We’ve all shared the frustration — software updates that are intended to make our applications run faster inadvertently end up doing the opposite. These bugs, dubbed performance regressions, are time consuming to fix since locating software errors normally requires substantial human intervention.
To overcome this obstacle, researchers at Texas A&M, in collaboration with computer scientists at Intel Labs, have developed an automated way of identifying the source of errors caused by software updates.
“We have designed a convenient tool for diagnosing performance regressions that is compatible with a whole range of software and programming languages, expanding its usefulness tremendously,” said Dr. Abdullah Muzahid.
Debuggers often check the status of performance counters within the central processing unit to pinpoint the source of errors within software, but newer desktops and servers have hundreds of performance counters, making it virtually impossible to keep track of all of their statuses manually.
Muzahid noted there are other research applications for the software such as developing the technology needed for autonomous driving.
Other contributors to the research include Dr. Mejbah Alam, Dr. Justin Gottschlich, Dr. Nesime Tatbul, Dr. Javier Turek and Dr. Timothy Mattson from Intel Labs.
This research is partly funded by the National Science Foundation CAREER Faculty Early Career Development grant and Intel.
Featured Researcher