Path: utzoo!mnetor!uunet!lll-winken!lll-lcc!ames!amelia!orville.nas.nasa.gov!fouts
From: fouts@orville.nas.nasa.gov (Marty Fouts)
Newsgroups: comp.arch
Subject: Task synchronization in multiprocessors?
Message-ID: <317@amelia.nas.nasa.gov>
Date: 2 Mar 88 18:41:37 GMT
Sender: news@amelia.nas.nasa.gov
Reply-To: fouts@orville.nas.nasa.gov (Marty Fouts)
Lines: 20

I've just finished Stones recent book (High Performance Computer
Architecture) which has left me wanting to know more about
architectural support for task synchronization in multiprocessors.

I'm particularly interested in production MIMD shared memory systems
and alternatives to semaphore critical region or barrier
synchronization.  A large part of the problem with using a semaphore
for synchronization is that it introduces a hot spot in the memory
system and forces some potentially parallel activities to be serial.

Stone mentions combining networks, "compare and swap", and "fetch and
add" as alternatives to a simple semaphore.  He doesn't talk about any
of the other software organizations for synchronization, such as
monitors and blocking sends, because he is discussing high granularity
numeric processes.

Does anyone care to comment on current implementations of these mechanisms,
especially comparing them?  Also, is anyone aware of any other
mechanisms in use in commercially available MIMD machines?

Marty