4 papers
Uncovering the Memory Hierarchy of Modern NVIDIA GPUs for Accurate Simulation
Ziwen Wang, Jiapeng Zhou, Changxi Liu +2
Emerging artificial intelligence workloads, particularly Large Language Models (LLMs), place unprecedented demands on GPU memory systems. Consequently, architectural innovations in…
Scaling Shapley Energy Attribution to Large LLM Batches
Qi Luo, Ziwen Wang, Kunlin Li +2
LLM services have become essential infrastructure for applications such as chat assistants and coding agents. Service providers need to attribute resource consumption to individual…
Exploiting What NVIDIA Profilers Hide: Fast and Accurate Analytical GPU Performance Modeling
Ziwen Wang, Qi Luo, Kunlin Li +3
GPUs have become essential to many fields, including AI and scientific computing. As GPUs grow more complex, the design space of their hardware configurations becomes increasingly…
Request-Level Energy Attribution for Batched LLM Serving
Qi Luo, Kunlin Li, Ziwen Wang +2
Batched LLM serving improves throughput but complicates energy accounting. GPU power telemetry is aggregate, whereas sustainability reporting, chargeback, and workload analysis oft…