There's a company, DRC, that sells a high-performance FPGA board that plugs into cpu sockets on multi-cpu motherboards:
http://www.drccomputer.com/pages/products.html "DRC's flagship product is the DRC RPU that plugs directly into an open processor socket in a multi-way Opteron system. This provides direct access to DDR memory and any adjacent Opteron processor at full HyperTransport bandwidth [12.8 GBps] and ±75 nanosecond latency. The RPU then becomes a resource for the remaining Opteron processor for implementing application subroutines in hardware." There's also an article from The Register that has quotes and photos: http://www.theregister.co.uk/2006/04/21/drc_fpga_module/print.html I expect FPGAs to grow in popularity for general computing. Perhaps some day every computer will have a CPU, RAM, FPGA, and IO. Will programmers study circuit design or will they write code in high level languages that can be compiled to the FPGA? I guess that it would be much easier to compile Haskell code to a circuit than C code. What would a language look like that is specifically designed for compilation to circuits? It would surely have buffers and bit streams as elements in the language. This is so interesting. :) -Michael [EMAIL PROTECTED] http://tamale.net/ Kragen Javier Sitaker wrote: <snip>
One implication of all this free-software hardware-design stuff is that the relative advantage of including some FPGA space in a general-purpose computer is gradually increasing. If you could transform your FPU into a fast integer FFT unit for one application, and then a crypto core for another, and then JPEG compression for a third, you might be better off than just having an FPU --- even at the cost of making the FPU larger and slower.
<snip>