Prospects For the CELL Microprocessor Beyond Games
News for nerds writes "The ISSCC 2005, the "Chip Olympics", is over and David T. Wang at Real World Technologies put a very objective review of the CELL processor (the slides for the briefing are also available), covering all the aspects disclosed at the conference. Besides the much touted 256 GFlops single-precision floating point performance the CELL processor has 25-30 GFlops in double-precision, which is useful enough for scientific computation. Linus seems interested in CELL, too."
No No NO! NOOOOOO!!!!!!!!
It's way underpowered for anything resembling a primary CPU. It can't hold a candle to the x86 or the PPC chips in the desktop market. But what it can do is provide backup horsepower as a math co-processor.
But don't let that kind of blindingly obvious observation get in the way of Sony and IBM's marketing machine.
Is it compatible with x86 in anyway?
What good is a new chip, no matter how fast it is, if you can't run anything on it?
How fast will this chip be at general purpose stuff? Who cares if it can do 100GFLOPS on a couple operations.
quit hyping this thing
Also note that the Pentium 4 is built by Intel, which liberally hires H-1B engineers.
Note further that Fujitsu built the SPARC64-V. Fujitsu in Japan generally does not hire foreign engineers.
As well, note that Sun built the UltraSPARC-IV. Sun liberally hires foreign engineers.
The case and the conclusion are clear. H-1Bs are not needed for the success of a product despite the claims of both Intel and, especially, Sun. UltraSPARC-IV is a performance failure, compared to the SPARC64-V. Cell is, at least, as good as the Pentium 4, and there are indications that the Cell will run rings around the Pentium 4.