[Cryptography] Speculation considered harmful?

[John Levine]

In article <f08fcecc-1cbf-1e12-79d8-5171319faddc at echeque.com> you write:
>Single thread of execution maxed out a long time ago.
>
>We still have not figured out how to take proper advantage of multi core 
>and multi thread.

No kidding.  We were having more or less this same discussion thirty
years ago, with people saying, well, we just have to figure out how
to parallelize everything.  We're still figuring, and Amdahl's law,
which dates from 1967, still applies.

>Node.js, an interpreted Javascript language, has a good start on the 
>problem, as do the latest operating systems implementing mapreduce,

Node's programming model is not exactly new.  It's the one that the
SAGE system used on vacuum tube computers in the 1950s, reused with
great success in the early 1960s in the SABRE air reservations system
on IBM 7094s, and used ever since in transaction monitors like TPF and
CICS.

R's,
John