include | |
skepu | |
src | |
unused_files | |
data_tune.h | A class not used currently but was helpful in storing tuning data |
device_mem_pointer_matrix_cl.h | Contains a class declaration for an object which represents an OpenCL device memory allocation for Matrix Container |
device_mem_pointer_matrix_cu.h | Contains a class declaration for an object which represents an CUDA device memory allocation for Matrix Container |
operator_macros_cucl.inl | Contains macro defintions for user functions using CUDA, OpenCL and CPU/OpenMP backend |
operator_macros_multi.inl | Contains macro defintions with support for different user functions for each back-end. Not used currently in the example code. Still experimental |
thread_management.h | Contains classes that help with thread management. Currently only Pthreads. This was used earlier when using multiple CUDA devices |
thread_pool.h | Contains class definition for thread pooling that was used for multi-GPU CUDA execution to reduce host thread creation overhead |
2dmapoverlap.h | Contains a class declaration for the MapOverlap skeleton |
2dmapoverlap.inl | Contains the definitions of non-backend specific member functions for the MapOverlap2D skeleton |
2dmapoverlap_cl.inl | Contains the definitions of OpenCL specific member functions for the MapOverlap2D skeleton |
2dmapoverlap_cpu.inl | Contains the definitions of CPU specific member functions for the MapOverlap2D skeleton |
2dmapoverlap_cu.inl | Contains the definitions of CUDA specific member functions for the MapOverlap2D skeleton |
2dmapoverlap_omp.inl | Contains the definitions of OpenCL specific member functions for the MapOverlap2D skeleton |
bandwidthMeasure.h | |
data_collector.h | Contains a declaration of a data collector class that simpifies data collection when testing SkePU |
debug.h | Defines a few macros that includes macros to output text when debugging. The macros use std::cerr |
device_allocations_cu.h | |
device_cl.h | Contains a class declaration for the object that represents an OpenCL device |
device_cu.h | Contains a class declaration for the object that represents a CUDA device |
device_mem_pointer_cl.h | Contains a class declaration for an object which represents an OpenCL device memory allocation for container |
device_mem_pointer_cu.h | Contains a class declaration for an object which represents an CUDA device memory allocation for Vector container |
deviceprop_cl.h | Declares a struct used to store OpenCL device properties |
environment.h | Contains a class declaration for Environment class |
environment.inl | Contains member function definitions for the Environment class |
exec_plan.h | Contains a class that stores information about which back ends to use when executing |
generate.inl | Contains the definitions of non-backend specific member functions for the Generate skeleton |
generate_cl.inl | Contains the definitions of OpenCL specific member functions for the Generate skeleton |
generate_cpu.inl | Contains the definitions of CPU specific member functions for the Generate skeleton |
generate_cu.inl | Contains the definitions of CUDA specific member functions for the Generate skeleton |
generate_kernels.h | Contains the OpenCL and CUDA kernels for the Generate skeleton |
generate_omp.inl | Contains the definitions of OpenMP specific member functions for the Generate skeleton |
helper_methods.h | Contains few helper methods that are used globally by different classes |
makedir.h | |
malloc_allocator.h | |
map.inl | Contains the definitions of non-backend specific member functions for the Map skeleton |
map_cl.inl | Contains the definitions of OpenCL specific member functions for the Map skeleton |
map_cpu.inl | Contains the definitions of CPU specific member functions for the Map skeleton |
map_cu.inl | Contains the definitions of CUDA specific member functions for the Map skeleton |
map_kernels.h | Contains the OpenCL and CUDA kernels for the Map skeleton |
map_omp.inl | Contains the definitions of OpenMP specific member functions for the Map skeleton |
map_sparse.inl | Contains the definitions of map methods for sparse matrices. All (CPU, OpenMP, CUDA,OpenCL) in one file |
maparray.inl | Contains the definitions of non-backend specific member functions for the MapArray skeleton |
maparray_cl.inl | Contains the definitions of OpenCL specific member functions for the MapArray skeleton |
maparray_cpu.inl | Contains the definitions of CPU specific member functions for the MapArray skeleton |
maparray_cu.inl | Contains the definitions of CUDA specific member functions for the MapArray skeleton |
maparray_kernels.h | Contains the OpenCL and CUDA kernels for the MapArray skeleton |
maparray_omp.inl | Contains the definitions of OpenMP specific member functions for the MapArray skeleton |
mapoverlap.inl | Contains the definitions of non-backend specific member functions for the MapOverlap skeleton |
mapoverlap_cl.inl | Contains the definitions of OpenCL specific member functions for the MapOverlap skeleton |
mapoverlap_convol_kernels.h | Contains the OpenCL and CUDA kernels for the MapOverlap convolution which supports overlap of neighbouring elements |
mapoverlap_cpu.inl | Contains the definitions of CPU specific member functions for the MapOverlap skeleton |
mapoverlap_cu.inl | Contains the definitions of CUDA specific member functions for the MapOverlap skeleton |
mapoverlap_kernels.h | Contains the OpenCL and CUDA kernels for the MapOverlap skeleton |
mapoverlap_omp.inl | Contains the definitions of OpenMP specific member functions for the MapOverlap skeleton |
mapreduce.inl | Contains the definitions of non-backend specific member functions for the MapReduce skeleton |
mapreduce_cl.inl | Contains the definitions of OpenCL specific member functions for the MapReduce skeleton |
mapreduce_cpu.inl | Contains the definitions of CPU specific member functions for the MapReduce skeleton |
mapreduce_cu.inl | Contains the definitions of CUDA specific member functions for the MapReduce skeleton |
mapreduce_kernels.h | Contains the OpenCL and CUDA kernels for the MapReduce skeleton |
mapreduce_omp.inl | Contains the definitions of OpenMP specific member functions for the MapReduce skeleton |
matrix.inl | Contains the definitions of non-backend specific member functions for the Matrix container |
matrix_cl.inl | Contains the definitions of OpenCL specific member functions of the Matrix class |
matrix_cu.inl | Contains the definitions of CUDA specific member functions of the Matrix class |
matrix_iterator.inl | Contains the definitions of Matrix::iterator class |
matrix_proxy.inl | Contains the definitions of the Matrix::proxy_elem class |
matrix_transpose.inl | Contains the definitions of the Matrix transpose functions for CPU, CUDA, OpenMP and OpenCL |
mem_pointer_base.h | |
operator_macros.h | Includes the macro files needed for the defined backends |
operator_macros_cl.inl | Contains macro defintions for user functions using OpenCL and CPU/OpenMP backend |
operator_macros_cpu.inl | Contains macro defintions for user functions using CPU/OpenMP backend |
operator_macros_cu.inl | Contains macro defintions for user functions using CUDA and CPU/OpenMP backend |
operator_type.h | Declares an enumeration with the different user function types |
reduce.inl | Contains the definitions of non-backend specific member functions for the Reduce skeleton |
reduce_2d.inl | Contains the definitions of non-backend specific member functions for the 2DReduce skeleton |
reduce_cl.inl | Contains the definitions of OpenCL specific member functions for the Reduce skeleton |
reduce_cl_2d.inl | Contains the definitions of OpenCL specific member functions for the 2DReduce skeleton |
reduce_common.h | Contains the definitions of common member functions for the Reduce skeleton that is used for both 1D and 2D reduction operations |
reduce_cpu.inl | Contains the definitions of CPU specific member functions for the Reduce skeleton |
reduce_cpu_2d.inl | Contains the definitions of CPU specific member functions for the 2DReduce skeleton |
reduce_cu.inl | Contains the definitions of CUDA specific member functions for the Reduce skeleton |
reduce_cu_2d.inl | Contains the definitions of CUDA specific member functions for the 2DReduce skeleton |
reduce_kernels.h | Contains the OpenCL and CUDA kernels for the Reduce skeleton (used for both 1D and 2D reduce operation) |
reduce_omp.inl | Contains the definitions of OpenMP specific member functions for the Reduce skeleton |
reduce_omp_2d.inl | Contains the definitions of OpenMP specific member functions for the 2DReduce skeleton |
scan.inl | Contains the definitions of non-backend specific member functions for the Scan skeleton |
scan_cl.inl | Contains the definitions of OpenCL specific member functions for the Scan skeleton |
scan_cpu.inl | Contains the definitions of CPU specific member functions for the Scan skeleton |
scan_cu.inl | Contains the definitions of CUDA specific member functions for the Scan skeleton |
scan_kernels.h | Contains the OpenCL and CUDA kernels for the Scan skeleton |
scan_omp.inl | Contains the definitions of OpenMP specific member functions for the Scan skeleton |
skepu_cuda_helpers.h | Contains the definitions of some helper functions related to CUDA backend |
skepu_opencl_helpers.h | Contains the definitions of some helper functions related to OpenCL backend |
sparse_matrix.inl | Contains the definitions of member functions of the SparseMatrix class that are not related to any backend |
sparse_matrix_cl.inl | Contains the definitions of member functions of the SparseMatrix class related to OpenCL backend |
sparse_matrix_cu.inl | Contains the definitions of member functions of the SparseMatrix class related to CUDA backend |
sparse_matrix_iterator.inl | Contains the definitions of the SparseMatrix::iterator class |
timer.h | |
timer_linux.h | Contains timer class that can be used by Linux systems |
trainer.h | |
generate.h | Contains a class declaration for the Generate skeleton |
globals.h | Contains some helper routines and typedefs that are shared by all classes |
map.h | Contains a class declaration for the Map skeleton |
maparray.h | Contains a class declaration for the MapArray skeleton |
mapoverlap.h | Contains a class declaration for the MapOverlap skeleton |
mapreduce.h | Contains a class declaration for the MapReduce skeleton |
matrix.h | Contains a class declaration for the Matrix container |
reduce.h | Contains a class declaration for the Reduce skeleton |
scan.h | Contains a class declaration for the Scan skeleton |
sparse_matrix.h | Contains a class declaration for the SparseMatrix container |
testing.h | Includes various testing helpers |
tuner.h | |
vector.h | Contains a class declaration for the Vector container |