Corrigendum for February 2024 Research Article
David Patterson
A detailed explanation from the authors on the errors they caught and corrected in their February 2024 research article.
Author Archives
Energy and Emissions of Machine Learning on Smartphones vs. the Cloud
An extensive study from Google finds machine-learning training in the cloud can significantly reduce carbon footprints.
Bringing Industry Back to Conferences, and Paying for Results
David Patterson wants to boost industry submissions to conferences, while Yegor Bugayenko suggests productivity should govern coders' pay when they work from home.
Restoring Industry Participation in Computer Science Conferences
When I complained at ISCA 2019 about a lack of papers on real industrial products, I was assigned to help fix the problem.
A Domain-Specific Supercomputer for Training Deep Neural Networks
Google's TPU supercomputers train deep neural networks 50x faster than general-purpose supercomputers running a high-performance computing benchmark.
A Domain-Specific Architecture for Deep Neural Networks
Tensor processing units improve performance per watt of neural networks in Google datacenters by roughly 50x.
Attack of the Killer Microseconds
Microsecond-scale I/O means tension between performance and productivity that will need new latency-mitigating ideas, including in hardware.
An Interview with Stanford University President John Hennessy
Stanford University President John Hennessy discusses his academic and industry experiences in Silicon Valley with UC Berkeley CS Professor David Patterson.
Do-It-Yourself Textbook Publishing
Comparing experiences publishing textbooks using traditional publishers and do-it-yourself methods.
How to Build a Bad Research Center
Sharing lessons learned from experiences creating successful multidisciplinary research centers.
Shape the Future of Computing
ACM encourages its members to take a direct hand in shaping the future of the association. There are more ways than ever to get involved.
Get Involved