Spyculative

This is the web site of Spyculative, a research project at the Compilers and Languages Group at Vienna University of Technology funded by the Austrian Science Fund (FWF) with the project number P23303-N23. The project ran from February 2011 until December 2014.

About

Modern programming languages offer a wide range of flexible features to programmers, but often at a large price in performance. The Spyculative project investigated the Python programming language to understand the performance of Python programs and discover ways of speeding them up.

Python is popular with many people who are not programmers in the traditional sense; for example, it is commonly used by researchers in the natural sciences for data processing and simulation tasks. Making Python programs execute faster can therefore have a large productivity impact across various disciplines.

In the Spyculative project we used various techniques to obtain information about the way Python programs are executed. We collected statistics from actual runs of the Python implementation as well as from a novel simulation-based approach which allows data collection at an unprecedented level of detail. The insights gained from this data allowed us to implement and validate some optimizations as well as identify key areas for further research. One of the implemented optimizations speeds up a large class of programs by up to 10%. Our data collection approach yields information which can be used to estimate the impact of other optimizations even before implementing them; in certain areas, speedups of over 30% are predicted by our simulator. In particular, we have demonstrated that adding data type annotations to Python programs (a feature to be adopted in future Python versions) can enable such highly beneficial optimizations.

Software

During the project we developed pylibjit, a Python library for compiling Python functions.

Publications

The following publications were produced over the course of the project:

• G. Barany. Python Interpreter Performance Deconstructed.
  Dyla'14 (colocated with PLDI), Edinburgh, UK, June 2014. [pdf] This is the author's version of the work. It is posted here for your personal use. Not for redistribution. The definitive Version of Record was published in Proceedings of the Workshop on Dynamic Languages and Applications, http://dx.doi.org/10.1145/2617548.2617552.
• G. Barany. pylibjit: A JIT Compiler Library for Python.
  17. Kolloquium Programmiersprachen und Grundlagen der Programmierung (KPS13), Wittenberg, Germany, October 2013. [pdf] [slides: pdf]
• G. Barany. Static and Dynamic Method Unboxing for Python.
  6. Arbeitstagung Programmiersprachen (ATPS 2013), Aachen, Germany, February 2013. [pdf] (The original publication appeared in volume 215 of Lecture Notes in Informatics.)
  Slides: [pdf]
• S. Brunthaler. Interpreter Instruction Scheduling.
  20th International Conference on Compiler Construction (CC'11), Saarbrücken, Germany, March/April 2011. [author's pdf] http://dx.doi.org/10.1007/978-3-642-19861-8_10

Members

People involved in the project:

• Jens Knoop (project lead)
• Gergö Barany
• Stefan Brunthaler

---