Clik here to view.
GCN ISA Assembler
Hi All I'm proudly presenting the first preview release of my GCN ISA Assembler / AMD_IL errorchecker / scripter IDE featuring syntax_highlighting and code_insight (ctrl+space) for fast assembly...
View ArticleBug of Catalyst drivers of version 12.10 and later running with Radeon HD...
An intricate bug has been found in the latest Catalyst drivers when running OpenCL kernels with constant indexes accessing the __local memory.Conditions: The bug only emerges in each group when...
View ArticleclBuildProgram segmentation fault
__kernel void testcrash ( __global double *diout ){double *d_XP = diout;d_XP[0] = 10.0;} I have a super simple kernel. This seems to be crashing the compiler only for GPU devices,...
View Articlerotate() broken
Here is an OpenCL Kernel which fails to compute some of the values correctly. I've tested this on Ubuntu 12.04 with Catalyst 13.4 but it fails on older versions, too. Reproduces on all my tested cards....
View ArticleNot to spec for OpenCL - OpenGL Interop
According to the 1.1 spec section 9.8.3.1 interop should support the following opengl internal formats: GL_RGBA8 CL_RGBA, GL_RGBA,GL_UNSIGNED_INT_8_8_8_8_REVGL_BGRA,GL_UNSIGNED_INT_8_8_8_8_REVGL_RGBA16...
View Articleint64 atom_cmpxchg on AMD 6168 CPU
The OpenCL code below fails to compile for an AMD 6168 CPU. AMD_APP version 2.8. Note the compiler does not complain about cl_khr_int64_base_atomics, so I have to assume they are supported for the...
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 ArticleConstant arrays of structs are corrupted.
I'm writing a path tracer. I have the following data (see attached file for the context): __constant Scene scene = { .planes = { {&mat_sky, {1000, 0, 0}, {-1, 0, 0}},...
View ArticleClik 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 Articlecan not debug openCL sample
hi, Guys i am looking at the samples provided by AMD sdk. i am try to debug the kernel code by using codeXL. but i always get below erroe: ERROR: could not debug kernel; Error during kernel debugging....
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 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 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 like:...
View ArticleBest memory layout for RGBA data in local memory?
What is the best way of layout this out in local memory to reduce bank conflicts ?I was thinking:RRRRRRRRRRRR... GGGGGGGGGGGG... BBBBBBBBBBBB... AAAAAAAAAAAA... I would like to grab all four channels...
View Articlevload4 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 ArticleAMD OpenCL compiler seems to ignore the -I include directory build option
When I pass in "-I SOME_DIRECTORY", the directory is ignored.I have to hard code absolute include paths in my kernels. Thanks,Aaron
View ArticleHW requirements for OpenCL 2.0
Hi! What are the HW requirements for OpenCL 2.0 in general, and for dynamic parallelism in particular? According to the spec, there are various levels of SVM that an OpenCL 2.0 conformant device may...
View ArticleCompiler crashes
Hello all, I am currently working on a application in python and opencl (using pyopencl) to accelerate computation of multiple small optimization problems. I took a C implementation of the...
View ArticleBlender Cycles(Opencl on AMD GPUS)
Dear Opencl DeveloperWhy doesn't the AMD opencl compiler work with blender cycles?whenever i compile the blender cycles kernel, the system either crashes due to lack of memory, or takes too long to...
View Article