Re: ratioanl number type

["Alexander E. Kopilovitch" <aek@pcaek.spb.su>]

In article <s57e138d53112@corp.supernews.com>,
  "Vladimir Olensky" <vladimir_olensky@yahoo.com> wrote:

> This technique was used for more than 20 years in Russian
> supercomputers "Elbrus". So no wonder that one of the
> leading scientists from "Elbrus" team (Pentkovsky) was invited
> to the Intel and he lead the development of SIMD extensions
> for Intel chips.

It is very astonishing to read about Elbrus as an innovation at its time. Do
you know that inside the Elbrus development team it was called "El-Burroughs"
(I can't recall exact English spelling of the name of that original computer -
Burroughs or something like) due to its source.
  Next, do you know the size of this computer? Yes, it may be called
"supercomputer" but only for the reason of its size (and its cooling system).
  And the last but not least - nobody (or almost nobody) employs this computer
as "Elbrus": it was equipped with second architecture (with another CPU) called
BESM-10 that was the old good BESM-6 implemented using new integrated logic.
And as far as I know, almost all real users of "Elbrus" (i.e. those that use it
for real computations, and not for development of operating systems and compilers
etc.) use it as BESM-10, totally avoiding all "innovations".


Alexander Kopilovitch                      aek@vib.usr.pu.ru
Saint-Petersburg
Russia