Memory module is the C++ backend for rlpack._C.memory.Memory class. Heavier workloads have been optimized with multithreading with OpenMP and CUDA (if CUDA compatible device is found).
More...
|
| offload |
| Template class to offload some heavier computation to specialised hardware. Functions will be executed in CUDA if CUDA device is available else OpenMP routines will be used to execute the functions on CPU.
|
|
|
class | C_Memory |
| The class C_Memory is the C++ backend for memory-buffer used in algorithms that stores transitions in a buffer. This class contains optimized routines to support Python front-end of rlpack._C.memory.Memory class. More...
|
|
class | SumTree |
| The class SumTree is a class which represents the Sum-Tree which is used in proportional prioritization. It implements all the methods necessary to create the Sum-Tree and sample from it. More...
|
|
class | SumTreeNode |
| The class SumTreeNode is a private class which represents a node in Sum-Tree. This is only used when we use proportional prioritization. More...
|
|
Memory module is the C++ backend for rlpack._C.memory.Memory class. Heavier workloads have been optimized with multithreading with OpenMP and CUDA (if CUDA compatible device is found).
◆ PYBIND11_MODULE()
Python bindings for C_Memory, C_MemoryData and all the opaque objects. All bindings are pickleable. Python binding for C_Memory class. Only relevant methods are exposed to Python