Questions tagged [opencl]

OpenCL (Open Computing Language) is a framework for writing programs that execute across heterogeneous platforms consisting of CPUs, GPUs, and other processors.

This tag refers to the OpenCL (Open Computing Language) by Khronos Group. It is the first open, royalty-free standard for cross-platform, parallel programming of modern processors found in personal computers, servers and handheld/embedded devices. Using OpenCL, one can affect execution of parallel computations greatly improving speed and responsiveness of a wide spectrum of applications: From gaming and entertainment to scientific and medical software.

OpenCL is an API and a C99-like language; for each device, implementations are provider-specific. Some of the OpenCL implementation providers are:

Questions about OpenCL can be asked here along with the vendor/provider and architecture details. Bug reports should be discussed in the respective forums of the vendors NVIDIA Forums, Intel Forums, AMD Forums

Books

5705 questions
2
votes
1 answer

Use T-API (Opencv 3.0) with OpenCL in Android Studio No Speed improvements

I was trying to switch to the new OpenCV 3.0, as it implicitly calls OpenCL for faster operations on matrices. I followed a nice Tutorial provided by Sony and was able to integrate the required OpenCV files to make it compiling. I'm simply reading…
beniroquai
  • 166
  • 2
  • 13
2
votes
1 answer

OpenCL function call stack size

Can I know OpenCL's function call stack size? I'm using NVIDIA OpenCL1.2 in Ubuntu. (NVIDIA CC=5.2) And I found some unexpected result in my testcode. When some function invoked 64 times, the next invoked function seems like can not access the…
soongk
  • 259
  • 3
  • 17
2
votes
2 answers

Convert OpenCL Image to pyOpenCL Array or numpy ndarray

I'm trying to implement a gaussian filter for images from a code I found online, using Python and PyOpenCL. My original images are numpy arrays, but I am confused as in which should I use to pass the images to the GPU. Originally, the kernel…
2
votes
2 answers

Values Change Randomly When Chaining Together Kernels

I'm pretty new to the whole OpenCL world, and I have created two pretty simple Kernels and I am trying to chain them togehter, but I am getting rather spurious results. When ran individually, they work as expected, but when slapped together, that is…
David Watts
  • 2,249
  • 22
  • 33
2
votes
1 answer

Maximum number of work items, work groups within NDRange

I have the following system parameters: CL_DEVICE_TYPE_GPU Device maximum compute units = 20 Device maximum Work Item Dimensions = 3 Device maximum Work Item Sizes = 512 x 512 x 512 Device maximum Work Group Size = 512 As I understand, if Item…
user3856196
  • 349
  • 4
  • 16
2
votes
2 answers

OpenCL code that compiles on linux, doesn't compile on windows

i've been writing some OpenCL code lately on linux (ubuntu 10.4, ati catalyst 10.4 and ati sdk v2.1) and its working great on linux. When i wanted to run my code on windows, i got program build errors complaining about "this declaration has no…
omarzouk
  • 933
  • 10
  • 23
2
votes
1 answer

clCreateSubBuffer not found oO

i can't seem to find clCreateSubBuffer in cl.h or cl.hpp (only error macro). it is mentioned in the specifications, any idea about this? or any other way to create a sub buffer? all i can think of is recreating the buffers using an incremented…
omarzouk
  • 933
  • 10
  • 23
2
votes
1 answer

OpenCL Compiler Weird Condition

I'm a new one working on OpenCL. I have some weird trouble when I try to compile the kernel. On Nvidia platform, no matter what code in the source, it always show me cl_success and the log is only "\n"; On Intel platform, no matter what code in the…
Soban
  • 81
  • 5
2
votes
1 answer

Linux Function Interception for OpenCL

I'm fairly new to C so be gentle. I want to use the library interception method for Linux to replace calls to the OpenCL library with my own library. I understand that this can be done using LD_PRELOAD. So I can just re-implement the OpenCL…
Chris
  • 617
  • 2
  • 6
  • 18
2
votes
0 answers

How to determine the maximum size of bus-addressable OpenCL memory buffer?

I am using the AMD bus-addressable memory extension to write from an FPGA to a GPU and vice versa. In the first case, an OpenCL buffer is created with the CL_MEM_BUS_ADDRESSABLE_AMD flag set. However, the largest size that I can allocate is much…
matthias
  • 2,161
  • 15
  • 22
2
votes
2 answers

A cuda wrapper to execute openCL

I'm involved in a project where I have to do gpu programming, one of my constraint is to do it on a nvidia device (thus in CUDA). But I haven't access to a device equipped with nvidia gpu. So I would like to know if there is any wrapper that exist…
jehutyy
  • 364
  • 3
  • 11
2
votes
1 answer

Python and T-API on OpenCV

OpenCV 3.0 now uses T-API (Transparent API), see: https://github.com/Itseez/opencv/wiki/Opencv3 it does not need to specify cv::ocl::Canny, cv::gpu::Canny etc; cv::Canny just works on both CPU and GPU. And this is an…
Rui Martins
  • 3,337
  • 5
  • 35
  • 40
2
votes
1 answer

What is the Optimal Memory Setup for OpenCL where the host needs access at regular time steps?

I'm looking to find the best way to setup the CL memory objects for my project, which does a device side physics simulation. The buffers will be accessed by the host every frame, approx every 16ms, to get the updated data for rendering.…
NIZGTR
  • 65
  • 1
  • 1
  • 6
2
votes
3 answers

Fast hashing of 32 bit values to between 0 and 254 inclusive

I'm looking for a fast way in C to hash numbers 32-bit numbers more or less uniformly between 0 and 254. 255 is reserved for a special purpose. As an added constraint, I'm looking for a method that would map well to being used with ISA-specific…
Huarache
  • 246
  • 2
  • 13
2
votes
0 answers

Error in OpenCL kernel compilation

I've included an OpenCL kernel (.cl file) in my OS X framework, and I'm able to reference it from one of my implementation (.m) files. However, when I compile, I get the following error, related with the kernel: openclc: error: cannot specify -o…
insys
  • 1,288
  • 13
  • 26
1 2 3
99
100