# GPU

**URL:** https://discourse.julialang.org/c/domain/gpu/11.md?page=34

[Latest](https://discourse.julialang.org/latest.md) · [Categories](https://discourse.julialang.org/categories.md) · [Tags](https://discourse.julialang.org/tags.md)

**Page:** 35

---

## [OpenCL: Feedback on install on OpenSUSE](https://discourse.julialang.org/t/opencl-feedback-on-install-on-opensuse/1980)

<div class="topic-metadata">

**Author:** [@Colin\_Beckingham](https://discourse.julialang.org/u/Colin_Beckingham)\
**Replies:** 6\
**Last updated:** [February 9, 2017, 12:55pm UTC](https://discourse.julialang.org/t/opencl-feedback-on-install-on-opensuse/1980 "2017-02-09T12:55:47Z")

</div>

I have openSUSE Leap 42.2 fully patched. CUDA 8 is installed with a physical GT 610 card which works fine with CUDAnative. I have tried to wake up OpenCL on Julia 0.5 and 0.6; both install without complaint, but Pkg.test…

---

## [CUDAnative: hitting a 1024 limit when the result comes back](https://discourse.julialang.org/t/cudanative-hitting-a-1024-limit-when-the-result-comes-back/1921)

<div class="topic-metadata">

**Author:** [@Colin\_Beckingham](https://discourse.julialang.org/u/Colin_Beckingham)\
**Replies:** 4\
**Last updated:** [February 6, 2017, 11:38am UTC](https://discourse.julialang.org/t/cudanative-hitting-a-1024-limit-when-the-result-comes-back/1921 "2017-02-06T11:38:20Z")

</div>

I have a working kernel for a basic matrix multiplication based on the add example. It checks out fine for small two dimensional matrices, but hits a problem with output matrix greater than 32x32. Here is how I send up …

---

## [CUDAnative: kernel multidimensional access](https://discourse.julialang.org/t/cudanative-kernel-multidimensional-access/1864)

<div class="topic-metadata">

**Author:** [@Colin\_Beckingham](https://discourse.julialang.org/u/Colin_Beckingham)\
**Replies:** 3\
**Last updated:** [February 3, 2017, 9:56pm UTC](https://discourse.julialang.org/t/cudanative-kernel-multidimensional-access/1864 "2017-02-03T21:56:24Z")

</div>

I have a toy example where the goal is to process a 3x3 matrix of integers on the GPU and do an element wise doubling of the numbers. I have no problem doing this allowing CUDAnative to linearize the array to a vector, b…

---

## [CUDAnative: Using second and third dims in the kernel](https://discourse.julialang.org/t/cudanative-using-second-and-third-dims-in-the-kernel/1799)

<div class="topic-metadata">

**Author:** [@Colin\_Beckingham](https://discourse.julialang.org/u/Colin_Beckingham)\
**Replies:** 2\
**Last updated:** [January 31, 2017, 3:58pm UTC](https://discourse.julialang.org/t/cudanative-using-second-and-third-dims-in-the-kernel/1799 "2017-01-31T15:58:38Z")

</div>

In my attempts to generalize the example code given on the README.md I have had good results including processing arrays larger than the device blocksize, but have run into a block regarding the use of the second and thi…

---

## [Error installing CUDAnative on v0.6 : Resolved](https://discourse.julialang.org/t/error-installing-cudanative-on-v0-6-resolved/1743)

<div class="topic-metadata">

**Author:** [@Colin\_Beckingham](https://discourse.julialang.org/u/Colin_Beckingham)\
**Replies:** 7\
**Last updated:** [January 29, 2017, 10:16am UTC](https://discourse.julialang.org/t/error-installing-cudanative-on-v0-6-resolved/1743 "2017-01-29T10:16:06Z")

</div>

I have installed a small GEForce GT-610 in my box and in BIOS directed the video output to the IGFX which hopefully leaves the CUDA card free for processing numbers. I had a problem getting CUDAnative,jl installed and w…

---

## [ArrayFire Julia: Performant way to calculate vector cross product?](https://discourse.julialang.org/t/arrayfire-julia-performant-way-to-calculate-vector-cross-product/1458)

<div class="topic-metadata">

**Author:** [@Boxed](https://discourse.julialang.org/u/Boxed)\
**Replies:** 0\
**Last updated:** [January 13, 2017, 9:51am UTC](https://discourse.julialang.org/t/arrayfire-julia-performant-way-to-calculate-vector-cross-product/1458 "2017-01-13T09:51:20Z")

</div>

Hi Is there a way to calculate vector cross product through ArrayFire.jl in a performant way? The function is not implemented in ArrayFire and the getindex() and setindex!() functions for Julia cause data movement betwe…

---

## [Testing OpenCL-based packages on Travis CI](https://discourse.julialang.org/t/testing-opencl-based-packages-on-travis-ci/403)

<div class="topic-metadata">

**Author:** [@juliohm](https://discourse.julialang.org/u/juliohm)\
**Replies:** 10\
**Last updated:** [December 5, 2016, 11:21am UTC](https://discourse.julialang.org/t/testing-opencl-based-packages-on-travis-ci/403 "2016-12-05T11:21:40Z")

</div>

My ImageQuilting.jl package has a big chunk of uncovered code because I am not sure what dependencies I should install on Travis CI before testing its GPU features. After a lot of effort refactoring and playing around wi…

---

## [ArrayFire Julia: Implementation of gfor?](https://discourse.julialang.org/t/arrayfire-julia-implementation-of-gfor/633)

<div class="topic-metadata">

**Author:** [@pedroborgesmelo](https://discourse.julialang.org/u/pedroborgesmelo)\
**Replies:** 4\
**Last updated:** [November 30, 2016, 5:03am UTC](https://discourse.julialang.org/t/arrayfire-julia-implementation-of-gfor/633 "2016-11-30T05:03:16Z")

</div>

Hi! Anyone knows how to implement something equivalent to gfor using the existing ArrayFire wrapper? I guess gfor is not wrapped… Regards,

---

## [What does Julia GPU today?](https://discourse.julialang.org/t/what-does-julia-gpu-today/311)

<div class="topic-metadata">

**Author:** [@JeffreySarnoff](https://discourse.julialang.org/u/JeffreySarnoff)\
**Replies:** 6\
**Last updated:** [November 25, 2016, 3:42am UTC](https://discourse.julialang.org/t/what-does-julia-gpu-today/311 "2016-11-25T03:42:19Z")

</div>

I would like to catch up with what has been accomplished, which sorts of capability are well supported and where Julia’s GPU adventure goes next.

[Previous page](https://discourse.julialang.org/c/domain/gpu/11.md?page=33)
