Univa HPC Job Bank
HPC in the Cloud


Dedicated to covering high-end cloud computing
in science, industry and the datacenter

Language Flags

asiGRID 'Breathing New Life' into Obsolete Machines


GRIDtoday recently spoke with Michael Andrescavage, chief software architect of Andrescavage Software Inc. (www.gridnow.com), about his namesake company and it's goal to ease Grid-enablement for organizations in all fields. The company recently announced its flagship solution, asiGRID, which is capable of controlling a heterogeneous configuration of computing resources.

---

GRIDtoday:
First, could you give me a background of yourself and your history in Grid computing?

MICHAEL ANDRESCAVAGE: My professional career spans almost 40 years of architecture, analysis, development and operation of information processing systems. My focus centers around large-scale distributed software architecture.

I have held Information Technology positions at Charles Schwab & Co. Inc., Computer Science Corp., FMC Corp., General Electric Aerospace (CIA, NSA, DEA, NASA, USA, USAF, NATO, ROK), General Accident Insurance, CIGNA Insurance and United States Air Force. Among the companies I have consulted with: Vanguard Investments, EDS, Exide and RCA.

My personal history in Grid computing starts in 1988. I was chief software architect for USAF's Space Based Experimental Version (SBEV) -- StarWars project. SBEV would provide a capability to demonstrate and evaluate alternative architectures for an experimental version of a Strategic Defense Initiative (SDI) space-based Battle Management Command, Control, Communications (BM/C3) System. This was one of the first successful Grid computing implementations -- long before the term acquired it's recent popularity.

The task was to build a software framework that would be deployed on a combination of 250 servers, desktops, single-board computers, five different networks, and operating under SunOs and vxWorks operating systems. Multiple demonstrations of alternative architectures would execute concurrently using all, or subsets, of these computing resources.

This successful implementation of a "Grid operating environment" led to a paper I presented at the 1991 International Conference on Parallel Processing: "FRAMEWORK -- A general purpose, heterogeneous, distributed/concurrent/parallel processing architecture that provides the overall management, execution, and synchronization, of software processes distributed among networks of computing resources."

My professional career led me away from Grid computing until 2002, when I started Andrescavage Software Inc. I would use lessons from the "FRAMEWORK" to build a software product that would be available for anyone who wanted to take advantage of Grid computing. It took two and a half years to build a prototype and BETA version of asiGRID -- which was recently launched in February.


Gt: Can you give me a background of Andrescavage Inc.?

ANDRESCAVAGE: I started the venture in July 2002 to develop the core asiGRID software. Completed working prototype in July 2003. Completed asiGRID BETA in Jan 2005. Brought in key set of advisors in September 2004 to help formulate business plans. Currently working on establishing key partnerships.


Gt: You recently announced a new product, asiGRID. Can you tell me more about it, how it works, and what you believe makes it a better choice than other Grid solutions? Is asiGRID primarily for linking desktops or is it more server/data center-oriented? Are most platforms supported?


ANDRESCAVAGE: asiGRID is control software residing on each individual computing resource -- within a collection of heterogeneous computing resources -- on behalf of asiGRID-enabled application software. We refer to this "collection of heterogeneous computing resources" as an "Andrescavage Software Grid" (ASG).

Some properties of an ASG:

  • 1 to n (unlimited) number of heterogeneous computing resources, always connected, in a hierarchy for scalability.
  • First floor ASG, Lab 1 ASG, Human Resources ASG, Production ASG, Test ASG.
  • Computing resources are dynamic -- they come and go.
  • Computing resources exist on intranet, extranet and Internet.
  • Operating system access on each computing resource.
  • Fault tolerant, dynamic routing.
  • ASG's are dynamically connected and disconnected to/from other ASGs.
  • asiGRID-enabled applications are distributed on an ASG.
  • Applications are dynamic -- they come and go.
  • Pieces of an application are dynamic -- they come and go.

How asiGRID works:

  • asiGRID is a command-processing software architecture -- where all processing accomplished is the direct result of a command received.
  • Commands have a unique name and a list of name/value pairs.
  • asiGRID commands for ASG control.
  • User application commands.
  • User application developers write command-processing logic for a specific command.
  • User applications consist of all "application-ID unique" user command-processors distributed within an ASG.
  • asiGRID control software routes commands from source to target and routes feedback back to source.
  • Minimum number of asiGRID APIs(13) required for a user application to use all computing resources and features within an ASG.
  • Further information found in "asiGRID Concepts and Facilities."

Why asiGRID is a better choice:

  • Dramatically simpler -- command processing -- minimum APIs.
  • Use existing machines -- breathes new life into potentially obsolete or underpowered machines.
  • Start out creating ASGs for projects -- connect project ASGs -- eventually data center.
  • Substantially cheaper to implement.

A recent benchmark of an existing vendor's Monte Carlo simulation versus an asiGRID developed simulation show promising results:

  • Two programs were written in two days.
  • Tenfold increase in iterations.
  • Processing time reduced by 95 percent.

Registered Users at www.gridNOW.com can download a free, fully-functional, BETA version of asiGRID.


Gt: The list of supported OS's is impressive but there are some notable absentees. Do you have plans to increase the number of supported operating systems, and what are they?

ANDRESCAVAGE: The operating systems that we currently support (Microsoft, Linux, FreeBSD, Apple OSX) were chosen because of their market penetration and low-cost entry. It is our intent to port asiGRID to any/all hardware/operating systems that support TCP/IP.


Gt: Do you think asiGRID will receive its customer base more from the academic/research communities, or from enterprises?

ANDRESCAVAGE: We envision our platform being applicable to all sectors, but we anticipate third party software providers looking to enhance the computing power of their applications would be very interested in our offering. In addition, our product will be of great interest to mid-sized technology support and business R&D organizations looking to establish internal Grid infrastructures.


Gt: What vertical markets (e.g., oil and gas, financial services, automotive, etc.) do you think stand to benefit most from asiGRID and Grid computing in general?

ANDRESCAVAGE: Our product will be of benefit to firms with intensive computer processing needs. New, more powerful applications could be developed within the financial services, life sciences, energy, entertainment and data mining markets that will take advantage of our powerful, yet simple, Grid-enabled platform.


Gt: What kind of role do you think Grid computing can play in enterprises, and what are your feeling on the current push for enterprises to start adopting the technology?

ANDRESCAVAGE: Grid computing will become a necessity for enterprises, especially in the area of breathing new life into potentially obsolete or underpowered computers. How long will we be able to justify the cost of replacing existing machines with faster or better ones. As for the current push within enterprises, the sooner the better. The key is for the IT industry to provide simplifying, rather than complicating, solutions.


Gt: What role would you like to see your company play in the Grid arena, and what steps have been taken to further this goal?

ANDRESCAVAGE: We would like to provide the capability for organizations to quickly and efficiently implement Grid solutions. Currently, we are evaluating potential partnerships with software providers looking to Grid-enable their product suites.


Gt: Finally, I have two questions that I like to ask: 1) What does Grid computing mean to you/How would you define Grid computing; and 2) What have been the biggest changes with Grid since you became involved?

ANDRESCAVAGE: 1) The ability to use all the computing resources available, applied to all information processing systems. Eventually, all information processing systems are Grid-enabled.

2) The biggest changes I have seen are the large numbers of existing and new software vendors that are participating.

Most Read Blogs


Short Takes

NASA Builds 'Climate in a Box'

May 23, 2013 | The study of climate change is one of those scientific problems where it is almost essential to model the entire Earth to attain accurate results and make worthwhile predictions. In an attempt to make climate science more accessible to smaller research facilities, NASA introduced what they call ‘Climate in a Box,’ a system they note acts as a desktop supercomputer.
Read more...

Running Computational Fluid Dynamics in the Cloud

May 16, 2013 | When it comes to cloud, long distances mean unacceptably high latencies. Researchers from the University of Bonn in Germany examined those latency issues of doing CFD modeling in the cloud by utilizing a common CFD and its utilization in HPC instance types including both CPU and GPU cores of Amazon EC2.
Read more...

Sponsored Whitepapers

Best Practices in Big Data Storage

05/10/2013 | Cleversafe, Cray, DDN, NetApp, & Panasas | From Wall Street to Hollywood, drug discovery to homeland security, companies and organizations of all sizes and stripes are coming face to face with the challenges – and opportunities – afforded by Big Data. Before anyone can utilize these extraordinary data repositories, however, they must first harness and manage their data stores, and do so utilizing technologies that underscore affordability, security, and scalability.

Exploring the Potential of Heterogeneous Computing

04/02/2012 | AMD | Developers today are just beginning to explore the potential of heterogeneous computing, but the potential for this new paradigm is huge. This brief article reviews how the technology might impact a range of application development areas, including client experiences and cloud-based data management. As platforms like OpenCL continue to evolve, the benefits of heterogeneous computing will become even more accessible. Use this quick article to jump-start your own thinking on heterogeneous computing.

Sponsored Multimedias

Newsletters

Stay informed! Subscribe to HPC in the Cloud email Newsletters.

HPC in the Cloud Update
HPCwire Weekly Update
Digital Manufacturing Report
Datanami
HPCwire Conferences & Events
Job Bank
HPCwire Product Showcases


ISC

HPC Job Bank


Featured Events



  • June 16, 2013 - June 20, 2013
    ISC'13
    Leipzig,
    Germany

  • June 17, 2013 - June 18, 2013
    Forecast 2013
    San Francisco, CA
    United States




HPC in the Cloud Conferences & Events