C3PO is a workshop at the intersection of compilers/translators, HPC middleware, and HPC applications. Practical compiler-enabled programming environments, applied analysis methodologies, and end-to-end toolchains are crucial to performance portability in the exascale era. The workshop brings together researchers with a shared interest in applying compilation and source-to-source translation methodologies to enhance parallel programming, including explicit programming models such as MPI, OpenMP, and hybrid models.
Original papers will identify and solve challenges in the tradeoffs of scalability, performance, predictability, correctness, productivity, and portability on-node and at massive scale. Strong-scaling, weak-scaling, and hybrid-scaling solutions assisted, augmented, and/or enabled by compiler technology are in scope.
We recognize that there are standard static analysis technologies (dataflow analysis, polyhedral analysis, etc); this workshop seeks innovative applications of such technologies to derive enhanced utility in parallel programs that are generalizable beyond a single case study or narrow application.
TBD <!–