USENIX Conference Policies
Optimizing the Performance of Dynamically-Linked Programs
W. Wilson Ho, Wei-Chau Chang, Lilian H. Leung, Silicon Graphics Computer Systems
Dynamically-linked programs in general do not perform as well as statically-linked programs. This paper identifies three main areas that account for the performance loss. First, symbols are referenced indirectly and thus extra instructions are required. Second, the overhead in run-time symbol resolution is significant. Third, poor locality of functions in shared libraries and data structures maintained by the run-time linker may result in poor memory utilization. This paper presents new optimization techniques we developed that address these three areas and significantly improve the performance of dynamically-linked programs. Also, we provide measurements of the performance improvement achieved. Most importantly, we show that all desirable features of shared libraries can be achieved without sacrificing performance.
author = {W. Wilson Ho and Wei-Chau Chang and Lilian H. Leung},
title = {Optimizing the Performance of {Dynamically-Linked} Programs},
booktitle = {USENIX 1995 Technical Conference (USENIX 1995 Technical Conference)},
year = {1995},
address = {New Orleans, LA},
url = {https://www.usenix.org/conference/usenix-1995-technical-conference/optimizing-performance-dynamically-linked-programs},
publisher = {USENIX Association},
month = jan
}