[Date Index] [Thread Index] [Author Index]

Re: Illusory Multicore Support in 5.2?

• To: mathgroup at smc.vnet.net
• Subject: [mg66128] Re: Illusory Multicore Support in 5.2?
• From: "Chris Chiasson" <chris.chiasson at gmail.com>
• Date: Sun, 30 Apr 2006 04:21:48 -0400 (EDT)
• References: <200604260838.EAA02742@smc.vnet.net><e2pp8k$su2$1@smc.vnet.net> <200604270836.EAA01610@smc.vnet.net> <e2ssde$49v$1@smc.vnet.net> <e2v700$nhl$1@smc.vnet.net>
• Sender: owner-wri-mathgroup at wolfram.com

I could guess. Mathematica likes to eat up 100% cpu and hog all of the
memory for a variety of kernel inputs (like some problems where it is
inverting a large symbolic matrix, or whatever). This is not to say
that I think the problem should be solvable, but maybe that the
computer should at least remain responsive. Maybe they decided to set #
kernel threads = # processors - 1 to improve responsiveness under high
load? Like I said, a guess - from a non-expert.

• References:
  • Illusory Multicore Support in 5.2?
    • From: "Contrablue" <tetraploidhybrid@hotmail.com>
  • Re: Illusory Multicore Support in 5.2?
    • From: Antti Penttilä <Antti.I.Penttila@invalid.helsinki.fi>