pith:SCKWSDFR
ArcLight: A Lightweight LLM Inference Architecture for Many-Core CPUs
ArcLight achieves up to 46% higher LLM inference throughput on many-core CPUs by reducing cross-NUMA memory access overhead.
arxiv:2603.07770 v2 · 2026-03-08 · cs.DC · cs.CL
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{SCKWSDFRL4P5H7GZ526FVX2FSN}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
Experimental results show that ArcLight significantly surpasses the performance ceiling of mainstream frameworks, achieving up to 46% higher inference throughput.
The assumption that cross-NUMA memory access is the dominant scalability bottleneck on many-core CPUs and that the proposed memory management and tensor parallelism will generalize without major tuning across different CPU models and workloads.
ArcLight delivers up to 46% higher LLM inference throughput on many-core CPUs by addressing cross-NUMA memory access costs through efficient memory management, thread scheduling, and tensor parallelism.
Formal links
Receipt and verification
| First computed | 2026-05-18T02:44:30.859438Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
9095690cb15f1fd3fcd9eebc5adf45935b7a196c3290054c5161cc8d9ae373b2
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/SCKWSDFRL4P5H7GZ526FVX2FSN \
| jq -c '.canonical_record' \
| python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: 9095690cb15f1fd3fcd9eebc5adf45935b7a196c3290054c5161cc8d9ae373b2
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "02a41d23caec35c01cb1b6d0217851f0a3d956ddab321608b8f99480cd219915",
"cross_cats_sorted": [
"cs.CL"
],
"license": "http://creativecommons.org/licenses/by/4.0/",
"primary_cat": "cs.DC",
"submitted_at": "2026-03-08T19:20:25Z",
"title_canon_sha256": "de3ee42c336be9f1c0388fd8927ce1400360eaf62d0d6c4152fddcb89492d115"
},
"schema_version": "1.0",
"source": {
"id": "2603.07770",
"kind": "arxiv",
"version": 2
}
}