Skip to content

fix(data): fill Xeon and Celeron thread counts from Intel spec pages - #316

Merged
Seungpyo1007 merged 2 commits into
developfrom
Seungpyo1007/grok-g3-intel-threads
Sep 28, 2026
Merged

Seungpyo1007 merged 2 commits into
developfrom
Seungpyo1007/grok-g3-intel-threads

Conversation

@Seungpyo1007

Copy link
Copy Markdown
Member

What & why

23 older Xeon and Celeron SKUs whose Wikipedia list rows give a core count and no thread count. Each threads value is the Total Threads figure on that exact SKU's Intel specification page. Thread count was not inferred from the core count or from Hyper-Threading.

Of the 83 SKUs in this batch that are still absent from the dataset, 23 were filled and 60 were skipped.

Filled (7 Celeron, 16 Xeon):

SKU Cores Threads
Celeron 787 1 1
Celeron 797 1 1
Celeron 927UE 1 1
Celeron B720 1 1
Celeron B810E 2 2
Celeron P1053 1 2
Celeron U3405 2 2
Xeon LC3518 1 1
Xeon LC3528 2 4
Xeon L5508 2 4
Xeon EC5509 4 4
Xeon L5518 4 8
Xeon EC5549 4 8
Xeon LC5518 4 8
Xeon LC5528 4 8
Xeon E6510 4 8
Xeon E7520 4 8
Xeon E6540 6 12
Xeon E5-1428L 6 12
Xeon E5-4607 6 12
Xeon E5-2448L 8 16
Xeon L7555 8 16
Xeon E7-8895 v3 18 36

Two of these are not "threads = 2 × cores": Celeron P1053 is 1 core / 2 threads (the Intel page says Hyper-Threading Yes and Total Threads 2), and Xeon EC5509 is 4 cores / 4 threads (Hyper-Threading No). Xeon LC3518 is 1 core / 1 thread.

Skipped, 60:

  • 31 have an Intel specification page that lists cores (and sometimes Hyper-Threading) but has no Total Threads field. Left out. Examples: Xeon E5220, Xeon X7542, Celeron 445, Celeron T3100.
  • 27 have no Intel product page for that exact SKU. Includes the cloud and custom parts called out before (E5-2689A v4, E5-2666 v4, E5-2699P v4, AWS-1100 v4, E5-1686 v3, E5-1691 v3, E5-2622 v3, E5-2652 v3, E5-2692 v3, E5-2698A v3, E5-2698B v3, E5-2449L, E3-1285 v2, E3-1285L v2) plus Celeron B730, T1400, T1500, T3000, Xeon E5330, E5340, E5-2618L, E5-2628L, E3-1283L v4, L3403, L5645, and the engineering sample E5-2693 v3 (ES). The combined Wikipedia cell "E5350, X5350" was not split into two records.
  • 2 (Xeon L3014, Xeon L5238) could not be confirmed because the archive lookup failed, so they were left out.

verified stays false. python -m app.validate passes. The last commit refreshes the static dump: 23 new CPU pages, CPU count 4507 → 4530. These SKUs have no benchmark scores, so the scored-CPU count does not change.

Closes #296

Source

Intel product specification pages (Wayback capture of the same page when the live URL no longer resolves), plus the Wikipedia Xeon and Celeron list page for the row. Each record's source_urls cites both.

Checklist

  • The PR targets develop (main only moves through release PRs)
  • python -m app.validate passes locally
  • Files live at the correct data/<category>/<...>/<slug>.json path
  • Slugs are kebab-case and unique within the category
  • source_urls cites at least one canonical reference

Wikipedia lists cores only for these 23 SKUs. Each thread count is the
Total Threads figure on that SKU's Intel specification page.
Adds the 23 new CPU pages. Other pages stay byte-for-byte the same;
these SKUs have no benchmark scores, so CPU percentiles do not move.
@github-actions github-actions Bot added bug Something isn't working data Dataset changes enhancement New feature or request labels Sep 28, 2026
@Seungpyo1007
Seungpyo1007 merged commit 48f5b11 into develop Sep 28, 2026
5 checks passed
@Seungpyo1007
Seungpyo1007 deleted the Seungpyo1007/grok-g3-intel-threads branch September 30, 2026 08:32
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

bug Something isn't working data Dataset changes enhancement New feature or request

Projects

Status: Done

Development

Successfully merging this pull request may close these issues.

Data accuracy: corrections, duplicates and dates (workstream)

1 participant