Marisabel Guevara Hechtman
Marisabel has been at Google since 2016. Currently as a performance software engineer, specializing on systems for video transcoding. Prior expertise as a Gmail site reliability engineer.
Research Areas
Authored Publications
Sort By
Warehouse-Scale Video Acceleration: Co-design and Deployment in the Wild
Alvin Adrian Wijaya
David Alexander Munday
Narayana Penukonda
Jeremy Dorfman
Sarah J. Gwin
Richard Ho
Danner Stodolsky
Drew Walton
In Suk Chong
Kyle Alan Lucke
Rob Springer
Alex Ramirez
Amir Salek
Maire Mahony
Hon Kwan Wu
Yoshiaki Hase
Niranjani Dasharathi
Mercedes Tan
Raghuraman Balasubramanian
Sathish K Sekar
Brian Fosco
Cho Mon Kyaw
JP Maaninen
Roy W Huffman
Fong Lou
Aaron James Laursen
Mark Steven Wachsler
Jia Feng
Aki Kuusela
Dake He
Poonacha Kongetira
Indira Jayaram
Ramon Macias
Don Stark
David Wickeraad
Yuan Li
Sandeep Bhatia
Anna Cheung
Elisha Indupalli
Jeff Calow
Devin Persaud
Yolanda Ripley
Srikanth Muroor
Prakash Chauhan
Ben Gelb
Clint Smullen
Ville-Mikko Rautio
Proceedings of the 26th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Association for Computing Machinery, New York, NY, USA (2021), pp. 600-615
Preview abstract
Video sharing (e.g., YouTube, Vimeo, Facebook, TikTok) accounts for the majority of internet traffic, and video processing is also foundational to several other key workloads (video conferencing, virtual/augmented reality, cloud gaming, video in Internet-of-Things devices, etc.). The importance of these workloads motivates larger video processing infrastructures and – with the slowing of Moore’s law – specialized hardware accelerators to deliver more computing at higher efficiencies. This paper describes the design and deployment, at scale, of a new accelerator targeted at warehouse-scale video transcoding. We present our hardware design including a new accelerator building block – the video coding unit (VCU) – and discuss key design trade-offs for balanced systems at data center scale and co-designing accelerators with large-scale distributed software systems. We evaluate these accelerators “in the wild" serving live data center jobs, demonstrating 20-33x improved efficiency over our prior well-tuned non-accelerated baseline. Our design also enables effective adaptation to changing bottlenecks and improved failure management, and new workload capabilities not otherwise possible with prior systems. To the best of our knowledge, this is the first work to discuss video acceleration at scale in large warehouse-scale environments.
View details
