eugene@eos.UUCP (Eugene Miya) (01/05/90)
For the past 5/6 years, I have asked knowledgable people the same
basic question. Welcome to the new year! The question is:
Suppose you are teaching a 1st or 2nd year graduate class on
parallel processing (multiprocessing, use your own term).
What ten readings would you require a student to get started?
Now, the "required" and "recommended" list from my bibliography [Miya85]
have been posted and requested numerous times. DON'T send me my own list.
I am requesting intelligent/knowledgeable opinions. The point is
to keep the list current. Some papers and texts fall out of
favor. I keep past "votes." How do you know if you have "my list?"
There are two keywords: "grequired" and "grecommended" is the
%K keyword fields of the pure refer entries. As always,
annotations are appreciated and inserted into fields. SOME people
have criticized my existing list for being too conservative with
readsings from too many old machines. Well?! Suggest newer
papers. I suspect there is a degree of conservativism: an
architecture in hand is worth 4 or 5 in vapor. Finally, the
10 papers (Top-10?) or books, etc. get "required reading" keywords
and the next 100 papers/texts get "recommended" readings.
Questions? Send email. Suggestions? Send email. Forward this
note to mailing lists or news groups not mentioned in the Newsgroups line.
[Ref: Miya, ACM Comp. Arch. News, Mar. 1985]
Another gross generalization from
--eugene miya, NASA Ames Research Center, eugene@aurora.arc.nasa.gov
resident cynic at the Rock of Ages Home for Retired Hackers:
"You trust the `reply' command with all those different mailers out there?"
"If my mail does not reach you, please accept my apology."
{ncar,decwrl,hplabs,uunet}!ames!eugene