GPU上的定时和内存遥测用于AI治理
Timing and Memory Telemetry on GPUs for AI Governance
AI总结：
通过GPU定时和内存遥测技术，实现对大规模AI计算资源的治理，以确保资源使用符合政策和法律要求。
摘要：
随着GPU加速计算的迅速扩展，大规模人工智能（AI）取得了重大进展，但对加速器在部署后如何被观察或治理的担忧也日益增加。治理对于确保大规模计算基础设施不被悄无声息地重新用于训练模型、绕过使用政策或在法律监管之外运行至关重要。由于当前GPU暴露的可信遥测有限，且可能被对手修改或虚拟化，我们探讨计算基于的测量是否能在主机和设备不可信时提供可操作的使用信号。我们介绍了一个测量框架，利用现代GPU的架构特性生成与计算活动相关的定时和内存观测指标。我们的设计借鉴了四个互补的原始机制：（1）一种概率性、工作负载驱动的机制，受工作证明（PoW）启发，以暴露并行努力；（2）通过可验证延迟函数（VDFs）衍生出的顺序、延迟敏感的工作负载，以表征标量执行压力；（3）基于通用矩阵乘法（GEMM）的张量核心测量，反映密集线性代数吞吐量；（4）一种VRAM驻留测试，通过带宽依赖的哈希区分设备内存局部性和非芯片访问。这些原始机制提供了即使在没有可信固件、加密容器或供应商控制计数器的情况下，GPU参与的统计和行为指标。我们评估了它们对竞争、架构对齐、内存压力和功率开销的响应，显示定时偏移和驻留延迟揭示了有意义的使用模式。我们的结果说明了计算基于的遥测如何通过暴露与后期部署GPU治理相关的架构信号，来补充未来的问责机制。
英文摘要：
The rapid expansion of GPU-accelerated computing has enabled major advances in large-scale artificial intelligence (AI), while heightening concerns about how accelerators are observed or governed once deployed. Governance is essential to ensure that large-scale compute infrastructure is not silently repurposed for training models, circumventing usage policies, or operating outside legal oversight. Because current GPUs expose limited trusted telemetry and can be modified or virtualized by adversaries, we explore whether compute-based measurements can provide actionable signals of utilization when host and device are untrusted. We introduce a measurement framework that leverages architectural characteristics of modern GPUs to generate timing- and memory-based observables that correlate with compute activity. Our design draws on four complementary primitives: (1) a probabilistic, workload-driven mechanism inspired by Proof-of-Work (PoW) to expose parallel effort, (2) sequential, latency-sensitive workloads derived via Verifiable Delay Functions (VDFs) to characterize scalar execution pressure, (3) General Matrix Multiplication (GEMM)-based tensor-core measurements that reflect dense linear-algebra throughput, and (4) a VRAM-residency test that distinguishes on-device memory locality from off-chip access through bandwidth-dependent hashing. These primitives provide statistical and behavioral indicators of GPU engagement that remain observable even without trusted firmware, enclaves, or vendor-controlled counters. We evaluate their responses to contention, architectural alignment, memory pressure, and power overhead, showing that timing shifts and residency latencies reveal meaningful utilization patterns. Our results illustrate why compute-based telemetry can complement future accountability mechanisms by exposing architectural signals relevant to post-deployment GPU governance.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
