Sunday, January 29, 2012

Happy New Year

A belated New Year greeting. It has been a crazy year for accelerated computing and the deployment of special purpose hardware.

1. The HPC world clearly has embraced GPUs as a route to getting more Flops. It is unclear if any of it actually adds up to a lot more science, but the tools are in the hands of the experts.

2. Though we have many more cores, not a single new paradigm for using them has emerged. Libraries are being optimized for MPI on the system and interest in OpenMP has increased. These modest incremental updates are, in a word, useless.

3. Virtualization in the real world is there. With most jobs able to max out a single socket, virtualization of clusters is starting to make sense - not just for deployment scenarios, but also for job scheduling.

4. The problem right now isn't memory bandwidth. It's I/O. Big Data style solutions that move the compute to the data are going to be increasingly popular. However, isn't this what siesmic has been doing for years? What is really going to be new?

5. SSSDs are mainstream. But the reference architectures by use case are still being developed.

6. Rise of PaaS should create opportunities for more specialized deployments, similar to the combined software and hardware solution of Amazon's latest DB efforts. NoSQL on SSSDs... what next?

Thoughts for January. Tune in for more thoughts in February.

doug

Monday, September 19, 2011

What do Subcommittees Think?

Interesting(?) line up at Ben Quayle's next hearing...

Two EMC companies, a Microsoft and the GSA on Cloud Computing. Two Dr(s) and two Mr(s) in front a room of JDs (lawyers) talking about current wave of tech.

In all fairness, it should be noted that Capellas in addition to being CEO of VCE is also the chair of TechAmerica and the other Mr (David McClure) has been front and center in fedearl Cloud adoption & cost.

I can guess what they will say. It is the doctors who might add some interest to the event. I suspect that Nick Combs of EMC will make a product-like pitch. But Dan Reed of MSFT tends to be higher level and aspirational. He is one of the handful of very interesting technologists Craig Mundie brought on several years ago. They need to start delivering on something more interesting that "To the Cloud" soon.



Mr. Michael Capellas, Virtual Computing Environment Company

Dr. Dan Reed, Corporate Vice President, Technology Policy Group, Microsoft Corporation

Mr. Nick Combs, Federal Chief Technology Officer, EMC Corporation

Dr. David McClure, Associate Administrator, Office of Citizen Services and Innovative Technologies, General Services Administration


http://science.house.gov/hearing/technology-and-innovation-subcommittee-hearing-cloud-computing

Thursday, September 15, 2011

Before Pandora...

Life in a cube is not one of quiet contemplation. It isn't one of privacy or focus.

I have an excellent set of in-ear isolation headphones. They don't help me get work done, but they do help me ignore others. I listen to Pandora mostly. I accept the advertising as a consequence of the pleasant surprises that sneak into my ear.

Feist's cover of the Beatles was perfect for avoiding sending that nasty email to a colleague on why the were (once again) failing to make my job easier.

Lately, I've been streaming other music on my iPhone (over Wifi) when I work out in the gym. It reinforced how little I care about the computer I use. I only care about the services that I can access.

Windows 8 is chasing the iPad/iPhone like Android is. Frankly, I know Android is better at some activities than my iPad or iPhone. There is nothing stopping Windows8 from being better than both at some tasks - so long as it remains open to also serve all the services I expect.

Could I become a Windows user again? I certainly don't want to go back any Windows that looks or acts like they did. All it has to be is a version of Windows that makes me forget that Windows ME, Clippy & Bob ever existed.

Maybe they should start with a new name?

Monday, January 24, 2011

Trying something new

My job(s) have evolved. I'm further from the tech these days & spending more time on purchasing behaviour, perception and reach. I'm also going to evolve this blog.

I tend to use Mondays to plan the week & check on progress toward strategic goals. That includes course correction on those goals. In that spirit, I also use Mondays to read material not exactly in my space. Here are my Monday factiods:

The economic impact of the "Office Lady" is global.

In Asia, the young, employed, stay-at-home female not only spends, but drives brand awareness - the alpha geek of fashinistas
http://bit.ly/ef30oy
Yet, Japan still has the largest gender gap in salaries.

In the US, young women out earn young men.
http://bit.ly/eXAsH5
And, despite some great women leaders, female CEOs are rare enough to make news

Men claim to be the primary grocery shopper
Ad Age reports that 51% of men claim to be the primary grocery shopper. And are more brand aware.

B2B marketing increasing is online
From email to virtual events to social media everyone is spending more online. This includes an increased investment in Social Media - mostly for "Brand Building". In other words, the impact of social media is something that can not be directly measured.
They also plan to hire.
http://bit.ly/h4P851

Friday, January 14, 2011

The Acceleration market is alive...

AMD's Fusion finally saw the light of day and it's getting awards. How this translates into better computing, more horsepower and better programming models is still to be seen.

http://www.zdnet.com/blog/computers/ces-2011-amds-fusion-apus-arrive-in-new-laptops/4656

With this hardware actually in the wild, I'm looking forward to hearing about students, professors and researchers actually programming something on it. If it only saves power, it is a sound silicon design. It's industry impact will be dependant upon simplified programming and more effective computing.
I haven't seen that demo-ed anywhere yet. Have you?


Meanwhile, the world sees a need to speed up math. Those GHz aren't getting any faster, are they?
http://www.hpcwire.com/features/Egyptian-Startup-Accelerates-High-Performance-Accounting-113319679.html

Tuesday, May 18, 2010

If it isn't one thing...

On the day after Sheldon Cooper declares "Ubunutu: You are my favorite linux-based operating system" (followed immediately by the phrase 'crap' in my house), three new pieces of news on hybrid computing models cross my desk.

The first is a story in Scientific American on the work Wu Feng and his colleagues are doing at Virginia Tech. http://www.scientificamerican.com/article.cfm?id=opencl-smooths-supercomputing Wu has long been on the leading edge of what defines power efficient computing and the placement of data next to compute.

The second was the announcement from IBM & NVIDIA that you can buy GPUs in a IBM server chassis. When IBM does it, it must be real? Or has the canceling of the next generation of Cell leave Dave Turek grasping at straws?
http://news.cnet.com/8301-13924_3-20005218-64.html

I'm going to close with another reference to Wu, the prolific Hokie. His group published a paper last month identifying missing genes in the microbial DNA sequences to date. The compute model was an "ephemeral supercomputer" of 12k cores across seven sites within the US. This may not look like hybrid computing, but it is about moving data independently of compute in order to manage the latencies between the compute nodes.

None of the compute Wu's team is doing, or the Tesla examples from NVidia tackle the really hard, communication dependent problems such as multiphase physics or simulation with dynamic meshing, but they do demonstrate that there are plenty of problems to be tackled with intelligent programming and massive parallel processing.

I still believe in the hybrid computing models and explicit data placement. Though my friend Mark may feel that he can show that density and efficiency of general purpose compute engines will subsume the specialty silicon market, we are certainly not yet there.

Monday, April 19, 2010

Linux on Wall Street

If there was ever a conference that appears unnecessary, it is the Linux on Wall Street (former HPC on Wall Street) conference. After all, Linux got it's mojo from the Wall Street crowd. There are visible community projects such as AMQP (open source messaging), OpenFabrics (transport) and Real-Time Linux launched and maintained by consortia of vendors and Wall Street customers.

However, this small show seems to pull it off each year. It has a nice mix of high-profile attendees plus a cross section of middle managers and vendors to keep it interesting. It is a good conference when you get to spend a little time with Bubba, Birnbaum & Bechtolsheim. Like a good house party, the conference shoehorns people into backward spaces that forces them to interact and creates a chemistry of its own.

It is a bit of old home week to see where the musical chairs of jobs and careers has landed people. You find out about competitor's strategy, new acquisitions and which vendor thinks they are making it out of the Wall Street POCs and into the data center. A couple of items I picked up of note include the optimism of the 10GbE vendors and yet-another optical switch company.

Unfortunately, the sessions themselves (and this includes mine) tend toward the vendor pitch. They are clearly sponsored and too short to have the very well informed audience play stump the panel. If I ever get to chair a panel, I am not having anything but audience questions.