Scientific Benchmarking of Parallel Computing Systems Twelve ways to tell the masses when reporting performance results

By Torsten Hoefler, Roberto Belli. 2017

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Yoshua Bengio
2. Peter Henderson
3. Sara Hooker
4. Sergey Levine
5. David Krueger
6. Pang Wei Koh
7. Bo Li
8. Shagun Sodhani

Citations in the corpus

• Toward Trustworthy AI Development: Mechanisms for Supporting Verifiable Claims (2020, background): “, Vitek & Kalibera [123] and Hoefler & Belli [124].”
• The Design and Operation of CloudLab (2019, background): “When the primary metric of interest in a system is its performance, anything that adds variability requires, at a minimum, a far greater number of experiment repetitions to achieve statistical confidence [22, 17].”