Skip to content

Accelerate exact P104 transpose checkpoint by 2.98x (no new κ) #6021

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
Mister-Meeseeks merged 1 commit into from
Oct 28, 2026
+1,315 −0
Merged

Accelerate exact P104 transpose checkpoint by 2.98x (no new κ) #6021

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
356 changes: 356 additions & 0 deletions research/packed-dyadic-transpose/BENCHMARK.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,356 @@
{
"code_sha256": {
"PROOF.md": "6542e8f305ab7f65b429a6de819df3ccf822a393d94314986f53b4aac48ef0ff",
"benchmark.py": "6590c8c851cbd9f1bb2b5f04aff81a46ae1cbbe80d106bc13238a523dc541dec",
"packed.py": "d725ca8b349959d6961911b85dd5e35e6cb9823d94c97c49ec5c391449a75cf5",
"verify.py": "669802f0521c7ed8d1781c6302502e576ebbb6c0cbdc99b6240e12b7c3618c20"
},
"cpu_count": 18,
"errors": 0,
"inputs": {
"research/p104-helper-subspace-splits/WORD.json.gz": "bbb072bced5824a8d9094c49be2fc51fbfdd05fb2b7dab8106e1275053075099",
"research/p104-helper-subspace-splits/local.py": "ef430511ce36fc658ab711bd84cd2d7b484b8af173238ff89cbfec6139fefbad"
},
"load_after": [
5.84326171875,
4.2919921875,
3.3154296875
],
"load_before": [
5.56884765625,
4.212890625,
3.2822265625
],
"order": "dense,packed repeated five times",
"pairs": 5,
"platform": "macOS-27.0.1-arm64-arm-64bit",
"profile": {
"dense": {
"result": {
"arithmetic": "Dense integer rows with binary denominators; reverse chronology",
"coefficients": 571536,
"columns": 756
},
"top": [
{
"calls": 1,
"function": "reverse_columns",
"inclusive_seconds": 0.84525275,
"self_seconds": 0.42496577700000004
},
{
"calls": 20650,
"function": "<built-in method builtins.any>",
"inclusive_seconds": 0.344353854,
"self_seconds": 0.18178822900000002
},
{
"calls": 5492230,
"function": "<genexpr>",
"inclusive_seconds": 0.16418927400000002,
"self_seconds": 0.16418927400000002
},
{
"calls": 22012,
"function": "__new__",
"inclusive_seconds": 0.055230937,
"self_seconds": 0.027610093000000002
},
{
"calls": 593547,
"function": "numerator",
"inclusive_seconds": 0.014518976000000001,
"self_seconds": 0.014518976000000001
},
{
"calls": 86084,
"function": "<method 'group' of 're.Match' objects>",
"inclusive_seconds": 0.007125123000000001,
"self_seconds": 0.007125123000000001
},
{
"calls": 22012,
"function": "<method 'match' of 're.Pattern' objects>",
"inclusive_seconds": 0.006653436,
"self_seconds": 0.006653436
},
{
"calls": 66036,
"function": "<built-in method builtins.isinstance>",
"inclusive_seconds": 0.010518061,
"self_seconds": 0.006153055
}
]
},
"packed": {
"result": {
"arithmetic": "Dense integer rows with binary denominators; reverse chronology",
"coefficients": 571536,
"columns": 756
},
"top": [
{
"calls": 44056,
"function": "step",
"inclusive_seconds": 0.11199083400000001,
"self_seconds": 0.106570706
},
{
"calls": 1,
"function": "source_events",
"inclusive_seconds": 0.105190875,
"self_seconds": 0.038724854
},
{
"calls": 24568,
"function": "__new__",
"inclusive_seconds": 0.051632917,
"self_seconds": 0.025851281
},
{
"calls": 1,
"function": "validate",
"inclusive_seconds": 0.021268917000000002,
"self_seconds": 0.016149868
},
{
"calls": 342148,
"function": "require",
"inclusive_seconds": 0.009716851,
"self_seconds": 0.009716851
},
{
"calls": 1,
"function": "plan",
"inclusive_seconds": 0.045311500000000005,
"self_seconds": 0.0071546100000000005
},
{
"calls": 86084,
"function": "<method 'group' of 're.Match' objects>",
"inclusive_seconds": 0.006753558000000001,
"self_seconds": 0.006753558000000001
},
{
"calls": 92270,
"function": "<built-in method builtins.isinstance>",
"inclusive_seconds": 0.010953938,
"self_seconds": 0.006717996
}
]
}
},
"python": "3.12.15 (main, Oct 14 2026, 00:55:37) [Clang 23.1.3 ]",
"samples": [
{
"checkpoint_seconds": 0.4840470829512924,
"errors": 0,
"events": 25475,
"inputs": {
"research/p104-helper-subspace-splits/WORD.json.gz": "bbb072bced5824a8d9094c49be2fc51fbfdd05fb2b7dab8106e1275053075099",
"research/p104-helper-subspace-splits/local.py": "ef430511ce36fc658ab711bd84cd2d7b484b8af173238ff89cbfec6139fefbad"
},
"peak_rss_bytes": 41369600,
"process_wall_seconds": 0.5316805420443416,
"result": {
"arithmetic": "Dense integer rows with binary denominators; reverse chronology",
"coefficients": 571536,
"columns": 756
},
"side": "dense"
},
{
"checkpoint_seconds": 0.13006100000347942,
"errors": 0,
"events": 25475,
"inputs": {
"research/p104-helper-subspace-splits/WORD.json.gz": "bbb072bced5824a8d9094c49be2fc51fbfdd05fb2b7dab8106e1275053075099",
"research/p104-helper-subspace-splits/local.py": "ef430511ce36fc658ab711bd84cd2d7b484b8af173238ff89cbfec6139fefbad"
},
"peak_rss_bytes": 46350336,
"process_wall_seconds": 0.17765537498053163,
"result": {
"arithmetic": "Dense integer rows with binary denominators; reverse chronology",
"coefficients": 571536,
"columns": 756
},
"side": "packed"
},
{
"checkpoint_seconds": 0.4846877920208499,
"errors": 0,
"events": 25475,
"inputs": {
"research/p104-helper-subspace-splits/WORD.json.gz": "bbb072bced5824a8d9094c49be2fc51fbfdd05fb2b7dab8106e1275053075099",
"research/p104-helper-subspace-splits/local.py": "ef430511ce36fc658ab711bd84cd2d7b484b8af173238ff89cbfec6139fefbad"
},
"peak_rss_bytes": 41009152,
"process_wall_seconds": 0.5281897919485345,
"result": {
"arithmetic": "Dense integer rows with binary denominators; reverse chronology",
"coefficients": 571536,
"columns": 756
},
"side": "dense"
},
{
"checkpoint_seconds": 0.12933166697621346,
"errors": 0,
"events": 25475,
"inputs": {
"research/p104-helper-subspace-splits/WORD.json.gz": "bbb072bced5824a8d9094c49be2fc51fbfdd05fb2b7dab8106e1275053075099",
"research/p104-helper-subspace-splits/local.py": "ef430511ce36fc658ab711bd84cd2d7b484b8af173238ff89cbfec6139fefbad"
},
"peak_rss_bytes": 46563328,
"process_wall_seconds": 0.1717405419331044,
"result": {
"arithmetic": "Dense integer rows with binary denominators; reverse chronology",
"coefficients": 571536,
"columns": 756
},
"side": "packed"
},
{
"checkpoint_seconds": 0.48029700003098696,
"errors": 0,
"events": 25475,
"inputs": {
"research/p104-helper-subspace-splits/WORD.json.gz": "bbb072bced5824a8d9094c49be2fc51fbfdd05fb2b7dab8106e1275053075099",
"research/p104-helper-subspace-splits/local.py": "ef430511ce36fc658ab711bd84cd2d7b484b8af173238ff89cbfec6139fefbad"
},
"peak_rss_bytes": 41402368,
"process_wall_seconds": 0.52419662498869,
"result": {
"arithmetic": "Dense integer rows with binary denominators; reverse chronology",
"coefficients": 571536,
"columns": 756
},
"side": "dense"
},
{
"checkpoint_seconds": 0.13182870810851455,
"errors": 0,
"events": 25475,
"inputs": {
"research/p104-helper-subspace-splits/WORD.json.gz": "bbb072bced5824a8d9094c49be2fc51fbfdd05fb2b7dab8106e1275053075099",
"research/p104-helper-subspace-splits/local.py": "ef430511ce36fc658ab711bd84cd2d7b484b8af173238ff89cbfec6139fefbad"
},
"peak_rss_bytes": 46448640,
"process_wall_seconds": 0.17697791696991771,
"result": {
"arithmetic": "Dense integer rows with binary denominators; reverse chronology",
"coefficients": 571536,
"columns": 756
},
"side": "packed"
},
{
"checkpoint_seconds": 0.48608795809559524,
"errors": 0,
"events": 25475,
"inputs": {
"research/p104-helper-subspace-splits/WORD.json.gz": "bbb072bced5824a8d9094c49be2fc51fbfdd05fb2b7dab8106e1275053075099",
"research/p104-helper-subspace-splits/local.py": "ef430511ce36fc658ab711bd84cd2d7b484b8af173238ff89cbfec6139fefbad"
},
"peak_rss_bytes": 41222144,
"process_wall_seconds": 0.5310359169961885,
"result": {
"arithmetic": "Dense integer rows with binary denominators; reverse chronology",
"coefficients": 571536,
"columns": 756
},
"side": "dense"
},
{
"checkpoint_seconds": 0.13196008396334946,
"errors": 0,
"events": 25475,
"inputs": {
"research/p104-helper-subspace-splits/WORD.json.gz": "bbb072bced5824a8d9094c49be2fc51fbfdd05fb2b7dab8106e1275053075099",
"research/p104-helper-subspace-splits/local.py": "ef430511ce36fc658ab711bd84cd2d7b484b8af173238ff89cbfec6139fefbad"
},
"peak_rss_bytes": 46465024,
"process_wall_seconds": 0.17785158299375325,
"result": {
"arithmetic": "Dense integer rows with binary denominators; reverse chronology",
"coefficients": 571536,
"columns": 756
},
"side": "packed"
},
{
"checkpoint_seconds": 0.4790517500368878,
"errors": 0,
"events": 25475,
"inputs": {
"research/p104-helper-subspace-splits/WORD.json.gz": "bbb072bced5824a8d9094c49be2fc51fbfdd05fb2b7dab8106e1275053075099",
"research/p104-helper-subspace-splits/local.py": "ef430511ce36fc658ab711bd84cd2d7b484b8af173238ff89cbfec6139fefbad"
},
"peak_rss_bytes": 41025536,
"process_wall_seconds": 0.5266580830793828,
"result": {
"arithmetic": "Dense integer rows with binary denominators; reverse chronology",
"coefficients": 571536,
"columns": 756
},
"side": "dense"
},
{
"checkpoint_seconds": 0.12288341706153005,
"errors": 0,
"events": 25475,
"inputs": {
"research/p104-helper-subspace-splits/WORD.json.gz": "bbb072bced5824a8d9094c49be2fc51fbfdd05fb2b7dab8106e1275053075099",
"research/p104-helper-subspace-splits/local.py": "ef430511ce36fc658ab711bd84cd2d7b484b8af173238ff89cbfec6139fefbad"
},
"peak_rss_bytes": 46579712,
"process_wall_seconds": 0.1656619580462575,
"result": {
"arithmetic": "Dense integer rows with binary denominators; reverse chronology",
"coefficients": 571536,
"columns": 756
},
"side": "packed"
}
],
"scope": "complete transpose checkpoint, not the complete supplier replay",
"status": "PASS_PACKED_TRANSPOSE_BENCHMARK",
"summary": {
"checkpoint_seconds_speedup": 3.721692766765926,
"dense": {
"checkpoint_seconds": {
"max": 0.48608795809559524,
"median": 0.4840470829512924,
"min": 0.4790517500368878
},
"peak_rss_bytes": {
"max": 41402368,
"median": 41222144,
"min": 41009152
},
"process_wall_seconds": {
"max": 0.5316805420443416,
"median": 0.5281897919485345,
"min": 0.52419662498869
}
},
"packed": {
"checkpoint_seconds": {
"max": 0.13196008396334946,
"median": 0.13006100000347942,
"min": 0.12288341706153005
},
"peak_rss_bytes": {
"max": 46579712,
"median": 46465024,
"min": 46350336
},
"process_wall_seconds": {
"max": 0.17785158299375325,
"median": 0.17697791696991771,
"min": 0.1656619580462575
}
},
"process_wall_seconds_speedup": 2.9844954726092463
}
}
Loading