GPCE 2017
Mon 23 - Tue 24 October 2017 Vancouver, Canada
co-located with SPLASH 2017
Tue 24 Oct 2017 10:55 - 11:20 at Regency A - Performance Chair(s): Matthew Flatt

This paper examines the causes and extent of code size overhead caused by the ARM calling convention in Thumb-2 binaries. We show that binaries generated from C++ source files generally have higher amounts of calling convention overhead, and present a binary file optimizer to eliminate some of that overhead. Calling convention overhead can negatively impact power consumption, flash memory costs, and chip size in embedded or otherwise resource-constrained domains. This is particularly true on platforms using "compressed" instruction sets, such as the 16-bit ARM Thumb and Thumb-2 instruction sets, used in virtually all smartphones and in many other smaller-scale embedded devices. In this paper, we examine the extent of calling convention overhead in practical software, and compare the results of C and C++ programs, and find that C++ programs generally have a higher percentage of calling-convention overhead. Finally, we demonstrate a tool capable of eliminating some of this overhead, particularly in the case of C++ programs, by modifying the calling conventions on a per-procedure basis.

http://dl.acm.org/authorize?N47291
this URL might only work when visiting from a http://www.sigplan.org/ URL.

Tue 24 Oct

Displayed time zone: Tijuana, Baja California change

10:30 - 12:00
PerformanceGPCE 2017 at Regency A
Chair(s): Matthew Flatt University of Utah
10:30
25m
Talk
Quoted Staged Rewriting: A Practical Approach to Library-Defined OptimizationsBest Paper
GPCE 2017
DOI Authorizer link Media Attached
10:55
25m
Talk
Reducing Calling Convention Overhead in Object-Oriented Programming on Embedded ARM Thumb-2 Platforms
GPCE 2017
Joseph Caldwell University of Tokyo, Japan, Shigeru Chiba University of Tokyo, Japan
DOI Authorizer link
11:20
25m
Talk
RaTrace: Simple and Efficient Abstractions for BVH Ray Traversal Algorithms
GPCE 2017
Arsène Pérard-Gayot Saarland University, Germany, Martin Weier Bonn-Rhein-Sieg University of Applied Sciences, Germany, Richard Membarth DFKI, Germany, Philipp Slusallek DFKI, Germany, Roland Leißa Saarland University, Germany, Sebastian Hack Saarland University, Germany
DOI Authorizer link
11:45
15m
Talk
Towards Compositional and Generative Tensor OptimizationsShort paper
GPCE 2017
Adilla Susungi MINES ParisTech, France, Norman A. Rink TU Dresden, Germany, Jeronimo Castrillon TU Dresden, Germany, Immo Huismann TU Dresden, Germany, Albert Cohen Inria, France / ENS, France, Claude Tadonki MINES ParisTech, France, Jörg Stiller TU Dresden, Germany, Jochen Fröhlich TU Dresden, Germany
DOI Authorizer link