Encoding, Fast and Slow: Low-Latency Video Processing Using Thousands of Tiny Threads
By Sadjad Fouladi, Riad S. Wahby, Brennan Shacklett, Karthikeyan Balasubramaniam, William J. Zeng, Rahul Bhalerao, Anirudh Sivaraman, George Porter, Keith Winstein. Symposium on Networked Systems Design and Implementation, 2017
374 citations recorded by the source corpus.
View Paper: https://www.semanticscholar.org/paper/e6654c70c990b64eb951771ece0a10c8bd001c56
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
- Simon Shillaker
- Istemi Ekin Akkus
- Peter R. Pietzuch
- Ruichuan Chen
- Edward Oakes
- Anurag Khandelwal
- Chia-che Tsai
- J. Carreira
Citations in the corpus
- Cloud Programming Simplified: A Berkeley View on Serverless Computing (2019, methodology): “To perform encoding in real time, ExCamera parallelizes the “slow” parts of the encoding, and performs the “fast” parts serially.”
- SAND: Towards High-Performance Serverless Computing (2018, methodology): “Despite its recency, serverless computing has already been used in various scenarios including Internet of Things and edge computing [7,16], parallel data processing [33, 34], data management [14], system security enhancement [13], and low-latency video processing [20].”
- SOCK: Rapid Task Provisioning with Serverless-Optimized Containers (2018, background): “Many lamb-das will need libraries for communicating with other services and for storing data externally [16] libraries may be somewhat less relevant, but lambda-based parallel unit testing is an interesting use case.”
- Pocket: Elastic Ephemeral Storage for Serverless Analytics (2018, background): “Early work in serverless analytics has identified the challenge of storing and exchanging data between hundreds of fine-grain, short-lived tasks [45, 32].”
- The rise of serverless computing (2019, background): “One class of applications that started gaining momentum are compute intensive applications.(13) Early results show (see Use Case 3 sidebar) the performance achieved is close to specialized optimized solutions and can be done in an environment that scientists prefer such as Python.”
- Faasm: Lightweight Isolation for Efficient Stateful Serverless Computing (2020, methodology): “Some systems avoid data movement costs by maintaining state in long-lived VMs or services, such as ExCamera [26], Shred-der [80] and Cirrus [17]; this loses the benefits of serverless computing by breaking out of the model.”