Groups   102 of 99+      julia-users › ArrayFire-jl - GPU Programming in Julia 17 posts by 14 authors      ran... juliacomputing.com    Jun 10   Hello,   We are pleased to announce ArrayFire-jl, a library for GPU and heterogeneous computing in Julia:  https:  github.com JuliaComputing ArrayFire-jl . We look forward to your feedback and your contributions as well!   For more information, check out Julia Computing's latest blog post: http:  juliacomputing.com blog 2016 06 09 julia-gpu.html  Thanks, Ranjan Julia Computing, Inc.      Fred    Jun 10   Hi !  Thank you for this great package ! I tried to install it on Julia 0.4.5 but I obtained :  julia                 _    _       _ _ _ _     |  A fresh approach to technical computing    _      |  _   _     |  Documentation: http:  docs.julialang.org    _ _   _| |_  __ _   |  Type  ?help  for help.   | | | | | | |  _` |  |   | | |_| | | |  _| |  |  Version 0.4.5  2016-03-18 00:58 UTC   _  |\__'_|_|_|\__'_|  |  Official http:  julialang.org release |__                    |  x86_64-linux-gnu   julia  using ArrayFire ERROR: LoadError: LoadError: could not load library  libaf  libaf: Ne peut ouvrir le fichier d'objet partagé: Aucun fichier ou dossier de ce type  in dlopen at . libdl-jl:36  in dlopen at libdl-jl:36  in include at . boot-jl:261  in include_from_node1 at . loading-jl:320  in include at . boot-jl:261  in include_from_node1 at . loading-jl:320  in require at . loading-jl:259 while loading  home fred .julia v0.4 ArrayFire src config-jl, in expression starting on line 6 while loading  home fred .julia v0.4 ArrayFire src ArrayFire-jl, in expression starting on line 5        Mauro    Jun 10  Re:  julia-users  Re: ArrayFire-jl - GPU Programming in Julia  You need to install the arrayfire library by hand:  https:  github.com JuliaComputing ArrayFire-jl installation   If done already, check the trouble shooting section.       Robert Feldt    Jun 10  Re:  julia-users  Re: ArrayFire-jl - GPU Programming in Julia  Thanks, this looks really nice.   I seem to be able to install it ok but when trying to run on a fairly recent MacBook Pro  Retina, 13-inch, Early 2015  I get an error when trying this on julia Version 0.4.5  2016-03-18 00:58 UTC  x86_64-apple-darwin15.4.0:  julia  using ArrayFire  julia   Random number generation        a   rand AFArray Float64 , 100, 100  ERROR:  ArrayFire Error  401  : Double precision not supported for this device   in af_randu at  Users feldt .julia v0.4 ArrayFire src wrap-jl:1033  in rand at  Users feldt .julia v0.4 ArrayFire src create-jl:7  Maybe update the docs to make the requirements and limitations more clear? Or is there a way around this?  My computer version details: Processor: 3,1 GHz Intel Core i7  Memory: 16 GB 1867 MHz DDR3  Graphics: Intel Iris Graphics 6100 1536 MB  OS: El Capitan, 10.11.3  15D21   Thanks,  Robert Feldt      Mauro    Jun 10  Re:  julia-users  Re: ArrayFire-jl - GPU Programming in Julia    On Fri, 2016-06-10 at 16:14, Robert Feldt  robert... gmail.com  wrote:    Thanks, this looks really nice.       I seem to be able to install it ok but when trying to run on a fairly    recent MacBook Pro  Retina, 13-inch, Early 2015  I get an error when trying    this on julia Version 0.4.5  2016-03-18 00:58 UTC     x86_64-apple-darwin15.4.0:       julia  using ArrayFire       julia   Random number generation           a   rand AFArray Float64 , 100, 100    a   rand AFArray Float32 , 100, 100    Most graphic cards only support 32 bit floats.     ERROR:  ArrayFire Error  401  : Double precision not supported for this    device      in af_randu at  Users feldt .julia v0.4 ArrayFire src wrap-jl:1033     in rand at  Users feldt .julia v0.4 ArrayFire src create-jl:7       Maybe update the docs to make the requirements and limitations more clear?    Or is there a way around this?       My computer version details:       Processor: 3,1 GHz Intel Core i7       Memory: 16 GB 1867 MHz DDR3       Graphics: Intel Iris Graphics 6100 1536 MB    OS: El Capitan, 10.11.3  15D21        Thanks,       Robert Feldt       Den fredag 10 juni 2016 kl. 12:19:16 UTC+2 skrev Mauro:         You need to install the arrayfire library by hand:     https:  github.com JuliaComputing ArrayFire-jl installation         If done already, check the trouble shooting section.         On Fri, 2016-06-10 at 12:10, Fred  fred.so... gmail.com  javascript:         Robert Feldt    Jun 10  Re:  julia-users  Re: ArrayFire-jl - GPU Programming in Julia  Great thanks. I suggest a comment about this or changing the example in the README so it's more clear to people like me... ;    Robert      Keno Fischer    Jun 10  Re:  julia-users  Re: ArrayFire-jl - GPU Programming in Julia  Some computers have more than one graphics card and the more powerful one needs to be activated manually. I know that's the case on my macbook.      Gabriel Goh    Jun 10   is there windows support? I have a pretty beefy gaming PC      David Anthoff    Jun 10  RE:  julia-users  Re: ArrayFire-jl - GPU Programming in Julia  https:  github.com JuliaComputing ArrayFire-jl issues 40        From: julia... googlegroups.com  mailto:julia... googlegroups.com  On Behalf Of Gabriel Goh Sent: Friday, June 10, 2016 3:00 PM To: julia-users  julia... googlegroups.com  Subject:  julia-users  Re: ArrayFire-jl - GPU Programming in Julia       Ranjan Anantharaman    Jun 11   Hey, I'm also giving a talk on ArrayFire-jl at JuliaCon 2016 too: http:  juliacon.org abstracts.html ArrayFire. See how ArrayFire-jl is useful in accelerating your code!  Thanks, Ranjan      Andrew    Jun 11   I have very little knowledge of GPU computing. Is it possible to use the GPU for not just simple matrix operations, but for arbitrary functions? I think I'm looking here for a GPU pmap f, A , where f is a function I've defined and A is some array with a few thousand elements.      Simon Danisch    Jun 11   That would need the capability of compiling arbitrary Julia functions for the GPU. If you remove the arbitrary  no allocations, no exceptions, no IO  and are confident with trying out prototypes, this already exists for NVidia GPU's: https:  github.com JuliaGPU CUDAnative-jl If you only have a couple of thousand elements, it might be that you won't profit much from the GPU, though ;       Kaj Wiik    Jun 20    For anyone trying to get things working in Ubuntu  Xenial  environment...  I could not get ArrayFire-jl working with the binary libraries, compiling from source was quite easy and everything works now fine.      Deniz Yuret    Aug 25   Thanks for this great package Ranjan.  I'd like to contribute to the development -- in particular integration with CUDNN, CUSPARSE, etc. under the JuliaGPU ecosystem, if others have not started doing so already.  With CUDNN, for example, I wrapped the low level library code to use CudaArrays, then implemented a high level interface.  Do you see a problem using AFArrays in the same way using kernels from other libraries or custom kernels?  Also I am not sure about the right place for this cross library support: should it go under ArrayFire-jl or CUDNN-jl?  best, deniz      Min-Woong Sohn    Aug 26   Does anybody know of any plan to support ArrayFire in GLM or MixedModels any time soon?      Douglas Bates    Aug 27   On Friday, August 26, 2016 at 6:08:13 PM UTC-5, Min-Woong Sohn wrote: Does anybody know of any plan to support ArrayFire in GLM or MixedModels any time soon?  Do you have a particular application in mind or is this a general question?  For MixedModels I would say that, depending upon the configuration of the random-effects terms in a model there could be a great advantage or almost no advantage in using a GPU, so details are important.  We're always looking for challenging GLM or mixed-effects problems that can be used to tune up these packages.  If you have cases that seem to be taking a long time and would be suitable for parallel or GPU computing we would love to hear about them.    On Friday, June 10, 2016 at 1:08:42 AM UTC-4, ran... juliacomputing.com wrote: Hello,   We are pleased to announce ArrayFire-jl, a library for GPU and heterogeneous computing in Julia:  https:  github.com JuliaComputing ArrayFire-jl . We look forward to your feedback and your contributions as well!   For more information, check out Julia Computing's latest blog post: http:  juliacomputing.com blog 2016 06 09 julia-gpu.html  Thanks, Ranjan Julia Computing, Inc.      Min-Woong Sohn    Aug 28   No, I don't have any particular application in mind right now, but in general I always found that mixed effects models take a long time to run on large data sets.