arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2310.01461cs.PL
收藏

Awkward 即时(JIT)编译:开发者经验

Awkward Just-In-Time (JIT) Compilation: A Developer's Experience

Ianna Osborne, Jim Pivarski, Ioana Ifrim, Angus Hollands, Henry Schreiner

AI总结:

本文介绍了 Awkward Array 库借助 JIT 编译实现加速的多种技术,重点分析 RDataFrame、cppyy 及 Numba(含 GPU 版本)的相关实现与复用机制。

摘要:

Awkward Array 是一个可对嵌套、可变大小数据执行类 NumPy 计算的库,支持在 Python 中对任意数据结构进行面向数组的编程。然而,命令式(过程式)解决方案有时编写更简单或运行速度更快。高性能命令式编程需要编译;JIT 编译则让在交互式 Python 环境中进行编译变得便捷。Awkward Arrays 中的各类函数会将用户代码 JIT 编译为可执行机器码,它们采用多种不同技术,但复用了彼此的部分实现。我们讨论了借助 JIT 编译实现 Awkward Arrays 加速所用到的技术,重点关注 RDataFrame、cppyy 和 Numba,尤其是 GPU 上的 Numba:Awkward Arrays 与 RDataFrame 的相互转换;独立 cppyy;将 Awkward Arrays 传入和传出由 Numba 编译的 Python 函数;将 Awkward Arrays 传入由 Numba 为 GPU 编译的 Python 函数;以及无需任何 Python 依赖即可从 C++ 填充 Awkward Arrays 的仅头文件库。

英文摘要:

Awkward Array is a library for performing NumPy-like computations on nested, variable-sized data, enabling array-oriented programming on arbitrary data structures in Python. However, imperative (procedural) solutions can sometimes be easier to write or faster to run. Performant imperative programming requires compilation; JIT-compilation makes it convenient to compile in an interactive Python environment. Various functions in Awkward Arrays JIT-compile a user's code into executable machine code. They use several different techniques, but reuse parts of each others' implementations. We discuss the techniques used to achieve the Awkward Arrays acceleration with JIT-compilation, focusing on RDataFrame, cppyy, and Numba, particularly Numba on GPUs: conversions of Awkward Arrays to and from RDataFrame; standalone cppyy; passing Awkward Arrays to and from Python functions compiled by Numba; passing Awkward Arrays to Python functions compiled for GPUs by Numba; and header-only libraries for populating Awkward Arrays from C++ without any Python dependencies.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑