Using FirePro V7800 with an AMD A8-3850 and Linux
Hi, I would like to use the V7800 as a pure OpenCL co-processor, no display attached. The display remains connected to motherboard, using the A8 integrated GPU. But I can not get it to work. When the...
View Articleprintf bug
I have the following kernel kernel void generate_bi(global uint *sizes, global uint *bi) { uint globalID0 = get_global_id(0); uint globalID1 = get_global_id(1); printf((__constant char*) "(%d,...
View ArticleQuestion about global pointers
The AMD optimization guide states: --------------------------------------------------------------------------------------------------------Avoid writing code with dynamic pointer assignment on the GPU....
View ArticleWhat is the fastest way to transfer data between host and device on Cape...
I have an HD 7700 GPU, on windows 7. Here is how I am currently managing my memory: 1) I allocate a host buffer using new[] operator, aligned to page size (4096 bytes)2) I allocate a device buffer via...
View ArticleBinary produced for Hawaii with CL_CONTEXT_OFFLINE_DEVICES_AMD is not working...
We ship our applications with a number of binaries for different GPUs. The binaries are produced by compiling source OpenCL files with clBuildProgram ("-fno-bin-source -fno-bin-llvmir -fno-bin-amdil...
View ArticleClik here to view.
Stack overflow in clBuildProgram on Catalyst 14.12 with R9 290
When I try to compile certain OpenCL code on a machine with R9 290 installed running a Catalyst 14.12 driver, the program crashes with stack overflow in amdocl64.dll when calling clBuildProgram.The...
View ArticleUndefined behavior when running a simple OpenCL app
Hello,Recently I stumbled upon this tutorial [ The Big Blob » Getting started with OpenCL and GPU Computing ]. I copied it and ran it (the only change made was changing the CL_DEVICE_TYPE_DEFAULT to...
View ArticleCatalyst 14.12 OpenCL problems
Hey AMD Devs, I'm not sure if you know about the problems that were introduced with Catalyst 14.12 (compared to 14.9). I was able to track down at least one of them (the most important one) and wanted...
View Article14.9 and higher OpenCL performance
I've tried dozens of tweaks to my Groestl implementation, and it refuses to get anywhere near as fast as pre-14.9 code. The pre-14.9 code is just butchered on 14.9 - a rewrite makes it better, but the...
View ArticleDiscussion
Ubuntu 11.10 64-bit Hi!I know it is not officially supported, but it might occur to others also they want to build SDK on new Ubuntu, or it could come in handy when releasing new Catalyst and SDK. I'm...
View ArticleClik here to view.
JPEG decoding is broken with Catalyst driver
I just confirmed that installing Catalyst driver (Omega as well as older versions) breaks Windows Photo Viewer. Uninstalling the driver completely using amdcleanuputility.exe restores the Windows Photo...
View ArticleHow to read/write GDS through AMD APP SDK
Now I want to read and write some data from or to GDS block.Is there any way to do this?
View Article__local memory optimization
Hi, I'd like to hear your comments if the suggested kernel modification is realistically (based on theory) expected to improve the current situation which shows a considerable bottleneck (profiled);...
View ArticleClik here to view.
Device-side enqueue, block syntax, and local kernel variables
Hello, I'm currently in the process of updating my code to make use of the new OpenCL 2.0 features. At the moment I'm implementing a kernel that enqueues some of my existing kernels from the device. In...
View ArticleOpenCL - GPU to GPU transfer
Hello,I am working on a DirectX 11 (might possibly port to other APIs) application utilizing multiple GPU's for rendering and I need a mechanism to exchenge data between them. Because Mantle is still...
View ArticleDigital Video Pipeline
A bit off topic, but: I am interested in building a digital video pipeline using AMD hardware. See this link for NVidia pipeline: NVIDIA Quadro Digital Video Pipeline for Broadcasting | NVIDIA I would...
View ArticleAPU vs Discrete GPU
I am currently testing my kernel on an HD 7700 discrete card. This 3 year old mid-level card is fast enough for my application. Carizo is arriving this year; will Carizo OpenCL perf be greaterthan 7700...
View ArticleBufferBandwidth results on Kaveri
Hello,I was wondering why the CPU read/writes are so slow on the BufferBandwidth example irrelevant of if the memory is allocated in host or not? Also why the GPU writes are slow if the kernel is...
View ArticleGuide to run OpenCL headless, without X server and as normal user
You may know that you can run OpenCL program as root without Xserver. I found patch which enable running the OpenCL programs even without Download catalyst driver. Then run chmod +x...
View ArticleSPIR and SVM?
Is it possible to use SVM with SPIR kernels? I've been trying various versions of the attached code, but can't seem to get anything to work.
View Article