There will a free CloudCamp ‘unconference’ in Chantilly VA (outside DC) from 3pm to 9pm on Wednesday 12 November.

“CloudCamp is an unconference where early adapters of Cloud Computing technologies exchange ideas. With the rapid change occurring in the industry, we need a place we can meet to share our experiences, challenges and solutions. At CloudCamp, you are encouraged you to share your thoughts in several open discussions, as we strive for the advancement of Cloud Computing. End users, IT professionals and vendors are all encouraged to participate.”

My colleague Marc Olano recently blogged about the new Larrabee chip from Intel, which will be described in a SIGGRAPH paper in a session he is chairing. This chip, with multiple old Pentium type cores running at 1GHz, seems a logical culmination of the recent multi/many core trend. IBM’s plans with the Cell/BE, and perhaps with the newer generation Power Chips, are also headed in a similar direction. Short of material scientists doing some magic with high K dielectrics or airgaps or CNFETs or whatever, the trend seems to be away from a single CPU with more transistors running faster and faster to multicored chips not clocked very fast. There’s a good reason for it (heat), as anyone who’s had a high end laptop and actually put it on their laps can testify. Further down the road, even more complex parallel architectures are proposed, with MCMs on chip connecting optically, and perhaps even memory stacked on top of the CPU layer talking optically back and forth! In other words, a few years down the road, the default box on which a system builder will write code will be something other than a single cored CPU. Bernie Meyerson from IBM discusses such issues in his talks — I can’t lay my hands on a publicly available power point, but some of the ideas are discussed in a recent interview.

Do these developments mean that we should be rethinking Programming 1 and 2, especially for CS majors. Do students now need to think parallel or multi-threaded programming from day one? Can that be done without first doing standard imperative programming? Given the less than ideal state of high school CS education, is it realistic to expect that students will get Programming 1 (and maybe 2) in high school? In our department, we’re offering class on programming the Cell/BE, and a course related to GPU programming, but those are typically meant for seniors. How about courses further upstream. Should data structures and algorithms change — maybe concepts like transactional memory need to be introduced ? Should OS change — talk much more about virtualization, and redoing virtual memory when ample NVRAM is available and accessible from a core ?

Next Monday (3:00pm, May 13), Fabrizio Petrini will visit and give a presentation on Streaming Applications on the Cell B.E. Processor. Here’s the abstract:

“We increasingly need to process large and complex data volumes to enable near-real-time informed human decisions or automated response actions. Current limitations in I/O and processing capabilities hinder the timely acquisition, processing, and presentation information to decision makers for rapid response. Multi-core processors, such as the Cell B.E. processor, provide an unprecedented computational capability to curb this data deluge. In this talk I will describe the challenge in designing new data streaming algorithms for multi-core processors and and present some recent results obtained with the Cell B.E. processor.”

David Chapman will defend his MS thesis, A General Algorithm for Gridding Earth Sensing Scanning Instruments, at 10:00am Monday May 5 in room 325 ITE. The abstract is below.

Gridding in remote sensing must re-project observations from their original coordinate system based on satellite orbit and attitude to a grid defined by Earth coordinates. Primitive methods assume that observations are located at points on Earth and typically average observations in grid cells, or interpolate geolocated observations. These approaches are inaccurate, because they do not make use of the instrument’s footprint geometry, and spatial response. Observation Coverage (Obscov) gridding techniques make use of the satellite optics and geometry to more accurately describe coverage of a footprint on within each grid cell. Obscov gridding provides significant accuracy improvements exceeding 1 Kelvin Brightness Temperature over most regions on Earth for a 12 micron window channel on-board the Atmospheric Infrared Sounder (AIRS). Existing Obscov algorithms are only applicable to specific instruments and depend heavily on implicitly defined spatial response functions. We make use of raycasting and adaptive grid numerical integration to compute Obscov for the spatial response function of any instrument while processing streaming satellite observation data faster than 400 Megabits/second on a 6 machine cluster. We discuss the quality benefits of our algorithm by analyzing the results of gridded AIRS infrared sensor data with 324 operational spectral channels. We also address parallel processing issues to integrate AIRS Obscov gridding with SOAR, an on demand climate processing system built on a 122 processor blade server.