Intel announced on Thursday during Intel Labs Day that it has created a machine programming research system that autonomously detect errors in code. The tool is ControlFlag and in preliminary tests it trained and learned novel defects on more than 1 billion unlabeled lines of production-quality code, according to Intel.
“We think ControlFlag is a powerful new tool that could dramatically reduce the time and money required to evaluate and debug code. According to studies, software developers spend approximately 50% of the time debugging. With ControlFlag, and systems like it, I imagine a world where programmers spend notably less time debugging and more time on what I believe human programmers do best—expressing creative, new ideas to machines,” said Justin Gottschlich, principal scientist and director/founder of machine programming research at Intel Labs, in a press release.
Intel said that it’s estimated that 50% of the $1.25 trillion spent annually by the IT industry on software development costs is used for debugging code.
ControlFlag is enabled by a mix of machine programming, machine learning, formal methods, programming languages, compilers and computer systems. It operates through anomaly detection. If anomalies in code are spotted, ControlFlag will detect them, regardless of programming language. It can also adapt to a developer’s style and identify stylistic variations in a programming language, according to Intel.
Intel is currently using ControlFlag internally to identify bugs in its own software and firmware production. It’s part of Intel’s Rapid Analysis for Developers project.