Hi,
just FYI..
I uploaded a paper of http://accc.riken.jp/maho/slides/mpack-0.6.4.pdf (sorry
in Japanese)
thanks
-- Nakata Maho http://accc.riken.jp/maho/ , JA OOO http://ja.openoffice.org/
http://blog.goo.ne.jp/nakatamaho/ ,GPG: http://accc.riken.jp/maho/maho.pgp.txt
--
To post to this group
Hi Bill again (sorry)
With 0.6.5, you can easily benchmark by just building and installing.
you'll find benchmarks in ${PREFIX}/share/mpack/bench/
in my case,
Raxpy.dd Raxpy.dd_ref ...
Thanks
Subject: [sage-devel] Re: multiprecision linear algebra
Date: Sat, 22 May 2010 00:04:26 -0700
Hi Bill
DD 136Mflops (250MFlops)
means that 250MFlops using OpenMP parallelism.
Note that above results are using 0.6.4. It would be bit different
using 0.6.5.
Also seems to depend which compiler you use.
thanks
On 5月22日, 午後3:58, Maho NAKATA wrote:
> Hi Bill
> thanks for your comments
>
> On
Hi Bill,
Currently usable MLAPACK routines are only 90 among total about 660.
Just fortran to C conversion is completed.
Purpose of MPACK
I'd like to provide reference build. based on that others can provide
faster implementations like GotoBLAS, ATLAS, intel MKL etc.
For Benchmark issue...
There
Hi Bill,
Of course, I'd like to provide MScaLAPACK etc.
Thanks,
On 5月22日, 午前12:09, Bill Hart wrote:
> For comparison, I just had a look at the MPLAPACK author's previous
> project:
>
> http://sdpa.indsys.chuo-u.ac.jp/sdpa/
>
> I *barely* know anything about this stuff - once did a basic course
Hi Bill
thanks for your comments
On 5月21日, 午後10:56, Bill Hart wrote:
> I just took a look at their website:
>
> http://mplapack.sourceforge.net/
>
> * I'm personally confused about the licensing (may be a reflection on
> me, not mplapack). The MBLAS part is BSD, but the MPLAPACK part is
> LGPL v3
Hi Jason
I'm Nakta, Maho, a principal developer of MPACK.
I've never used ALGLIB before...
thanks,
On 5月21日, 午前8:48, Jason Grout wrote:
> A while ago someone talked about incorporating ALGLIB into Sage to
> provide, among other things, multiprecision linear algebra. I just saw
> another packa
For comparison, I just had a look at the MPLAPACK author's previous
project:
http://sdpa.indsys.chuo-u.ac.jp/sdpa/
I *barely* know anything about this stuff - once did a basic course on
this sort of thing as an undergrad.
However, SDPA might be an indication of what to expect from the same
autho
On 05/21/2010 08:56 AM, Bill Hart wrote:
I became acquainted with ALGLIB and Sergey through his interaction
with the MPIR project. Even if at some point mplapack is better than
ALGLIB, I reckon Sergey would be exceptionally helpful in addressing
that. He's a smart guy and very supportive of what
Ah, I missed that. Thanks for the clarification!
On 21 May, 14:46, Fredrik Johansson
wrote:
> On Fri, May 21, 2010 at 3:26 PM, Bill Hart wrote:
>
> > Oh my, I never noticed this! I'd been looking for mpfr_addmul in line
> > with GMP!! I see it is slightly different in that it doesn't do a = a
> >
I just took a look at their website:
http://mplapack.sourceforge.net/
* I'm personally confused about the licensing (may be a reflection on
me, not mplapack). The MBLAS part is BSD, but the MPLAPACK part is
LGPL v3+, but the authors say they are going to replace this later.
But with what? They li
On Fri, May 21, 2010 at 3:26 PM, Bill Hart wrote:
> Oh my, I never noticed this! I'd been looking for mpfr_addmul in line
> with GMP!! I see it is slightly different in that it doesn't do a = a
> + b*c.
>
> I can actually speed some code up with this!!
>
> Bill.
>
> Nice. Indeed, I specified the f
On 21 May, 07:36, Sergey Bochkanov
wrote:
> Hello, Jason.
>
> You wrote 21 мая 2010 г., 3:48:03:
>
> > A while ago someone talked about incorporating ALGLIB into Sage to
> > provide, among other things, multiprecision linear algebra.
>
> It was me :) I am working on this issue. I expect th
Oh my, I never noticed this! I'd been looking for mpfr_addmul in line
with GMP!! I see it is slightly different in that it doesn't do a = a
+ b*c.
I can actually speed some code up with this!!
Bill.
On 21 May, 10:39, Fredrik Johansson
wrote:
> On Fri, May 21, 2010 at 11:17 AM, Sergey Bochkanov
14 matches
Mail list logo
