PoCC - the Polyhedral Compiler Collection
PoCC, the Polyhedral Compiler Collection, is a flexible source-to-source platform to quickly prototype and develop loop nest optimizations in the polyhedral model. It features iterative and model-driven heuristics for parallelization and locality optimization, including an enhanced version of Pluto, the state-of-the-art automatic parallelization algorithm for static control loop nests. It handles a large subset of C and can generate parallelization and vectorization pragmas and builtins for the GCC and ICC backend compilers. Many state-of-the art techniques in polyhedral optimization are available and distributed over small, single-purpose tools. This design greatly eases research and development and smooths the learning curve for recent converts. Recent and ongoing developments include support for data-dependent control flow and integrated handling of vectorization constraints.
Adaptive Compilation
Adaptive compilation
- Home page
- Kick-off Meeting
- Research Areas
- Call For Funding (Feb 2008)
- Context-Aware Optimization and Run-Time Adaptation of Sequential Libraries for Multi-Core Systems
- Barcelona Meeting (June 2008)
- Using Adaptive Compilation to Produce High Performance Sparse Computations
- Split Compilation and Code Specialization
- Split Vectorisation Using Gcc and Mono
- Value-Based Optimisation
- Performance Counter-Based Power and Temperature Prediction
- Paris Meeting (November 2008)
- Related Research Groups and Activities
- Paphos Meeting (January 2009)
- Munich Meeting (June 2009)
