Documenting the Coming Singularity

Tuesday, July 03, 2007

Huge Leaps Forward for Computing Power

The public is largely ignorant about developments in technology. Until, that is, they can buy it and take it home. But some people, like me, want to know what will be coming to our living rooms and offices before we can add it to our credit card balance. Why? Is it just so we can salivate as we imagine using it? No. It is so we can prepare ourselves, mentally and culturally, to make best use of it when it becomes available. Technological advances have become like a gathering ocean wave that we are furiously paddling to keep up with so that we can ride it.

A few quiet announcements are worth reading about along these lines...

Sun's Constellation System - The world's first petascale computing environment.
June 26, 2007 -- It was a mere decade ago that terascale computing took hold in science and engineering communities, giving researchers the tools to break new ground in physics, biomedicine, astronomy, and other areas. Now, Sun is ushering in a new era of high performance computing (HPC) with the Sun Constellation System, the world's first petascale computing environment.

Sun's unique approach to petascale computing combines state-of-the-art technology with system level innovation and off-the-shelf components in an open architecture. The result is a powerful HPC platform that is extremely powerful, easier to manage, and very cost efficient. A technology preview is being announced today; the shipping version will be available early next year.

NVIDIA's Tesla Architecture
  • Massively-parallel computing architecture with 128 multi-threaded processors per GPU
  • Scalar thread processor with full integer and floating point operations
  • Thread Execution Manager enables thousands of concurrent threads per GPU
  • Parallel Data Cache enables processors to collaborate on shared information at local cache performance
  • Ultra-fast memory access with 76.8 GB/sec. peak bandwidth per GPU
  • IEEE 754 single-precision floating point
  • Scalable from one to thousands of GPUs
  • Available in GPU computing processor, deskside supercomputer and 1U rack-mount GPU computing server
Uzi Vishkin's Desktop Supercomputer
A prototype of what may be the next generation of personal computers has been developed by researchers in the University of Maryland's A. James Clark School of Engineering. Capable of computing speeds 100 times faster than current desktops, the technology is based on parallel processing on a single chip.

Parallel processing is an approach that allows the computer to perform many different tasks simultaneously, a sharp contrast to the serial approach employed by conventional desktop computers. The prototype developed by Uzi Vishkin and his Clark School colleagues uses a circuit board about the size of a license plate on which they have mounted 64 parallel processors. To control those processors, they have developed the crucial parallel computer organization that allows the processors to work together and make programming practical and simple for software developers.
These developments are coming faster and faster, so stay tuned.

Singularity & The Price of Rice is updated daily; the easiest way to get your daily dose is by subscribing to our news feed. Stay on top of all our updates by subscribing now via RSS or Email.