2022 Developer Survey is open! Take survey.

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
3 votes
0 answers
52 views

Accelerating this stacked matrix-matrix product in OpenCL

I am trying to compute a matrix-matrix product of N stacked complex double N x N matrices. For simplicity, I assume N = 512. I have written code in C++ parallelized with OMP and using OpenBLAS for the ...
user avatar
  • 31
0 votes
0 answers
35 views

3 sync approaches for parallel reduction on GPU using openCL + jocl

Parallel reduction kernels using different synchronization approaches + JOCL host level application that runs all 3 sync modes and CPU reduction on random data and outputs evaluation times: ...
user avatar
  • 141
1 vote
1 answer
83 views

pointer jumping on a GPU using Aparapi

Classic pointer jumping algorithm summarizing values from an array adapted to run on a GPU instead of a PRAM. Read about openCL and Aparapi yesterday for the first time, so this is my first trial: ...
user avatar
  • 141
0 votes
1 answer
73 views

Implement 2D and 1D std::array in opencl kernel

I am asked to implement the following part of code into kernel code. Actually, I have tried but not sure about the std::array. This is the original code for the ...
user avatar
1 vote
1 answer
77 views

OpenCL approximation of Pi using vectorized implementation

Yesterday I started following the hands-on OpenCL course. I now got to the point where we are requested to reimplement an approximation algorithm for Pi in OpenCL (in steps, up to a vectorized ...
user avatar
  • 1,032
1 vote
0 answers
59 views

brute force algorithm keys with 32bit block and 64bit key using OpenCL

I wrote a brute-force attack on passwords using video cards for any algorithms with a 32-bit block and a 64-bit key, the password is only in BCD format, in the kernel source code the TEA algorithm, ...
user avatar
0 votes
0 answers
53 views

Performance discrepancy between Windows and Ubuntu for a video-memory-based virtual array implementation

I implemented virtual array using OpenCL and graphics cards as backing store, with caching some of data on RAM using a LRU algorithm and accessing data through some simple setters/getters. Accession ...
user avatar
4 votes
1 answer
470 views

Computational verification of Collatz conjecture using OpenCL

This code review request follows my previous request Computational verification of Collatz conjecture. Unlike the previous program (which was designed for the CPU), this code should run on modern GPUs....
user avatar
  • 249
4 votes
1 answer
114 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 ...
user avatar
3 votes
0 answers
86 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): ...
user avatar
  • 131
13 votes
1 answer
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 ...
user avatar
  • 425
4 votes
1 answer
110 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 ...
user avatar
  • 353
1 vote
0 answers
71 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 ...
user avatar
1 vote
1 answer
563 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 ...
user avatar
  • 165
4 votes
1 answer
1k 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 ...
user avatar
  • 362
7 votes
2 answers
186 views

Generating permutation of indices from seed ID

In my OpenCL kernel, I have the following logic: ...
user avatar
  • 247
5 votes
1 answer
1k 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 ...
user avatar
8 votes
1 answer
600 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, ...
user avatar
  • 1,091
6 votes
1 answer
647 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 ...
user avatar
  • 265