Conventional wisdom says that choosing between a GPU versus CPU architecture for running scientific visualization workloads or irregular code is easy. GPUs have long been the go-to solution, although recent research shows how the status quo could be shifting.
At SC 16 in Salt Lake City in a talk called CPUs versus GPUs, Dr. Aaron Knoll of the University of Utah, and Professor Hiroshi Nakashima of Kyoto University, presented comparisons of various CPU and GPU-based architectures running visualizations and irregular code. Notably, both researchers have found that Intel Xeon Phi processor-based systems show stand-out performance compared to GPUs for …
CPU, GPU Potential for Visualization and Irregular Code was written by Nicole Hemsoth at The Next Platform.
An excellent post from Eyvonne Sharp highlights one of Cisco’s weakest areas, its enduring passion for too many products, too many options, too much complexity:
With that in mind consider Cisco, a company in love with complexity. They’ve built their business making complex systems. Their culture breeds nerd knobs. They’ve built certification tracks — through which many network engineers have built their careers — to develop expert level understanding of their products.
At the same time, engineers operate in a culture were we believe configuration and operational complexity have inherent value. We unconsciously embrace the following logic: Networks are complex. One must be smart to understand networks. I understand networks. Therefore, I’m smart.
We extrapolate this logic and believe that complexity, for complexity’s sake, makes us superior. In truth, our pride has tied gordian knot with complexity and we don’t know how to unravel it.
Using SD-WAN as a use case to highlight Cisco’s love of its own complex technology instead of radically redefining itself. Cisco has limited traction in SD-WAN space because its current technology is hard to design, harder to operate and lacks features. While the business units are doing their best to make it simple, building on Continue reading
By automating routine tasks, IT engineers can help businesses compete more effectively.
What about the computer server at Trump Tower?
Several news media outlets have reported that investigators last year were puzzled by data transmissions between a computer server at Trump Tower and a computer server associated with a Russian bank. Although Mr. Trump on Twitter Continue reading
Matthias Luft (a good friend of mine, and a guest speaker in the upcoming Building Next-Generation Data Center course) wrote a great post about the (lack of) security in software development.
The parts I like most (and they apply equally well to networking):
Read more ...This post is part of a series of posts sharing the stories of other users who have decided to migrate to Linux as their primary desktop OS. Each person’s migration (and their accompanying story) is unique; some people have embraced Linux only on their home computer; others are using it at work as well. I believe that sharing this information will help readers who may be considering a migration of their own, and who have questions about whether this is right for them and their particular needs.
For more information about other migrations, see part 1 or part 2 of the series.
This time around we’re sharing the story of Rynardt Spies.
Q: Why did you switch to Linux?
In short, I’ve always been at least a part-time Linux desktop user and a heavy RHEL server user. My main work machine is Windows. However, because of my work with AWS, Docker, etc., I find that being on a Linux machine with all the Linux tools at hand (especially OpenSSL and simple built-in tools like SSH) is invaluable when working in a Linux world. However, I’ve always used Linux Mint, or Ubuntu (basically Debian-derived distributions) for my desktop Continue reading