clEnqueueCopyImage returning CL_MEM_COPY_OVERLAP
Hi I'm trying to use clEnqueueCopyImage to copy from one region of an image to another part of the same image. The specification says the error CL_MEM_COPY_OVERLAP is returned if "src_image and...
View Articleapp sdk installers mislabeled?
On the download page for the APP SDK 2.8 the linux 32 bit installer is labelled as version 2.8 while all others are labelled 2.7. The column with the version number says 2.7 for all of them. The...
View ArticlePersistent Threads and Wavefronts per CU
I created a sparse (dia format) linear solver (Biconjugate Gradient Stabilized Method) using persistent threads and profiled it using both the APP KernelAnalyzer and the APP Profiler. The majority of...
View Articlesimple OpenCL example returns error
Hi, I am trying to run a simple example code in OpenCL which just returns device info and runs a very simple kernel. It is from the MacResearch tutorials on OpenCL: #include <stdio.h> #include...
View ArticleCompiler Option for Optimization OpenCL
I am running the OpenCL code with debug and release mode under Visual Studio. The time it takes to run the OpenCL kernel is the same. I am wondering if there is anything wrong with the settings. I did...
View ArticleMeaning of VM in OpenCL Programming Guide?
Hi, I notice that the OpenCL Programming Guide changelog indicates that the table of memory behaviour has been updated to include whether or not "VM" is enabled. I don't know what term this refers to,...
View ArticleMultiple fft kernels
Hi , I am using AMD Radeon HD 6770 graphics card for OpenCL application. It has 800 stream core processors. I have installed the clAMDfft library and developed an application for 8000 point...
View ArticleAPP SDK archive site not functioning correctly
I need (asap) to download the previous APP SDK 2.7 to test against the new one (2.8), but the links on the archive site don't seem to be working....
View ArticleJapanese comments couldn't be displayed and compiled.
Hello. I tried to compile attached file. - Character set is Shift-JIS - It is including Japanese comments. But, I have these problems.1. Kernel Analyzer 2 cannot display Japanese comments...
View ArticleWhy is OpenCL startup so slow?
Hello, We have a Linux (3.2) server with two Radeon 7970 and Catalyst 12.10. OpenCL takes more than a second to start. Basically the first OpenCL call, usually clGetPlatformIDs() takes 1.25s. All the...
View ArticleCompile SDKUtil with gcc under win8 32bit
Hi, I am using gcc4.7.2 for win 32 bit which is found here http://www.equation.com/servlet/equation.cmd?fa=fortran I use below commands to compile .cpp->.o: g++ -O2 -c SDKApplication.cpp -Iinclude...
View ArticleenqueueAcquireGLObjects won't work
Heya everyone, some friends and me decided to use OpenCL for a teamproject at university.Well only 1 worked with OpenCL yet and built most of those parts. Our Project works fine with NVIDIA yet but as...
View ArticleDoes AMD Mobility Radeon™ HD 5650 supports openCl.
I am the beginner in openCl.I am Using Sony Vaio VPCEB26FG laptop that comes with AMD Mobility Radeon HD 5650 grahics card. When i ran a code for device info in openCL with java binding. It returned...
View Articlememory aliasing and use of mem_fence
Hello, All I have a bit of a specific question related to how compiler may rearrange my OpenCL source code and side effect of this. In my kernel, I am allocating some local memory and define 2 pointers...
View ArticleSupport for new OCL 1.2 new extensions and more suggestions..
Hi, would be good if amd can share if new extensions anounced this month like cl_khr_gl_msaa_sharing, cl_khr_depth_images and cl_khr_gl_depth_images which Intel seems working on shipphing it for IVB...
View ArticleSmall temporary arrays in OpenCL
Hi, Does OpenCL take advantage of the following techniques when using small local arrays?- On VLIW -> indexed_temp_arrays (x0[n]) (aka. R55[A0.x] indirect register addressing in ISA)- On GCN ->...
View ArticleOpenCL analogue of GL_ARB_draw_indirect
Hi, All Iis there any (planned) support for this kind of feature? It is very usefull if you know your parameters to glEnqueueNDRange on GPU side and do not want to do round trip. for now only one...
View Articlelow valu utilization without memory accesses
good morning. thanks for listening. here's the riddle: i have written an opencl kernel, which is 99% alu bound, using only bit operation instructions,(v_xor, v_not, v_or, v_bfi)no access to memory...
View ArticleProblems with Cat 12.10 and up and HD7xxx (and not only) GPUs
My app starts to produce invalid results if source CL file is compiled with Catalyst 12.10 and causes driver restarts if it compiled with Cat 12.11 beta 8.All this observed on HD7770 GPU. Looks like...
View ArticleClik here to view.
Gcn compiler bug, lds pointer arithmetic?
The following seems to be a bug in the gcn compiler, starting with catalyst 12.9, and does not occur on other architectures like Cayman and Barts. The test program fills an array[64] with some data and...
View Article