Improvements in CoMD Cell Method Performance
Times are all in μs/atom. System size is 4000 atoms. Hardware is Xeon E5-2630 v3 @ 2.4 Ghz, OS is Ubuntu 12.04. The 'Initial Time' column results from the minimal amount of code changes to get the compiler working. The 'Final Time' is the time after the tuning in this post. Julia The cell version contains the same issue with array operations as the nsquared version - the computation of dd allocate
PyPy の Tips - Qiita
PyPy を導入して結果的に Python 部分の処理速度や、処理できる秒間リクエスト数が大きく向上しました。 コードにあまり手を入れずにパフォーマンス向上ができるのは素晴らしいと思います。 Tips がいくつかあるのでそれを書きます。 Ubuntu PyPy で性能を出す OS として Ubuntu が確実だと考えた。 ダウンロードページには or download PyPy from your release vendor (usually an outdated version): Ubuntu (PPA), Debian, Homebrew, MacPorts, Fedora, Gentoo and Arch are known to package PyPy, with various degrees of being up-to-date. とあり、主な選択肢はこれらだと思う。
PyPy を本番に導入した
計画したのは半年以上前、検証は 2 ヶ月かかった。 結果的には CPU 使用率は半分になり性能は倍になった。もちろん、本番で、だ。 これから徐々に CPython 環境を PyPy 環境へと置き換えていく。PyPy の最大の魅力はその性能だろう。性能が大きく上がるため、既存環境にかかっているサーバ費用を削減することが出来る。 ただ、注意して欲しいのは PyPy はとてつもなくメモリーを消費する。 Python 環境でパフォーマンス向上を狙うには PyPy はとてもよい選択肢だと思う。とても安定しているし、互換性が本当に高い。 Python + Django という環境で、2 倍性能を上げることはそうそう出来ない。 ただ、PyPy が最後の砦ではあるので、これ以上のパフォーマンスを望む場合は言語を変更する必要がある。Golang なのか Elixir なのか。 PyPy を導入したことで、次
Visualization of JITted code
Hello. We're proud to announce the first public release of the jitviewer. As of now, jitviewer is a slightly internal tool that helps understanding how your Python source code is compiled by the PyPy's JIT all the way down to machine code. To install it, you need a very recent version of PyPy (newer than 9th of August), for example one of the nightly builds: install pip and distribute either by cr
PyPy and the future of the Python ecosystem
Python has a great versatile ecosystem but the competition is getting better, this talk is about how Python can keep up with these new languages and where PyPy fits into this. Recently we’ve seen the rise of new technologies like Go, Node.js and Julia, those have the ability to build an ecosystem on a clean slate and thus be better than Python in some aspects. What would it take to be as good as t
The GIL is dead: PyPy-STM
Take a big, non-multithreaded program, and run in on multiple cores! PyPy, the Python implementation written in Python, experimentally supports Software Transactional Memory (STM). It runs without the Global Interpreter Lock (GIL). The strength of STM is not only to remove the GIL, but to also enable a novel use of multithreading, inheritently safe, and more useful in the general case than other a
Python and PyPy performance (not) for dummies
In this talk we would like to have a short introduction on how Python programs are compiled and executed, with a special attention towards just in time compilation done by PyPy. PyPy is the most advanced Python interpreter around and while it should generally just speed up your programs there is a wide range of performance that you can get out of PyPy, ranging from slightly faster than CPython to
ijson on PyPy
I happen to follow Alex Gaynor on Twitter and his ravings on speed and general awesomeness of PyPy have inspired me to a small experiment. I have this iterative JSON parser — ijson — which is a ctypes-based wrapper around C library yajl by Lloyd Hilaiel. I don't know of any pure Python iterative JSON parsers so I decided to implement one and see how it compares to yajl by speed under PyPy. It wort
PyPy and ijson - a guest blog post
This gem was posted in the ijson issue tracker after some discussion on #pypy, and Dav1dde kindly allowed us to repost it here: "So, I was playing around with parsing huge JSON files (19GiB, testfile is ~520MiB) and wanted to try a sample code with PyPy, turns out, PyPy needed ~1:30-2:00 whereas CPython 2.7 needed ~13 seconds (the pure python implementation on both pythons was equivalent at ~8 min
uwsgi and pypy
uwsgi_on_pypy.md Deploying pypy on uwsgi Instructions are kind of sporadic around the internet, so I thought I would gather them all in one place. The following example uses a Flask app as the thing deployed. You should only have to this once, and then you can pass the bin around. Requirements pypy 2.x (tested) uwsgi 1.9.11+ (trunk as of this gist) Build translated pypy binary and pypy lib. Follow
Bulding an interpreter in RPython - PyCon SE 2015
Julian Berman Target audience: Advanced users RPython is a language and toolchain for building interpreters, most prominently PyPy, a Python interpreter. But RPython is a powerful tool for writing interpreters for many dynamic languages. We'll learn how to write a simple interpreter in RPython by implementing a parser, bytecode compiler and VM for a small language.
[Video 223] Julian Berman: Building an interpreter in RPython - Daily Tech Video
[Video 223] Julian Berman: Building an interpreter in RPython PyPy, an alternative implementation of Python, has been gaining attention and interest over the last few years, in no small part because of its high speed. PyPy has, at its core, a small language called RPython (“restricted Python”) in which PyPy is implemented. In theory, you can use RPython to implement other languages. In this talk,
リリース、障害情報などのサービスのお知らせ
最新の人気エントリーの配信
j次のブックマーク
k前のブックマーク
lあとで読む
eコメント一覧を開く
oページを開く
GitHub - pygobject/pgi: [Unmaintained: Use PyGObject instead] GTK+ / GObject Introspection Bindings for PyPy.![GitHub - pygobject/pgi: [Unmaintained: Use PyGObject instead] GTK+ / GObject Introspection Bindings for PyPy.](https://cdn-ak-scissors.b.st-hatena.com/image/square/68352604cc672c2656e93c507c7f5f9851552b06/height=288;version=1;width=512/https%3A%2F%2Fopengraph.githubassets.com%2F65e210cd19e7ac89c9eb3274a07c4a9f0318e9494e5b9850cbdf2380493d0050%2Fpygobject%2Fpgi)
Python3に準拠したPyPy 安定版をリリース - python.jp
PyPy 2.6.1 released
Antonio Cuni - Python and PyPy performance (not) for dummies
「Visual Studio 2015」に対応した「Python Tools for Visual Studio 2.2」が正式版に
Client Challenge
Client Challenge
Releases · pypyjs/pypyjs
