View Full Version : OpenCL

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

  1. Getting wrong values from image2d_
  2. Work-groups scheduled to/on compute units
  3. How does the OpenCL Platform model map to actual hardware?
  4. Adding up a large array.
  5. Workgroups and global IDs
  6. Image objects
  7. Too many images?
  8. include files using "I -dir" function
  9. Maximum code size of kernel(s)
  10. Is there maximum amount of loaded kernels?
  11. Optimize compile time
  12. CPU vs GPU optimizations
  13. casting char* to struct
  14. Detecting same device on different platforms
  15. Calculations and results on different devices
  16. Copying data from GPU to another GPU
  17. searching through an array
  18. local_work_size question
  19. The order of parameters in kernel function
  20. Rotating Object about different axis
  21. Better way to get neighborhood on image2d_t?
  22. Inner loops with OpenCL
  23. Problem maybe in clBuildProgram
  24. Timing with clGetEventProfilingInfo
  25. how do work-groups affect performance?
  26. Non-blocking write buffer problem with multiple contexts
  27. What's going to happen if not releasing kernels
  28. Dynamically creating 2 dimensional local memory arrays
  29. opencl questions !!
  30. Task parallel programming
  31. thnks
  32. Sync across work groups
  33. vector datatypes
  34. 2D FFT Routine Needed
  35. How to make directshow an OpenMAX compliant
  36. clEnqueueNDRangeKernel() returns with error code "-54"
  37. clEnqueueTask is returning CL_INVALID_COMMAND_QUEUE
  38. AMD OpenCL vs Nvidia OpenCL
  40. Double type problem
  41. CPU Usage 200%
  42. Porting fortran spread() function to OpenCL
  43. How to read a clCreateImage3D
  44. Shared Data Structures
  45. clBuildProgram Problem?
  46. clSerKernelArg and __global qualified
  47. How can kernels that operate on single items be efficient?
  48. Practice exercises for learning OpenCL
  49. Very poor OpenCL performance
  50. Array of image_Xt objects as parameter?
  51. OpenCL/OpenGL interop problem with textures on NVIDIA
  52. Buffer with USE_HOST_PTR doesn't work
  53. busy wait when executing kernel
  54. CL_INVALID_BINARY (-42) while trying to use double on Tesla
  55. Finding embedded GPU board for robotics application
  56. The execution in GPU is not the same that CPU
  57. OpenCL and plain C++ implementatios of the same algorithm
  58. Can a kernel function call another kernel function?
  59. Default Optimization in OpenCL
  60. Question on OpenCL image memory consumption
  61. Is Device Memory copy required between different kernels
  62. lot of if and while loops inside a for loop
  63. how to initiate
  64. if and while loops better on gpu or cpu
  65. Problems in performing Saxpy with mapping/unmapping
  66. Can i call a same kernel more than a time?
  67. [XF] Float16 vs 16 float
  68. Allocating memory for kernels
  69. Performance on APU with different buffer creation strategies
  70. Tool for viewing threads' information
  71. Passing struct to kernel
  72. No speed up from using 2 GPUs
  73. Is write/read buffer a work on cpu or gpu side?
  74. OpenCL.NET
  75. kernel invocation
  76. header file in kernel file
  78. __constant array initialization
  79. buffer for structure
  80. Verbose output from OpenCL context
  81. Some newbie questions about workitems and workgroup sizes.
  82. using Nvidia's visual profiler with OpenCL
  83. Macro to facilitate debugging
  84. Measuring, and discrepancy of sequential and parallel times
  85. double with select() function doesn't compile
  86. data type FILE in kernel
  87. CPU OpenCL local+private+constant memories
  88. CPU faster in vector addition than GPU
  89. Wondering when I should use clFlush or clFinish.
  90. DirectX 11 compute shader Versus OpenCL.
  91. OCL programm without *.cl file
  92. 2D Vectors
  93. atomics for shared memory variables?
  94. How Can i work with matrix inside a kernel?
  95. help with work items in work groups
  96. Problem Including Headers in Kernels
  97. clEnqueueKernel with implicit or or explicit local_size
  98. Problem with coping golbal to local memory
  99. async_work_group_strided_copy
  100. OpenGL-OpenCL Interoperability for GL_TEXTURE_2D_ARRAY
  101. problem with clFinish
  102. Error in opencl-1.1.pdf ?
  103. Getting Started with OpenCL
  104. A couple of questions about C# wrappers
  105. c++ code into a OpenCL kernel????
  106. Arrays in the cl program
  107. OpenCV Libraries within .cl Files
  108. Documentation Issues : clEnqueue(Read|Write)Image
  109. Using pair barriers in the condtional statement
  110. Specifics of barriers
  111. clCreateContext() question.
  112. OpenCL only reads/writes from/to 1/4 of the buffer memory
  113. problems with memories
  114. EnqueueWriteBuffer vs direct writes performance
  115. preprocessor macros to detect if compiled for CPU or GPU
  116. Problem with clCreateFromGLTexture2D
  117. clGetPlatformIDs : Device Not Found
  118. Blocking memory transfers faster?
  119. Bullet Physics and OpenCL
  120. AMD parallel processing library
  121. opencl dealing with unsigned long long integers
  122. Data not copied from host to device
  123. Kernel call from within another kernel
  124. OpenCL conflict on shared workstation
  126. clBuildProgram failed
  127. Memory access pattern
  128. tiny change hangs kernel - vectorizing problem
  129. Memory test: cpu timers vs. gpu timer sample
  130. OpenCL doesn't work with multiple host threads?
  131. Enviroment Variables in VS2010 and XP
  132. Global workgroup size and performance
  133. Using the CPU and GPU in one algorithm
  134. options for passing short array
  135. Memory occupancy
  136. Inconsistent description of cl_image_format in 1.1 man pages
  137. Copy Memory objects
  138. Vectorizing for AMD; can't write output buffer elements
  139. Reaction-diffusion: an ideal system for OpenCL?
  140. Small matrix operations
  142. passing array of typedef'd structs to kernel
  143. Strange problem with python + ctypes + opencl
  144. function clGetPlatformIDs returning error
  145. Question about OpenCL NVIDIA CUDAC
  146. Is it OpenCL properly installed in my PC?
  147. Problem with bitwise or
  148. Difference between several runs of opencl code
  149. Concurrent Kernel and data transfer on multi-GPU systems
  150. clEnqueueCopyBufferToImage
  151. recreate clCreateKernel
  152. Unable to pass structure to a opencl kernel
  153. Emulating vector insert/delete in kernel -is this safe?
  154. Command Queue
  155. Transfers between host and device memory
  156. Screen grabber on GPU for openCL/openGL/cuda
  157. How to get neighborhood pixels with shared memory
  158. Strange problem wirting to image
  159. How to represent 4x4 matrix?
  160. OpenCL/OpenGL Problems: clEnqueue{Acquire|Release}GLObjects
  161. Kernel code is not working for NVIDIA GPU but working CPU
  162. cl_ext_atomic_counters_32 vs global memory atomics
  164. Issues in OpenCL spec 1.2
  165. determine Registers per work-item and Shared Memory Per work
  166. I can't get a basic opencl program to run
  167. high precision
  168. clCreateSubBuffer and clreleaseMemObject
  169. OpenCL offline compilation
  170. Change arguments before start running
  171. multiple command-queues in the same context for one device
  172. Sampler 2D CLK_ADDRESS_REPEAT problem.
  173. Allocate __private memory inside a kernel
  174. Naive problem with Images and Kernels
  175. normalize( float4 ) precision errors
  176. compileWithBinnaries and calling Kernels
  177. Researches with OpenCL and simple code with binaries
  178. OpenCL Bandwidth Testkernel
  179. Opencl arbitary precision and calculating factorial
  180. Problem with normalized image coordinates
  181. Local memory simple counter
  182. Static Libraries
  183. "* has not been declared" when including cl.hpp
  184. OpenCL semaphores again and again...
  185. Forced stopping a launched kernel
  186. Deleting buffer in c++ binding
  187. Find a median in an unsorted array
  188. OpenCL books
  189. [newbie] OpenCL code within C++ program
  190. Failed to build
  191. Kernel uses too much local data
  192. Callback When Event Already Set?
  193. Arbitrary-precision arithmetic
  194. getting number of CL-GL interop devices creates sigsegv
  195. driver falls while kernel is being executed
  196. work item adjacency for 2D and 3D work ranges
  197. Recursion ia possible or not
  198. How do I pass 7 arrays to device for kernal processing?
  199. help with globalWorkSize
  200. opencl debugger
  201. When is sizeof(cl_mem) in clSetKernelArg not cl_mem?
  202. My kernel returns # of bytes instead of value of variable
  203. Compile OpenCL SDK 1.5 Samples in VC 2010
  204. Passing a especific library in compilation of Kernel
  205. Completely Starter in OpenCL
  206. clEnqueueReadBuffer fails with BSOD
  207. opencl programming for face recognition
  208. opencl programming
  209. clCreateFromGLTexture2D returns CL_INVALID_IMAGE_FORMAT_DESC
  210. Opencl setting up kdevelop + cmake
  211. Starter: matrix mul
  212. Distributed compilation
  213. GPU parallelism
  214. [OS X, AMD Radeon] Kernel execution freezes system
  215. Searching for non 0 values in a sparse array
  216. Kernel pre-compilation
  217. Maximum array index limited to 16 bits ?
  218. Trouble with first OpenCL program
  219. Runtime Error
  220. How to bind an OpenCL image 2d to a ci_image?
  221. [OS X, CoreImage]How to bind a CIImage to an openCL image2d?
  222. Interoperability block texture access
  223. Newbi: add two matrices
  224. Crash after trying recreate buffers
  225. Caching of source files
  226. clbuildprogram
  227. Is there a way to post and read the threads via e-mail?
  228. clBuildProgram(), -I option to include another folder .h
  229. clSetKernelArg set NULL __global buffer pointer ( Unclear )
  230. CL_OUT_OF_RESOURCES with any more than 49152 byte local mem.
  231. Math constant definitions
  232. normalize creating some compiler errors ?!?
  233. What is best way to implement an atomic add with clamp?
  234. Error in pointer arithmetic
  235. float VS floatN
  236. Second chance exception after kernel execution
  237. Transposed matrix-vector product in OpenCL
  238. float4 and possible out of range?
  239. jpeg compression opencl on Matlab
  240. Avoiding data alignment in OpenCL
  241. Kernel precompilation
  242. Reading part of a 2D image
  243. clEnqueueMapBuffer in discrete systems
  244. minimal efficient workgroup size
  245. Normalized vs unnormalized
  246. Redistributing OpenCL.lib
  247. OpenCL, NVIDIA on Windows 7 - Program freezes
  248. OpenCL functions
  249. workaround for no pointers to image2d_t restriction
  250. How to get the warp/wavefront size in runtime?