Ivannikov Institute for System Programming of the RAS


Optimizing programs on the target user machine for the target architecture and user's behavior.

Start of project – 2011. End of project - 2013. Customer - RFBR.

One has to harness dynamic and adaptive recompilation methods when designing the system for general-purpose languages compilation which takes into account the specific factors of target hardware and the most likely way of usage. It is favorable to research those methods in the LLVM infrastructure environment. Unfortunately, LLVM does not support dynamic profile collection and recompilation at the moment, and it contains only one profile-based optimization. Within the introduced work, we proposed and implemented the system for hardware interruptions profile collection and the algorithm to correct profile estimations, and, apart from that, the number of profile-based optimizations. We integrated dynamic profile collection into the LLVM dynamic compiler resulting in constant program quality regardless of hardware architecture.

Implementer

Compiler Technology

Go to the list of projects