The pC++ programming system includes an integrated set of performance
instrumentation, measurement, and analysis tools.
With this support, we have been able to validate performance scalability
claims of the language and characterize important performance factors of
the runtime system ports during pC++ system development [9].
As a consequence, the first version of the compiler is being introduced
with an extensive set of performance experiments already documented.
The environment demonstrates the advantages of language-specific
program analysis tools. Its design and integration with the pC++ language
system allows important programming productivity issues to be addressed.
In addition,
enables more sophisticated debugging and performance
analysis tools to be developed and effectively applied.
The pC++ project is an on-going research effort. We are planning to enhance the current version in several ways. First, the pC++ language will be extended to include task-parallel programming and more aggressive compiler optimizations. Second, we are working on better tools for the programming environment (graphical instrumentation control, data distribution visualization, barrier breakpoint debugger, etc.). Lastly, we will try to provide interaction with other high-performance languages like HPF, C++, Fortran-M, etc.