A better way to do embedded Floating point?

Has anybody come across a company called Clearspeed Technology?

formatting link

Apparently they are about to do a press release next week announcing a

50Gflop/s massively parallel co-processor, you can program it in standard C. Its being delivered on a 100Gflop/sec PCI-X boardset that dissipates less than 25watts, which is extraordinary when you consider that your typical x86 is in the 100watt region for the processor alone.

Worth checking out if anybody is seriously considering using an FPGA to accelerate their floating point application. Just imagine what you could do with this, fill up a 6 slot PC with these cards and you have a do it yourself supercomputer, a few of these could probably take you into the Top500 supercomputer list.


Reply to
David Smith
Loading thread data ...

X-Original-Trace: 30 Sep 2004 14:52:36 GMT, koo.clearspeed.com

Apparently you have.

Has anyone come across a stupid f**k trying to advertise his product by spamming fake questions on usenet?

Apparently I have.

Reply to

ElectronDepot website is not affiliated with any of the manufacturers or service providers discussed here. All logos and trade names are the property of their respective owners.