Clik here to view.
Segfault when linking
I try to use OpenCL spir with amd drivers. I compiled my kernel successful to spir (with clang 3.2 & khronos spir changes). Loading the program with clCreateProgramWithBinary shows no error....
View ArticleExtension for parallel primitives
Hi everyone, Since the begining of OpenCL AMD has tried to make it easier to develop with OpenCL by providing tools and SDKs. I am thankful to you for that. As I have seen during my different projects...
View Articlememory conflicts when reading same address
Hi, The AMD SDK 2.9 states (6.1.1.2): "Under certain conditions, one unexpected case of a channel conflict is that reading from the same address is a conflict, even on the FastPath. This does not...
View Articlealignment of vector types
Hi, Consider an array of ints to be read using vector types: __kernel void someKernel(__global int const * values){int8 A = *((__global int8 const *) (values)); // no issues I supposeint8 B =...
View ArticleDetecting GCN, list of chips?
Hello,I'm having quite some hard time obtaining data about which chips use which architecture. So far, I'm relying on the CL_DEVICE_VENDOR_ID and CL_DEVICE_NAME. I see all chip names in CodeXL (which I...
View ArticleCompiling Simple Program on Opencl
Well I am trying to compile a simple program in OpenCl ( i am new to OpenCl)using visual studio 2013, it breaks immediately at clCreateContext command and error is "Unhandled exception at 0x524E132F...
View ArticleBuffer vs. Image performance
Can anyone comment on their experience using buffer/local memory as opposed to images ? It seems that the standard way of doing image convolution is to: 1) read from system memory into global buffer2)...
View ArticleLinux 290x OpenCL ?
Hello, I am trying to get 290x to be visible under Ubuntu 12.04 with latest 13.11 beta6 64bit Linux drivers. It looks like fglrx module is loaded and aticonfig is functioning # aticonfig --adapter=0...
View ArticleRead problem from device buffer in Zerocopy mode
I use a single buffer to store multiple values. At the last line of my openCL kernel I update one of these variables using an atmoic operation. Reading this variable in C after the end of kernel...
View ArticleClik here to view.
APP SDK samples can't find GPU
I have installed a Radeon R9 290 into a 64-bit Ubuntu 12.04 Linux machine and successfully installed amd-catalyst-13.11-beta-v9.4-linux-x86.x86_64 driver and AMD-APP-SDK-v2.9-lnx64. My X is working...
View ArticleClik here to view.
how to compile OpenCL project on eclipse?
1. eclipse : luna2. AMD3. Window 7 I try to setting my workspace like this...and compile this project and run project ( sorry, i can't speak english) what can i do solve this problems? please help me
View ArticleAbout the cache coherence between CPU and descrete GPU
Hi all,I am studying how to create an interactive connection between a CPU and a descrete CPU on OpenCL.I create a buffer(unsigned long) with CL_MEM_ALLOC_HOST_PTRflag, and then I pass the buffer to be...
View Articlealignment of vector types
Hi, Consider an array of ints to be read using vector types: __kernel void someKernel(__global int const * values){int8 A = *((__global int8 const *) (values)); // no issues I supposeint8 B =...
View Articlenested-if performance penalty if no else
Hi, In 6.8.7.4 of the AMD OpenCL Programming Guide for AMD SDK (2.9; that's the version used here) it says there are performance penalties for nested if-statements and that "if blocks are nested k...
View Articleclinfo claims my Radeon HD 6970 has no cache
According to clinfo output, my Radeon HD 6970 (lspci -nn output: 01:00.0 VGA compatible controller [0300]: Advanced Micro Devices, Inc. [AMD/ATI] Cayman XT [Radeon HD 6970] [1002:6718]) has no global...
View ArticleClik here to view.
how to compile OpenCL project on eclipse?
1. eclipse : luna2. AMD3. Window 7 I try to setting likes pictures..(sorry, i can't speak english...) and .. I try Build ProjectThis is my source code.. #include <CL/cl.h>#include...
View ArticleUtilising the gpu in a headless envrionment
Is there any way to have OpenCL run in a terminal (ubuntu server 14.04) but still use the gpu to compute processes? I want to use the gpu, aswell as the cpu, for programming but I don't want to install...
View ArticleRunning OpenCL SPIR programs on GPU
Hi all, as reported here: Re: Re: Standard Portable Intermedopencl_spir.hiate Representation (SPIR)cl_khr_spir happears as an available extension for GPUs with the new OpenCL driver.I am currently...
View ArticleClik here to view.
Incorrect results when multiple processes use the same GPU
Hello. I've noticed strange behaviour of our scientific application when launching several instances on the same GPU - sometimes it gives incorrect results.I've reproduced this behaviour on the small...
View Articleprintf bug
I have the following kernel kernel void generate_bi(global uint *sizes, global uint *bi) { uint globalID0 = get_global_id(0); uint globalID1 = get_global_id(1); printf((__constant char*) "(%d,...
View Article
