Toshiba to demonstrate prototype of new 'SpursEngine' processor

Toshiba to demonstrate prototype of new 'SpursEngine' processor

quote from the article:

"Notebook PCs integrating SpursEngine will be used in the world's first public demonstration of the processor's capabilities in 3D image processing and manipulation: real-time transformations of hair styles and makeup that instantaneously recognize and process changes in position, angle, and facial expression, and render them as computer graphics....SpursEngine, a co-processor that works in cooperation with a host CPU, fuses Cell/B.E.'s high performance multi-core technology with Toshiba's advanced image processing technology to perform stream processing of video sources--image recognition and processing--at the increasingly sophisticated level required by new generations of digital consumer products."

What interests me about these this article is not the SpursEngine, the new Toshiba chip, but the fact that it is integrated with the Cell/B.E.---the same chip that is at the core of the PlayStation 3.

While there may be other examples, this is the first example I know of the the revolutionary Cell/B.E. that is the core of the Sony PlayStation 3 being utilized for another (non-PlayStation) application. This powerful computer chip---jointly developed by IBM, Sony Group and Toshiba---was initially developed for the PlayStation 3 but the idea was that would be utilized for other applications as well.

This is an incredibly powerful chip that in some ways is analogous to a supercomputer (if I remember correctly). However, utilizing the full power is quite difficult and, as far as I know, no game maker has yet come close to doing so. As I recall, there are nine cells in the core of the chip. Each cell is somewhat akin to a separate microprocessor. What gives the system so much power potentially is the fact that each cell utilizes its own separate memory.

Unfortunately, this is also what makes the chip so incredibly difficult to program. The chip can be used in an easier, more conventional programming fashion without utilizing this great power, but then the results end up being somewhat mediocre. Mediocre is the description of all of the games made for PlayStation 3 so far ,and the reason is the failure of any group of programmers to fully utilize the power of the Cell/B.E..

However, it looks like a breakthrough has occurred in the utilization of the Cell/B.E. Although the Toshiba product does not utilize all the cells, it utilizes four of them according to this news story. The key question in regards to PlayStation 3 would be whether Toshiba would share with Sony the programming expertise it developed during the course of this project. If they did so, Sony would then share the expertise with all potential game makers. My understanding is that this means they would essentially make the knowledge public. Whether Toshiba would do this or not I do not know.