On Oct 9, 1:35 am, jmakov <[EMAIL PROTECTED]> wrote:
> Hi,
>
Hello,
> I understand that your primary concern is to implement as much
> functionality as possible into Sage, but I`m wondering how much of the
> algorithms are able to use multicore/multiprocessor systems. It`s
> obvious that some algorithms could run few times faster without much
> of mathematical research. Also I understand that GPUs are wastly
> faster for some operations than CPUs
Those operations are mostly single precision and there are limits to
the systems you can solve due to memory constraints, but with AMD's
new architecure coming in a year or so these limitations will be done.
Intel also has some very interesting multicore designs, but those are
lap prototypes for now.
> and some months ago an arbitrary
> precision library for GPUs appeared.
>
Can you give me a pointer? I have never seen or heard of one of those.
> Would it be wise to consider GPU implementations of certain algorithms
> or parallelize them instead of finding computational less demanding
> method?
Cheers,
Michael
--~--~---------~--~----~------------~-------~--~----~
To post to this group, send email to [email protected]
To unsubscribe from this group, send email to [EMAIL PROTECTED]
For more options, visit this group at http://groups.google.com/group/sage-forum
URLs: http://sage.math.washington.edu/sage/ and http://sage.scipy.org/sage/
-~----------~----~----~----~------~----~------~--~---
