Questions tagged [cudalink]

Questions about using CUDALink, Mathematica's method to accelerate programs using NVidia graphics cards.

Filter by
Sorted by
Tagged with
8
votes
3answers
516 views

Mathematica 12, supported GPUs

It seems that Mathematica 12 doesn't support NVidia 2xxx (i.e 2080), 16xx or 1xxx series. Could it be that the CUDA section has not yet been rewritten for 12? https://reference.wolfram.com/language/...
0
votes
0answers
36 views

Why am I getting strange results from CUDADot?

This is what I am getting: This is what I am expecting:
2
votes
1answer
108 views

CUDA on Manjaro Linux (Arch)

I have been struggling getting CUDA to work on Mathematica 11.3 and Manjaro Linux (kernel 4.19.16-1-MANJARO). Trying some commands I get the following: ...
1
vote
0answers
26 views

How to set parameters for CUDAFunctionLoad for a CUDA kernel?

I am trying to load the following CUDA kernel using CUDAFunctionLoad: ...
1
vote
0answers
54 views

CUDACCompilers[] returns an empty list

I have just installed Mathematica 11.3.0.0 on Windows 10 (Professional), with an NVIDIA GT 630M GPU on my Dell Inspiron. I have Visual Studio 2010 Express C++ Compiler installed on my system. I am ...
0
votes
0answers
72 views

CUDAQ::internal: CUDALink experienced an internal error

I have Mathematica 11.0.0 installed on Windows 10, with an NVIDIA GT 630M GPU on my Dell Inspiron. I am trying to run the CUDA examples in the Help files. All of the setup functions for CUDALink work ...
0
votes
0answers
58 views

CUDADeviceCount is 0 on Mathematica 11.3 and Paclet 11.3.82

I am Normi. I am using Mathematica 11.3 and trying to use CUDA Kernel on Windows 10. My Graphic Cards NVIDIA Tesla K20c (it is not in the list of supported GPU. But it has Tesla K20 in the list) ...
0
votes
1answer
61 views

Why does CUDAFunctionLoad not accept character types (strings)? [closed]

Why does CUDAFunctionLoad not accept character types (strings)? I want to load equations defined in an array (a list of equations) which is written in Mathematica ...
3
votes
1answer
118 views

Use of GPU/CUDA to speed up rendering of surface

I am attempting to create several surface renderings of expressions that come out of a solution for the eigenvalues of a matrix and the resulting expressions are considerably messy The eigenvalue ...
0
votes
0answers
27 views

how to add header (.h) file to CUDALink Mathematica?

I am purely new to CUDALink. How can I add new .h files, for example #include math.h. If someone writes the file math.h, and I would like to include it in CUDALink,...
2
votes
1answer
57 views

CUDALink experienced an internal error when assigning values to shared variable

Following is the CUDA kernel: ...
2
votes
1answer
49 views

Target system specification is not available for NVIDIA CUDA Compiler installation

I Installed Mathematica correctly and it indeed found my GPU. My case is exactly the same as : the same issue link However, it is not answered. Does anyone know the reason? My case: ...
2
votes
0answers
109 views

Cuda Paclet for 11.3

I have Wolfram Mathematica 11.3 installed on Ubuntu 16.04. My card is GTX-750Ti. I had "Installed" the CUDAResources-Lin64-11.3 over the internet. Can I "create" a Paclet of it so that I don't have to ...
6
votes
1answer
504 views

CUDA for linear equations

TLDR; Is there a way to solve linear equations of a sparse matrix (discretized laplace operator) efficiently using CUDALink in Mathematica? I didn't find a CUDALinearSolve or CUDAMatrixInverse or ...
1
vote
0answers
88 views

CUDAQ[ ] returns False after update

When I try Needs["CUDALink`"] CUDAQ[] It returns False I tried CUDAResourceUninstall ...
1
vote
1answer
127 views

Using library code (specifically curand) with CUDALink

...
5
votes
1answer
199 views

cannot load CUDAFunction from cubin, ptx or library file

According to the documentation of CUDAFunctionLoad it should be easy to specify a compiled file (cubin, ptx, dll should all work) as the source for loading a ...
1
vote
2answers
354 views

Why is CUDALink failing?

I have a new windows 10 laptop with a discrete nvidia graphics card (all drivers up to date). The first example from the documention of CUDAFunctionLoad[] in v11.2 ...
2
votes
0answers
55 views

CUDAQ[] returns false in Mathematica 10.0.2.0, Mac OS 10.13.2, CUDA Driver Version 387.99

CUDAQ[] returns False on my Mac OS 10.13.2. I typed Needs["CUDALink`"] and it returns no error. ...
4
votes
0answers
278 views

NVCC CUDA Compiler not showing up

I am trying to follow instructions for "Compiling for CUDA", so that I can write my own functions to run on the GPU. However, CUDAFunctionLoad gives me errors. ...
0
votes
0answers
54 views

Will CUDAlink accelerate my already written code?

I'm reading through CUDAlink's documentation, but I can't quite understand if with I'll boost my code, that I've already written, or if I'll need to rewrite my code in C to take advantage of CUDA's ...
2
votes
1answer
256 views

CUDALink and eGPU for Mac?

I have: MacBook Pro mid 2014 13" (i.e. just an onboard Intel graphics card) NVIDIA GeForce Titan X Akitio Node Thunderbolt 2 Cable Thunderbolt 2 to Thunderbolt 3 Adaptor I have installed the NVIDIA ...
1
vote
0answers
146 views

Wrong number of CUDA cores shown (GTX1070)

I installed the CUDA toolkit by directly obeying to the WRI instructions and use MMA 11.1.1.0 as well as the paclet version 10.5.0. While CUDA's deviceQuery sample ...
3
votes
1answer
141 views

CUDAMap does not work for the Sqrt function

CUDALink is working fine on my LINUX machine. I am using Mathematica 11.1 and CUDAMap works for all of the functions that it supports: ...
5
votes
1answer
586 views

CUDALink support-Mathematica 11

Greetings & Salutations, I have Mathematica 11.0 on a Windows 10(Home) system with a Nvidia GTX1050Ti gpu, driver version 382.33 and CUDA version 8.0.61; I am getting CUDALink is not supported ...
3
votes
1answer
535 views

Fast element wise multiplication of many, many submatrices of a 2D array

There is an edited section at the bottom to clarify some questions which have come up in the comments. I have some code which generates (according to two coordinates) two $m\times n$ arrays and then ...
1
vote
0answers
246 views

Mma 11.1.1 does not recognize GPU

The newest version of Mma 11.1.1 advertises "Re-enabled GPU support for neural networks for Mac." But when I install on an Apple MacBook Pro with an NVIDIA GeForce GT 750M GPU, and I do: ...
4
votes
1answer
251 views

How to determine MMA/CUDA support for specific GPUs?

This question asked how to target an Nvidia GTX 1080 with MMA 11.0.1 (which is also my current version) and from the comments it is clear that the user was then able to use this card successfully even ...
4
votes
0answers
140 views

CUDA not recognized on MacBookPro

I am running Mma 11.1.0 on MacOS 10.12.4 on MacBook Pro (Retina, 15-inch, Mid 2014) with NVIDIA GeForce GT 750M 2048 MB I installed the Nvidia CUDA driver 8.0.71. I evaluate ...
2
votes
1answer
533 views

Parallel Table and CUDA

I have a large matrix computation and I use Parallel table, which launches 4 Kernels. I do not have a GPU. Will having a GPU help me in Launching more Kernels and solve the problem faster? All my ...
7
votes
2answers
389 views

CUDA image processing

I am having an issue with image processing involving CUDALink. ...
1
vote
0answers
67 views

Help Getting GPU and the attached graphic monitor device information using CUDA or Open CL from Mathematica

My project is in the area of image analysis. I am analyzing the output of a projector attached to the computer running W Mathematica. Therefore, I will like to get information of the graphical device ...
1
vote
0answers
243 views

CUDAFunctionLoad doesn't work -> Target system specification

W`hen I try to execute simple kernels with CUDAFunctionLoad I get this message: "Target system specification \"TargetSystemID\" -> \ !(\"Windows-x86-64\") is not available for !(\"NVIDIA CUDA \ ...
4
votes
0answers
224 views

CUDADot runs slowly and writes “CUDALink experienced a kernel launch failure” with matrix size > 3300

I am trying to learn CUDA and start from the help examples. It turnes out that CPU calculation is much faster for matrix sizes < 3200 than CUDA, while CUDADot gives the error for sizes > 3300. I ...
2
votes
1answer
95 views

Change FourierParameters in CUDAFourier

CUDAFourier does not have option FourierParameters. I need to change its convention. It has default ...
4
votes
1answer
560 views

Help with CUDA nvcc error in Mandelbulb example Mathematica 11.0 NVIDIA GTX 1070 on Ubuntu

I am exploring the Nvidia GTX 1070 with Mathematica, I tried this example from the Help guide and it fails with a nvcc complier error. A little google research seems to indicate that I need the nvcc ...
1
vote
1answer
94 views

CUDATranspose bad result

A fairly simple experiment, I am trasponsing an identitiy (3x3) matrix, and I got a weird result. I tried also CUDADot and works as expected. The code I used: ...
0
votes
2answers
334 views

NDSolve with CUDALink

I am solving a system of non linear differential equations. The time needed to solve them is quite long and I would like to shorten it. Is it possible to send the NDSolve command to be solved by the ...
2
votes
0answers
211 views

calling CUDA library functions using MathematicaGPULibrary (WGL)

Recently I want implement a sparse linear solver in Mathematica with cuda, and I found the following resource: calling CUDA library functions. As it shows, I tried to use CreateLibrary function to ...
3
votes
0answers
152 views

Figure out how to copy to constant memory (CUDA)

I found a function. The help gives: CUDALink`Internal`CUDAConstantMemoryCopy[mem1, mem2] copies constant memory to and from host memory. As of now I have not ...
6
votes
0answers
227 views

Getting CUDALink (Toolkit 7.5) to work on Linux, Mathematica 10.0.2, GTX750

I want to make use of some CUDA functionality on my machine. It is running Gentoo Linux (64bit), Mathematica 10.0.2 on an Intel Xeon E5-1620v3 with a Geforce GTX750. So everything on the hardware/OS ...
3
votes
1answer
592 views

CreateLibrary for CUDA with NVCCCompiler

I am currently learning to use CUDA to speed up calculations. The book I am working with uses C code on the CPU to supply certain variables etc.. So I would like to compile the give code in ...
3
votes
0answers
108 views

Monitor CUDA function

Is there a way to monitor CUDA function without bringing much performance reduction. For example, Map can be monitored by ...
4
votes
0answers
460 views

Mathematica will not detect NVIDIA Titan X for CUDA functions [closed]

I've run Needs["CUDALink`"] CUDAResourcesInstall[] which, after a long download, returns ...
7
votes
2answers
852 views

CUDAQ not working in Mathematica 10.2.0.0 on Windows 7 (using CUDA 7.5)

I have been trying to get CUDA to work in Mathematica for kernel development. I downloaded and installed Visual Studio 2013 Community and the latest NVIDIA developers toolkit 7.5 (in that order). ...
4
votes
0answers
159 views

errors in CUDA example

It seems that there are some errors in the documentation page Consider these functions in the documentation CUDA Programming. However, I'm not a expert in CUDA nor C, could you check whether these are ...
11
votes
3answers
1k views

Are you able to use CUDA on Linux?

I am using Mathematica 10.2 on Ubuntu 15.04 x64. At first, I try to use CUDALink: Needs["CUDALink`"]; CUDAQ[] It returns ...
3
votes
0answers
391 views

Calling CUDA cuFFT

Following ybeltukov's excellent answers (see here and here) about how to access the CUDA library functions and interact with Mathematica through CUDAMemory, I tried to compile the code given in ...
5
votes
0answers
616 views

How to invert a matrix with 100 trillion elements?

I have a $10^{7}\times 10^{7}$ matrix with the following properties: it is sparse it is gamma-5 it is almost Hermitian. If $M$ is the matrix we are trying to invert, we know $M=A M^{\dagger} A$ ...
5
votes
2answers
528 views

CUDA 6.5, Mathematica 10.0.2, and Ubuntu 14.04

I have CUDA 6.5 working fine on Ubuntu 14.04. Mathematica recognizes the driver (Nvidia 340), but CUDAQ[] returns False and I cannot get any CUDA functions to work in Mathematica. I have created ...