> On Apr 17, 2017, at 9:26 PM, Henry Rich <[email protected]> wrote:
>
> If you have an implementation of +/ . * on double-precision floats that's
> faster than J 8.06, I would be obliged if you'd send me a copy of the source
> code.
I'm sure your code is much faster than naive c loops. But some how the
matrix-matrix multiplication is much slower (10x) than that in julia (tested
with a 3-year old version).
% julia
_
_ _ _(_)_ | A fresh approach to technical computing
(_) | (_) (_) | Documentation: http://docs.julialang.org
_ _ _| |_ __ _ | Type "help()" to list help topics
| | | | | | |/ _` | |
| | |_| | | | (_| | | Version 0.2.1 (2014-02-11 06:30 UTC)
_/ |\__'_|_|_|\__'_| |
|__/ | x86_64-linux-gnu
julia> A=rand(4096,4096); B=rand(4096,4096);
julia> @time A*B;
elapsed time: 2.260157127 seconds (149184640 bytes allocated)
julia>
% jconsole
JVERSION
Engine: j806/j64avx/linux
Beta-3: commercial/2017-04-10T17:51:14
Library: 8.06.02
Platform: Linux 64
Installer: J806 install
InstallPath: /nfs2/xjin/pkgs/j64-806
Contact: www.jsoftware.com
'A B'=:0?@$~2,,~4096
timespacex'A+/ .*B'
23.8976 2.68437e8
timespacex'A+/ .*B'
----------------------------------------------------------------------
For information about J forums see http://www.jsoftware.com/forums.htm
