John R Pierce <[EMAIL PROTECTED]> (Hi, John!) writes:

>interesting... Picked off a email newsletter on microprocessor design...
>This thing sounds like it could *smoke* through Lucas-Lehmer FFT's...
>
>*** Intrinsity Arrays 2GHz Adaptive Matrix ***

(rest snipped)

Man, who comes up with these stupid soundalike Silicon Valley
Tech Company names? Is this some popular Java Applet CEOs
are using, which combines various techy-sounding word fragments to
generate the most silly-sounding possible name for their company?
(Thankfully, the SiVal company I work for, Leopard Logic, appears to
have no immediate plans to change their name to "Leopardicity" or
"Leopardalis". :)

But, to get back to the real topic, I checked out Intrinsificitienceality's
supercalafragalistic website, and unless I'm misreading something, it's
all 32-bit fixed-point arithmetic - very fast, and also completely useless for
LL testing large exponents. We need fast double-precision floating-point
(or even fixed-point, but *something* on the order of 64 bits) for that.
Unfortunately, there's not a very large market demand for cellphones
and wireless equipment that can do fast high-precision arithmetic.

-Ernst

Reply via email to