[sage-devel] Re: parallel computation

2008-05-21 Thread Mikael Vejdemo Johansson
On May 20, 10:00 pm, "William Stein" <[EMAIL PROTECTED]> wrote: > On Tue, May 20, 2008 at 12:43 PM, Mark V <[EMAIL PROTECTED]> wrote: > > - shipping MPI itself (a dependency) would significantly complicate > > Sage so use of MPI packages is currently optional. > > True. Also there has been no dem

[sage-devel] Re: parallel computation

2008-05-20 Thread Mark V
Hi Brian, Thanks for reading and responding to my comments. On Wed, May 21, 2008 at 8:11 AM, Brian Granger <[EMAIL PROTECTED]> wrote: >> IPython1 is a Python library that Sage ships that builds on MPI. >> Maybe Fernando or Brian (who I've just cc'd) can comment. >> We also build on Twisted, which

[sage-devel] Re: parallel computation

2008-05-20 Thread Brian Granger
> IPython1 is a Python library that Sage ships that builds on MPI. > Maybe Fernando or Brian (who I've just cc'd) can comment. > We also build on Twisted, which is somewhat relevant for > certain types of problems.. A few comments along these lines: - mpi these days is actually really easy to bu

[sage-devel] Re: parallel computation

2008-05-20 Thread William Stein
On Tue, May 20, 2008 at 12:43 PM, Mark V <[EMAIL PROTECTED]> wrote: > Hi Devs, > > I suppose the issues below could be described as related to the question: > Is SAGE being written as a desktop application, or being written as a > grid/cloud application? Sage should be both. > From what I've gle

[sage-devel] Re: parallel computation

2008-05-20 Thread Mark V
On Tue, May 20, 2008 at 3:48 PM, Mark V <[EMAIL PROTECTED]> wrote: > Hi William, > Thanks for taking time to respond so promptly. > > On Tue, May 20, 2008 at 1:17 PM, William Stein <[EMAIL PROTECTED]> wrote: >> On Mon, May 19, 2008 at 6:57 PM, MarkV <[EMAIL PROTECTED]> wrote: >>> Q1) Is the focus

[sage-devel] Re: parallel computation

2008-05-19 Thread Mark V
Hi William, Thanks for taking time to respond so promptly. On Tue, May 20, 2008 at 1:17 PM, William Stein <[EMAIL PROTECTED]> wrote: > On Mon, May 19, 2008 at 6:57 PM, MarkV <[EMAIL PROTECTED]> wrote: >> Q1) Is the focus on performing symbolic calculations in parallel, or >> are numerically orien

[sage-devel] Re: parallel computation

2008-05-19 Thread William Stein
On Mon, May 19, 2008 at 6:57 PM, MarkV <[EMAIL PROTECTED]> wrote: > Q1) Is the focus on performing symbolic calculations in parallel, or > are numerically oriented calculations currently being considered? Both are equally important and relevant to Sage. >> Yes. But this won't happen on a grand

[sage-devel] Re: parallel computation

2008-05-19 Thread MarkV
Hi Devs, Firstly thanks for making the effort to get SAGE this far. At the moment I'm a MMA user tracking its progress, and have some 'user-level' questions about SAGE's development, specifically related to parallel calculations. I'll also indulge in some observations that may be a little off-top

[sage-devel] Re: parallel computation

2007-02-07 Thread Brian Granger
> > Here are some questions that I would love to see answered: > > * OpenMP vs MPI: which one would be better for SAGE and why? > > * Is there a clear winner in the python world for parallel > > applications? googling for either "open mp python" or "mpi python" > > shows several modules. mpi4py h

[sage-devel] Re: parallel computation

2007-02-07 Thread Martin Albrecht
On Wednesday 07 February 2007 19:47, Yi Qiang wrote: > On Feb 7, 2007, at 12:40 AM, Joshua Kantor wrote: > > I assume that yi will talk about distributed > > sage > > Yes I plan on giving a talk. Hopefully there are still time slots > available either on Saturday or Sunday, does anyone know wher

[sage-devel] Re: parallel computation

2007-02-07 Thread Iftikhar Burhanuddin
On Wed, 7 Feb 2007, Yi Qiang wrote: > Yes I plan on giving a talk. Hopefully there are still time slots > available either on Saturday or Sunday, does anyone know where to > sign up for presentation time? I did not find anything in the wiki. Yi, your talk has been slotted over the weekend. You

[sage-devel] Re: parallel computation

2007-02-07 Thread Yi Qiang
On Feb 7, 2007, at 12:40 AM, Joshua Kantor wrote: > I assume that yi will talk about distributed > sage Yes I plan on giving a talk. Hopefully there are still time slots available either on Saturday or Sunday, does anyone know where to sign up for presentation time? I did not find anythin

[sage-devel] Re: parallel computation

2007-02-07 Thread William Stein
On Wed, 07 Feb 2007 18:07:32 -0700, didier deshommes <[EMAIL PROTECTED]> wrote: > > On 2/2/07, David Harvey <[EMAIL PROTECTED]> wrote: >> >> Hi everyone, >> >> It would be good if someone who was at the parallel computing workshop >> could volunteer to give a talk about parallelism issues at SAGE

[sage-devel] Re: parallel computation

2007-02-07 Thread didier deshommes
On 2/2/07, David Harvey <[EMAIL PROTECTED]> wrote: > > Hi everyone, > > It would be good if someone who was at the parallel computing workshop > could volunteer to give a talk about parallelism issues at SAGE Days 3, > as they might relate to SAGE. I'm sure some of the other SAGE > developers woul

[sage-devel] Re: parallel computation

2007-02-07 Thread Brian Granger
Hi, I had a great time at the MSRI workshop last week. We were able to get lots of stuff done on IPython and it was great meeting and talking with all the SAGE folks. Thanks for including us in the meeting! I should mention that I will be giving two talks about IPython at PyCon in late Feb. W

[sage-devel] Re: parallel computation

2007-02-07 Thread Joshua Kantor
I was planning on talking and hadn't decided what I was talking about. I would be willing to do this unless somewhat else wants to. I assume that yi will talk about distributed sage so I would mostly focus on chainsaw and threading issues. Jos On Feb 2, 2:36 pm, David Harvey <[EMAIL PROTECTED]

[sage-devel] Re: parallel computation

2007-02-02 Thread Martin Albrecht
On Friday 02 February 2007 14:36, David Harvey wrote: > Hi everyone, > > It would be good if someone who was at the parallel computing workshop > could volunteer to give a talk about parallelism issues at SAGE Days 3, > as they might relate to SAGE. I'm sure some of the other SAGE > developers wou