Ian Foster

MidWest Grid Workshop

The MidWest Grid Workshop will be held at the University of Illinois in Chicago on March 24 and 25. From the Web page

The aim of the workshop is to give the students a basic foundation in distributed computing, and valuable hands-on training in computing techniques. The workshop introduces essential skills that will be needed by students in the natural and applied sciences, engineering, and computer science to conduct and support scientific analysis in the emerging grid computing environment.

Participants will work with some of the world's leading experts in grid computing, through a blend of lectures, discussions and hands-on computing exercises on large-scale grid hardware and software resources.

Cool Second Life Hack ...

Matt Biddulph writes about connecting a physical sensor to an object in Second Life (there's a neat movie). The connection is one-way (from sensor to SL object), although presumably it could work the other way too (SL object to sensor).

I'm interested in exploring the use of Second Life to mirror the real world (David Gelertner wrote about that). It seems it's easy to do. Not clear what data rates SL can sustain, though.

Cyber-enabled Discovery and Innovation

The National Science Foundation's Information Technology Research program was (IMHO) one of the most successful efforts to support interdisciplinary research in computational science. (The Department of Energy's SciDAC program does well too.) Thus it has been a great concern that this program was terminated with no clear next step.

The new Cyber-enabled Discovery and Innovation (CDI) program, announced as beginning in 2008, seems to be a worthy successor. Five key elements:

• Knowledge extraction
• Interacting elements
• Computational experimentation
• Virtual environments
• Educating researchers and students in computational discovery
  

New GridShib release

I've written previously about advances in attribute-based authorization. An important part of this work is the GridShib tools. From Tim Freeman's blog on Virtualization and Grid Computing, information on new GridShib components:

Microfluidic Bubble Logic

A wonderful article in Science (press release and article): Manu Prakash and Neil Gershenfeld describe how to use bubbles in a microfluidic device to carry on-chip process control information, while also performing chemical reactions.

Microfluidics is a fascinating technology that deals with the control and manipulation of microliter and nanoliter volumes of fluids. Fluids flow through microfabricated channels (see figure), allowing the delivery of precise quantities of reactants and the precise control of chemical reactions.

Previously, control has been achieved via external valves and control systems. The authors present channel geometrics that exploit nonlinear behavior of bubbles in microfluidic flows to perform logic operations (e.g., "a bubble has arrived on channel A AND B") and to store bubbles. (E.g., the figure shows three AND-gates connected in a ring oscillator. A bubble flows clockwise around the ring until it joins a stream.)

Quoting the press release: "Controlling chemical reactions will likely be a primary application for the chips. It will be possible to create large-scale microfluidic systems such as chemical memories, which store thousands of reagents on a chip (similar to data storage), using counters to dispense exact amounts and logic circuits to deliver them to specific destinations."
   

A New Paper Makes Clear The Benefits of GRAM4

The Grid Resource Allocation and Management (GRAM) service was one of the first Globus services. What we now call pre-Web Services GRAM service (or “GRAM2”) first appeared back in 1999, and it has since been widely deployed on grids around the world.

We have been working for a while on a new, Web Services-based GRAM service (“GRAM4”). This process has taken much longer than we would have liked, but a positive outcome has been that the final product is (IMHO) really good.

A new paper describes the many improvements that GRAM4 offers over GRAM2 in functionality, scalability, and manageability. On the performance side: GRAM4 is faster in the case of many concurrent submissions, but slower for sequential submissions and when file staging is involved. However, we are not far off, and we are working on further optimizations.

A strange week

It has been a strange week. No sign of Jim Gray--we must presume him lost at sea. And the death of another distinguished computer scientist, Ken Kennedy--who certainly had a major impact on my life, via his leadership of the Center for Research on Parallel Computation, his work on PITAC (which created the ITR program), and many other things.

Meanwhile, the Intergovernmental Panel on Climate Change announced its 4th assessment. The summary makes extremely sobering reading: the expected impacts on the environment and human life are spelt out in detail and with great certainty. While distressing, I have to see this as positive: as Scientific America summarized it, "Science Debate Ends, Solution Debate Begins." We have a lot to do.

On the entirely positive side, I was cheered to see a neighbor of mine, Barack Obama, announce his candidacy for presidency this morning. (The speech is worth watching.) I've always thought it would be interesting to have a president younger than me--I just didn't think it might happen so soon.

News from Puerto Rico

I spent last weekend in Puerto Rico, thanks to an invitation from Wilson Rivera to speak at a Workshop on Wireless Networking, Automated Information Processing, and Web & Grid Services held in conjunction with the International Symposium on Wireless Pervasive Computing.

The weather was of course pleasant (on a telecon with colleagues in Chicago, I mentioned it was 85 F; one replied "it's just like that here--but without the 80"). But I was particularly impressed with what I learned about work being done at the University of Puerto Rico Mayaguez, e.g., in Wilson's very dynamic Parallel and Distributed Computing Lab. For example, they're doing a lot of work with Globus, and building end-to-end systems to monitor Puerto Rico ecosystems. It's certainly a place to watch.

Help Find Jim Gray ...

On Sunday, January 28th, 2007, the renowned computer scientist Jim Gray was reported missing at sea. As of Thursday, Feb. 1st, the US Coast Guard has called off the search, having found no trace of the boat or any of its emergency equipment. Follow the story here.

Through the generous efforts of his friends, family, various communities and agencies, detailed satellite imagery has been made available for his last known whereabouts. You can help search this data using Amazon's Mechanical Turk service, here.

I was expecting to host Jim at the University of Chicago this coming Friday, and was looking forward to the stimulating and fun discussions that are the norm with this engaging and brilliant person. I'll be searching on Mechanical Turk; I hope that many others can do the same.