Productivity, portability, performance

Ziogas, Alexandros Nikolaos; Schneider, Timo; Ben-Nun, Tal; Calotoiu, Alexandru; Matteis, Tiziano De; Licht, Johannes de Fine; Lavarini, Luca; Hoefler, Torsten

doi:10.1145/3458817.3476176

Cited by 19 publications

(4 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They present a workflow, that both keeps Python's high productivity and achieves portable performance across different architectures. [12]…”

Section: Related Literaturementioning

confidence: 99%

Evaluative Comparison of ASGI Web Servers: A Systematic Review

2024

International Journal of Science and Engineering Applications

View full text Add to dashboard Cite

This paper aims to research major ASGI (Asynchronous Server Gateway Interface) server implementations, including Uvicorn, Daphne, and Hypercorn, and provide a comprehensive comparison. Utilizing a methodology that incorporates both quantitative performance metrics and qualitative feature analysis, this study offers a thorough evaluation of these servers in the context of modern asynchronous web applications. In this study, performance metrics such as request handling capacity (RPS) and resource consumption (specifically, RAM consumption) are carefully measured under controlled conditions to identify the most efficient ASGI implementations. Additionally, we examine the features provided by each ASGI server implementation, covering critical aspects such as protocol support, scalability options, and an overview of license restrictions. As a result, this study compares the strengths and limitations of each ASGI implementation. Most importantly, it provides valuable insights for developers and system architects in selecting the most suitable ASGI server for their specific needs.

show abstract

“…They present a workflow, that both keeps Python's high productivity and achieves portable performance across different architectures. [12]…”

Section: Related Literaturementioning

confidence: 99%

Evaluative Comparison of ASGI Web Servers: A Systematic Review

2024

International Journal of Science and Engineering Applications

View full text Add to dashboard Cite

show abstract

“…For example, Python’s flexibility (e.g., monkey patching and flexible typing) disables many static optimizations. However, when restricting the syntax to high-performance Python (much of NumPy), then optimizations become simpler (Ziogas et al, 2021). Any language becomes more complex over time—Fortran 66 evolved into the complex Fortran 2018 language standard.…”

Section: Myth 10: Fortran Is Dead Long Live the Dsl!mentioning

confidence: 99%

Myths and legends in high-performance computing

Matsuoka

Domke

Wahib

et al. 2023

The International Journal of High Performance Computing Applica

Self Cite

View full text Add to dashboard Cite

In this thought-provoking article, we discuss certain myths and legends that are folklore among members of the high-performance computing community. We gathered these myths from conversations at conferences and meetings, product advertisements, papers, and other communications such as tweets, blogs, and news articles within and beyond our community. We believe they represent the zeitgeist of the current era of massive change, driven by the end of many scaling laws such as Dennard scaling and Moore’s law. While some laws end, new directions are emerging, such as algorithmic scaling or novel architecture research. Nevertheless, these myths are rarely based on scientific facts, but rather on some evidence or argumentation. In fact, we believe that this is the very reason for the existence of many myths and why they cannot be answered clearly. While it feels like there should be clear answers for each, some may remain endless philosophical debates, such as whether Beethoven was better than Mozart. We would like to see our collection of myths as a discussion of possible new directions for research and industry investment.

show abstract

“…Following its success, many other projects accelerate Python, either through bindings to existing C libraries such as CuPy [4], PyOpenCL [5], and PyKokkos [6] or by compiling a subset of Python to native code. Examples of the latter approach are Numba [7], Pythran [8], or Data-Centric Python [9].…”

Section: Introductionmentioning

confidence: 99%

Performance Evaluation of Python Parallel Programming Models: Charm4Py and mpi4py

Fink¹,

Liu²,

Choi³

et al. 2021

Preprint

View full text Add to dashboard Cite

Python is rapidly becoming the lingua franca of machine learning and scientific computing. With the broad use of frameworks such as Numpy, SciPy, and TensorFlow, scientific computing and machine learning are seeing a productivity boost on systems without a requisite loss in performance. While highperformance libraries often provide adequate performance within a node, distributed computing is required to scale Python across nodes and make it genuinely competitive in large-scale highperformance computing. Many frameworks, such as Charm4Py, DaCe, Dask, Legate Numpy, mpi4py, and Ray, scale Python across nodes. However, little is known about these frameworks' relative strengths and weaknesses, leaving practitioners and scientists without enough information about which frameworks are suitable for their requirements. In this paper, we seek to narrow this knowledge gap by studying the relative performance of two such frameworks: Charm4Py and mpi4py.We perform a comparative performance analysis of Charm4Py and mpi4py using CPU and GPU-based microbenchmarks other representative mini-apps for scientific computing.

show abstract

Productivity, portability, performance

Cited by 19 publications

References 38 publications

Evaluative Comparison of ASGI Web Servers: A Systematic Review

Evaluative Comparison of ASGI Web Servers: A Systematic Review

Myths and legends in high-performance computing

Performance Evaluation of Python Parallel Programming Models: Charm4Py and mpi4py

Contact Info

Product

Resources

About