On Nov 29, 2008, at 07:35 , pong wrote:
> > Hi, > > I wonder if SAGE is optimized for multi-core CUPs (people told me > that many programs don't). This is not an easy question to answer. Sage is built from many components that were not specifically designed with Sage or multiprocessor issues in mind. Most programmers and algorithm designers, even today, don't think in terms of a "tight-coupled" multiprocessor implementation. Some do think of loose coupling. The distinction is the amount of information needed to be shared between the "cooperating processes". For example, Michael and a host of others worked hard to get the Sage build to take advantage of multiple processors. This was not easy, because the components come from many sources, and their build process was not designed to take advantage of these systems, but it was feasible because the different components need very little information from the other components (basically, 'make' has to know what the dependencies are, so it can find independent builds to run at the same time). The software that makes up Sage is another matter entirely. Code does not automatically work optimally on a multiprocessor system (whether multi-core or multiple single-core chips). That effort takes a lot of work. > Also, does it matter (in term of speed) > that SAGE is running on a 64-bit OS vs 32-bit? This is another very difficult question, that involves the hardware design as well as the specific algorithm being implemented. I think it's safe to say that, as a rule of thumb, utilizing 64-bit processes only helps if your algorithm needs a *lot* of memory. There is some (minor, I think) advantage in the larger size of the "int" type, but for most things that Sage does, I doubt that it counts for much. > In general, what would > have to most significant impact on the speed of running SAGE, # of > cores, OS or simply the clock-rate of the CUP? I think that the clock rate would have the most impact on today's version of Sage. Most algorithms in this area are compute intensive, and not built for multiprocessors. The OS comes into play for overall performance during a long session, where library usage, file system access, and other "ancillary" aspects increase in importance. One reason that the number of cores (or processors) becomes important for the kinds of systems that Sage runs on is "sharing": you can run one or more heavily compute-bound Sage jobs at the same time you are typesetting your thesis, surfing the web, and sending email to Dad asking for money (think "Dad == NSF") :-}. As an aside, if you run Mac OS X, you can use Activity Monitor to see what your processors are doing. Select the "floating CPU window' in the Window menu. This gives you a bar graph, one bar for each processor or core, that shows its %usage. I imagine Linux must have a similar gizmo available. HTH Justin -- Justin C. Walker, Curmudgeon at Large Institute for the Absorption of Federal Funds ----------- If it weren't for carbon-14, I wouldn't date at all. ----------- --~--~---------~--~----~------------~-------~--~----~ To post to this group, send email to sage-support@googlegroups.com To unsubscribe from this group, send email to [EMAIL PROTECTED] For more options, visit this group at http://groups.google.com/group/sage-support URLs: http://www.sagemath.org -~----------~----~----~----~------~----~------~--~---
