Dynamic parallelism on 290X OpenCL 2.0 or extension
The new arch revisions for GCN in the 290X seem like they would allow for dynamic parallelism. Will this be offered via an extension for OpenCL 1.2 or will it not be until 2.0 is final?
View ArticleValgrind complaining about uninitialized values coming from libamdocl64.so
I'm building an application using OpenCL, and while running Valgrind I am seeing a bunch of warnings about various problems inside libamdocl64. I'm not so worried about them as I see many other people...
View ArticleGraphics driver crash since 13.4 when using atomic_inc
Hi, I'm using a HD5770 on Win7-64 with Cat13.10. Since 13.4 till today, my appication crashes the GPU driver or even causes blue screens. Now I've been able to provide a small test case based on the...
View ArticleKernel compiler segfaults on this sample
Hey, I have a small code snippet that leads to a segfault on the most recent driver and CodeXL. https://gist.github.com/ginkgo/7554966 The major culprit seems to be fhash(). Nevermind the usefulness of...
View ArticleClik here to view.
Problem with bit operations with openCL
Hi, I did some tests on an HD7970 card recently, simply running the md5 hash function in openCL on it. But I found that the result is wrong (the same code runs fine on an NVIDIA card).It became correct...
View ArticleLinux 290x OpenCL ?
Hello, I am trying to get 290x to be visible under Ubuntu 12.04 with latest 13.11 beta6 64bit Linux drivers. It looks like fglrx module is loaded and aticonfig is functioning # aticonfig --adapter=0...
View ArticleGPU not found. Falling back to CPU device
Hello, I have a problem getting OpenCL to work with AMD Radeon HD 8570. When I try to run programs from AMD APP SDK v2.5, I get the following message:"GPU not found. Falling back to CPU device".When I...
View ArticleSuggest Feature you want in AMD APP
Suggest Feature you want in AMD APPHi EveryBody,I was preparing a top feature requests for the AMD's openCL implementation. I will be looking to as many old forum topics as i can. But there can always...
View ArticleClik here to view.
Persistent __local variable option as a fast communication between kernels
For small patches of cloth animations, 2D fluid computation or even some reduction techniques, will there be an option to make __local variables stationary until next kernel execution or at least for...
View Articleprogram counter in instruction vs program counter in wavefront
Hi,I have two questions.As I know that each wavefront has its own program counter.So, 1. what is the different between program counter for wavefront and program counter for each instruction??2. what is...
View Articlehough transform using opencl
Hi alli am trying to do lane detection using opencl and i have detected the edges of image but not getting how to detect lines using hough transform.
View Articlepossible bug found: *single* threaded race condition with clSetKernelArg +...
First of all let me say a *BIG* thanks for finally adding support for the OpenCL 1.2 Direct3D9 interop extension. I've been waiting for this for years! And it seems to work just fine. Finally I can use...
View ArticleOpenCL very long array multiplication
Hi everybody,I am working on an Acer Inspire with an Intel Core i7-720QM CPU, using OpenCL 1.2, ATI Mobility Radeon HD 5650 with 5 compute units and maximum work-item sizes per dimension of 256. I've...
View ArticleAMD OpenCL compiler wasting VGPRs like crazy
(Windows 8.1 x64, HD7770, driver: 13.251-131206a-165817C-ATI) Can anybody explain to me why the following kernel compiles to 140 VGPRs and 32 SGPRs? From what I can see this kernel should only consume...
View ArticleResolving Driver Conflicts in Xorg -> Running 2 Discrete Video Cards, Primary...
I've been trying to get this setup to work for almost a week now, All I want to do is use my Nvidia GTX 670 as my primary video card for display with occasional computing with CUDA, and use my AMD R9...
View ArticleNested for loops GPU crashing
Hi,I have a set of vectors and I need to find the triple product of all combinations of the vectors. I wrote a very simple 3-dimensional kernel code: __kernel void compute_triple_prod(__global float4*...
View ArticleCache size in AMD Radeon HD7660D
Hi, I am having a little confusion and couldn't find a clear cut solution. Is the cache (L1 and L2) size of AMD Radeon HD7660D in APU A10-5800K the same as that of CPU or is it different? The CPU has...
View Articlehelp pls
guys i have put the the graphics card in my pc but the CD drivers cannot be installed for some reason! (windows 7 32 bit btw)
View ArticleClik here to view.
pinned buffer vs device buffer
Hi,I am new with OpenCL so maybe it is a stupid question.I already know how to use pinned buffer, zero copy buffer, or device buffer in OpenCL.I have 3 questions that really make me confuse:1.What is...
View ArticleclGetPlatformIDs block?
hiHas anyone come across the clGetPlatformIDs interface blocking problem? When i use clGetPlatformIDs api, it did not return. The call stack info as follows. Anybody know why clGetPlatformIDs is...
View Article
