Remove 2010 Remove Efficiency Remove Hardware Remove Internet
article thumbnail

USENIX SREcon APAC 2022: Computing Performance: What's on the Horizon

Brendan Gregg

Google and Amazon’s latest AI chips have arrived," [link] Oct 2022 - [Intel 22] Intel, "Intel® Developer Cloud," [link] accessed Dec 2022 I've taken care to cite the author names along with the talk titles and dates, including for Internet sources, instead of the common practice of just listing URLs.

article thumbnail

USENIX SREcon APAC 2022: Computing Performance: What's on the Horizon

Brendan Gregg

As for attending USENIX conferences: I finally started attending and speaking at them in 2010 when a community manager encouraged me to (thanks Deirdre Straughan), and since then I've met many friends and connections, including Amy who is now USENIX President, and Rikki with whom I co-chaired the USENIX LISA18 conference.

Insiders

Sign Up for our Newsletter

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.

Trending Sources

article thumbnail

The Ethics of Web Performance

Tim Kadlec

My home internet connection gives me somewhere around 3 Mbps down. Hardware gets better, sure. In a 2012 paper, The American Council for an Energy-Efficient Economy estimated the internet uses 5 kWh on average to support every GB of data. It seems blazingly fast compared to the 0.42 It makes sense.

article thumbnail

The Performance Inequality Gap, 2024

Alex Russell

HTML, CSS, images, and fonts can all be parsed and run at near wire speeds on low-end hardware, but JavaScript is at least three times more expensive, byte-for-byte. Many critiques are possible, both of the target (five seconds for first load), the sample population (worldwide internet users), and of the methodology (informed reckons).

article thumbnail

Amazon EC2 Cluster GPU Instances - All Things Distributed

All Things Distributed

By Werner Vogels on 14 November 2010 04:00 PM. Now that our ability to generate higher and higher clock rates has stalled and CPU architectural improvements have shifted focus towards multiple cores, we see that it is becoming harder to efficiently use these computer systems. Comments (). General Purpose GPU programming.

AWS 136