





















Abstract:JPEG decode is routine ML infrastructure, but Python decoder choices are often justified by single-process, single-thread microbenchmarks. We audit this evaluation assumption with thirteen Python-accessible JPEG decode paths on five matched 16 vCPU Google Cloud CPUs: Intel Emerald Rapids, AMD Zen 4, AMD Zen 5, ARM Neoverse V2, and ARM Neoverse N1. ImageNet validation is the workload, not a new dataset contribution: each run decodes the full 50,000-image split from memory and reports single-thread throughput for all decoders, PyTorch \texttt{DataLoader} throughput for eligible decoders at worker counts $\{0,2,4,8\}$, and decoder skip behavior. The evaluation protocol changes the supported conclusion. On Neoverse V2, \texttt{imageio} is ninth in single-thread throughput yet lands in the top DataLoader tier with \texttt{torchvision}; on Zen 4, \texttt{torchvision} rises from seventh single-thread to the top measured DataLoader tier; on Neoverse N1, \texttt{imagecodecs} is the single-thread leader but fifth at peak DataLoader throughput. We also find that worker-count conclusions differ between Zen 4 and Zen 5, TensorFlow has a large single-thread ARM penalty, and strict native JPEG decoders/wrappers reject the same rare ImageNet JPEG. For PyTorch DataLoader workloads, \texttt{torchvision} and \texttt{simplejpeg} form the strongest measured zero-skip tier: \texttt{torchvision} has the highest mean normalized throughput, while \texttt{simplejpeg} has the highest minimum. OpenCV remains a robust general-purpose fallback above 90\% of the platform-local winner on every tested CPU. We release raw JSON, generated tables/figures, and an executable local/cloud benchmark framework.
| Comments: | 10 pages, 4 figures. Code and data: this https URL |
| Subjects: | Performance (cs.PF); Machine Learning (cs.LG) |
| Cite as: | arXiv:2605.08731 [cs.PF] |
| (or arXiv:2605.08731v2 [cs.PF] for this version) | |
| https://doi.org/10.48550/arXiv.2605.08731 arXiv-issued DOI via DataCite |
From: Vladimir Iglovikov [view email]
[v1]
Sat, 9 May 2026 06:34:17 UTC (165 KB)
[v2]
Wed, 20 May 2026 11:28:10 UTC (166 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理,仅供阅读参考。 原文来自 — 版权归原作者所有。