2 papers
cs.LG2026
Detecting Hidden ML Training With Zero-Overhead Telemetry
Robi Rahman, Sabiha Tajdari
Hardware-enabled monitoring of GPU workloads underpins many proposals for AI compute governance, but if developers can defeat monitoring mechanisms, such schemes are unworkable. We…
cs.AR2025
JSPIM: A Skew-Aware PIM Accelerator for High-Performance Databases Join and Select Operations
Sabiha Tajdari, Anastasia Ailamaki, Sandhya Dwarkadas
Database applications are increasingly bottlenecked by memory bandwidth and latency due to the memory wall and the limited scalability of DRAM. Join queries, central to analytical…