Releases: AMYPAD/CuVec
Releases · AMYPAD/CuVec
cuvec v2.1.1 beta
- catch exceptions
- update
__init__
keywords - build updates
- add
CUVEC_DEBUG
flag (default:OFF
) - use CMake
add_compile_definitions
- add
- test updates
- increase verbosity
- documentation updates
- add contributing notes
- using editable install &
pytest
- using editable install &
- add contributing notes
- misc tidy
- clean
asarray
implementation
- clean
cuvec v2.1.0 beta
- add
asarray
convenience for wrapping external libraries - minor code tidy
cuvec v2.0.1 beta
- add external project usage documentation
- add more accurate build warning message
cuvec v2.0.0 beta
- add seamless
numpy
-like functionality- rename
cuvec.from_numpy()
=>cuvec.copy()
- make
cuvec.zeros()
andcuvec.copy()
returnnumpy.ndarray
-like objects
- rename
- fix potential installation errors
- add complete documentation
- add citation information
cuvec v1.0.0 beta
Unifying Python/C++/CUDA memory: Python buffered array <-> C++11 std::vector
<-> CUDA managed memory.
- Provides creation functions
- Python object
zeros
from_numpy
- C++ vector
CuVec<T>
with identical interface asstd::vector<T>
- CPython API (castable to
PyObject *
)PyCuVec<T> *PyCuVec_zeros(std::vector<Py_ssize_t> shape);
PyCuVec<T> *PyCuVec_zeros_like(PyCuVec<T> *other);
PyCuVec<T> *PyCuVec_deepcopy(PyCuVec<T> *other);
- Python object
- Quick start documentation
- 100% test coverage
- Allows CUDA-free installation for
sdist
Requires a C++11 compiler, CUDA compiler, and an NVIDIA GPU with compute capability 3.5 or greater.
Python functionality requires Python 3.6 or greater.
cuvec v0.1.0 alpha
Initial proof of concept.