First Workshop on the High Performance Scripting Languages

In conjunction with PPoPP 2015

Saturday, February 7, 2015

San Francisco, California

8:30-10:00 Session 1: Automatic parallelization

A Julia-based Problem Solving Environment for HPC
Youfeng Wu, Todd Anderson, Raj Barik, Chunling Hu, Victor Lee, Hai Liu, Hongbo Rong, Tatiana Shpeisman, Geoff Lowney, and Paul Petersen (Intel Corporation)

Statement-Level Parallelism
Dibakar Gope and Mikko H. Lipasti (University of Wisconsin - Madison)

Automatic Discovery of Multi-level Parallelism in MATLAB
Arun Chauhan (Indiana University and Google Inc.) and Pushkar Ratnalikar (Indiana University)

10:00-10:30 Break

10:30-12:00 Session 2: Compiled modules

Efficient Compilation of High Level Python Numerical Programs with Pythran
Serge Guelton (Telecom Bretagne), Pierrick Brunet (INRIA/MOAIS), and Mehdi Amini

Furious.js: a Model for Offloading Compute-Intensive JavaScript Applications
Marat Dukhan, Robertson Taylor, Robert Guthrie, and Richard Vuduc (Georgia Institute of Technology)

Scripting Language Performance Through Interoperability
Simon A. F. Lund, Niels Bohr (University of Copenhagen), Bradford L. Chamberlain (Cray, Inc.) and Brian Vinter (University of Copenhagen)

12:00-2:00 Lunch

2:00-2:30 Invited talk
Understanding JavaScript: from benchmarks to virtual machines
Jan Vitek (Northeastern University)
Abstract: Creating a high-performance implementation of a language such as JavaScript presupposes an understanding of the behavior of real-world workloads. This talks summarizes some lessons learned analyzing large numbers of web pages, our experience creating benchmarks, and lists open problems and challenges for implementers.

2:30-3:30 Session 3: Parallel Extensions

Safe Parallel Programming in an Interpreted Language
Chen Ding, Brian Gernhardt, Pengcheng Li (University of Rochester), and Matthew Hertz (Canisius College).

RABID: A Parallel R
Hao Lin, Samuel P. Midkiff (Purdue University) and Shuo Yang (Huawei)

3:30-4:00 Break

4:00-5:00 Session 4: New compound instructions

Super-Bytecode Construction for Accelerating JavaScript Object Property Accesses
Seong-Won Lee and Soo-Mook Moon (Seoul National University).

Analysis and optimization of Javascript engines
Gem Dot, Alejandro Martínez and Antonio González (Universitat Politècnica de Catalunya)

5:00-6:00 Session 5: Improving the interpreter and its JIT compiler

Optimizing R VM with specialization
Haichuan Wang, David Padua (University of Illinois), Peng Wu (Huawei)

Deconstructing the Javascript Type System
Wonsun Ahn, Jiho Choi, Thomas Shull, Maria Garzara and Josep Torrellas (University of Illinois) @