[brlcad-tracker] [ brlcad-Bugs-1565171 ] Not using dual core chip correctly on Benchmark
Open Source Solid Modeling CAD
Brought to you by:
brlcad
From: SourceForge.net <no...@so...> - 2006-10-04 02:22:00
|
Bugs item #1565171, was opened at 2006-09-25 15:39 Message generated for change (Comment added) made by brlcad You can respond by visiting: https://sourceforge.net/tracker/?func=detail&atid=640802&aid=1565171&group_id=105292 Please note that this message will contain a full copy of the comment thread, including the initial issue submission, for this request, not just the latest update. Category: Benchmark & Performance Group: performance Status: Open >Resolution: Accepted Priority: 5 Submitted By: David Lynch (daviddlynch) >Assigned to: Sean Morrison (brlcad) Summary: Not using dual core chip correctly on Benchmark Initial Comment: I have run the benchmark routine on a new Intel Core Duo on a MAC mini. I noticed that it only utilized one of the cores. In the past I have noticed that it will utilize all of the CPU's on a machine. ---------------------------------------------------------------------- >Comment By: Sean Morrison (brlcad) Date: 2006-10-04 02:22 Message: Logged In: YES user_id=785737 Yeah, this is a known issue that should be fixed in one of the upcoming releases. The issue stems from the code that detects the number of CPUs being tied to a PPC section and that instead neads to be bound to something more generic (detection of the posix sysctl() call availability). Another related issue is that if you disable a CPU with the CHUD tools, the ray-trace library doesn't perform the correct accounting. Apple had recommended and provided code for a fix for that issue, but it hasn't yet been applied and tested sufficiently yet. ---------------------------------------------------------------------- You can respond by visiting: https://sourceforge.net/tracker/?func=detail&atid=640802&aid=1565171&group_id=105292 |