vload4 vs 4 individual memory accesses : bank conflicts
What is the advantage of vload4 over 4 single memory accesses?Suppose I am loading memory from local memory. Below are two kernels. The second kernel should exhibit no bank conflict.Does the first have...
View Articlekernel crashes with access violation on windows 7
Hello,Below is a kernel that crashes with an access violation on windows 7 with latest intel opencl sdk,targeting a nehalem quad core CPU.Actually, the kernel as written will not crash, but if you...
View ArticleLinux support for GPU on intel Core Processor
Hi All,I am taking investigation on intel OpenCL developing under linux.I found the release note (Intel® SDK for OpenCL™ Applications 2014) did not listed GPU of Core Processor as the target platform...
View ArticleFloating point reproducibility across devices
Hi all,Is there a way to get reproducible float results from kernels across all devices?I'm running an OpenCL kernel on different devices (different CPUs and GPUs), and the computation results for...
View ArticleDoes the OpenCL2.0 SVM support allocate memory for images?
Does the OpenCL2.0 SVM support allocate memory for images?We can test the SVM performance...
View ArticleOpenCL support for C++ template
Hi,I'm trying to port an OpenCL kernel that contains C++ template declarations. The compilation of the kernel code (with clCreateProgramWithSource) fails because it does not recognise the "template"...
View ArticleOpenCL support for C++ template
Hi,I'm trying to port to Xeon Phi an OpenCL kernel that contains C++ template declarations originally written against AMD APP SDK. The compilation of the kernel code (with clCreateProgramWithSource)...
View ArticleOpenGL TextureBufferObject and normal Textures
There doesn't seem to be a dedicated forum for opengl driver problems, so please feel free to point me in the right direction.I'm currently trying to use a shader that uses a TextureBufferObject and a...
View ArticleAtom E3825 Support
I am considering using the Intel minnowboard max for a compute-intensive project, and I was wondering if the GPU in the included Atom E3825 chip supports OpenCL. The release notes mention some...
View ArticleHD4600 crash: fcl build 1 succeeded
Using the following OpenCL with a HD 4600 device (as found on a Dell AlienWare 17) stops compilation with:fcl build 1 succeeded.Build failed! Video driver is 10.18.10.3496 (latest available through...
View ArticleBug in cl.hpp, enqueueMapBuffer does not properly call clReleaseEvent before...
Hi, I am not very experienced as c++ programmer so forgive me if I have missed something obvious. Please direct me somewhere else if this is the wrong forum. I am on windows 7 with visual studio 2013....
View ArticleNew update for OpenCL™ runtime to Xeon and Xeon Phi is available - Check it out
OpenCL runtime 14.2 with support to CPU and Intel® Xeon Phi™ coprocessor is now available. Designed to support high performance applications with Intel’s server line of processors. This release...
View ArticleOpenCL Optimization guide for celeron N2820
Hi, I have celeron N2820 based NUC. I would like to to optimize my opencl programs for this SoC having Intel HD graphics. Can some one point me to a guide or other resources for :1- A block diagram of...
View ArticleSome questions on no. of threads and work groups
I have some background on NVIDIA, and so to learn OpenCL for Intel, I would like to correlate.In case of Nvidia, we have following rules :1- Warp size: 32 (or in some cases 64) 2- Maximum no. of...
View Articlewhat looks like a boolean expression bug
I am running the latest sdk, targetting the CPU. ( core i7 Q720)My work group X-dimension is 128.I have an expression bool doWrite = (get_local_id(0) >= 0) && (get_local_id(0) <...
View ArticleDebugger doesn't display local variable
I try to debug some opencl kernel in Visual Studio 2013. After entering in kernel debugger show me local variables, but only before row with union operator (#11). Once debug go to row 11 a "Locals"...
View ArticleOpenCL SDK download link broken
Hi,I tried to download OpenCL SDK from the page(https://software.intel.com/en-us/vcsource/tools/opencl-sdk) using 'download button' at right side of the page. But, the link doesn't direct me to...
View Articlefastest way to pass an image to the GPU
Hi,I am using Intel's VME extension to calculate ME and the time that it take to pass the image to the GPU is very long about 1MsecI have tried 2 methods: #1 Map /Unmap - about 0.4 Msec for 1280*720...
View ArticleHow to crash the compiler....
constant sampler_t sampler = CLK_NORMALIZED_COORDS_TRUE | CLK_ADDRESS_MIRRORED_REPEAT | CLK_FILTER_NEAREST;int4 temp = (int4)(0,0,0,0); ( read_imagei(idata, sampler, (float2)(0, temp)) + temp)...
View ArticleHelp me!,compile opencl error for mic
Help me!compile my opencl code for cpu is ok.icpc -o ArrayAdd -L/opt/intel/opencl-1.2-4.5.0.8/lib64 -L/opt/intel/opencl-1.2-4.5.0.8/libmic -I/opt/intel/opencl-1.2-4.5.0.8/include/...
View Article