libamdocl32.so seems to prevent debugging of SSE exceptions
Hi, to find the locations in my SSE/AVX code where something goes wrong, I enable various exceptions in the mxcsr register using the ldmxcsr command. When my code then triggers the exception, my...
View ArticleclBuildProgram and KernelAnalyzer2 crash
Hello everyone. This simple Kernel: struct foo{ float a; }; __kernel void asdf(__global float* a) { struct foo asdf = (struct foo){1}; a[get_global_id(0)] = asdf.a; } crashes clBuildProgram and...
View Article__global vs __constant qualifier in OpenCL
I want an array variable to have a program scope. One way I can do this by passing it as a function pointer throughout the program, which might be complex when we have multiple functions...
View ArticleClik here to view.
wglMakeAssociatedContextCurrentAMD and OpenGL-OpenCL Interop
So I have a software architecture where I pick a differing GPU for each thread in my program and run OpenCL on each thread (and hence GPU) in parallel. So far so good. As you might imaging, not all...
View ArticlePartial Histogram code as given in OpenCL code samples on GoogleCode
//******************************************************************// This kernel takes an RGBA 8-bit-per-channel input image and// produces a partial histogram for R, G, and B. Each work-group//...
View Articleinvalid unroll factor
I have some problems with unroling loops, AMD retun clBuildProgram, with Intel OCL works fine code: __kernel void conv(...) { #pragma unroll (SIZECOEF+8) for (j = 1; j <= SIZECOEF+8; j++)...
View ArticleStrange behavior in kernel - Losing variables during kernel run
Hi, I've come across some very strange kernel behavior when running a certain kernel on my Radeon Device. Interestingly, the exact same code performs fine using the CPU-Device, either with the AMD-APP...
View ArticleUSE_HOST_PTR with dynamic array?
I have a piece of code that I'm trying to optimize for an APU that looks something like this: float* temp = new float[x]; // some size x determined at runtime// create/copy values into temp// sizeof *...
View ArticleAnyone know anything about Brecht Van Lommel on the new cycles for AMD?.
Anyone know anything aboutBrechtVanLommelon the newcyclesforAMD?_____________________Alguien sabe algo de Brecht Van Lommel sobre el nuevo cycles para Amd?..
View Articleissue with -g flag compiler option of clBuildProgram
Hi, To debug my OpenCL kernel,I used "Debugging CPU Kernels with GDB" method as explained in OpenCL Programming Guide book by making two changes in the program1. CL_DEVICE_TYPE_GPU to...
View ArticleClik here to view.
Save binary using C++ wrapper
Hi everyone, I have a small question which should be simple enough for you. I am trying to save a binary to disk in order to load if later on. I am able to do it using C, but using the C++ wrapper, I...
View ArticleclFlush() and Event Profiling Problem.
Hi, I am trying to parallelize DMA and computation with two in order queues, facing strange Event Profiling results when clFlush() is being used.On AMD GPU almost all events recorded with same/invalid...
View ArticleCan't even get the examples to work - missing runtime
I got some Issue with Open Cl running on this Linux machine (PCLinuxOS 11, the lightweight one). I did Install Open cl, and also the dcc. Wenn I try to compile and try the samples delivered with it, it...
View ArticleCL-GL Interop: CL_INVALID_IMAGE_FORMAT_DESCRIPTOR with recent APP SDK or...
Hi! The example I mentioned in http://devgurus.amd.com/thread/159639: https://code.google.com/p/opencl-book-samples/source/browse/trunk/src/Chapter_10/GLinterop/GLinterop.cpp doesn't work anymore since...
View Article4X HD7970 not working
Hi! My institute has invested in 'small' GPU cluster based on Radeon GPUs, all in hopes of doing rough OpenCL computations. I have installed Ubuntu 13.04 and Ubuntu 12.10, both show the same faulty...
View ArticlePlease help with clBuildProgram crash / segmentation fault
Hi, probably more for 'driver support' forum, but I would like here as well.I have a problem with openCL program, clBuildProgram does segfault / crash with newer drivers. Please help me improve the...
View ArticleClik here to view.
Memory allginment for GPU use with _aligned_malloc
I have been working with the latest SDK and see many examples like the following: matrixGPU_double = static_cast<double*>(_aligned_malloc(SIZE, 4096)); My question is what is the reason...
View ArticleclBuildProgram and KernelAnalyzer2 crash
Hello everyone. This simple Kernel: struct foo{ float a; }; __kernel void asdf(__global float* a) { struct foo asdf = (struct foo){1}; a[get_global_id(0)] = asdf.a; } crashes clBuildProgram and...
View ArticleStrange behavior in kernel - Losing variables during kernel run
Hi, I've come across some very strange kernel behavior when running a certain kernel on my Radeon Device. Interestingly, the exact same code performs fine using the CPU-Device, either with the AMD-APP...
View ArticleAPU: No uncached hostmemery when context is shared
Hi,I have an Trinity APU (A10-5800K) and would like to use both CPU and GPU in one context. When I use the GPU in a single context, I can specify buffers with CL_MEM_READ_ONLY | CL_MEM_ALLOC_HOST_PTR...
View Article