Ethan Berkley

Bio

Ethan Berkley is a full-time undergraduate research assistant at Cornell University's Computer Systems Laboratory (CSL), advised by Professor Mohammad Alian. His current work is conducting workload analysis on AI training and inference tasks to enable fine-grained NUMA-aware memory allocation for accelerators with heterogeneous, multi-tier memory layouts. Furthermore, he is exploring the effect different parallelism techniques have on both latency requirements and data/IO access patterns to motivate architectural designs for next generation accelerators.

In the past, he has investigated how dynamic compute granularity in CPU workloads can affect resource efficiency, and created techniques to identify performant granularities that minimize resource allocations under mixed-QoS requirements.

Research Interests

• Architectural simulation.
• Minimizing interference in shared resources.
• QoS-aware scheduling/allocation policies.
• Datacenter networking.