[ buster ]
[ bullseye ]
[ 原始碼： pycuda ]
套件：python3-pycuda-dbg（2020.1~dfsg1-1） [contrib]
Python 3 module to access Nvidia‘s CUDA API (debug extensions)
PyCUDA lets you access Nvidia‘s CUDA parallel computation API from Python. Several wrappers of the CUDA API already exist–so what’s so special about PyCUDA?
* Object cleanup tied to lifetime of objects. This idiom, often called RAII in C++, makes it much easier to write correct, leak- and crash-free code. PyCUDA knows about dependencies, too, so (for example) it won’t detach from a context before all memory allocated in it is also freed. * Convenience. Abstractions like pycuda.driver.SourceModule and pycuda.gpuarray.GPUArray make CUDA programming even more convenient than with Nvidia’s C-based runtime. * Completeness. PyCUDA puts the full power of CUDA’s driver API at your disposal, if you wish. * Automatic Error Checking. All CUDA errors are automatically translated into Python exceptions. * Speed. PyCUDA’s base layer is written in C++, so all the niceties above are virtually free. * Helpful Documentation.
This package contains debug extensions for the Python 3 debug interpreter.
其他與 python3-pycuda-dbg 有關的套件
|
|
|
|
-
- dep: libboost-python1.74.0 (>= 1.74.0)
- Boost.Python Library
-
- dep: libboost-python1.74.0-py39
- 本虛擬套件由這些套件填實： libboost-python1.74.0
-
- dep: libboost-thread1.74.0 (>= 1.74.0)
- portable C++ multi-threading
-
- dep: libc6 (>= 2.14)
- GNU C 函式庫：共用函式庫
同時作為一個虛擬套件由這些套件填實： libc6-udeb
-
- dep: libcuda1 (>= 450.66)
- NVIDIA CUDA Driver Library
- 或者 libcuda.so.1 (>= 450.66)
- 套件暫時不可用
-
- dep: libcurand10
- NVIDIA cuRAND Library
-
- dep: libgcc-s1 (>= 3.0)
- GCC 支援函式庫
-
- dep: libstdc++6 (>= 5.2)
- GNU Standard C++ Library v3
-
- dep: python3-dbg (<< 3.10)
- debug build of the Python 3 Interpreter (version 3.9)
- dep: python3-dbg (>= 3.9~)
-
- dep: python3-numpy (>= 1:1.16.0~rc1)
- Fast array facility to the Python 3 language
-
- dep: python3-numpy-abi9
- 本虛擬套件由這些套件填實： python3-numpy
-
- dep: python3-pycuda (= 2020.1~dfsg1-1)
- Python 3 module to access Nvidia‘s CUDA parallel computation API