 08:37

rod-chapman force-pushed the faster_aarch64_intt branch 5 times, most recently from 64bd87e to 2f4c339 Compare February 24, 2025 13:09

rod-chapman force-pushed the faster_aarch64_intt branch 4 times, most recently from 2523d7a to e59b18b Compare March 7, 2025 14:42

rod-chapman force-pushed the faster_aarch64_intt branch 2 times, most recently from 6553ca4 to 7baea43 Compare March 10, 2025 17:02

rod-chapman added benchmark this PR should be benchmarked in CI and removed benchmark this PR should be benchmarked in CI labels Mar 10, 2025

oqs-bot reviewed Mar 10, 2025

View reviewed changes

rod-chapman added 2 commits March 12, 2025 09:25

Faster INTT on AArch64 - removes 1 redundant reduction step

49d2102

Signed-off-by: Rod Chapman <[email protected]>

Add SLOTHY-optimized versions of this new INTT code.

95a15a3

Updated HOL proof remains TBD. Signed-off-by: Rod Chapman <[email protected]>

rod-chapman force-pushed the faster_aarch64_intt branch from 2b96f0c to 95a15a3 Compare March 12, 2025 09:25

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Faster INTT on AArch64 by more efficient reduction #773

Faster INTT on AArch64 by more efficient reduction #773

rod-chapman commented Feb 14, 2025

oqs-bot left a comment •

edited

Loading

oqs-bot left a comment •

edited

Loading

oqs-bot left a comment •

edited

Loading

oqs-bot left a comment •

edited

Loading

oqs-bot left a comment •

edited

Loading

oqs-bot left a comment •

edited

Loading

oqs-bot left a comment •

edited

Loading

oqs-bot left a comment •

edited

Loading

oqs-bot left a comment •

edited

Loading

oqs-bot left a comment •

edited

Loading

oqs-bot left a comment •

edited

Loading

oqs-bot left a comment •

edited

Loading

oqs-bot left a comment •

edited

Loading

oqs-bot left a comment •

edited

Loading

oqs-bot left a comment •

edited

Loading

oqs-bot left a comment •

edited

Loading

oqs-bot left a comment •

edited

Loading

oqs-bot left a comment

oqs-bot left a comment •

edited

Loading

hanno-becker left a comment

rod-chapman commented Feb 16, 2025

oqs-bot left a comment

Faster INTT on AArch64 by more efficient reduction #773

Are you sure you want to change the base?

Faster INTT on AArch64 by more efficient reduction #773

Conversation

rod-chapman commented Feb 14, 2025

oqs-bot left a comment • edited Loading

Choose a reason for hiding this comment

Intel Xeon 4th gen (c7i)

oqs-bot left a comment • edited Loading

Choose a reason for hiding this comment

Arm Cortex-A76 (Raspberry Pi 5) benchmarks

oqs-bot left a comment • edited Loading

Choose a reason for hiding this comment

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

oqs-bot left a comment • edited Loading

Choose a reason for hiding this comment

Intel Xeon 3rd gen (c6i)

oqs-bot left a comment • edited Loading

Choose a reason for hiding this comment

AMD EPYC 3rd gen (c6a)

oqs-bot left a comment • edited Loading

Choose a reason for hiding this comment

AMD EPYC 4th gen (c7a)

oqs-bot left a comment • edited Loading

Choose a reason for hiding this comment

Graviton4

oqs-bot left a comment • edited Loading

Choose a reason for hiding this comment

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

oqs-bot left a comment • edited Loading

Choose a reason for hiding this comment

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

oqs-bot left a comment • edited Loading

Choose a reason for hiding this comment

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

oqs-bot left a comment • edited Loading

Choose a reason for hiding this comment

Graviton3

oqs-bot left a comment • edited Loading

Choose a reason for hiding this comment

Graviton4 (no-opt)

oqs-bot left a comment • edited Loading

Choose a reason for hiding this comment

Graviton2

oqs-bot left a comment • edited Loading

Choose a reason for hiding this comment

Graviton3 (no-opt)

oqs-bot left a comment • edited Loading

Choose a reason for hiding this comment

Graviton2 (no-opt)

oqs-bot left a comment • edited Loading

Choose a reason for hiding this comment

SpacemiT K1 8 (Banana Pi F3) benchmarks

oqs-bot left a comment • edited Loading

Choose a reason for hiding this comment

Arm Cortex-A72 (Raspberry Pi 4) benchmarks

oqs-bot left a comment

Choose a reason for hiding this comment

⚠️ Performance Alert ⚠️

oqs-bot left a comment • edited Loading

Choose a reason for hiding this comment

Arm Cortex-A55 (Snapdragon 888) benchmarks

hanno-becker left a comment

Choose a reason for hiding this comment

rod-chapman commented Feb 16, 2025

oqs-bot left a comment

Choose a reason for hiding this comment

⚠️ Performance Alert ⚠️

oqs-bot left a comment •

edited

Loading

oqs-bot left a comment •

edited

Loading

oqs-bot left a comment •

edited

Loading

oqs-bot left a comment •

edited

Loading

oqs-bot left a comment •

edited

Loading

oqs-bot left a comment •

edited

Loading

oqs-bot left a comment •

edited

Loading

oqs-bot left a comment •

edited

Loading

oqs-bot left a comment •

edited

Loading

oqs-bot left a comment •

edited

Loading

oqs-bot left a comment •

edited

Loading

oqs-bot left a comment •

edited

Loading

oqs-bot left a comment •

edited

Loading

oqs-bot left a comment •

edited

Loading

oqs-bot left a comment •

edited

Loading

oqs-bot left a comment •

edited

Loading

oqs-bot left a comment •

edited

Loading

oqs-bot left a comment •

edited

Loading