Intel unveiled MISIM, a new machine programming (MP) system with MIT and Georgia Institute of Technology. Machine inferred code similarity (MISIM) is an automated engine designed to learn a piece of software by studying the structure of the code and analyzing differences of codes with similar behavior.
Justin Gottschlich, principal scientist and director/founder of Machine Programming Research at Intel said, “Intel’s ultimate goal for machine programming is to democratize the creation of software. When fully realized, MP will enable everyone to create software by expressing their intention in whatever fashion that’s best for them, whether that’s code, natural language or something else. That’s an audacious goal, and while there’s much more work to be done, MISIM is a solid step toward it”.
As heterogeneous computing rising so hardware and software systems are becoming increasingly complex. This complexity and shortage of programmers highlights a need for new development approaches. Machine programming aims to improve development productivity through the use of automated tools.
Intel MISIM can determine when two pieces of code perform a similar computation, even when those pieces use different data structures and algorithms. Gottschlich said, “This is an important step toward the grander vision of machine programming”.
A core differentiation between MISIM and existing code-similarity systems is in its context-aware semantic structure (CASS). CASS can be configured to a specific context to capture information that describes the code at a higher level, and it can provide more specific insight into code working rather than how it does it.
MISIM can do all this without using a compiler, which translates human-readable source code into computer-executable machine code.
Once the code’s structure is integrated into CASS, neural network systems give similarity scores to pieces of code based on its job.
Bringing together these principles, MISIM becomes able to identify similar pieces of code up to 40x more accurately than previous systems.
Intel’s Machine Programming Lab is also engaging with software groups to see how MISIM can be integrated into their day-to-day development. Gottschlich said, “I imagine most developers would happily let the machine find and fix bugs for them, if it could – I know I would”.
You can read more details here.