Archives for category: High Performance Computing

LSUindustrypanelI’ve been invited to represent Dell and speak at LSU’s upcoming HPC Industry Panel.  It’s exciting to go back to my alma mater!  Students from across LSU’s summer research programs will be in attendance.

It’s just too bad this didn’t happen a month later so I could catch an LSU football game in Death Valley!  At least I will get a chance to see SuperMike-II which I had a considerable role in designing.

UPDATE:  LSU published a nice recap of the session.  Below are a few of my quotes:

“I decided to co-op in college, and it was the best decision I ever made,” said Blake Gonzales, high performance computing scientist at Dell Inc. “What you can actually do will make the world of difference, not your GPA or where you went to school,” he added.

“I had a low GPA at one point as an undergraduate student, but received 13 job offers. So if you don’t have a job yet, walk out of this room after our meeting and find one!” he said.

“Learning is very important for me, too, and while designing supercomputers at Dell, I spend a lot of time reading and writing papers,” said Gonzales.

“Teach them how to work in groups more effectively,” Gonzales suggested. “The hardest part is not the actual assignment, but dealing with people. And that’s what real life is all about.”

When talking about job opportunities at Dell, Gonzales pointed out that there are many open positions in the area of high performance computing (HPC).  “HPC is infiltrating every part of society, every manufacturing process, every biological process, and it is becoming a very exciting field to work in,” he said.

Gonzales mentioned a project recently implemented by Dell that involved the top cancer that strikes children. After the little patients are diagnosed, it takes several weeks to start treatment, because doctors first must complete DNA sequencing that requires a lot of computation. Dell’s specialists in HPC were able to cut down the time from several weeks to four hours. This can literally save lives, as children will be getting their treatment sooner now.


I want to highlight some of the amazing work my teammate Dr. Glen Otero has done.  This is an amazing accomplishment to provide children with neuroblastoma their treatment in days rather than months.  It’s great to be part of a team that is really making a difference.  Full story here


Dell has leapfrogged HP to capture the #2 top HPC vendor crown!

IBM, followed by Dell, was the top named [HPC] vendor for number of nodes installed when outliers (i.e., systems with 2,000 or more nodes) were excluded.  Click for full article

I’m sure that most users reading this are using HPC systems with less than 2000 nodes.  It’s the core of the HPC market and Dell has captured a very large portion of it.

Our goal in this report was to discover system-level trends within the HPC user communities by examining supplier penetration, architecture trends, and node configurations.  As with previous years, we surveyed a broad range of users about their current computer system installations, storage systems, networks, middleware, and the applications software supporting these installations.

A few weeks ago Rich Brueckner over at insideHPC pointed the HPC community to an excellent lecture on Computational Fluid Dynamics (CFD).   Dr. Margot Gerritsen, a Computational Scientist and the Director of the Institute for Computational and Mathematical Engineering at Standford University, gives a great overview of CFD.   It’s worth your time to watch if you are interested in, or even tangentially associated with, CFD.   She explains CFD with very clear and easy to understand examples.  I really appreciate those who have a passion for applied mathematics and go a step further and make it interesting!

[I want to share] with you a bit of the passion that I have for computational mathematics … [The] mathematical harassing of undergraduate and graduate students is led by my institute … that’s a wonderful feeling to be able to control that … very painful experience… But I love it!

When you look at it very carefully, all of the equations that govern fluid flow processes.. be it climate models, weather models, optimization of sail design for competitive yacht races … optimizing wings … fluid flow in oil and gas reservoirs, aquifers, ground water models, coastal oceans, wind turbine optimization …

All of these processes that may seem completely different, are all governed by these equations, it’s all the same stuff… they look very complex … [but] it’s all relatively simple.

Dr. Gerritsen does a great job of presenting an overview of what is involved in CFD calculations.  She then goes into the how and why of creating  an effective mesh, and then solving  this mesh on a cluster.  This is a very excellent introduction to fluid dynamics!

Dell’s Blake Gonzales @ SC11 talks about some of the HPC workloads customers have been asking about with him.

Cars wind through the infield section of the I...

Take a look at my recent article over at regarding the Supercomputing landscape in Formula One racing.  Here’s a snippet from the post:

HPC technology enables F1 engineers to test hundreds of ideas virtually, and select those that perform well for physical testing, saving F1 teams both time and money. Its importance has been recognized with new regulations that limit F1 teams to 20 teraflops of compute power.

HPC solutions have transformed the competitive landscape of Formula One racing. Which industry is next?

What do you think?

It appears physicists in Japan have come up with a new one-way function that can be used for public-key encryption.  The difference here is that the new function can theoretically be used on future quantum based computers.  “Akinori Kawachi at the Tokyo Institute of Technology in Japan and a few buddies suggest that all is not lost for public key encryption. These guys have discovered a quantum problem that is hard to solve in one direction but easy to do in reverse. And they say this asymmetry could form the basis of a new kind of quantum public key encryption system.”  The advent on quantum based computing may trivially break current PKEA algorithms… so it’s good we have new quantum algorithms starting to be developed.  This is all very cool stuff.

I wanted to point you to some interesting things going on at SC10 and also some content I’ve contributed to this week in New Orleans.  I’ll be updating this post occasionally.

SC10 SCC Shows Excitement & Sense of Community!
Can the Flux Capacitor & Dellorean Power Univ of Texas to the Top?
SCC … Flashback to SC09 … Fast Forward to SC10
Insight & thoughts about Clayton Christensen’s Keynote Address
Supercomputing 2010 – Preview, Thoughts, Trends

TACC’s Student Cluster Challenge Team Wins Highest Linpack Award

Video: SC10 Recap: Student Cluster Competition Awards

The Register
SCC after dark: Clustering all night long

HPC clustering: A new spectator sport in the Lone Star state?

TACC – TACC’s Student Cluster Challenge Team Wins Highest Linpack

SCC Competition Site – SC10 SCC Results

Twitter – HPCatDell SC10

I thought I would point you to some exciting work students are participating in over at Texas Advanced Computing Center.  TACC is mentoring several University of Texas at Austin students in the SC10 Student Cluster Competition to be held this November in New Orleans.  This is great work that the students are doing, and it is great to see involvement from TACC and support from the HPC community.  Here are some brief details of the SC10 challenge to build a system within the power constraints equivalent to only three coffee-makers!

The Student Cluster Competition (SCC) showcases the computational impact of clusters and open source software in the hands of motivated and sleep-deprived students under both a time and power constraint. Uh, no pressure…

During SC10, teams consisting of six students… will compete in real-time on the exhibit floor to run a workload of real-world applications on clusters of their own design while never exceeding the dictated power limit.

Prior to the competition, teams work with their advisor and vendor partners to design and build a cutting-edge commercially available small cluster constrained by the 26 amps available during the conference. Teams must also learn the four open source competition applications and are encouraged to enlist the help of domain specialists.”

It is exciting to see students motivated to work on some of the challenges we face in the industry.  I first met the two student leaders of this six-person group at SC09 in Portland last year. Read the rest of this entry »

There was a recent article in IEEE Spectrum entitled The Trouble With Multicore that gives a really nice background on how multicore processors have taken hold in the computing industry.  I wrote about this article on my blog Multicore in HPC – Where will we stand in 10 years? In doing so, I offered some additional insight into the future of multicore in HPC.

Additionally, and more importantly, I posed the same question to the High Performance Computing group on LinkedIn and there has been lots of great insight posted there as well. So much so, that I thought it would be very beneficial to share some very keen insight others in the industry have shared.

Head on over to my blog at, to read some of the highlights of the great discussion going on at LinkedIn.

Zack’s Investment Research is taking note of Dell’s HPC expertise and HPC product line.  After the announcement of Dell’s $5.1M upgrade at NASA’s National Center for Climate Science (NCCS), Zack’s had this to say about Dell’s HPC practice:

NASA’s involvement does signal growing interest in Dell’s expertise.

Dell’s HPC solutions are gaining popularity in universities and organizations keen on deploying upgraded technology for their research work.

They also mentioned the value of Dell’s PowerEdge C line of servers in HPC:

Dell’s HPC solutions are based on Intel Corp.’s Xeon Processors and facilitate designers, engineers and program developers to conduct research work faster and more efficiently.

Dell’s PowerEdge C6100 server, which is one of the HPC solutions, will empower NCCS to look into minute environmental details with the help of faster research and innovation, thereby reducing energy consumption.

On a personal note..  This is great news for our team.  It is great to be a part of HPC at Dell right now!  And as always, check out my other HPC blogs over at

David Patterson over at IEEE Spectrum has written an article entitled “The Trouble With Multicore.” Kudos to David for a very thorough and well thought out article.  He gives plenty of background on how we arrived at multicore processors, and some of the techniques and challenges that come with parallel processing.  The advent of multicore processing was pretty much a gamble on the part of the semiconductor manufacturers, although their hand was forced due to the power wall associated with increased processor speeds:

“[In 2005] the semiconductor industry threw the equivalent of a Hail Mary pass when it switched from making microprocessors run faster to putting more of them on a chip—doing so without any clear notion of how such devices would in general be programmed. The hope is that someone will be able to figure out how to do that, but at the moment, the ball is still in the air.”

Achieving sustained parallel performance with application codes is a major effort.  In research and engineering communities, we have had increased success, but with that comes a major outlay of time and resources.  Here are a couple of choice quotes in the article that indicate the increased effort it takes to exploit multicore processors: Read the rest of this entry »

A recent article in IT Business Edge asks “Do Processors Really Matter Anymore?”  There is a statement in the article that got me thinking:

It would seem …  that the only users still focusing on clock speeds and overall processing capability are in the HPC market…

To this statement, I tend to disagree.  In HPC there is a focus on processors, but not so much on flops per core anymore.  There is a real concentration on how to leverage parallel computational resources in order to get your application to run efficiently.

Take a look at my comments over at

What do you think?

File systems on your HPC cluster provide data storage to individual nodes, and entire subsets of nodes.  This is the home for your data and results, so lets keep it safe!  It is important to configure journaling, multiple data stores, and of course RAID.  Take a look at my tips for correctly configuring file systems on your cluster. Feel free to share your thoughts as well.

I was reading in a recent ACM journal a few days ago, and I came across an article entitled In Search of a Natural Gesture.  The article explores human input/output methods and devices for computing systems, and I noticed some indirect comparisons to HPC.  This quote caught my attention:

The average consumer’s demand for more powerful technology has simply not kept up with the exponentially increasing supply. Some have referred to this stall in performance demand as the era of “good enough computing.” Read the rest of this entry »

Adding resiliency to your job scheduler can make a real difference in the overall reliability of your cluster.  With shared memory systems, a single hardware failure can bring your entire system down causing a restart of all jobs.  Single hardware failures in a cluster though will usually effect only a single job…. unless the failure occurs in the hardware running your scheduler!  If you lose the job scheduling state, a complete restart of all jobs might also be necessary.  Take a look at my suggestions for building resiliency into your job scheduler. Let me know what you think below!

What You Should Know about Power and Performance Efficiency

I contributed to this article for the May/June issue.  Let me know what you think about the article, including the comments from others in the HPC industry.

%d bloggers like this: