Workshop

Benchmarking Machine Learning Workloads on Emerging Hardware

Tom St John, Murali Emani

Abstract:

"With evolving system architectures, hardware and software stack, diverse machine learning workloads, and data, it is important to understand how these components interact with each other. Well-defined benchmarking procedures help evaluate and reason the performance gains with ML workload to system mapping.

Key problems that we seek to address are: (i) which representative ML benchmarks cater to workloads seen in industry, national labs, and interdisciplinary sciences; (ii) how to characterize the ML workloads based on their interaction with hardware; (iii) what novel aspects of hardware, such as heterogeneity in compute, memory, and bandwidth, will drive their adoption; (iv) performance modeling and projections to next-generation hardware.

The workshop will invite experts in these research areas to present recent work and potential directions to pursue. Accepted papers from a rigorous evaluation process will present state-of-the-art research efforts. A panel discussion will foster an interactive platform for discussion between speakers and the audience."

Chat is not available.

Timezone: »

Schedule

Fri 8:00 a.m. - 8:10 a.m.
Introduction - Tom St. John (Cruise) (Introduction)
Tom St John
Fri 8:10 a.m. - 8:50 a.m.
"System-Level Design of Machine Learning Accelerators with the Open Source ESP Platform - Luca Carloni (Columbia) (Invited Talk)
Luca Carloni
Fri 8:50 a.m. - 9:00 a.m.
Morning Break 1 (Break)
Fri 9:00 a.m. - 9:40 a.m.
"Designing and Optimizing AI Systems for Deep Learning Recommendation and Beyond" - Carole-Jean Wu (Facebook) (Invited Talk)
Carole-Jean Wu
Fri 9:40 a.m. - 10:00 a.m.
Morning Break 2 (Break)
Fri 10:00 a.m. - 10:30 a.m.
"Being-Ahead: Benchmarking and Exploring Accelerators for Hardware-Efficient AI Deployment" - Xiaofan Zhang (UIUC) (Paper)
Xiaofan Zhang
Fri 10:30 a.m. - 10:50 a.m.
"Benchmarking Machine Learning Inference in FPGA-Based Accelerated Space Applications" - Amir Raoofy (TU Munich) (Paper)
AMIR RAOOFY
Fri 10:50 a.m. - 11:30 a.m.
"Machine Learning Tools: Skyline and RL-Scope" - Gennady Pekhimenko and James Gleeson (University of Toronto) (Invited Talk)
Gennady Pekhimenko
Fri 11:30 a.m. - 1:30 p.m.
Lunch (Break)
Fri 1:30 p.m. - 2:10 p.m.
"Benchmarking Scientific ML on Disaggregated Cognitive Simulation HPC Platforms" - Brian Van Essen (LLNL) (Invited Talk)
Brian Van Essen
Fri 2:10 p.m. - 2:50 p.m.
"Challenges with Running DNN Workloads with Hardware Simulators" - David Kaeli (Northeastern University) and "GNNMark: a Benchmark for GNN Training" - Trinayan Baruah (Northeastern University) (Invited Talk)
Dave Kaeli
Fri 2:50 p.m. - 3:20 p.m.
Afternoon Break (Break)
Fri 3:20 p.m. - 4:50 p.m.
Panel Session - Lizy John (UT Austin), David Kaeli (Northeastern University), Tushar Krishna (Georgia Tech), Peter Mattson (Google), Brian Van Essen (LLNL), Venkatram Vishwanath (ANL), Carole-Jean Wu (Facebook) (Discussion Panel)
Tom St John, LIZY JOHn, Tushar Krishna, Peter Mattson, Venkatram Vishwanath, Carole-Jean Wu, Dave Kaeli, Brian Van Essen
Fri 4:50 p.m. - 5:00 p.m.
Conclusion - Murali Emani (ANL) (Conclusion)
Murali Emani