Compiler-Assisted OpenMP Runtime Organization for Embedded Multicores

The recently introduced OpenMP device constructs open a whole new world for application writers, enabling them to easily utilize the host cpus along with other attached computational resources, in an intuitive and productive manner. At the same time, multicore architectures have conquered the whole computing spectrum. General-purpose and embedded system alike integrate multicore cpus and multicore co-processors or accelerators. The new OpenMP target-related directives offload portions of the program code (kernels) to any of the available devices; the kernels themselves can take advantage of the multiplicity of processing elements within the target device by employing OpenMP constructs. However, most co-processors or accelerators, especially embedded ones, have limited resources. This severely constrains the extend of OpenMP support that can be implemented within a device. A usual design decision is to only support OpenMP partially, in effect hindering the full exploitation of the device capabilities through a high-level programming model. In this work, we present a novel solution to this problem. We propose a compiler-assisted, adaptive runtime system organization, which generates applicationspecific support by implementing only the OpenMP functionality required each time. In particular, based on extensive compiler analysis, the offloaded kernels can be accompanied by a runtime library tailored to the needs of the given application. Full OpenMP support is thus available, if needed. However, in the usual scenario where kernels do not require complex OpenMP functionalities, our method can lead to dramatically reduced executable sizes and/or execution times. To demonstrate the potential of our proposal we present an implementation on the popular Parallella board. ∗S.N. Agathos is supported by the Greek State Scholarships Foundation (IKY)