CALL FOR PAPERS

FastPath 2020:  International Workshop on Performance Analysis of Machine Learning Systems

https://fastpath2020.github.io

April 5, 2020 - Boston, Massachusetts, United States

In conjunction with ISPASS 2020:  http://www.ispass.org/ispass2020


SUMMARY

FastPath 2020 brings together researchers and practitioners involved
in crossstack hardware/software performance analysis, modeling, and
evaluation for efficient machine learning systems. Machine learning
demands tremendous amount of computing. Current machine learning
systems are diverse, including cellphones, high performance computing
systems, database systems, self-driving cars, robotics, and in-home
appliances. Many machine-learning systems have customized hardware
and/or software. The types and components of such systems vary, but a
partial list includes traditional CPUs assisted with accelerators
(ASICs, FPGAs, GPUs), memory accelerators, I/O accelerators, hybrid
systems, converged infrastructure, and IT appliances. Designing
efficient machine learning systems poses several challenges.

These include distributed training on big data, hyper-parameter tuning
for models, emerging accelerators, fast I/O for random inputs,
approximate computing for training and inference, programming models
for a diverse machine-learning workloads, high-bandwidth interconnect,
efficient mapping of processing logic on hardware, and cross system
stack performance optimization. Emerging infrastructure supporting big
data analytics, cognitive computing, large-scale machine learning,
mobile computing, and internet-of-things, exemplify system designs
optimized for machine learning at large.


TOPICS

FastPath seeks to facilitate the exchange of ideas on performance
optimization of machine learning/AI systems and seeks papers on a wide
range of topics including, but not limited to:

 o Workload characterization, performance modeling and profiling of machine
   learning applications
   
 o GPUs, FPGAs, ASIC accelerators
 
 o Memory, I/O, storage, network accelerators
 
 o Hardware/software co-design
 
 o Efficient machine learning algorithms
 
 o Approximate computing in machine learning
 
 o Power/Energy and learning acceleration
 
 o Software, library, and runtime for machine learning systems
 
 o Workload scheduling and orchestration
 
 o Machine learning in cloud systems
 
 o Large-scale machine learning systems
 
 o Emerging intelligent/cognitive system
 
 o Converged/integrated infrastructure
 
 o Machine learning systems for specific domains, e.g., financial, biological, 
   education, commerce, healthcare


SUBMISSION

Prospective authors must submit a 2-4 page extended abstract:
https://easychair.org/conferences/?conf=fastpath2020

Authors of selected abstracts will be invited to give a 30-min presentation at the workshop.


KEY DATES

Submission:   February 21, 2020

Notification: March 2, 2020

Final Materials / Workshop: April 5, 2020


ORGANIZERS

General Chair:             Erik Altman

Program Committee Chairs:  Parijat Dube
                           Vijay Janapa Reddi
                           
Publicity Chair:           Falk Pollok


PROGRAM COMMITTEE

Christophe Dubach 	     McGill University
Christopher Fletcher 	     University of Illinois at Urbana-Champaign
Jangwoo Kim 	             Seoul National University
Tushar Krishna 	             Georgia Tech
Gennady Pekhimenko 	     University of Toronto
Brandon Reagan 	             NYU / Facebook