NSA Spy Machine and DES

[Ian Farquhar]

On Aug 18,  4:41pm, Peter Wayner wrote:
> But let's give the NSA/SRC some credit. These new SIMD processors are
probably
> smarter. Let's say that they're  64 bit wide RISC machines which can only
> access their own local on chip memory. If they can run 2 times faster (100
> MHz) and do DES encryption in 1000 cycles, then this means that the brute
> force attack on DES could be done in 4 days. Bam.

Actually, I would be surprised if the "SIMD" processors were not a huge
array of reprogrammable FPGA's, quite possibly Xilinx's.  The possibilities
of a large array of these chips, each with local memory, is quite
interesting.  I have personally seen an array of 64 Xilinx chips in a DEC PeRL
box doing RSA, at speeds similar or better to almost all available custom
hardware implementations of the cipher.

BTW, with a purchase of half a million chips, economies of scale would get
the devices well within budget.

						Ian.