Re: JavaMemoryModel: A memory model for the masses

From: David F. Bacon (dfb@watson.ibm.com)
Date: Wed Nov 10 1999 - 09:23:51 EST


> These are just demos and benchmarks, but I invite you to try out the
> taskDemo programs in my util.concurrent, and compare them to versions
> in Cilk and Hood (C and C++ respectively -- see the URLs in
> util.concurerrent to find them). Unfortunately, I believe that Cilk
> and Hood are only available for sparcs and linux-intel.

i gave away my sparcstation a year or so ago, but we do speak linux here (it's
even supported!). i'll see about getting an intel MP box, and maybe play with
these programs during the slack period in december.

one area that i neglected to mentioned in my last note where java does have a
potential performance advantage: user-level threads. on a heavily
multiprogrammed system, a java app running on top of user-level threads should
be able to significantly out-perform a similar app in C/C++ on top of posix
threads. of course, once you use JNI extensively, all bets are off....

david
-------------------------------
JavaMemoryModel mailing list - http://www.cs.umd.edu/~pugh/java/memoryModel



This archive was generated by hypermail 2b29 : Thu Oct 13 2005 - 07:00:22 EDT