Questions tagged [opencl]

OpenCL is a C-based API for writing parallel programming intended to be executed on a compute device, typically (though not limited to) graphics cards and enterprise compute cards.

Filter by
Sorted by
Tagged with
4
votes
1answer
50 views

Repeatedly incrementing array elements using OpenCL

I am learning how to program in opencl and I made a simple program that simply takes an array and adds 1 to every element. I want to run it many times (this is just so that i can benchmark how it does ...
3
votes
0answers
56 views

Numpy versus Theano GPU parallelization

I am learning Theano to accelerate my image processing functions. As a start, I am trying to reimplement the function to turn images from colors to black and white (with the same number of channels): ...
13
votes
1answer
1k views

OpenCL implementations of IQZZ and IDCT for MJPEG

I am using this code for MJPEG decoding and I am trying to make two functions (IQZZ and IDCT) run faster on the GPU (NVIDIA Tesla k20c). I am using the OpenCL framework to accomplish this task. I ...
4
votes
1answer
93 views

Computing the Fourier transform of a distribution of electron charge (represented by atomic positions in space)

I am computing a nested loop operation using OpenCL (open computing language). My main question is, given the code outlined below, how might I optimize the speed and efficiency of using the GPU, for ...
1
vote
0answers
65 views

GPGPU helper API

C# project to generate a 64-bit Cekirdekler.dll C++ project to generate a64-bit KutuphaneCL.dll (used in Cekirdekler.dll) Apart from error handling, does it have any catastrophic errors? I uploaded ...
1
vote
1answer
323 views

Mandelbrot Set with OpenCL and SFML [closed]

I don't know if I'm doing this correctly, using OpenCL and SFML together but I know a little about both so I decided to make something with them. I've already tried implementing a pure C++ and SFML ...
4
votes
1answer
795 views

Speeding up OpenCL matrix-vector multiplication

So I'd like to get a performance boost above and beyond standard Julia matrix-vector multiply, using my Intel HD Graphics 4000 1536 MB GPU, but I can't do better than an order of magnitude worse ...
7
votes
2answers
145 views

Generating permutation of indices from seed ID

In my OpenCL kernel, I have the following logic: ...
5
votes
1answer
960 views

Two-step OpenCL convolution for series of matrices

I've implemented a two-step convolution in OpenCL running on GPUs. The convolution is applied to a series of 1480x1552 matrices. All matrices are pre-loaded and are stored in the ...
8
votes
1answer
488 views

Parallel accumulated sum in OpenCL

This is my first relevant code in OpenCL. Please, let me know if I'm doing something wrong in a logical level (i.e., I guess it can crash in situations?) or accounting for performance (bottlenecks, ...
5
votes
1answer
629 views

New Haskell package: OpenCL

I am developing a high level OpenCL binding in Haskell, and I need peer-review and testing. It currently only gets platform and device info from OpenCL. I have lots of functions that only change the ...