VizWorld.com

I was sent this article by a colleague of mine about the interesting relationship between Cloud Computing & Exascale Computing.  I keep hearing more about Exascale, in particular with the “big vis” and “big data” problems associated, and this article is a short but interesting viewpoint on one common mantra: Move to the Cloud.

Confused about Cloud Computing?

Join the club.

A big factor behind the confusion is the many self-serving definitions of ‘Cloud Computing’ being used by the various hardware, software and service vendors.

As we’ve been discussing the topic of ‘Exascale’ with many different companies, I have heard people comment that “cloud computing will be a key factor in achieving exascale.”

This is very interesting – and also very misleading. While cloud computing may very well be a factor in supporting an exascale-level ecosystem, it will not be a factor in achieving exaFLOPS levels of computation.

The market hype, over simplification, and the many (usually vendor-driven) definitions of cloud computing make it difficult for companies looking to make an investment in cloud computing technology.

Even the analyst firms align the market forecasts based on different ways of looking at the cloud computing infrastructure and revenue-generating components and services. This is nothing new for the analyst firms, however, the challenge in intelligently using these market forecasts is that they are being tossed around (by vendors and users) without adequate differentiation.

No matter how you slice it, and for the most part, no matter how you define it, cloud computing holds tremendous promise. It will likely be a significant part of the exascale world, but not a factor in achieving exaFLOPS computation. The analyst firms are aligned in predicting strong growth of sales and services in this colorful and somewhat controversial market segment.

As an example, these numbers are taken from recent publicly stated forecasts. Rest assured, you can expect these to change at least every six months moving forward:

Is there a lesson in here for marketers? Sure.

Whether talking about exascale, cloud computing, grid computing, or anything else – be transparent in your definitions and understand the subtle (or not so subtle) differences in the other definitions being used so you can talk intelligently and factually to your audiences – without trying to sell them or convert them. Don’t get lost in the hype. This is true for exascale – and it’s true for Cloud Computing.

Submitted by:
Mike Bernhardt
The Exascale Report
http://theexascalereport.com

Science analyst, exascale

Cloud Computing?

At the recent HPC360 event, several people showed up talking about using “cloud resources” for HPC research.  Running big sim codes in the cloud isn’t a problem, in fact it’s not much different from how it’s done now.  The real sticky point is then doing the analysis and visualization with data in the cloud and resources in the cloud.  There aren’t many of these resources out right now, and the tools are a bit confusing.  Dassault Systemes’s Matt Dunbar said it best:

As Dunbar stated, “doing actual batch simulation in the cloud is reasonably straightforwared but doing 3D graphics post-processing is something that remains a question mark for us. There are a number of ways we can do that, but right now we’re trying to decide how best to do that.” This is a difficult decision because software architects are either faced with waiting for a long time or taking what might be a performance hit with their use of utility resources versus their own, slightly more time-intensive (due to wait time) use of workstations.

This is personally a big area of interest for me.  I really thought the Sun Visualization System was a great start, but it was a bit before its time and died in the Oracle acquisition (if not before).  Products like the TACC EnVision and Longhorn suite are a great step in the right direction, putting existing applications on remote resources through a single web-client.

Eventually, tho, we’re going to need smarter applications that can handle the kind of integrity and latency problems that come from super-huge runs.  Tools like EnSight and ParaView are already working on scaling to these larger systems, but still don’t gracefully handle the death of a node or graphics resource.  Of course, some will say that’s an MPI problem or an OS problem, and they’re right.  Exascale computing has lots of challenges, and I just hope that Visualization doesn’t get left behind as it has in the past.

via HPC in the Cloud: Weighing the Queue, Evaluating the Utility.

Science cloud, exascale, hpc