Reintroduce struct definitions for mlk_poly{mat,vec} #1263

hanno-becker · 2025-10-31T14:00:11Z

Change mlk_polyvec back to struct { mlk_poly vec[MLKEM_K]; }
Change mlk_polymat to struct { mlk_polyvec vec[MLKEM_K]; }
Update all function signatures to use pointer style
Fix all implementations to use struct member access
Update tests, benchmarks, and CBMC harnesses
Add consistent const annotations

hanno-becker · 2025-11-06T11:03:03Z

The runtime of polyvec_add further degrades here to >6min. That should certainly be addressed before this PR can be merged.

oqs-bot

Mac Mini (M1, 2020) benchmarks

Benchmark suite	Current: `478f245`	Previous: `90fed62`	Ratio
`ML-KEM-512 keypair`	`12293` cycles	`12294` cycles	`1.00`
`ML-KEM-512 encaps`	`14952` cycles	`14952` cycles	`1`
`ML-KEM-512 decaps`	`19485` cycles	`19486` cycles	`1.00`
`ML-KEM-768 keypair`	`21348` cycles	`21349` cycles	`1.00`
`ML-KEM-768 encaps`	`23927` cycles	`23934` cycles	`1.00`
`ML-KEM-768 decaps`	`30495` cycles	`30501` cycles	`1.00`
`ML-KEM-1024 keypair`	`30334` cycles	`30333` cycles	`1.00`
`ML-KEM-1024 encaps`	`34542` cycles	`34540` cycles	`1.00`
`ML-KEM-1024 decaps`	`44142` cycles	`44142` cycles	`1`

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

oqs-bot

Intel Xeon 4th gen (c7i)

Benchmark suite	Current: `478f245`	Previous: `90fed62`	Ratio
`ML-KEM-512 keypair`	`9636` cycles	`9660` cycles	`1.00`
`ML-KEM-512 encaps`	`11108` cycles	`11123` cycles	`1.00`
`ML-KEM-512 decaps`	`15078` cycles	`15126` cycles	`1.00`
`ML-KEM-768 keypair`	`16586` cycles	`16536` cycles	`1.00`
`ML-KEM-768 encaps`	`17723` cycles	`17836` cycles	`0.99`
`ML-KEM-768 decaps`	`23385` cycles	`23516` cycles	`0.99`
`ML-KEM-1024 keypair`	`22298` cycles	`22440` cycles	`0.99`
`ML-KEM-1024 encaps`	`24416` cycles	`24254` cycles	`1.01`
`ML-KEM-1024 decaps`	`32087` cycles	`31850` cycles	`1.01`

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

oqs-bot

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

Benchmark suite	Current: `478f245`	Previous: `90fed62`	Ratio
`ML-KEM-512 keypair`	`28525` cycles	`29001` cycles	`0.98`
`ML-KEM-512 encaps`	`36417` cycles	`35123` cycles	`1.04`
`ML-KEM-512 decaps`	`45540` cycles	`44660` cycles	`1.02`
`ML-KEM-768 keypair`	`48958` cycles	`47791` cycles	`1.02`
`ML-KEM-768 encaps`	`58392` cycles	`57583` cycles	`1.01`
`ML-KEM-768 decaps`	`70202` cycles	`69633` cycles	`1.01`
`ML-KEM-1024 keypair`	`73376` cycles	`71515` cycles	`1.03`
`ML-KEM-1024 encaps`	`85851` cycles	`83296` cycles	`1.03`
`ML-KEM-1024 decaps`	`101994` cycles	`99912` cycles	`1.02`

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) (no-opt)'.
Benchmark result of this commit is worse than the previous benchmark result exceeding threshold 1.03.

Benchmark suite	Current: `478f245`	Previous: `90fed62`	Ratio
`ML-KEM-512 encaps`	`36417` cycles	`35123` cycles	`1.04`
`ML-KEM-1024 encaps`	`85851` cycles	`83296` cycles	`1.03`

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

oqs-bot

Arm Cortex-A72 (Raspberry Pi 4) benchmarks

Benchmark suite	Current: `478f245`	Previous: `90fed62`	Ratio
`ML-KEM-512 keypair`	`50616` cycles	`51095` cycles	`0.99`
`ML-KEM-512 encaps`	`58394` cycles	`59240` cycles	`0.99`
`ML-KEM-512 decaps`	`74713` cycles	`76953` cycles	`0.97`
`ML-KEM-768 keypair`	`87822` cycles	`86535` cycles	`1.01`
`ML-KEM-768 encaps`	`95617` cycles	`94269` cycles	`1.01`
`ML-KEM-768 decaps`	`118833` cycles	`117525` cycles	`1.01`
`ML-KEM-1024 keypair`	`129952` cycles	`130035` cycles	`1.00`
`ML-KEM-1024 encaps`	`142718` cycles	`141886` cycles	`1.01`
`ML-KEM-1024 decaps`	`174120` cycles	`173869` cycles	`1.00`

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

oqs-bot

AMD EPYC 4th gen (c7a)

Benchmark suite	Current: `478f245`	Previous: `90fed62`	Ratio
`ML-KEM-512 keypair`	`11761` cycles	`11882` cycles	`0.99`
`ML-KEM-512 encaps`	`13378` cycles	`13408` cycles	`1.00`
`ML-KEM-512 decaps`	`18229` cycles	`18325` cycles	`0.99`
`ML-KEM-768 keypair`	`20928` cycles	`20573` cycles	`1.02`
`ML-KEM-768 encaps`	`21788` cycles	`21548` cycles	`1.01`
`ML-KEM-768 decaps`	`28760` cycles	`28753` cycles	`1.00`
`ML-KEM-1024 keypair`	`28131` cycles	`27718` cycles	`1.01`
`ML-KEM-1024 encaps`	`29963` cycles	`29917` cycles	`1.00`
`ML-KEM-1024 decaps`	`39412` cycles	`39244` cycles	`1.00`

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

oqs-bot

AMD EPYC 3rd gen (c6a)

Benchmark suite	Current: `478f245`	Previous: `90fed62`	Ratio
`ML-KEM-512 keypair`	`16894` cycles	`16846` cycles	`1.00`
`ML-KEM-512 encaps`	`18604` cycles	`18587` cycles	`1.00`
`ML-KEM-512 decaps`	`24017` cycles	`23921` cycles	`1.00`
`ML-KEM-768 keypair`	`28547` cycles	`28690` cycles	`1.00`
`ML-KEM-768 encaps`	`29924` cycles	`29693` cycles	`1.01`
`ML-KEM-768 decaps`	`37790` cycles	`37509` cycles	`1.01`
`ML-KEM-1024 keypair`	`41156` cycles	`41797` cycles	`0.98`
`ML-KEM-1024 encaps`	`43396` cycles	`44188` cycles	`0.98`
`ML-KEM-1024 decaps`	`53881` cycles	`54630` cycles	`0.99`

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

oqs-bot

Graviton2

Benchmark suite	Current: `478f245`	Previous: `90fed62`	Ratio
`ML-KEM-512 keypair`	`28321` cycles	`28301` cycles	`1.00`
`ML-KEM-512 encaps`	`34062` cycles	`34094` cycles	`1.00`
`ML-KEM-512 decaps`	`44316` cycles	`44394` cycles	`1.00`
`ML-KEM-768 keypair`	`48241` cycles	`48260` cycles	`1.00`
`ML-KEM-768 encaps`	`54244` cycles	`54137` cycles	`1.00`
`ML-KEM-768 decaps`	`68692` cycles	`68631` cycles	`1.00`
`ML-KEM-1024 keypair`	`70385` cycles	`70477` cycles	`1.00`
`ML-KEM-1024 encaps`	`78841` cycles	`78880` cycles	`1.00`
`ML-KEM-1024 decaps`	`98444` cycles	`98478` cycles	`1.00`

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

oqs-bot

Graviton4

Benchmark suite	Current: `478f245`	Previous: `90fed62`	Ratio
`ML-KEM-512 keypair`	`17649` cycles	`17658` cycles	`1.00`
`ML-KEM-512 encaps`	`20622` cycles	`20648` cycles	`1.00`
`ML-KEM-512 decaps`	`27061` cycles	`27099` cycles	`1.00`
`ML-KEM-768 keypair`	`30251` cycles	`30257` cycles	`1.00`
`ML-KEM-768 encaps`	`32982` cycles	`32953` cycles	`1.00`
`ML-KEM-768 decaps`	`42184` cycles	`42194` cycles	`1.00`
`ML-KEM-1024 keypair`	`43827` cycles	`43858` cycles	`1.00`
`ML-KEM-1024 encaps`	`48859` cycles	`48900` cycles	`1.00`
`ML-KEM-1024 decaps`	`61580` cycles	`61574` 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: `478f245`	Previous: `90fed62`	Ratio
`ML-KEM-512 keypair`	`36214` cycles	`36418` cycles	`0.99`
`ML-KEM-512 encaps`	`42638` cycles	`42824` cycles	`1.00`
`ML-KEM-512 decaps`	`55417` cycles	`55736` cycles	`0.99`
`ML-KEM-768 keypair`	`59411` cycles	`59610` cycles	`1.00`
`ML-KEM-768 encaps`	`67646` cycles	`67703` cycles	`1.00`
`ML-KEM-768 decaps`	`84800` cycles	`84883` cycles	`1.00`
`ML-KEM-1024 keypair`	`88072` cycles	`87511` cycles	`1.01`
`ML-KEM-1024 encaps`	`98221` cycles	`98447` cycles	`1.00`
`ML-KEM-1024 decaps`	`120114` cycles	`120095` 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: `478f245`	Previous: `90fed62`	Ratio
`ML-KEM-512 keypair`	`39857` cycles	`38475` cycles	`1.04`
`ML-KEM-512 encaps`	`48111` cycles	`47545` cycles	`1.01`
`ML-KEM-512 decaps`	`62502` cycles	`60958` cycles	`1.03`
`ML-KEM-768 keypair`	`65134` cycles	`63930` cycles	`1.02`
`ML-KEM-768 encaps`	`75372` cycles	`74866` cycles	`1.01`
`ML-KEM-768 decaps`	`93932` cycles	`92866` cycles	`1.01`
`ML-KEM-1024 keypair`	`95141` cycles	`94448` cycles	`1.01`
`ML-KEM-1024 encaps`	`109209` cycles	`108832` cycles	`1.00`
`ML-KEM-1024 decaps`	`132320` cycles	`131550` 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 3rd gen (c6a) (no-opt)'.
Benchmark result of this commit is worse than the previous benchmark result exceeding threshold 1.03.

Benchmark suite	Current: `478f245`	Previous: `90fed62`	Ratio
`ML-KEM-512 keypair`	`39857` cycles	`38475` cycles	`1.04`

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

oqs-bot

Intel Xeon 3rd gen (c6i)

Benchmark suite	Current: `478f245`	Previous: `90fed62`	Ratio
`ML-KEM-512 keypair`	`16343` cycles	`16272` cycles	`1.00`
`ML-KEM-512 encaps`	`18549` cycles	`18582` cycles	`1.00`
`ML-KEM-512 decaps`	`25130` cycles	`25048` cycles	`1.00`
`ML-KEM-768 keypair`	`27542` cycles	`29620` cycles	`0.93`
`ML-KEM-768 encaps`	`29598` cycles	`29856` cycles	`0.99`
`ML-KEM-768 decaps`	`41443` cycles	`39363` cycles	`1.05`
`ML-KEM-1024 keypair`	`37564` cycles	`37801` cycles	`0.99`
`ML-KEM-1024 encaps`	`40338` cycles	`40405` cycles	`1.00`
`ML-KEM-1024 decaps`	`54071` cycles	`54083` 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 'Intel Xeon 3rd gen (c6i)'.
Benchmark result of this commit is worse than the previous benchmark result exceeding threshold 1.03.

Benchmark suite	Current: `478f245`	Previous: `90fed62`	Ratio
`ML-KEM-768 decaps`	`41443` cycles	`39363` cycles	`1.05`

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

oqs-bot

Graviton4 (no-opt)

Benchmark suite	Current: `478f245`	Previous: `90fed62`	Ratio
`ML-KEM-512 keypair`	`35444` cycles	`35391` cycles	`1.00`
`ML-KEM-512 encaps`	`40022` cycles	`40758` cycles	`0.98`
`ML-KEM-512 decaps`	`51165` cycles	`51511` cycles	`0.99`
`ML-KEM-768 keypair`	`58420` cycles	`58800` cycles	`0.99`
`ML-KEM-768 encaps`	`65442` cycles	`66075` cycles	`0.99`
`ML-KEM-768 decaps`	`79702` cycles	`80060` cycles	`1.00`
`ML-KEM-1024 keypair`	`87218` cycles	`87780` cycles	`0.99`
`ML-KEM-1024 encaps`	`97289` cycles	`97071` cycles	`1.00`
`ML-KEM-1024 decaps`	`115786` cycles	`116309` cycles	`1.00`

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

oqs-bot

Graviton3

Benchmark suite	Current: `478f245`	Previous: `90fed62`	Ratio
`ML-KEM-512 keypair`	`18684` cycles	`18685` cycles	`1.00`
`ML-KEM-512 encaps`	`21974` cycles	`22018` cycles	`1.00`
`ML-KEM-512 decaps`	`29047` cycles	`29017` cycles	`1.00`
`ML-KEM-768 keypair`	`31943` cycles	`31932` cycles	`1.00`
`ML-KEM-768 encaps`	`35051` cycles	`34994` cycles	`1.00`
`ML-KEM-768 decaps`	`45015` cycles	`45066` cycles	`1.00`
`ML-KEM-1024 keypair`	`46287` cycles	`46318` cycles	`1.00`
`ML-KEM-1024 encaps`	`51612` cycles	`51639` cycles	`1.00`
`ML-KEM-1024 decaps`	`65225` cycles	`65206` cycles	`1.00`

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

oqs-bot

Graviton2 (no-opt)

Benchmark suite	Current: `478f245`	Previous: `90fed62`	Ratio
`ML-KEM-512 keypair`	`59323` cycles	`59278` cycles	`1.00`
`ML-KEM-512 encaps`	`68660` cycles	`68898` cycles	`1.00`
`ML-KEM-512 decaps`	`87376` cycles	`87495` cycles	`1.00`
`ML-KEM-768 keypair`	`99611` cycles	`99102` cycles	`1.01`
`ML-KEM-768 encaps`	`111130` cycles	`111265` cycles	`1.00`
`ML-KEM-768 decaps`	`135990` cycles	`136232` cycles	`1.00`
`ML-KEM-1024 keypair`	`149209` cycles	`148897` cycles	`1.00`
`ML-KEM-1024 encaps`	`165083` cycles	`164445` cycles	`1.00`
`ML-KEM-1024 decaps`	`196302` cycles	`195870` 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: `478f245`	Previous: `90fed62`	Ratio
`ML-KEM-512 keypair`	`45856` cycles	`46140` cycles	`0.99`
`ML-KEM-512 encaps`	`54825` cycles	`54792` cycles	`1.00`
`ML-KEM-512 decaps`	`70082` cycles	`69955` cycles	`1.00`
`ML-KEM-768 keypair`	`76363` cycles	`75977` cycles	`1.01`
`ML-KEM-768 encaps`	`86740` cycles	`86806` cycles	`1.00`
`ML-KEM-768 decaps`	`107333` cycles	`106572` cycles	`1.01`
`ML-KEM-1024 keypair`	`112553` cycles	`110543` cycles	`1.02`
`ML-KEM-1024 encaps`	`125545` cycles	`124839` cycles	`1.01`
`ML-KEM-1024 decaps`	`151731` cycles	`150341` cycles	`1.01`

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

oqs-bot

Graviton3 (no-opt)

Benchmark suite	Current: `478f245`	Previous: `90fed62`	Ratio
`ML-KEM-512 keypair`	`38862` cycles	`38795` cycles	`1.00`
`ML-KEM-512 encaps`	`44525` cycles	`44883` cycles	`0.99`
`ML-KEM-512 decaps`	`56649` cycles	`56662` cycles	`1.00`
`ML-KEM-768 keypair`	`64122` cycles	`64171` cycles	`1.00`
`ML-KEM-768 encaps`	`71985` cycles	`72703` cycles	`0.99`
`ML-KEM-768 decaps`	`87772` cycles	`87936` cycles	`1.00`
`ML-KEM-1024 keypair`	`95755` cycles	`95674` cycles	`1.00`
`ML-KEM-1024 encaps`	`106434` cycles	`106231` cycles	`1.00`
`ML-KEM-1024 decaps`	`126707` cycles	`126780` cycles	`1.00`

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

oqs-bot

Arm Cortex-A55 (Snapdragon 888) benchmarks

Benchmark suite	Current: `478f245`	Previous: `90fed62`	Ratio
`ML-KEM-512 keypair`	`59718` cycles	`59677` cycles	`1.00`
`ML-KEM-512 encaps`	`67098` cycles	`67051` cycles	`1.00`
`ML-KEM-512 decaps`	`85851` cycles	`85797` cycles	`1.00`
`ML-KEM-768 keypair`	`101885` cycles	`101908` cycles	`1.00`
`ML-KEM-768 encaps`	`113104` cycles	`113148` cycles	`1.00`
`ML-KEM-768 decaps`	`140131` cycles	`139847` cycles	`1.00`
`ML-KEM-1024 keypair`	`155144` cycles	`155074` cycles	`1.00`
`ML-KEM-1024 encaps`	`172555` cycles	`172207` cycles	`1.00`
`ML-KEM-1024 decaps`	`208114` cycles	`208317` 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: `478f245`	Previous: `90fed62`	Ratio
`ML-KEM-512 keypair`	`28346` cycles	`28331` cycles	`1.00`
`ML-KEM-512 encaps`	`34143` cycles	`34042` cycles	`1.00`
`ML-KEM-512 decaps`	`44427` cycles	`44301` cycles	`1.00`
`ML-KEM-768 keypair`	`48273` cycles	`48258` cycles	`1.00`
`ML-KEM-768 encaps`	`54147` cycles	`54204` cycles	`1.00`
`ML-KEM-768 decaps`	`68625` cycles	`68683` cycles	`1.00`
`ML-KEM-1024 keypair`	`70524` cycles	`70523` cycles	`1.00`
`ML-KEM-1024 encaps`	`78835` cycles	`78791` cycles	`1.00`
`ML-KEM-1024 decaps`	`98569` cycles	`98341` 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: `478f245`	Previous: `90fed62`	Ratio
`ML-KEM-512 keypair`	`155327` cycles	`155256` cycles	`1.00`
`ML-KEM-512 encaps`	`163181` cycles	`163119` cycles	`1.00`
`ML-KEM-512 decaps`	`206422` cycles	`206392` cycles	`1.00`
`ML-KEM-768 keypair`	`261310` cycles	`260945` cycles	`1.00`
`ML-KEM-768 encaps`	`276085` cycles	`275525` cycles	`1.00`
`ML-KEM-768 decaps`	`338416` cycles	`337755` cycles	`1.00`
`ML-KEM-1024 keypair`	`395622` cycles	`395102` cycles	`1.00`
`ML-KEM-1024 encaps`	`422736` cycles	`422177` cycles	`1.00`
`ML-KEM-1024 decaps`	`506687` cycles	`505892` cycles	`1.00`

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

- Change mlk_polyvec back to struct `{ mlk_poly vec[MLKEM_K]; }` - Change mlk_polymat to struct `{ mlk_polyvec vec[MLKEM_K]; }` - Update all function signatures to use pointer style - Fix all implementations to use struct member access - Update tests, benchmarks, and CBMC harnesses - Add consistent const annotations Somewhat surprisingly and dissatisfyingly, I could not salvage the CBMC proof for the 'monolithic' polymat_permute_bitrev_to_custom_native but had to break it in two functions. It would be good to resolve this as the split causes a lot of code-overhead for an entirely trivial function. Signed-off-by: Hanno Becker <beckphan@amazon.co.uk>

hanno-becker force-pushed the structured branch 3 times, most recently from f300f02 to f18ce9f Compare November 2, 2025 05:36

hanno-becker changed the title ~~[WIP] Reintroduce struct definitions for mlk_poly{mat,vec}~~ Reintroduce struct definitions for mlk_poly{mat,vec} Nov 2, 2025

hanno-becker marked this pull request as ready for review November 2, 2025 05:36

hanno-becker requested a review from a team as a code owner November 2, 2025 05:36

hanno-becker force-pushed the structured branch 5 times, most recently from 32c1493 to 3dc4b2c Compare November 5, 2025 19:53

hanno-becker mentioned this pull request Nov 6, 2025

CBMC: Improve proof stability pq-code-package/mldsa-native#611

Closed

hanno-becker force-pushed the structured branch from 3dc4b2c to 332a785 Compare November 6, 2025 09:43

hanno-becker added the needs-work label Nov 6, 2025

hanno-becker force-pushed the structured branch 2 times, most recently from e9256dd to 478f245 Compare November 7, 2025 12:12

hanno-becker added benchmark this PR should be benchmarked in CI and removed needs-work labels Nov 7, 2025

oqs-bot reviewed Nov 7, 2025

View reviewed changes

hanno-becker added enhancement New feature or request CBMC labels Nov 19, 2025

hanno-becker force-pushed the structured branch from 478f245 to 1b406c3 Compare November 21, 2025 04:58

This was referenced Nov 25, 2025

Reduce RAM usage by streaming matrix pq-code-package/mldsa-native#736

Open

Wrap matrix in struct wrapper pq-code-package/mldsa-native#737

Open

Reintroduce struct definitions for mlk_poly{mat,vec} #1263

Are you sure you want to change the base?

Reintroduce struct definitions for mlk_poly{mat,vec} #1263

Uh oh!

Conversation

hanno-becker commented Oct 31, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

hanno-becker commented Nov 6, 2025

Uh oh!

oqs-bot left a comment

Choose a reason for hiding this comment

Mac Mini (M1, 2020) benchmarks

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!

oqs-bot left a comment

Choose a reason for hiding this comment

⚠️ Performance Alert ⚠️

Uh oh!

oqs-bot left a comment

Choose a reason for hiding this comment

Arm Cortex-A72 (Raspberry Pi 4) benchmarks

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

AMD EPYC 3rd gen (c6a)

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

Uh oh!

oqs-bot left a comment

Choose a reason for hiding this comment

AMD EPYC 4th gen (c7a) (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

⚠️ Performance Alert ⚠️

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

⚠️ Performance Alert ⚠️

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

Graviton3

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

hanno-becker commented Oct 31, 2025 •

edited

Loading