View Full Version : OpenCL - parallel programming of heterogeneous systems

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

  2. OpenCL 1.1 Rev. 44
  3. Coelesced memory access details?
  4. When are/aren‘t memory buffers necessary?
  5. clCreateSubBufferRect
  6. IBM OpenCL Common Runtime SDK
  7. C++ Object to handle confusing parts
  8. Array initialization failed
  9. Image/Buffer Objects : Which is fastest? When?
  10. Buffer size for clCreateImage3D with CL_INTENSITY
  11. Best way to implement this?
  12. Basics
  13. OpenCL tradeoffs with driver
  14. How to convert an OpenCL buffer to an OpenGl 3D texture
  15. Is it possible to batch a 2d portion of a grid?
  16. The design of Composable OpenCL 3'rd Party Library Standard
  17. C++ Binding Enhancements
  18. Barrier and Array copying
  19. Efficient use of memory in GPU
  20. local declaration inside the kernel
  21. using workgroups
  22. compile prob: ext. func __sind can't be found (NO doubles!)
  23. Device Synchronization ?
  24. A few quick questions from a newbie
  25. Open-source libOpenCL.so
  26. OpelCL doesn't see my ATI 5870
  27. Cross-platform issues MacOSX / Linux
  28. Can event callbacks be preempted by other event callbacks?
  29. Invalid Operation using clBuildProgram
  30. making a passed-in structptr accessible globally in kernel
  31. clBuildProgram pfn_notify
  32. Program Build Error
  33. Initializing array on the GPU!
  34. Buffers, Images and cuTexRef
  35. File-level var, touched by passed-in param, becomes unusable
  36. image_channel_order for Ultrasound image
  37. Sharing host memory with clSetKernelArg!
  38. two level of parallel
  39. free web-service for testing OpenCL applications on AMD GPUs
  40. Type casting question
  41. Kernel now working -- card to buy -- NVidia or ATI?
  42. Data Parallelism but with Unknown Iteration Count
  43. Problem in the kernel output!!
  44. Automatic Load-balancing compiler?
  45. OpenCL ideas for Masters Dissertation
  46. Struct in VS 2008 compiler
  47. How to draw an image from openCL?
  48. clCreateProgramWithSource returns CL_OUT_OF_HOST_MEMORY erro
  49. "random" kernel crash after running for minutes.... HEP!?
  50. AMD OpenCL set up.
  51. Failed Buffer Access
  52. Calling CPU kernels with lower overhead!
  53. Ability to READ multisample image buffers
  54. Compilation of the Kernel is always at runtime?
  55. OpenCL - local memory over multiple kernels
  56. strange array problem
  57. Error codes: clSetKernelArg
  58. How to copy global memory to local memory
  59. OutOfResources and InvalidCommandQueue errors
  60. OpenCL specification questions
  61. AMD OpenCL with Nivida GPU
  62. LU factorization
  63. How to pass complex structures to kernel?
  64. Getting wrong values from image2d_
  65. Work-groups scheduled to/on compute units
  66. How does the OpenCL Platform model map to actual hardware?
  67. Adding up a large array.
  68. Workgroups and global IDs
  69. Image objects
  70. Too many images?
  71. include files using "I -dir" function
  72. Maximum code size of kernel(s)
  73. Is there maximum amount of loaded kernels?
  74. Optimize compile time
  75. CPU vs GPU optimizations
  76. casting char* to struct
  77. Detecting same device on different platforms
  78. Calculations and results on different devices
  79. Copying data from GPU to another GPU
  80. searching through an array
  81. local_work_size question
  82. The order of parameters in kernel function
  83. Rotating Object about different axis
  84. Better way to get neighborhood on image2d_t?
  85. Inner loops with OpenCL
  86. Problem maybe in clBuildProgram
  87. Timing with clGetEventProfilingInfo
  88. how do work-groups affect performance?
  89. Non-blocking write buffer problem with multiple contexts
  90. What's going to happen if not releasing kernels
  91. Dynamically creating 2 dimensional local memory arrays
  92. Need a way to calculate theoretical FLOPS of a device
  93. opencl questions !!
  94. Task parallel programming
  95. thnks
  96. Sync across work groups
  97. vector datatypes
  98. 2D FFT Routine Needed
  99. How to make directshow an OpenMAX compliant
  100. clEnqueueNDRangeKernel() returns with error code "-54"
  101. clEnqueueTask is returning CL_INVALID_COMMAND_QUEUE
  102. AMD OpenCL vs Nvidia OpenCL
  104. Double type problem
  105. CPU Usage 200%
  106. Porting fortran spread() function to OpenCL
  107. How to read a clCreateImage3D
  108. Shared Data Structures
  109. clBuildProgram Problem?
  110. clSerKernelArg and __global qualified
  111. How can kernels that operate on single items be efficient?
  112. Practice exercises for learning OpenCL
  113. Very poor OpenCL performance
  114. Array of image_Xt objects as parameter?
  115. OpenCL/OpenGL interop problem with textures on NVIDIA
  116. Buffer with USE_HOST_PTR doesn't work
  117. busy wait when executing kernel
  118. CL_INVALID_BINARY (-42) while trying to use double on Tesla
  119. Finding embedded GPU board for robotics application
  120. The execution in GPU is not the same that CPU
  121. OpenCL and plain C++ implementatios of the same algorithm
  122. Can a kernel function call another kernel function?
  123. Default Optimization in OpenCL
  124. Question on OpenCL image memory consumption
  125. Is Device Memory copy required between different kernels
  126. Templates support
  127. lot of if and while loops inside a for loop
  128. how to initiate
  129. if and while loops better on gpu or cpu
  130. Problems in performing Saxpy with mapping/unmapping
  131. Can i call a same kernel more than a time?
  132. [XF] Float16 vs 16 float
  133. Allocating memory for kernels
  134. Performance on APU with different buffer creation strategies
  135. Tool for viewing threads' information
  136. Passing struct to kernel
  137. No speed up from using 2 GPUs
  138. Is write/read buffer a work on cpu or gpu side?
  139. OpenCL.NET
  140. kernel invocation
  141. header file in kernel file
  143. __constant array initialization
  144. Image2D OpenCL & Snow Leopard
  145. buffer for structure
  146. Verbose output from OpenCL context
  147. Some newbie questions about workitems and workgroup sizes.
  148. using Nvidia's visual profiler with OpenCL
  149. Macro to facilitate debugging
  150. Measuring, and discrepancy of sequential and parallel times
  151. double with select() function doesn't compile
  152. data type FILE in kernel
  153. CPU OpenCL local+private+constant memories
  154. CPU faster in vector addition than GPU
  155. Wondering when I should use clFlush or clFinish.
  156. DirectX 11 compute shader Versus OpenCL.
  157. Kernel with >8 float3 parameters fail on Intel device
  158. OCL programm without *.cl file
  159. 2D Vectors
  160. atomics for shared memory variables?
  161. How Can i work with matrix inside a kernel?
  162. New feature request : kernel parameters as 'static' !
  163. help with work items in work groups
  164. Problem Including Headers in Kernels
  165. clEnqueueKernel with implicit or or explicit local_size
  166. libOpenCL.so and header files
  167. Problem with coping golbal to local memory
  168. async_work_group_strided_copy
  169. OpenGL-OpenCL Interoperability for GL_TEXTURE_2D_ARRAY
  170. Add to OpenCL 1.2 some CUDA 4.0 and DX11.1 CS features!
  171. problem with clFinish
  172. Error in opencl-1.1.pdf ?
  173. Getting Started with OpenCL
  174. A couple of questions about C# wrappers
  175. Robustness
  176. c++ code into a OpenCL kernel????
  177. Arrays in the cl program
  178. Predefined Macros: device type
  179. setKernelArg as size in bytes and NULL for __global pointers
  180. OpenCV Libraries within .cl Files
  181. Support of Multi-dimensional arrays
  182. Documentation Issues : clEnqueue(Read|Write)Image
  183. Using pair barriers in the condtional statement
  184. Specifics of barriers
  185. clCreateContext() question.
  186. OpenCL only reads/writes from/to 1/4 of the buffer memory
  187. CL_MAP_WRITE: avoid copying data from device to host
  188. problems with memories
  189. EnqueueWriteBuffer vs direct writes performance
  190. preprocessor macros to detect if compiled for CPU or GPU
  191. Problem with clCreateFromGLTexture2D
  192. clGetPlatformIDs : Device Not Found
  193. Blocking memory transfers faster?
  194. Bullet Physics and OpenCL
  195. AMD parallel processing library
  196. opencl dealing with unsigned long long integers
  197. Data not copied from host to device
  198. Kernel call from within another kernel
  199. OpenCL conflict on shared workstation
  201. clBuildProgram failed
  202. Memory access pattern
  203. tiny change hangs kernel - vectorizing problem
  204. Memory test: cpu timers vs. gpu timer sample
  205. OpenCL doesn't work with multiple host threads?
  206. Enviroment Variables in VS2010 and XP
  207. Global workgroup size and performance
  208. Using the CPU and GPU in one algorithm
  209. Tails automatization
  210. options for passing short array
  211. Memory occupancy
  212. Inconsistent description of cl_image_format in 1.1 man pages
  213. Copy Memory objects
  214. OpenCL/OpenGL interoperability - error of "-1000" returned.
  215. Vectorizing for AMD; can't write output buffer elements
  216. Reaction-diffusion: an ideal system for OpenCL?
  217. Small matrix operations
  219. Dynamic workitems insertion while kernel is running
  220. passing array of typedef'd structs to kernel
  221. Strange problem with python + ctypes + opencl
  222. function clGetPlatformIDs returning error
  223. Question about OpenCL NVIDIA CUDAC
  224. Is it OpenCL properly installed in my PC?
  225. Problem with bitwise or
  226. letting runtime decide where to execute stuff
  227. Difference between several runs of opencl code
  228. Concurrent Kernel and data transfer on multi-GPU systems
  229. clEnqueueCopyBufferToImage
  230. recreate clCreateKernel
  231. Unable to pass structure to a opencl kernel
  232. Emulating vector insert/delete in kernel -is this safe?
  233. Command Queue
  234. Transfers between host and device memory
  235. Screen grabber on GPU for openCL/openGL/cuda
  236. How to get neighborhood pixels with shared memory
  237. Strange problem wirting to image
  238. How to represent 4x4 matrix?
  239. OpenCL/OpenGL Problems: clEnqueue{Acquire|Release}GLObjects
  240. Kernel code is not working for NVIDIA GPU but working CPU
  241. cl_ext_atomic_counters_32 vs global memory atomics
  243. Issues in OpenCL spec 1.2
  244. determine Registers per work-item and Shared Memory Per work
  245. I can't get a basic opencl program to run
  246. high precision
  247. clCreateSubBuffer and clreleaseMemObject
  248. OpenCL offline compilation
  249. Change arguments before start running
  250. multiple command-queues in the same context for one device