View Full Version : OpenCL - parallel programming of heterogeneous systems

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

  1. Managing the transparency textures
  2. Cross-platform issues MacOSX / Linux
  3. OpenCL syntax highlighting
  4. Lack of double Support in C Types
  5. Who will write the platform -> driver interface specs ?
  6. Feedback and errata for the 1.0.29 spec
  7. CL_INVALID_DEVICE_LIST seems to be missing in cl.h
  8. Is openCL suitable for task oriented parallelization really?
  9. How to compile OpenCL example in MS VC++?
  10. Passing scalar values to kernel
  11. OpenCL on combined CPU/FPGA systems?
  12. When will OpenCL implementations arrive?
  13. Is a event object can be passed to other command-queue?
  14. OpenCL C++ Bindings
  15. Math Function - fract -
  16. Rationale for eliminating Function Pointers
  17. support for multiple heterogeneous systems over a network?
  18. Syntax of vector literals conflicts with C99 comma operator.
  19. Discrepancy between cl.h and OpenCL Spec 1.33
  20. Is Khronos working on interoperability/deployment scenarios?
  21. OpenCL code samples
  22. OpenCL memory model
  23. OpenCL Books / tutorials
  24. Specification 1.33 Questions
  25. Compiling to Visual Studio
  26. Feedback and errate for the 1.0.33 spec
  27. Can the vector types be made more C++ friendly?
  28. How to compile OpenCL example in GCC?
  29. How to compile OpenCL example in GCC?
  30. setArg
  31. CL_KHR_gl_sharing documentation
  32. True Heterogeneous Computing
  33. Array of pointers in device memory
  34. OpenCL Quick Reference card out-of-date
  35. OpenCL Addition Example (Mac OS X 10.6 Snow *Leopard)
  36. cl.h please avoid bitshift definitions
  37. Undefined buffer object location ?
  38. OpenCL C# bindings
  39. Some newbie questions about OpenCL
  40. Spurious allocation in Default OpenGL ES application
  41. One cl_context includes devices from different cl_platforms?
  42. Limits/recommandations for number of contexts/queues?
  43. create context from list of devices with different types?
  44. Persistent storage on opencl GPU
  45. mapping buffers vs using host pointers
  46. address space on multiple chips
  47. Assigning a number to a __global int *p and resolving it
  48. work-size dimensions difference between 2 APIs
  49. performance diff clEnqueueWriteBuffer vs clEnqueueMapBuffer
  50. Why does OpenCL define 'bool' but does not define '_Bool'?
  51. input and output having different dimensions
  52. offline compilation ?
  53. Passing arrays of complex structures
  54. kernel execution returns CL_INVALID_VALUE
  55. Time of clReleaseMemObject : strange behaviour
  56. clEnqueueWriteBuffer question
  57. Error propagation from devices to application level
  58. evaluating side-effetcs and Logical && and || for vectors
  59. Newbie question
  60. completion of the kernel to retrieve buffer from device
  61. Using the cl_context_properties parameter
  62. clEnqueueReadBuffer() takes msec to complete???
  63. calling the same kernel object multiple times
  64. OpenCl and Nvidia!
  65. cl_mem and devices inside a context...
  66. clGetDeviceInfo
  67. non-blocking call to clEnqueueNDRangeKernel?
  68. How many CUDA registers uses an OpenCL kernel
  69. Error Propagation in OpenCL Specification
  70. Timeline for a future cluster/cloud extension?
  71. OpenCL + SiSoft Sandra
  72. OpenCL DDK?
  73. OpenCL harware support list
  74. PyOpenCL: OpenCL Python Bindings
  75. Why is 'cl_mem' associated to 'cl_context'?
  76. Unexpected output clGetContextInfo
  77. Provisions for separating compiling and linking?
  78. Can vector types be returned from functions?
  79. OpenCL syntax highlighting
  80. 3 Element Vectors in Memory
  81. profiling
  82. 2 data-parallel models
  83. Sharing Renderbuffer OpenGL object with OpenCL
  84. Sharing OpenGL object with OpenCL and use CPU device ?
  85. initializing __constant vector arrays
  86. Command Queue going invalid
  87. Installing opencl
  88. build sampler direcly on buffer object
  89. Profiling Code
  90. clGetDeviceIDs() failing
  91. cl.hpp: Kernel::getWorkGroupInfo bugs
  92. Is possible to porting opencl to other systems by myself
  93. Two small problems in Appendix D.3
  94. ATI Stream SDK v2.0 beta 3 released
  95. local memory within two different kernels in the same file?
  96. OpenCL bindings for Java & Scala
  97. Inteface layer
  98. Newbie question - Only see one of two GPUs on Macbook Pro
  99. Hello List
  100. vector types not friendly to C++ (specifically, std::vector)
  101. half conversion in host code
  102. can iPhone OS support OpenCL?
  103. Need help!
  104. VLA : workaround to get Variable Length Arrays
  105. Create Vertex Array With No Input
  106. Device-host memory communication
  107. Function Question
  108. Passing variable length structure to kernel
  109. Array reduction example
  110. Global writable parameters passing
  111. error to string?
  112. user defined data Structures as kernel arguments
  113. very weird problem with ADC examples on Snow Leopard 16,1
  114. Maximum private memory?
  115. Semantics system
  116. Reliable distributed computing w/ OpenCL, anyone doing this?
  117. Conflicting calling and naming conventions AMD/nVidia
  118. Running the same kernel on multiple devices
  119. Convolution Example/Tutorial from AMD
  120. Not having functions return values via pointer arguments
  121. How to report NVidia OpenCL driver problems?
  122. Non-power of 2 vector types
  123. Call to fract causing crash
  124. how fast is it as compared to OpenMP?
  125. OpenCL specification--Chinese version
  126. In the case the 2 or more platforms is aviailable
  127. Constant Memory latency
  128. specify work group sizes
  129. Passing pointers in a struct
  130. Local memory access question in the specification
  131. Single context, multiple devices, where does the memory go?
  132. cl_command_queue , cl_context as member variable of a class?
  133. Intel CPU drivers?
  135. passing constant value to kernel
  136. #include problems in Apple's implementation
  137. Wierd behavior of pointers to structs in constant memory.
  138. Spelling issue in quick reference card
  139. Question about "Definitions", Basic Ideas for MD-Simulation
  140. intel support for open cl
  141. passing in array of struct to kernels (and updating VBO)
  142. bakeoff
  143. Emacs-Kernelyzer
  144. Whises for OpenCL 1.1 and more!
  145. OpenCL + OpenGL (interop)
  146. OpenCL function syntax
  147. Moving data from __global to __private
  148. Port of Apple demos to Windows..
  149. OpenCL-z Khronos ICD compatible version
  150. Using AMD SDK with Nvidia driver and Nvidia samples with AMD
  151. About Khronos ICD model..
  152. CLH_ERROR_NO_BINARY_FOR_GPU for image2d_t
  153. LLVM compilation failure -- why?
  154. How to Include Common File into OCL file!
  155. Async kernel execution and data copy
  156. caching variables from arrays
  157. Finding a general lib for OpenCL
  158. OpenCL error at clEnqueueReadBuffer
  159. Cannot enqueue> ~65k threads
  160. how to set a buffer's memory to 0
  161. why use barrier?
  162. Convolution with Wrapped Edges
  163. system goes into some indefinite loop - adding two vectors
  164. How to kill a hung/slow kernel
  165. CL_DEVICE_IMAGE_SUPPORT with ATI cards on Snow Leo 10.6.2
  166. Multiple Image Inputs to OpenCL Kernel
  167. Fill array
  168. clBuildProgram returns CL_INVALID_BINARY for certain code
  169. CL_INVALID_WORK_GROUP_SIZE on MacOS 10.6.2 with ATI
  170. Predicate variable must be in register state space
  171. GPU Query
  172. Copying memory of zero size
  173. CLH_ERROR_NO_BINARY_FOR_GPU when not using sampler!?
  174. Linking problems with Nvidia`s OpenCL-Library in VS 2009
  175. CL_CONTEXT_DEVICES info different from clGetDeviceIDs
  176. description for CL_MEM_USE_HOST_PTR on the use of host_ptr
  177. Enabling double precision
  178. Asynchronous Events
  179. Single float2 Output from OpenCL Kernel
  180. Unmap crash with map_read
  181. clBuildProgram return 1
  182. Abysmal performance on HD4870 / Snow Leopard.. why?
  183. Error code -54
  184. Dynamically allocated shared memory
  185. CL_OUT_OF_RESOURCES problem when an expression gets 2 long?
  186. Writing to shared global memory
  187. Writing to an OpenGL Texture
  188. What is a uint4?
  189. anonymous_jit_identity exception
  190. OpenCL spec -- Table 7.1: Where do the ULP values come from?
  191. Accesing both Amd/nVidia OpenCL
  192. OpenMP / OpenCL CPU
  193. Working Linux OpenCL Driver
  194. how to use math.h functions in __kernel
  195. is clGetEventInfo thread-safe?
  196. extensions for cl / cl_gl + header files
  197. Should clGet*Info increment the reference to the cl_* type?
  198. GPGPU and rendering calculations on same GPU?
  199. clEnqueueNDRangeKernel max global_work_size
  200. Open CL Support for Solaris
  201. Driver Nvidia 195.62 problem
  202. Calculation of average values of an image sequence
  203. Constant memory
  204. Sharing Image Data between two processes
  205. Multiple command queues from the same device: why?
  206. How to define a function that processes N-vectors ?
  207. Very Basic Question
  208. out of resources when clEnqueueReadBuffer
  209. missing Double and Half FP_CONFIG
  210. GPU/CPU Thread allocation
  211. about pointer variable
  212. OpenCL compiler
  213. Building programs with pre-compiled binaries
  214. Buffer and context with multi devices
  215. size_t usage in OpenCL
  216. OpenCl+llvm+clang
  217. clBuildProgram fails when write_imageui is used
  218. clBuildProgram crashes with varying kernel args
  219. Strange results when using image objects
  220. OpenCL 1.0 HTML Reference Pages error
  221. bandwidth test
  222. Prevent kernel timeout on second GPU device
  223. have problem finding maximum in a work-group
  224. Backtracking algorithm and OpenCL?
  225. isequal() for ints?
  226. Why no async_work_group_copy for halfs in core specification
  227. vload_half and vloada_half
  228. __constant args cause Segfault in the OpenCL library
  229. how to run openCL on one CPU?
  230. OpenCL only for CPU (linux)
  231. Image2D objects in OpenCL and OpenCL kernel performance
  232. using the OpenCL ICD
  233. Apple OpenCL_OceanWave Demo crashes
  234. Complex type
  235. OpenCL and SSE
  236. CPU code for converting from floats to halfs?
  237. Kernel execution's problem
  238. opengl 3.2 core profile not compatible with cl_gl.h
  239. structs and function-declaration
  240. error LNK2019
  241. confusing duplication
  242. Doubles/Floats
  243. Arrays of Variable Length
  244. Controling register usage through clBuildProgram?
  245. Can't assign char numeric value in kernel
  246. Hello world program - compilation error
  247. valgrind shows a lot of errors with leak check
  248. [ASk] What good topic for my undergraduate thesis/research
  249. querying kernel execution status
  250. Passing a float4 as a pointer