Automatically Mining Program Build Information via Signature Matching
This addresses the need for efficient auditing and benchmarking in HPC systems, but it is incremental as it applies an existing signature-matching method to a new domain.
The researchers tackled the problem of automatically extracting program build information, such as compilers and libraries, by developing a tool that uses signature-based detection on program binaries, and the experiment showed it successfully identified many compilers, libraries, and their versions.
Program build information, such as compilers and libraries used, is vitally important in an auditing and benchmarking framework for HPC systems. We have developed a tool to automatically extract this information using signature-based detection, a common strategy employed by anti-virus software to search for known patterns of data within the program binaries. We formulate the patterns from various "features" embedded in the program binaries, and the experiment shows that our tool can successfully identify many different compilers, libraries, and their versions.