pith:3LCNAPOE
Single-Thread JPEG Decoder Benchmarks Mis-Evaluate ML Data Loaders
Single-thread JPEG decoder benchmarks produce different rankings than measurements inside PyTorch DataLoaders.
arxiv:2605.08731 v2 · 2026-05-09 · cs.PF · cs.LG
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{3LCNAPOENBX2YNEWXJF4KDAFAP}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
The evaluation protocol changes the supported conclusion. On Neoverse V2, imageio is ninth in single-thread throughput yet lands in the top DataLoader tier with torchvision; on Zen 4, torchvision rises from seventh single-thread to the top measured DataLoader tier.
That the observed ranking changes are driven primarily by the single-thread versus multi-worker protocol rather than by unmeasured interactions between specific decoder implementations, memory hierarchy, or the exact PyTorch DataLoader configuration used.
Single-thread JPEG decoder throughput rankings change substantially when measured inside PyTorch DataLoaders across Intel, AMD, and ARM CPUs.
Formal links
Receipt and verification
| First computed | 2026-05-21T01:05:20.666655Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
dac4d03dc4686fac3496ba4bc50c0503dc0bc093f2536a053a579773f2e910bb
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/3LCNAPOENBX2YNEWXJF4KDAFAP \
| 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: dac4d03dc4686fac3496ba4bc50c0503dc0bc093f2536a053a579773f2e910bb
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "cfcc0c5c828564c5913b69324cbb27b3a75362b5faba1f62c407c82cc0ddcb28",
"cross_cats_sorted": [
"cs.LG"
],
"license": "http://creativecommons.org/licenses/by/4.0/",
"primary_cat": "cs.PF",
"submitted_at": "2026-05-09T06:34:17Z",
"title_canon_sha256": "3964a7ee2c6aac594c3bdb69c1cba526b53084cdf6ed055a8076b4bc281afc9f"
},
"schema_version": "1.0",
"source": {
"id": "2605.08731",
"kind": "arxiv",
"version": 2
}
}