Hallo,
I am trying to venture into the world of gpu computing, but im having some problems getting the examples from the sds to work. The example I am trying is the oclMarchingCube project. It compiles fine (all of the projects do, apart from the ones that links to dx10), but it returns an error in the first clBuildProgram() call. I am able to remeove this eror by not passing in any build options, but that couses the second clBuildProgram() call to fail.
Here is the output log created by the program:
oclMarchingCubesUsing CL-GL Interop...
CL_DEVICE_NAME: GeForce 8800 GTX
CL_DEVICE_VENDOR: NVIDIA Corporation
CL_DRIVER_VERSION: 263.06
CL_DEVICE_VERSION: OpenCL 1.0 CUDA
CL_DEVICE_TYPE: CL_DEVICE_TYPE_GPU
CL_DEVICE_MAX_COMPUTE_UNITS: 16
CL_DEVICE_MAX_WORK_ITEM_DIMENSIONS: 3
CL_DEVICE_MAX_WORK_ITEM_SIZES: 512 / 512 / 64
CL_DEVICE_MAX_WORK_GROUP_SIZE: 512
CL_DEVICE_MAX_CLOCK_FREQUENCY: 1350 MHz
CL_DEVICE_ADDRESS_BITS: 32
CL_DEVICE_MAX_MEM_ALLOC_SIZE: 182 MByte
CL_DEVICE_GLOBAL_MEM_SIZE: 731 MByte
CL_DEVICE_ERROR_CORRECTION_SUPPORT: no
CL_DEVICE_LOCAL_MEM_TYPE: local
CL_DEVICE_LOCAL_MEM_SIZE: 16 KByte
CL_DEVICE_MAX_CONSTANT_BUFFER_SIZE: 64 KByte
CL_DEVICE_QUEUE_PROPERTIES: CL_QUEUE_OUT_OF_ORDER_EXEC_MODE_ENABLE
CL_DEVICE_QUEUE_PROPERTIES: CL_QUEUE_PROFILING_ENABLE
CL_DEVICE_IMAGE_SUPPORT: 1
CL_DEVICE_MAX_READ_IMAGE_ARGS: 128
CL_DEVICE_MAX_WRITE_IMAGE_ARGS: 8
CL_DEVICE_SINGLE_FP_CONFIG: INF-quietNaNs round-to-nearest round-to-zero round-to-inf fma
CL_DEVICE_IMAGE <dim> 2D_MAX_WIDTH 4096
2D_MAX_HEIGHT 32768
3D_MAX_WIDTH 2048
3D_MAX_HEIGHT 2048
3D_MAX_DEPTH 2048
CL_DEVICE_EXTENSIONS: cl_khr_byte_addressable_store
cl_khr_icd
cl_khr_gl_sharing
cl_nv_d3d9_sharing
cl_nv_d3d10_sharing
cl_khr_d3d10_sharing
cl_nv_d3d11_sharing
cl_nv_compiler_options
cl_nv_device_attribute_query
cl_nv_pragma_unroll
CL_DEVICE_COMPUTE_CAPABILITY_NV: 1.0
NUMBER OF MULTIPROCESSORS: 16
NUMBER OF CUDA CORES: 128
CL_DEVICE_REGISTERS_PER_BLOCK_NV: 8192
CL_DEVICE_WARP_SIZE_NV: 32
CL_DEVICE_GPU_OVERLAP_NV: CL_FALSE
CL_DEVICE_KERNEL_EXEC_TIMEOUT_NV: CL_TRUE
CL_DEVICE_INTEGRATED_MEMORY_NV: CL_FALSE
CL_DEVICE_PREFERRED_VECTOR_WIDTH_<t> CHAR 1, SHORT 1, INT 1, LONG 1, FLOAT 1, DOUBLE 0
!!! Error # -42 at file c:\programdata\nvidia corporation\nvidia gpu computing sdk 3.2\opencl\src\oclmarchingcubes\oclmarchingcubes.cpp, line 522
-----------------------------------------------------------
Build Log:
: Considering profile 'compute_10' for gpu='sm_10' in 'cuModuleLoadDataEx_4'
-----------------------------------------------------------
Writing ptx to separate file: oclMarchinCubes.ptx ...
!!! Error # -34 (CL_INVALID_CONTEXT) at line 96 , in file c:\programdata\nvidia corporation\nvidia gpu computing sdk 3.2\opencl\src\oclmarchingcubes\oclscan_launcher.cpp !!!
Exiting...
-----------------------------------------------------------
Any ideas?