Skip to main content
16 votes

CUDA on Tesla V100 card

The CUDALink package doesn't work right on Linux. For years and years I've been reporting it, they don't fix it. You have to go through some hoops, but when you get it working, it's really sweet! My ...
Andreas Lauschke's user avatar
12 votes
Accepted

CUDA for linear equations

Turning the comments into an answer. Making a linear solver work on a GPU is highly nontrivial (it's a task to be assigned to someone who poisened his mother and father), and as far as I can tell, no ...
Henrik Schumacher's user avatar
10 votes
Accepted

CUDALink support-Mathematica 11

Your CUDA paclet is outdated. Updating it with CUDAResourcesInstall[Update -> True] should fix your problems. The output of ...
Karsten7's user avatar
  • 27.5k
10 votes
Accepted

Mathematica 12, supported GPUs

Tl;dr Version 12 supports CUDA 10.1, which includes support for Turing Architecture. To download the most updated version, even if you’ve just updated & are having trouble: ...
CA Trevillian's user avatar
9 votes
Accepted

CUDA on Tesla V100 card

In the end, in our case, the following allowed us to get CUDA to work. export NVIDIA_DRIVER_LIBRARY_PATH /usr/lib64/libnvidia-tls.so.418.116.00 (adapt to your ...
chris's user avatar
  • 23k
7 votes

CUDA on Tesla V100 card

This is a reply to a question from chris, not a "new" answer. You mean a working example? How about 250 million normally-distributed random numbers, displayed in a histo: ...
Andreas Lauschke's user avatar
7 votes
Accepted

CUDA image processing

CUDAImageConvolve is slow due to memory tranfert between the different memories (CPU and GPU). One can decompose the action of ...
andre314's user avatar
  • 18.6k
7 votes

CUDA image processing

This is an extended comment on code style, rather than on your problem. Unfortunately I don't have a CUDA-capable card, so I can't test your actual issue. Generally speaking, however, you will want ...
MarcoB's user avatar
  • 67.3k
6 votes
Accepted

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

I would use ListCorrelate and rely on Mathematica's internal parallel implementation. Here is your code: ...
Carl Woll's user avatar
  • 131k
5 votes

Use of GPU/CUDA to speed up rendering of surface

This might be a bit faster although it does not look as fancy as output of ContourPlot3D. It needs 4 seconds on my laptop: ...
Henrik Schumacher's user avatar
5 votes
Accepted

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

Yes, the nvcc compiler is installed with Mathematica, but you can specify the use of another one. For you the problem seems to be that the architecture sm_61 (this refers to "Compute Capabilities" -> ...
Wizard's user avatar
  • 2,720
5 votes
Accepted

cannot load CUDAFunction from cubin, ptx or library file

Here we go: Upfront, this was a pain as the CUDALink` package uses GPUTools`, LibraryLink` ...
halirutan's user avatar
  • 113k
5 votes

CUDALink ran out of available memory

There's no fixing for that memory leak problem so far (ver 10.4). Here is the workaround I post in another place https://stackoverflow.com/a/35922539/6046035
entropi99's user avatar
5 votes

CUDA on Tesla V100 card

The automatic detection has been improved with a paclet update for version 12.0, so after doing ...
ilian's user avatar
  • 25.5k
4 votes
Accepted

Change FourierParameters in CUDAFourier

Since, as you say, CUDAFourier[] does not support the FourierParameters option, you will need to use ...
J. M.'s missing motivation's user avatar
4 votes
Accepted

CUDA on Manjaro Linux (Arch)

After struggling for two days, I finally figure it out minutes after asking for help... so typical :) Nevertheless, I post my solution here in case anyone else gets stuck. The Mathematica ...
a20's user avatar
  • 912
3 votes
Accepted

Using library code (specifically curand) with CUDALink

The compiler accepts the following code : ...
andre314's user avatar
  • 18.6k
3 votes

CUDAMap does not work for the Sqrt function

I was able to duplicate this and contacted wolfram technical support after a little back and forth they finally confirmed it as a bug. They said they would notify the development team. Hopefully this ...
hskramer's user avatar
3 votes

Why is CUDALink failing?

This should be working better with Visual Studio 2017 and recent Nvidia cards after updating to the latest CUDAResources for version 11.3: ...
ilian's user avatar
  • 25.5k
3 votes

How to determine MMA/CUDA support for specific GPUs?

ALL Nvidia GPUs with Compute Capability >=3.0 are supported for neural networks. However, you're out of luck with great hardware and a buggy version of Mathematica. 11.0 had an issue with all 10xx ...
Gregory Klopper's user avatar
3 votes

Parallel Table and CUDA

Too long for comments ParallelTable uses CPU cores so having a GPU will not speed it up. However, you can use the GPU by writing your matrix operations with the ...
Edmund's user avatar
  • 42.3k
3 votes

CUDATranspose bad result

For the sake of an answer: After several tries I have found that with Mathematica 10.4 and nvidia drivers 367.27 and upgrading to the latest CUDAResources paclet everythig is working ok – Javier ...
2 votes

NDSolve with CUDALink

No, that's not possible. If you could show your code there might be other ways to speed it up.
user21's user avatar
  • 39.9k
2 votes

Are you able to use CUDA on Linux?

January 2017 I have installed Mathematica 10.2 on Ububtu 16.04(64bit) Nvidia GeForce GTX 760M after installing NvidiaDriver 367.57.0 and CUDA Toolkit 7.5 from the Ubuntu repos. The method above: <...
Eik's user avatar
  • 21
2 votes

CUDALink experienced an internal error when assigning values to shared variable

It seems that extern is not supported in Mathematica CUDALink. So I just need to delete extern. Also the shared array should be ...
ZHANG Juenjie 's user avatar
2 votes
Accepted

CUDA usage in "everyday life"

CUDA (GPU computing) works well as long as you have many independent calculations on lists, matrices,... . Shifting data back and forth from memory CPU to GPU takes time. This spoils the calculation ...
Eisbär's user avatar
  • 1,476
1 vote

Mathematica 12, supported GPUs

I replaced CUDAToolkit 10.1 with 10.0. The fallback fixed my problems with "GPU not found". (Windows 10 home, Mathematica 12.0)
user65322's user avatar
1 vote

Mathematica 12, supported GPUs

Cuda seems to work on Mathematica 12 on a Windows 10 machine: CUDAQ[] True CUDAInformation[] {1 -> {"Name" -> "GeForce ...
Niki Estner's user avatar
  • 36.1k
1 vote

Why does CUDAFunctionLoad not accept character types (strings)?

The way to do this is to construct C code as a string. CForm is a useful tool for simple expressions, but more complicated programming needs help. Here's an example ...
John Doty's user avatar
  • 13.7k
1 vote

Why is CUDALink failing?

The situation is that you (and me) have a card that is too new. You can try the following: Set the option "ShellCommandFunction" :> Print and run again. There, ...
halirutan's user avatar
  • 113k

Only top scored, non community-wiki answers of a minimum length are eligible