CodeXL support question.
CodeXL release notes says "An AMD GPU (Radeon HD 5xxx or newer) or APU is required".Does CodeXL work on the mobile gpus(5xxxM, 6xxxM, 7xxxM, 8xxxM)?
View ArticleDecrement Loop doesn't work correctly.
Hello. I made a program including loop which calls a simple function. I had made it with "decrement" loop at first, but it didn't work correctly.I remade it with "increment" loop, it worked.I think...
View ArticleDevice Fission/Partition
Dear All, I'm trying to use the device partition to evaluate OpenCL as an alternative to OpenMP with vectorization on NUMA architectures.However I'm unable to use partitioning by affinity with NUMA...
View ArticleUsing clEnqueueReadBufferRect to read a sub-matrix
Hi all, I'm trying to use clEnqueueReadBufferRect to read back a sub-matrix (for use with clBlas), but can't get the region parameter to work for this - despite being an array of 3 size_ts, it always...
View Articlegcn assembler
when is the gcn assembler coming?opencl is driving me nuts again.it thinks that precalculating 20 offsets into LDS in the outer loop is more important than stayingbelow 128 registers.and i didnt even...
View ArticleOpenCL / DirectX9 texture interop?
I'm having trouble using cl_dx9_media_sharing to write OpenCL results to a IDirect3DTexture9. In the snippet below, I get an exception from accessing a null pointer somewhere inside the first call to...
View Articleopencl data type
Hi forum, I am trying to typedef a opencl type as follows: typedef float2 cData; cData *field = NULL; I am doing in the host . Bu i am getting a compilation error . Is it possible to declare stuff...
View ArticlePossible OpenCL kernel (CPU) compiler bug
I have following (quite simple) function my kernel code. Problem is that this function compiles without any problems on GPU (RV770), but on CPU (AMD FX-8350) call to clBuildProgram causes "access...
View ArticleKernel uses less registers since 13.1 - harming performance of my application
Hello!Since drivers 13.1 and later, the AMD OpenCL compiler has been rather sparse with allocating registers for my code, and as a result there is massive register spilling and about 3x reduction in...
View Articleproblem to run open cl program
I have problem to run open cl program I have done all installation . And try to run sample hello world program it is unable to find GPU. kindly help me
View ArticleOpen cl programming basic
Tell me steps to setup environment for OpenCL.In windows or Linux.I have AMD Radeon HD 6470M.Tell which software I should install.
View Articleexplicit copy from host to device
Hi forum, I am allocating a host memory and then i am creating a device memory buffer with the host copy pointer. Do i have to explicitly copy the contents from host to device then? If the host...
View Articleopencl porting
Hi forum, I am trying to port an existing cuda application to OpenCL and i am not getting the corresponding OpenCL function of the following CUDA function: cudaError_t cudaMallocPitch(void **...
View Articlecopy program in opencl....
hi...i m trying to write a opencl program for copy an array into another array....this is the Kernel which i have written.....__kernel void vector_add(__global const int *A, __global const int *B) {...
View ArticleCompilation under windows
Hi I'm very new to opencl. I'm trying to compile c opencl code under windows 7 without Visual Studio. I always use console.How can i compile using only console (cmd) under windows 7. Can i use icl? I...
View ArticleDevice Fission/Partition
Dear All, I'm trying to use the device partition to evaluate OpenCL as an alternative to OpenMP with vectorization on NUMA architectures.However I'm unable to use partitioning by affinity with NUMA...
View ArticleclAmdBlasTune usage
Hello, I'm try to run clAmdBlasTune on a FireProv8800 and I get segfaults or weird incomplete output like: <pre>C:\Program Files (x86)\AMD\clAmdBlas\bin64>env...
View ArticleclAmdFft in-place vs. out-of-place performance
Hello, I need the input data to be conserved. There are two solutions for this: Either make a copy of the input data in the device memory and use the copy as input for a in-place fft or directly use...
View ArticleProbable usage of texture memory
Hello forum, The simulation i am trying to run represents data on a 2D grid. The natural representation for this grid on the CPU is array . The analog of array on the GPU is the texture. So i believe...
View ArticleClik here to view.
result image from SimpleImage sample has artifacts
Hi! I started learning OpenCL two days ago in Java with LJWGL. I loosely based by learning project program after the SimpleImage example that came with AMD-APP-SDK-v2.8-Windows-64. It does the same...
View Article
