Because the impact of heterogeneity on all computing tasks is rapidly increasing, innovative architectures, algorithms, and specialized programming environments and tools are needed to efficiently use these new and mixed/diversified parallel architectures. Many challenges plan to be addressed by the proposed architecture as for example, to fully understand the impact of different hardware configurations on software systems (both rapidly evolving); the automated techniques implemented in compilers and execution environments are not designed to deal with disruptive changes in the hardware-software interfaces; or additional factors such as performance, security, time criticality, data movement and power consumption resulting from the software operating on heterogeneous hardware need careful consideration. This achitecture tries to be a holistic and high level approach to address the hetereogeneity challenges in as broader as possible manner.