Daniele Cono D'Elia edited abstract.tex  over 8 years ago

Commit id: e60195b4b604df1a5d5cf93a48c32d5b37c4e421

deletions | additions      

       

In this paper we present a novel framework to perform OSR transitions. Compared to extant OSR techniques, our approach is platform-independent as transitions are encoded entirely at the Intermediate Representation (IR) level; it supports OSR-point insertion at arbitrary locations in a function, and it allows a function version reached via OSR to fire an OSR itself, either to a more optimized version or to a less optimized one from which it was derived.  We implement and evaluate our technique in the LLVM compiler infrastructure, which is nowadays being increasingly used as Just-In-Time (JIT) compiler in virtual machines for dynamic languages such as Javascript, MATLAB, Python and Ruby. We then present a case study on the integration of our technique in the McVM virtual machine for MATLAB, showing interesting speedupsachieved  from the run-time  optimization of a popular construct of the language.