Does OpenCL on Intel CPU device use CPU and HD graphic GPU at the same time?
Hello, I made a benchmark on my OpenCL application on i7-4771 and Xeon E5-2643 machine and the result is shocking me. E5-2643 spent much longer time to complete the test than i7-4771. I guess...
View Article"Deep Analysis" showing 7 HW threads on Ivy Bridge EUs
Small interface issue in Kernel Builder... the y-axis of the EU chart only shows 7 threads on Ivy Bridge EUs.I thought IB EUs have 8 threads and Haswell EUs have 7 threads?
View ArticleXeon PHI and enqueueCopyBuffer()
Hi!I'm having synchronization problems with enqueueCopyBuffer() and Xeon PHI. Suppose the following pseudocode:/* Begin host code */ cl::Buffer b0, b1; ///initialize with size N cl::CommandQueue c0,...
View ArticleClik here to view.
Kernel Builder "Deep Analysis" can't instrument large kernels
I have a large kernel that errors out in Kernel Builder with a: "-11 CL_BUILD_PROGRAM_FAILURE".Is there a practical size limit for Kernel Builder kernels? The kernel does build using the offline...
View ArticleAlgnment question
In one of the sample apps, there is an align_malloc method.Inside, there is this assert: assert(size/sizeof(void*)*sizeof(void*) == size);Why must the memory size be divisible by sizeof(void*)...
View ArticleThe new Intel® SDK for OpenCL™ Applications 2014 is Here!
Dear OpenCL developers,The new Intel SDK for OpenCL Applications 2014 introduces a unified software development environment for OpenCL API with new debugging capabilities.New production...
View ArticleLLVM bitcode and machine code
The current process to acquire an OpenCL binary looks something like this: program = clCreateProgramWithSource(...) clGetProgramInfo( program, CL_PROGRAM_BINARIES,..., binary )This binary is then...
View ArticleThe OpenCL™ runtime for Intel® Xeon Phi™ is compatible with MPSS 3.2.3
Dear OpenCL developers,The new OpenCL™ runtime for Intel® Xeon Phi™ (14.1) is confirmed to be compatible with recently released MPSS 3.2.3.MPSS 3.2 remains supported by version 14.1 of the OpenCL™...
View ArticleRunning OpenCL on MIC got error, but CPU is fine.
Hi,I'm a beginner to OpenCL, and I want to run it on MIC. I download the monte-carlo example from the below url:https://software.intel.com/en-us/vcsource/samples/monte-carlo/Run it on CPU if fine, but...
View ArticleIntel CPU and AMD GPU: clGetPlatformIDs returns 1
Using the latest SDK, I make the following call: errorCode = clGetPlatformIDs(0, NULL, &numPlatforms);and numPlatforms is one. This happens both on my laptop and desktop,each with an AMD video...
View ArticleIntel Core i7 Q 720 faster than Intel Core i7 3770
This is strange: I am running a program on windows that reads a file from disk and executes a number of OpenCL kernels on the CPU device.When I run it on my 4 year old laptop, i7 720 with mechanical...
View Articlelocal work group size of 512 is too small for Haswell
512 items is too small for Haswell. A workgroup of 512 items cannot cover a Haswell half-slice.The minimum acceptable max work group size for Haswell should be at least 10 EUs x 7 h/w threads x 8 work...
View ArticleLocal memory on CPU device
What is the meaning of local memory when targetting the CPU? Does it map to the L1 cache?Thanks,Aaron
View ArticleOpenCL equivalent of CUDA warp vote functions
Do equivalents exist for CUDA __all and __any methods?http://docs.nvidia.com/cuda/cuda-c-programming-guide/#warp-vote-functions
View ArticleDoes __attribute__((vec_type_hint(float8))) work with Intel HD Graphics?
If this feature isn't implemented yet then please please add it to your list! :)It would really help "unlock" some useful GPU programming idioms.
View ArticleMost efficient way of dividing by power of two
I have an array of signed ints, and I would like to divide by 2^n. I currently use this routine to do it: int out = in >= 0 ? int >> n : -((int & 0x7FFFFFFF) >> n);Is there a better...
View Articlegetting a crash when building a program
Crashing on build/*Kernel is attempting to average float8 values between neighboring elements of inputBuffer and then multiply them by associated 64 elements in matrixBuffer Crash occurs when DIM is 2...
View ArticleDangers of Running 3rd Party OpenCL
Hello fellow OpenCL enthusiasts!I'm currently working on a process that will run 3rd party OpenCL sources automatically and I'm worried about security on my system. I was wondering how secure it is to...
View ArticleCLBenchmark 1.1.3 Beta driver not running
https://downloadcenter.intel.com/Detail_Desc.aspx?agr=Y&DwnldID=23985Not running, CLBenchmark 1.1.3 is crashing.
View Articlemul_hi bug report
Windows 8.1 64-bit, Intel HD 4600 (both latest release and beta drivers), the following snippet from an OpenCL kernel produces an incorrect result: if (k_delta == 38443432 && jj==4620)...
View Article