Version 7 (modified by binoy, 51 years ago) (diff)


Welcome to HydraVM


The HydraVM project focuses on extracting parallelism from sequential code (e.g., legacy systems) through a set of techniques including code profiling and visualization, data dependency analysis, execution analysis, and software transactional memory, all done at the bytecode-level. Thus, no changes or recompilation are needed to application source codes. HydraVM is a virtual machine prototype that incorporates these techniques, built by extending Jikes RVM. Though the project's current implementation is a modification to Jikes RVM baseline compiler, the techniques are broadly applicable to other architectures and JIT compilers.

Hydra VM Team

Starting Points

Locations of Site Visitors

Attachments (1)

Download all attachments as: .zip