Man pages for duncantl/RCUDA
R Bindings for the CUDA Library for GPU Computing
| convertToPtr | Convert an R object to a pointer for use with CUDA |
| copyFromDevice | Copy data betwen R and GPU |
| createContext | Create or query current context |
| cuArray3DCreate | Creates a 3D CUDA array |
| cuArray3DGetDescriptor | Get a 3D CUDA array descriptor |
| cuArrayCreate | Creates a 1D or 2D CUDA array |
| cuArrayDestroy | Destroys a CUDA array |
| cuArrayGetDescriptor | Get a 1D or 2D CUDA array descriptor |
| cuCtxCreate | Create a CUDA context |
| cuCtxDestroy | Destroy a CUDA context |
| cuCtxDisablePeerAccess | Disables direct access to memory allocations in a peer... |
| cuCtxEnablePeerAccess | Enables direct access to memory allocations in a peer... |
| cuCtxGetApiVersion | Gets the context's API version. |
| cuCtxGetCacheConfig | Returns the preferred cache configuration for the current... |
| cuCtxGetCurrent | Returns the CUDA context bound to the calling CPU thread. |
| cuCtxGetDevice | Returns the device ID for the current context |
| cuCtxGetLimit | Returns resource limits |
| cuCtxGetSharedMemConfig | Returns the current shared memory configuration for the... |
| cuCtxPopCurrent | Pops the current CUDA context from the current CPU thread. |
| cuCtxPushCurrent | Pushes a context on the current CPU thread |
| cuCtxSetCacheConfig | Sets the preferred cache configuration for the current... |
| cuCtxSetCurrent | Binds the specified CUDA context to the calling CPU thread |
| cuCtxSetLimit | Set resource limits |
| cuCtxSetSharedMemConfig | Sets the shared memory configuration for the current context. |
| cuCtxSynchronize | Block for a context's tasks to complete |
| cuda | Invoke a GPU kernel |
| cudaArrayGetInfo | Gets info about the specified cudaArray |
| cudaChooseDevice | Select compute-device which best matches criteria |
| cudaCreateChannelDesc | Returns a channel descriptor using the specified format |
| cudaDeviceCanAccessPeer | Queries if a device may directly access a peer device's... |
| cudaDeviceDisablePeerAccess | Disables direct access to memory allocations on a peer... |
| cudaDeviceEnablePeerAccess | Enables direct access to memory allocations on a peer device. |
| cudaDeviceGetAttribute | Returns information about the device |
| cudaDeviceGetByPCIBusId | Returns a handle to a compute device |
| cudaDeviceGetCacheConfig | Returns the preferred cache configuration for the current... |
| cudaDeviceGetLimit | Returns resource limits |
| cudaDeviceGetPCIBusId | Returns a PCI Bus Id string for the device |
| cudaDeviceGetSharedMemConfig | Returns the shared memory configuration for the current... |
| cudaDeviceProp-class | Class '"cudaDeviceProp"' |
| cudaDeviceReset | Destroy all allocations and reset all state on the current... |
| cudaDeviceSetCacheConfig | Sets the preferred cache configuration for the current... |
| cudaDeviceSetLimit | Set resource limits |
| cudaDeviceSetSharedMemConfig | Sets the shared memory configuration for the current device. |
| cudaDeviceSynchronize | Wait for compute device to finish |
| cudaEventCreate | Creates an event object |
| cudaEventCreateWithFlags | Creates an event object with the specified flags |
| cudaEventDestroy | Destroys an event object |
| cudaEventElapsedTime | Computes the elapsed time between events |
| cudaEventQuery | Queries an event's status |
| cudaEventRecord | Records an event |
| cudaEventSynchronize | Waits for an event to complete |
| cudaFreeArray | Frees an array on the device |
| cudaFreeHost | Frees page-locked memory |
| cudaFuncGetAttributes | Find out attributes for a given function |
| cudaFuncSetCacheConfig | Sets the preferred cache configuration for a device function |
| cudaFuncSetSharedMemConfig | Sets the shared memory configuration for a device function |
| cudaGetChannelDesc | Get the channel descriptor of an array |
| cudaGetDevice | Returns which device is currently being used |
| cudaGetSymbolAddress | Finds the address associated with a CUDA symbol |
| cudaGetSymbolSize | Finds the size of the object associated with a CUDA symbol |
| cudaGraphicsMapResources | Map graphics resources for access by CUDA |
| cudaGraphicsResourceGetMappedPointer | Get an device pointer through which to access a mapped... |
| cudaGraphicsResourceSetMapFlags | Set usage flags for mapping a graphics resource |
| cudaGraphicsSubResourceGetMappedArray | Get an array through which to access a subresource of a... |
| cudaGraphicsUnmapResources | Unmap graphics resources. |
| cudaGraphicsUnregisterResource | Unregisters a graphics resource for access by CUDA |
| cudaHostAlloc | Allocates page-locked memory on the host |
| cudaHostGetDevicePointer | Passes back device pointer of mapped host memory allocated by |
| cudaHostGetFlags | Passes back flags used to allocate pinned host memory... |
| cudaHostRegister | Registers an existing host memory range for use by CUDA |
| cudaHostUnregister | Unregisters a memory range that was registered with... |
| cudaLaunch | Launches a device function |
| cudaMalloc3D | Allocates logical 1D, 2D, or 3D memory objects on the device |
| cudaMalloc3DArray | Allocate an array on the device |
| cudaMallocArray | Allocate an array on the device |
| cudaMallocHost | Allocates page-locked memory on the host |
| cudaMallocPitch | Allocates pitched memory on the device |
| cudaMemInfo | Determine the memory on the active GPU |
| cudaPeekAtLastError | Returns the last error from a runtime call |
| cudaPointerGetAttributes | Returns attributes about a specified pointer |
| cudaSetDevice | Set device to be used for GPU executions |
| cudaSetDeviceFlags | Sets flags to be used for device executions |
| cudaSetDoubleForDevice | Converts a double argument to be executed on a device |
| cudaSetDoubleForHost | Converts a double argument after execution on a device |
| cudaSetValidDevices | Set a list of devices that can be used for CUDA |
| cudaStreamAddCallback | Add a callback to a compute stream |
| cudaStreamCreate | Create an asynchronous stream |
| cudaStreamCreateWithFlags | Create an asynchronous stream |
| cudaStreamDestroy | Destroys and cleans up an asynchronous stream |
| cudaStreamQuery | Queries an asynchronous stream for completion status |
| cudaStreamSynchronize | Waits for stream tasks to complete |
| cudaStreamWaitEvent | Make a compute stream wait on an event |
| cudaVersion | Determine the version of the CUDA SDK |
| cuDeviceCanAccessPeer | Queries if a device may directly access a peer device's... |
| cuDeviceGet | Returns a handle to a compute device |
| cuDeviceGetAttribute | Returns information about the device |
| cuDeviceGetByPCIBusId | Returns a handle to a compute device |
| cuDeviceGetCount | Returns the number of compute-capable devices |
| cuDeviceGetName | Returns an identifer string for the device |
| cuDeviceGetPCIBusId | Returns a PCI Bus Id string for the device |
| cuDeviceTotalMem | Returns the total amount of memory on the device |
| cuEventCreate | Creates an event |
| cuEventDestroy | Destroys an event |
| cuEventElapsedTime | Computes the elapsed time between two events |
| cuEventQuery | Queries an event's status |
| cuEventRecord | Records an event |
| cuEventSynchronize | Waits for an event to complete |
| cuFuncGetAttribute | Returns information about a function |
| cuFuncGetAttributes | Get the attributes of CUDA kernel routine |
| cuFuncSetBlockShape | Sets the block-dimensions for the function |
| cuFuncSetCacheConfig | Sets the preferred cache configuration for a device function |
| cuFuncSetSharedMemConfig | Sets the shared memory configuration for a device function. |
| cuFuncSetSharedSize | Sets the dynamic shared-memory size for the function |
| cuGraphicsMapResources | Map graphics resources for access by CUDA |
| cuGraphicsResourceGetMappedPointer | Get a device pointer through which to access a mapped... |
| cuGraphicsResourceSetMapFlags | Set usage flags for mapping a graphics resource |
| cuGraphicsSubResourceGetMappedArray | Get an array through which to access a subresource of a... |
| cuGraphicsUnmapResources | Unmap graphics resources. |
| cuGraphicsUnregisterResource | Unregisters a graphics resource for access by CUDA |
| cuInit | Initialize CUDA |
| cuModuleGetFunction | Returns a function handle |
| cuModuleGetGlobal | Returns a global pointer from a module |
| cuModuleGetSurfRef | Returns a handle to a surface reference |
| cuModuleGetTexRef | Returns a handle to a texture reference |
| cuModuleLoad | Loads a compute module |
| cuModuleLoadData | Load a module's data |
| cuModuleLoadDataEx | Load a module's data with options |
| cuModuleLoadFatBinary | Load a module's data |
| cuModuleUnload | Unloads a module |
| cuPointerGetAttribute | Returns information about a pointer |
| CUresult-class | Class '"CUresult"' |
| cuStreamAddCallback | Add a callback to a compute stream |
| cuStreamCreate | Create a stream |
| cuStreamCreateWithPriority | Create a stream with the given priority |
| cuStreamDestroy | Destroys a stream |
| cuStreamGetFlags | Query the flags of a given stream |
| cuStreamGetPriority | Query the priority of a given stream |
| cuStreamQuery | Determine status of a compute stream |
| cuStreamSynchronize | Wait until a stream's tasks are completed |
| cuStreamWaitEvent | Make a compute stream wait on an event |
| getDeviceProperties | Query the number and details of the GPU devices |
| loadModule | Load a GPU module and access its Routines |
| mallocPitch | A higher-level interface to cudaMallocPitch |
| memoryFunctions | Memory operations |
| nvcc | Compile CUDA code |
| profileCUDA | Profiling functions for CUDA calls |
