You are here: home | sciGPGPU | 1.1

sciGPGPU

Gpu Computing for Scilab

(3736 downloads for this version - 20741 downloads for all versions)

Details

Version

1.1
A more recent valid version with binaries for Scilab exists: 1.2

Authors

Cedric Delamarre

Vincent LEJEUNE, Allan CORNET, Cedric DELAMARRE

Owner Organization

Consortium Scilab

Maintainer

C?dric DELAMARRE

Categories

Linear algebra

Numerical Maths

Website

http://forge.scilab.org/index.php/p/sciCuda/

License

CeCILL

Creation Date

January 25, 2012

Source created on

No source archive has been provided for this toolbox version.

Binaries available on

Scilab 5.3.x:

Linux 64-bit

Windows 64-bit

Linux 32-bit

Windows 32-bit

Install command

--> atomsInstall("sciGPGPU")

Report a bug

GitLab's issues for sciGPGPU

Description

            This toolbox provides a gpu computing capabilities at Scilab. 
It uses an implementation of BLAS (cuBLAS) and FFT (cuFFT) through gpuAdd,
gpuMult, gpuFFT and other functions.
This toolbox uses essentially Cuda but some functions, as gpuBuild, have been
created for build and use kernels developed with OpenCL or Cuda.

link to sources : http://forge.scilab.org/index.php/p/sciCuda/

/****** Warning ******/
This version of toolbox don't work with cuda toolkit 4.1

Files (4)

[7.05 MB]

sciGPGPU_1.1.bin.x64.linux.tar.gz

Linux 64-bit binary for Scilab 5.3.x

Upload date : 2012-01-25 15:51:10
MD5         : 4a0b851a9a244e48c0d25f3133b4f10b
SHA1        : fe36c84c314cd51a8b91f168b0d2c255d3875456
Downloads   : 1213
 File list

[30.04 MB]

sciGPGPU_1.1.bin.x64.windows.zip

Windows 64-bit binary for Scilab 5.3.x

Upload date : 2012-01-25 15:51:53
MD5         : 9aa9d8a6298e6786f5719abc99e61e03
SHA1        : 9169b772309ff6dd3ff584c7d9099398d346ee0b
Downloads   : 889
 File list

[6.73 MB]

sciGPGPU_1.1.bin.x86.linux.tar.gz

Linux 32-bit binary for Scilab 5.3.x

Upload date : 2012-01-25 15:51:33
MD5         : 42ca779eea13e5857041000f4a7ffa1e
SHA1        : 29802ab3e78adc7ba607a9e42fe6efc63d9f3798
Downloads   : 904
 File list

[30.15 MB]

sciGPGPU_1.1.bin.x86.windows.zip

Windows 32-bit binary for Scilab 5.3.x

Upload date : 2012-01-25 15:52:26
MD5         : 060ec7b20c3ea98a1f9256d3cdfe4520
SHA1        : 96731c58590505d2884e296993c67ac1d6f9a297
Downloads   : 730
 File list

News (0)

Comments (3) ↑ Leave a comment

Comment from Ronadlo de Abreu -- March 12, 2012, 05:51:14 PM

Hi Cédric, 
my name is Ronaldo de Abreu and I tried to install the sciGPGPU in my personal workstation
computer, but I was unsuccessfull.
My computer has 2 GeForce GTX 560 Ti Graphic Cards, which has a 2.1 Nvidia Compute
Capability. I don't know if there is a incompatibility of sciGPGPU with non professional
graphic cards, so if there it is maybe it could be posted in the initial remarks of the
project.
However, all developer devices are installed but when I type the commmand
atomsInstall('sciGPGPU') the installation seems to be right. The result is 
ans  =
 
!sciGPGPU  1.1-0  allusers  SCI/contrib/sciGPGPU/1.1-0  I  !

 But when I quit Scilab and try to launch the environment again it freezes. It gives the
messages:
 
Execução de iniciação:
  carregando o ambiente inicial

Start sciGPGPU
	Load macros
	Load help
Arquivo compartilhado carregado.
Link feito.
Arquivo compartilhado carregado.
Link feito.

Which could be translate to English as
 
Starting Execution:
  loading initial environment

Start sciGPGPU
	Load macros
	Load help
Shared File Loaded.
Link done.
Shared File Loaded.
Link done.


As I couldn't compile from source as well, which it can't find the script help_loader.sce,
I decided to write it as a comment and ask for help.

Thank you for the initiative.

Answer from Cédric DELAMARRE -- March 13, 2012, 01:05:38 PM

Hi Ronaldo,

Your GPU is not the problem (I have the same), but try to downgrade to the cuda toolkit
4.0 and reinstall the toolbox with atomsInstall.

For the help_loader problem, I have upload a new sources package which should resolve
that.

If you have any problems, don't hesitate.
In your futur posts, please indicate me your OS (64/32 bits), the Scilab version, the Cuda
version and the toolbox version.

Thanks for your post,
Cédric

Answer from Ronadlo de Abreu -- March 14, 2012, 04:13:15 PM

This answer has been deleted.

Answer from Ronadlo de Abreu -- March 14, 2012, 04:13:47 PM

Hi Cédric,

I am sorry for the laziness on my post. Well to retify the information, I am under a
OpenSUSE 12.1 64-bit Linux using Scilab 5.3.3 that I just downloaded from the site.

I followed the instructions you posted with the atomsInstall, but I still have the same
result.
I installed the cudatoolkit 4.0.17 just recently downloaded from Nvidia's website, erased
the previous installation and reinstalled the toolkit.

I did not rebooted the machine once the device drivers where alread installed, and I did
not preformed a second installation.

The Messages and the problems, unfurtunate, remain.

Well, thank you for the help.

Ronaldo.

Comment from Cédric DELAMARRE -- March 13, 2012, 12:23:33 PM

This comment has been deleted.

Comment from Ronadlo de Abreu -- March 14, 2012, 04:12:06 PM

This comment has been deleted.