Optimizing programs to exploit the underlying hardware architecture is an important task. Much research has been done on enabling compilers to find the best set of code optimizations that can build the fastest and less resource-hungry executable for a given program. A common approach is iterative compilation, sometimes enriched by machine learning techniques. This provides good results, but requires extremely long compilation times and an initial training phase lasting even for days or weeks.We present long-term learning, a new algorithm that allows the compiler user to improve the performance of compiled programs with reduced compilation times with respect to iterative compilation, and without an initial training phase. Our algorithm does not just build good programs: it acquires knowledge every time a program is compiled and it uses such knowledge to learn compiler heuristics, without the need for an expert to manually define them. The heuristics are evolved during every compilation, by evaluating their effect on the generated programs. We present implementations of long-term learning on top of two different compilers, and experimental data gathered on multiple hardware configurations showing its effectiveness.

Abstract-The 2PARMA project focuses on the development of parallel programming models and run-time resource management techniques to exploit the features of many-core processor architectures.The main goals of the 2PARMA project are: the definition of a parallel programming model combining component-based and singleinstruction multiple-thread approaches, instruction set virtualisation based on portable byte-code, run-time resource management policies and mechanisms as well as design space exploration methodologies for manycore computing architectures.

No abstract

Abstract-The 2PARMA project focuses on the development of parallel programming models and run-time resource management techniques to exploit the features of many-core processor architectures.The main goals of the 2PARMA project are: the definition of a parallel programming model combining component-based and singleinstruction multiple-thread approaches, instruction set virtualisation based on portable byte-code, run-time resource management policies and mechanisms as well as design space exploration methodologies for manycore computing architectures.

This paper presents a Just-In-Time compilation system for ARM processors. The complete architecture is described, starting from static compilation of the sources into CIL (Common Intermediate Language) bytecode. The intermediate languages that are used are explained, together with the instuction selection and code generation techiniques. Finally, some experimental results are presented, comparing them with those of our best open source competitor: Mono.