发表机构
The Institute of Energetic Paradigm（能量范式研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究通过实验证明，在联合硬件约束下，架构排名可移植性不等于可行性可移植性，跨设备评估需明确目标环境支持的工作点。
AI 中文摘要
跨设备硬件评估通常假设，如果架构排名在设备间可转移，则代理设备可以支持目标端的模型选择。我们针对两个公开架构家族，对联合延迟-能耗可行性方面的这一假设进行了压力测试。在NAS-Bench-201上，跨设备排名相关性中等，而目标可比较的可行集重叠仍不完整。一个忠实的AdaProxy诊断显著改善了延迟排名，表明观察到的边界失败并非仅仅由于适应能力弱。精确的有限样本分裂共形分析也揭示了一个证据瓶颈：有限的一侧90%阈值至少需要九个校准观测值。随后，我们在13个HW-GPT-Bench设备上的10,000个GPT架构上复制了这一现象。相对于RTX3080代理，目标延迟SRCC范围从0.951到0.996，但在匹配的联合约束下，代理重用违规风险范围从33.3%到100%。这些结果表明，排名可移植性、可行性可移植性和目标特定决策支持是不同的评估对象。因此，跨设备评估应报告哪些目标环境实际支持所声称的工作点。
英文摘要
Cross-device hardware evaluation often assumes that if architecture rankings transfer across devices, a proxy device can support target-side model selection. We stress-test this assumption for joint latency-energy feasibility across two public architecture families. On NAS-Bench-201, cross-device rank correlations are moderate, while target-comparable feasible-set overlap remains incomplete. A faithful AdaProxy diagnostic substantially improves latency ranking, showing that the observed boundary failures are not simply due to weak adaptation. Exact finite-sample split-conformal analysis also exposes an evidence bottleneck: a finite one-sided 90% threshold requires at least nine calibration observations. We then replicate the phenomenon on 10,000 GPT architectures across 13 HW-GPT-Bench devices. Relative to an RTX3080 proxy, target latency SRCC ranges from 0.951 to 0.996, yet proxy-reuse violation risk ranges from 33.3% to 100% under matched joint constraints. These results show that rank portability, feasibility portability, and target-specific decision support are distinct evaluation objects. Cross-device evaluations should therefore report which target environments actually support the operating point being claimed.
