View Full Version : OpenCL - parallel programming of heterogeneous systems

Pages : 1 2 [3] 4 5 6 7 8 9 10

  1. How to index local accrays for best performance?
  2. Libraries compilation
  3. Serveral problems in OpenCl,Help!
  4. how to pass an arbirary length constant array to a kernel?
  5. Question about the OpenCL Platform
  6. Local memory allocation
  7. Higher register usage after migration from cuda
  8. Specification 1.0 to 1.1 diff
  9. OpenCL overview, vec3 missing
  10. Can the GPUs be leaveraged differently
  11. mixmode MPI/OpenCL
  12. functions called in a kernel
  13. help with work-group
  14. Gaussian blur
  15. Different output on GPU vs CPU
  16. Polygon graphics library in OpenCL?
  17. Constraints of limited RAM on GPGPUs
  18. work_dim > 3?
  19. How to use double in kernel function?
  20. 16bits per channel RGB Image
  21. Help setting up OpenCL
  22. Limitation of local sizes on N-Dimensional NDRanged problems
  23. No GPU devices found... But yesterday everything worked...
  24. how to convert index of cuda into opencl
  25. OpenCL 1.0 - Any vendors support 3D write_imagef?
  26. OpenCL on Windows much slower than on Mac?
  27. Open Intermediate Language
  28. Ternary operation for vector (select)
  29. Newbie question about number of CL devices
  30. initializing constant variable from file
  31. correctly deleting buffers
  32. max local array size?
  33. Out of resources problem
  34. Embedded profile
  36. Function to get human readable error messages
  37. OpenCL and encapsulation
  38. Cannot find -loclUtil_x86_64
  39. Tutorial series for OpenCL with C++
  40. Is CL_KERNEL_WORK_GROUP_SIZE value hardware dependent?
  41. ATI and NVIDIA from OpenCL perspective
  42. Suggestion for future OpenCL functionalities
  43. The Correct way to populate a lighting buffer
  44. problem of communication between global memory and private's
  45. Affine transform, floatnxm
  46. Why is default interpolation done this way?
  47. About writing to Global Memory
  48. Division by Zero on Large Problem Sizes
  49. Working with single channel images? (Is it possible?)
  50. Difference between USE_HOST, ALLOC_HOST, COPY_HOST pointer
  51. clBuildProgram crashes
  52. Passing NULL pointer to the kernel ?
  53. Searching for simple code
  54. Euler Rotation and Bounding box calculation of point cloud.
  55. Grabbing image from OpenGL via OpenCL
  56. strange behavior - clEnqueueWriteBuffer/ReadBuffer
  57. ICD and OpenCL on Windows CPU + GPU. How?
  58. sorting big array in GPU
  59. clCreateBuffer() need lots of time
  60. OpenCL.net
  61. OpenCL system, device type
  62. OpenCL precompiled kernel faster?
  63. Device types
  64. Sharing the GPU between OpenCL capable programs
  65. Atomic operations in OpenCL 1.0
  66. Trying to understand OpenCL Vs OpenCL on Cuda Architecture
  67. Different pointer size on host and device causing problems
  68. Faster on CPU than on the GPU
  69. max work item and max workgroup sizes for CPUs (MacOS / AMD)
  70. How does OpenCL handle loops ??
  71. using atom_inc to append to the end of an array
  72. Error in online manpages
  73. OpenCL on embedded processors
  74. unsigned int or cl_uint?
  75. How to get free memory size on the device?
  76. Release cl::Context
  77. Is it possible to create context from multiple platforms?
  78. Open CL with OpenMP
  79. Multiple host threads with single command queue and device
  80. error:CL_OUT_OF_RESOURCES when work dimention is 2
  81. On conformance image tests
  82. Question of openCL use of gpu and cpu
  83. Problem with code running on CPU
  84. help aligning struct for sending array of structs to the GPU
  85. One host, two devices, different vendors
  86. OpenCL Object Queries and speed
  87. can doing a loop calculation on a gpu be faster than a cpu ?
  88. PHP and OpenCL
  89. Tutorial
  90. C++ OpenCL helper object/function
  91. Run-time error in clBuildProgram(-11)
  92. Multiple kernels and constant memory
  93. Embedded RTOS hardware and software configuration
  94. OpenCL/OpenGL interop syncing issues
  95. Printf within a Kernel
  96. clGetEventProfilingInfo error
  97. Image functions
  98. error in the clBuildProgram
  99. Confusion with write_imagef()
  100. error gl.h included before glew.h oclutils.h
  101. quicklz compression offloaded to GPU
  102. Task parallelism
  103. static int inside a __kernel
  104. OpenGL OpenCL Interoperatibility not Working Debian Linux
  105. Dynamic OpenGl Texture
  106. Combinatorics?
  107. array of images?
  108. Failed to build CL program on Radeon 4670
  109. Beginnings of an audio loop
  110. Possibility to access every cl_mem object as buffer NEEDED!!
  111. a brief tutorial
  112. Getting started on MacOs X 10.6
  113. Section 8.2 Addressing mode and filtering
  115. clGetPlatformIDs returns 4294967266, not expected
  116. Writing var to output array is very slow.
  117. cpu working, gpu not
  118. Getting "Error in reading profiler output" w/Visual Profiler
  119. Global Arrays in OpenCL
  120. Shared OpenCL buffers between processes
  121. Share OpenCL buffers between processes
  122. Debugging in OpenCL
  123. OpenCL struct alignment on host and device
  124. Problem with image object and clEnqueueReadImage
  125. Get Devices Help Needed
  126. Looking for Simple Image Processing
  127. Calling a kernel from within a kernel?
  128. How to use tex2D
  129. barrier(CLK_LOCAL_MEM_FENCE) ??
  130. Which memory is user for buffer object allocation ?
  131. OpenCL for IBM double hummer architecture? (BlueGene)
  132. passing an array of char* to kernel function
  133. Converting from Loops to ND Ranges
  134. Alignment problem?
  135. openCL on visual studio 2008 on vista - where to start?
  136. what is the use of sampler objects .give me an example
  137. what is the difference between the sampler objects creation
  138. Thesis - OpenCL Computation of Magnetic Susceptibility
  139. Access to Khronos repository for academia
  140. How to have one kernel signal all other kernels to return
  141. Invalid command queue / access violation
  142. opencl can be used in visual studio 2010?
  143. how to write opencl kernels
  144. Some startup tips
  145. OpenCL .icd file
  146. Kernel compilation problem....
  147. C++ templated cl::Buffer creation problem on AMD platform
  148. Experiments with memory object allocation flags
  149. Clarify CL_MEM_USE_HOST_PTR
  150. Device watchdog
  151. Better cache control
  152. Problem with using local memory and global memory
  153. an opencl puzzle
  154. Does Pci express lane width matter?
  156. opencl performance
  157. Recursion?
  158. Recursion
  159. /usr/bin/ld: cannot find -lshrutil_x86_64
  160. [BUG] cl::BufferRenderGL not derived from cl::Image
  161. How parallel is this code?
  162. Only read specific chunks of a buffer
  163. Optimized FFT for 32k complex numbers
  164. Kernel sincronization problem
  165. runtime error
  166. Iterate over built-in vector type?
  167. Work Item
  168. mapping buffer host on GPU device
  169. Multi-vendor OpenCL support in a single EXE?
  170. Retrieving local *current* GPU core, shader, memory clock
  171. why they are different
  172. OpenCL CL_OUT_OF_RESOURCES on event.wait()
  173. devices selection
  174. OpenCL C++ Bindings and premature program deallocation
  175. One Code - Three different output images
  176. Memory space clarification
  177. Matrix Addition - what is wrong?
  178. One device, many contexts
  179. Draw many spheres
  180. where can i find cl_d3d9.h?
  181. opencl interop with directx9
  182. Problem creating cl_context
  183. Cannot use math functions
  184. Describing kernel parameters
  185. Optimization
  186. Memory Problem when trying to speed up Kernel
  187. OpenCL on CPU and GPU with Nvidia cards on Ubuntu 10.10 ?
  188. constant memory
  189. performance comparison between OpenCL & DirectCompute
  190. Compile error for float4 array
  191. Global Memory - when is it changed?
  192. Casting int2, float2
  193. OpenCL compression code running 10 times than serial code !!
  194. Bring this DirectCompute features to OpenCL!
  195. use pointer in kernel code
  196. Vector's(float4, float8) calculation
  197. OpenCL : scope of application
  198. thread creation overhead
  199. render cl_mem(image object) to window
  200. Add support for #warning directive
  201. Memory Access
  202. Strange Bug
  203. Reading file in OpenCL program
  204. Test kernel, Error:E010:Irreducible ControlFlow Detected
  205. Events and callback functions
  206. clEnqueueReleaseD3D10ObjectsKHR bug?
  207. speed factor
  208. How to reduce the read buffer time
  209. one device, no cpu and no context
  210. OpenCL Intel x86_64 code generation
  211. clEnqueueNDRangeKernel() returns with error code "-58"
  212. Using 2 ATI cards on Ubuntu 10.4 with OpenCL
  213. OpenCL development tool for OS X
  214. reduce the number of registers used
  215. How to use C++ templates in kernel?
  216. Apple FFT vs. AMD APP FFT
  217. OpenCL Fluid Simulator
  218. different local variables share memory?
  219. Memory object allocation
  220. loading images opencl
  221. maximum pinned memory
  222. Make it easier to get the CL version number
  223. Globally visible buffers or direct memory access?
  224. const variable / memory latency
  225. unique kernel names?
  226. Correct way to declare a global sampler_t
  227. which format supported in clCreateFromD3D10Texture2DKHR?
  228. Ability to change border color with image objects
  229. creating objects in shared memory
  230. calling kernel from another kernel
  231. Kernels and mutexes
  232. Multi-GPU System, multiple contexts or command queues?
  233. Problem in compile
  234. Communication between OpenCL and CUDA
  235. clGetKernelWorkGroupInfo does not return correct local mem
  236. Errors Running AMD OpenCL Tutorial Code
  237. Using DLL-functions in a Kernel?
  238. clCreateFromD3D10Texture2DKHR returning CL_INVALID_OPERATION
  239. Will ATI support interoperability between OpenCL and D3d9?
  240. OpenCL weird error from clBuildProgram
  241. Constant memory execution error
  242. OpenCL name usage
  243. Cached Buffers
  244. Runtime differences __global, __constant, __local
  245. Read Image via OpenCL commands
  246. What is special about cl specific data types?
  247. Undefined reference errors with image2d functions
  248. Kernel's source code protection
  249. Support for cubemaps
  250. Support for bit-fields