[TEST] Investigate impact of clang's version on size of improvement #539

jammychiou1 · 2025-10-13T09:25:09Z

No description provided.

Signed-off-by: Jake Massimo <[email protected]>

Run the updated autogen and format scripts again. Signed-off-by: jammychiou1 <[email protected]>

Signed-off-by: jammychiou1 <[email protected]>

This commit adds a native implementation of poly_pointwise_montgomery written from scratch. Co-authored-by: Matthias J. Kannwischer <[email protected]> Signed-off-by: jammychiou1 <[email protected]>

This commit adds native implementations of polyvecl_pointwise_acc_montgomery written from scratch. Co-authored-by: Matthias J. Kannwischer <[email protected]> Signed-off-by: jammychiou1 <[email protected]>

Signed-off-by: jammychiou1 <[email protected]>

github-actions

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

Benchmark suite	Current: `57c9909`	Previous: `abf8281`	Ratio
`ML-DSA-44 keypair`	`115333` cycles	`115355` cycles	`1.00`
`ML-DSA-44 sign`	`379122` cycles	`380513` cycles	`1.00`
`ML-DSA-44 verify`	`120819` cycles	`120663` cycles	`1.00`
`ML-DSA-65 keypair`	`199794` cycles	`199958` cycles	`1.00`
`ML-DSA-65 sign`	`627821` cycles	`630974` cycles	`1.00`
`ML-DSA-65 verify`	`199072` cycles	`199181` cycles	`1.00`
`ML-DSA-87 keypair`	`327407` cycles	`327118` cycles	`1.00`
`ML-DSA-87 sign`	`796723` cycles	`797677` cycles	`1.00`
`ML-DSA-87 verify`	`326514` cycles	`326175` cycles	`1.00`

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

oqs-bot

Intel Xeon 4th gen (c7i)

Benchmark suite	Current: `57c9909`	Previous: `abf8281`	Ratio
`ML-DSA-44 keypair`	`34838` cycles	`35216` cycles	`0.99`
`ML-DSA-44 sign`	`121184` cycles	`125138` cycles	`0.97`
`ML-DSA-44 verify`	`38357` cycles	`39121` cycles	`0.98`
`ML-DSA-65 keypair`	`62830` cycles	`63454` cycles	`0.99`
`ML-DSA-65 sign`	`201858` cycles	`208653` cycles	`0.97`
`ML-DSA-65 verify`	`62636` cycles	`64036` cycles	`0.98`
`ML-DSA-87 keypair`	`93790` cycles	`96943` cycles	`0.97`
`ML-DSA-87 sign`	`230473` cycles	`251543` cycles	`0.92`
`ML-DSA-87 verify`	`93310` cycles	`96969` cycles	`0.96`

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

oqs-bot

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

Benchmark suite	Current: `57c9909`	Previous: `abf8281`	Ratio
`ML-DSA-44 keypair`	`95909` cycles	`95709` cycles	`1.00`
`ML-DSA-44 sign`	`345744` cycles	`345734` cycles	`1.00`
`ML-DSA-44 verify`	`101489` cycles	`101338` cycles	`1.00`
`ML-DSA-65 keypair`	`164662` cycles	`164680` cycles	`1.00`
`ML-DSA-65 sign`	`568162` cycles	`568266` cycles	`1.00`
`ML-DSA-65 verify`	`165583` cycles	`165518` cycles	`1.00`
`ML-DSA-87 keypair`	`270497` cycles	`270264` cycles	`1.00`
`ML-DSA-87 sign`	`724427` cycles	`725295` cycles	`1.00`
`ML-DSA-87 verify`	`273052` cycles	`273484` cycles	`1.00`

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

oqs-bot

AMD EPYC 3rd gen (c6a)

Benchmark suite	Current: `57c9909`	Previous: `abf8281`	Ratio
`ML-DSA-44 keypair`	`69381` cycles	`72965` cycles	`0.95`
`ML-DSA-44 sign`	`186485` cycles	`209026` cycles	`0.89`
`ML-DSA-44 verify`	`69410` cycles	`74357` cycles	`0.93`
`ML-DSA-65 keypair`	`119675` cycles	`122701` cycles	`0.98`
`ML-DSA-65 sign`	`296336` cycles	`330324` cycles	`0.90`
`ML-DSA-65 verify`	`115462` cycles	`121320` cycles	`0.95`
`ML-DSA-87 keypair`	`201393` cycles	`208588` cycles	`0.97`
`ML-DSA-87 sign`	`385909` cycles	`432454` cycles	`0.89`
`ML-DSA-87 verify`	`193704` cycles	`203545` cycles	`0.95`

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

oqs-bot

Intel Xeon 3rd gen (c6i)

Benchmark suite	Current: `57c9909`	Previous: `abf8281`	Ratio
`ML-DSA-44 keypair`	`57353` cycles	`57825` cycles	`0.99`
`ML-DSA-44 sign`	`181032` cycles	`190230` cycles	`0.95`
`ML-DSA-44 verify`	`61488` cycles	`63174` cycles	`0.97`
`ML-DSA-65 keypair`	`100094` cycles	`102038` cycles	`0.98`
`ML-DSA-65 sign`	`296995` cycles	`317731` cycles	`0.93`
`ML-DSA-65 verify`	`100778` cycles	`104176` cycles	`0.97`
`ML-DSA-87 keypair`	`154228` cycles	`157788` cycles	`0.98`
`ML-DSA-87 sign`	`354894` cycles	`378266` cycles	`0.94`
`ML-DSA-87 verify`	`153750` cycles	`158668` cycles	`0.97`

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

oqs-bot

Graviton4

Benchmark suite	Current: `57c9909`	Previous: `abf8281`	Ratio
`ML-DSA-44 keypair`	`69475` cycles	`69452` cycles	`1.00`
`ML-DSA-44 sign`	`214191` cycles	`214770` cycles	`1.00`
`ML-DSA-44 verify`	`72626` cycles	`72508` cycles	`1.00`
`ML-DSA-65 keypair`	`122983` cycles	`122780` cycles	`1.00`
`ML-DSA-65 sign`	`352171` cycles	`353195` cycles	`1.00`
`ML-DSA-65 verify`	`120338` cycles	`120430` cycles	`1.00`
`ML-DSA-87 keypair`	`201608` cycles	`200488` cycles	`1.01`
`ML-DSA-87 sign`	`451717` cycles	`451124` cycles	`1.00`
`ML-DSA-87 verify`	`198451` cycles	`198358` cycles	`1.00`

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

oqs-bot

AMD EPYC 4th gen (c7a)

Benchmark suite	Current: `57c9909`	Previous: `abf8281`	Ratio
`ML-DSA-44 keypair`	`43279` cycles	`42495` cycles	`1.02`
`ML-DSA-44 sign`	`130816` cycles	`136953` cycles	`0.96`
`ML-DSA-44 verify`	`44647` cycles	`45651` cycles	`0.98`
`ML-DSA-65 keypair`	`73246` cycles	`73514` cycles	`1.00`
`ML-DSA-65 sign`	`212540` cycles	`222961` cycles	`0.95`
`ML-DSA-65 verify`	`73097` cycles	`75361` cycles	`0.97`
`ML-DSA-87 keypair`	`110008` cycles	`111831` cycles	`0.98`
`ML-DSA-87 sign`	`247964` cycles	`264029` cycles	`0.94`
`ML-DSA-87 verify`	`109522` cycles	`113897` cycles	`0.96`

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

oqs-bot

Graviton2

Benchmark suite	Current: `57c9909`	Previous: `abf8281`	Ratio
`ML-DSA-44 keypair`	`115430` cycles	`116321` cycles	`0.99`
`ML-DSA-44 sign`	`379337` cycles	`382918` cycles	`0.99`
`ML-DSA-44 verify`	`120855` cycles	`121647` cycles	`0.99`
`ML-DSA-65 keypair`	`199807` cycles	`200280` cycles	`1.00`
`ML-DSA-65 sign`	`628243` cycles	`631576` cycles	`0.99`
`ML-DSA-65 verify`	`199027` cycles	`199420` cycles	`1.00`
`ML-DSA-87 keypair`	`327894` cycles	`327953` cycles	`1.00`
`ML-DSA-87 sign`	`798204` cycles	`799114` cycles	`1.00`
`ML-DSA-87 verify`	`326568` cycles	`326610` 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: `57c9909`	Previous: `abf8281`	Ratio
`ML-DSA-44 keypair`	`135996` cycles	`135835` cycles	`1.00`
`ML-DSA-44 sign`	`542460` cycles	`543662` cycles	`1.00`
`ML-DSA-44 verify`	`148820` cycles	`148551` cycles	`1.00`
`ML-DSA-65 keypair`	`227011` cycles	`227293` cycles	`1.00`
`ML-DSA-65 sign`	`880341` cycles	`880495` cycles	`1.00`
`ML-DSA-65 verify`	`235774` cycles	`235973` cycles	`1.00`
`ML-DSA-87 keypair`	`374424` cycles	`376279` cycles	`1.00`
`ML-DSA-87 sign`	`1099853` cycles	`1099997` cycles	`1.00`
`ML-DSA-87 verify`	`387007` cycles	`388895` 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: `57c9909`	Previous: `abf8281`	Ratio
`ML-DSA-44 keypair`	`157942` cycles	`157874` cycles	`1.00`
`ML-DSA-44 sign`	`563118` cycles	`563418` cycles	`1.00`
`ML-DSA-44 verify`	`169551` cycles	`169267` cycles	`1.00`
`ML-DSA-65 keypair`	`269947` cycles	`269343` cycles	`1.00`
`ML-DSA-65 sign`	`926951` cycles	`928710` cycles	`1.00`
`ML-DSA-65 verify`	`274204` cycles	`274926` cycles	`1.00`
`ML-DSA-87 keypair`	`453164` cycles	`450143` cycles	`1.01`
`ML-DSA-87 sign`	`1184436` cycles	`1177838` cycles	`1.01`
`ML-DSA-87 verify`	`461921` cycles	`458629` cycles	`1.01`

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

oqs-bot

Graviton4 (no-opt)

Benchmark suite	Current: `57c9909`	Previous: `abf8281`	Ratio
`ML-DSA-44 keypair`	`132649` cycles	`132765` cycles	`1.00`
`ML-DSA-44 sign`	`498561` cycles	`498360` cycles	`1.00`
`ML-DSA-44 verify`	`144908` cycles	`144978` cycles	`1.00`
`ML-DSA-65 keypair`	`227233` cycles	`227374` cycles	`1.00`
`ML-DSA-65 sign`	`813841` cycles	`813162` cycles	`1.00`
`ML-DSA-65 verify`	`232149` cycles	`231727` cycles	`1.00`
`ML-DSA-87 keypair`	`374349` cycles	`374649` cycles	`1.00`
`ML-DSA-87 sign`	`1021393` cycles	`1021467` cycles	`1.00`
`ML-DSA-87 verify`	`383785` cycles	`383727` 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: `57c9909`	Previous: `abf8281`	Ratio
`ML-DSA-44 keypair`	`123804` cycles	`120120` cycles	`1.03`
`ML-DSA-44 sign`	`461484` cycles	`453371` cycles	`1.02`
`ML-DSA-44 verify`	`133466` cycles	`132326` cycles	`1.01`
`ML-DSA-65 keypair`	`205872` cycles	`204716` cycles	`1.01`
`ML-DSA-65 sign`	`738671` cycles	`737570` cycles	`1.00`
`ML-DSA-65 verify`	`210051` cycles	`210009` cycles	`1.00`
`ML-DSA-87 keypair`	`338313` cycles	`338444` cycles	`1.00`
`ML-DSA-87 sign`	`939587` cycles	`941628` cycles	`1.00`
`ML-DSA-87 verify`	`349154` cycles	`349377` 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 'AMD EPYC 4th gen (c7a) (no-opt)'.
Benchmark result of this commit is worse than the previous benchmark result exceeding threshold 1.03.

Benchmark suite	Current: `57c9909`	Previous: `abf8281`	Ratio
`ML-DSA-44 keypair`	`123804` cycles	`120120` cycles	`1.03`

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

oqs-bot

Graviton3

Benchmark suite	Current: `57c9909`	Previous: `abf8281`	Ratio
`ML-DSA-44 keypair`	`73722` cycles	`73940` cycles	`1.00`
`ML-DSA-44 sign`	`226999` cycles	`228396` cycles	`0.99`
`ML-DSA-44 verify`	`77929` cycles	`78071` cycles	`1.00`
`ML-DSA-65 keypair`	`129727` cycles	`129923` cycles	`1.00`
`ML-DSA-65 sign`	`375554` cycles	`377186` cycles	`1.00`
`ML-DSA-65 verify`	`128823` cycles	`129040` cycles	`1.00`
`ML-DSA-87 keypair`	`210479` cycles	`210651` cycles	`1.00`
`ML-DSA-87 sign`	`476607` cycles	`478561` cycles	`1.00`
`ML-DSA-87 verify`	`209702` cycles	`210198` cycles	`1.00`

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

oqs-bot

Graviton2 (no-opt)

Benchmark suite	Current: `57c9909`	Previous: `abf8281`	Ratio
`ML-DSA-44 keypair`	`213642` cycles	`213647` cycles	`1.00`
`ML-DSA-44 sign`	`781292` cycles	`794200` cycles	`0.98`
`ML-DSA-44 verify`	`230217` cycles	`230157` cycles	`1.00`
`ML-DSA-65 keypair`	`381252` cycles	`381964` cycles	`1.00`
`ML-DSA-65 sign`	`1287174` cycles	`1286398` cycles	`1.00`
`ML-DSA-65 verify`	`373040` cycles	`373972` cycles	`1.00`
`ML-DSA-87 keypair`	`610155` cycles	`609842` cycles	`1.00`
`ML-DSA-87 sign`	`1644416` cycles	`1645519` cycles	`1.00`
`ML-DSA-87 verify`	`621966` cycles	`621691` cycles	`1.00`

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

oqs-bot

Graviton3 (no-opt)

Benchmark suite	Current: `57c9909`	Previous: `abf8281`	Ratio
`ML-DSA-44 keypair`	`138591` cycles	`138584` cycles	`1.00`
`ML-DSA-44 sign`	`494681` cycles	`495481` cycles	`1.00`
`ML-DSA-44 verify`	`148737` cycles	`148760` cycles	`1.00`
`ML-DSA-65 keypair`	`241540` cycles	`241312` cycles	`1.00`
`ML-DSA-65 sign`	`809880` cycles	`809760` cycles	`1.00`
`ML-DSA-65 verify`	`241006` cycles	`240909` cycles	`1.00`
`ML-DSA-87 keypair`	`396501` cycles	`396477` cycles	`1.00`
`ML-DSA-87 sign`	`1031630` cycles	`1031613` cycles	`1.00`
`ML-DSA-87 verify`	`402462` cycles	`402260` cycles	`1.00`

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

jakemas and others added 12 commits October 13, 2025 00:45

AVX2: Add pointwise native backend

5a346c8

Signed-off-by: Jake Massimo <[email protected]>

hooked up pointwise_acc_mont

76db11d

Signed-off-by: Jake Massimo <[email protected]>

linting

34645a1

Signed-off-by: Jake Massimo <[email protected]>

added pointwise to bench_components

dbcbbdf

Signed-off-by: Jake Massimo <[email protected]>

linting

1d4dd84

Signed-off-by: Jake Massimo <[email protected]>

linting

bdfa297

Run the updated autogen and format scripts again. Signed-off-by: jammychiou1 <[email protected]>

CBMC: Add bounds assertions to the native paths of pointwise{_acc}

f8d37bb

Signed-off-by: jammychiou1 <[email protected]>

AVX2: Split off pointwise_acc asm into a new file

f5ae63d

Signed-off-by: jammychiou1 <[email protected]>

Split pointwise_acc native API into 3 for l=4,5,7

230e7ee

Signed-off-by: jammychiou1 <[email protected]>

AArch64: Add native implementation of poly_pointwise_montgomery

39f12f9

This commit adds a native implementation of poly_pointwise_montgomery written from scratch. Co-authored-by: Matthias J. Kannwischer <[email protected]> Signed-off-by: jammychiou1 <[email protected]>

AArch64: Add native implementations of polyvecl_pointwise_acc_montgomery

a2e40c1

This commit adds native implementations of polyvecl_pointwise_acc_montgomery written from scratch. Co-authored-by: Matthias J. Kannwischer <[email protected]> Signed-off-by: jammychiou1 <[email protected]>

[TEST] Investigate impact of clang's version on size of improvement

57c9909

Signed-off-by: jammychiou1 <[email protected]>

jammychiou1 added the benchmark label Oct 13, 2025

github-actions bot reviewed Oct 13, 2025

View reviewed changes

oqs-bot reviewed Oct 13, 2025

View reviewed changes

[TEST] Investigate impact of clang's version on size of improvement #539

Are you sure you want to change the base?

[TEST] Investigate impact of clang's version on size of improvement #539

Conversation

jammychiou1 commented Oct 13, 2025

Uh oh!

github-actions bot left a comment

Choose a reason for hiding this comment

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

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

Intel Xeon 3rd gen (c6i)

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)

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

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

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

Graviton4 (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!

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

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

Graviton3 (no-opt)

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants