In this paper we introduce a new hardware/software approach to reduce the energy of the shared register file in upcoming embedded architectures with several VLIW processors. This work includes a set of architectural extensions and special loop unrolling techniques for the compilers of MPSoC platforms. This complete hardware/software support enables reducing the energy consumed in the register file of MPSoC architectures up to a 60% without introducing performance penalties.
Details
Title
Optimal Loop-Unrolling Mechanisms and Architectural Extensions for an Energy-Efficient Design of Shared Register Files in MPSoCs
Published in
Proceedings of the III IEEE International Workshop on Innovative Architecture for Future Generation High-Performance Processors and Systems (IWIA ‘05)
Pages
65-71
Conference
III IEEE International Workshop on Innovative Architecture for Future Generation High-Performance Processors and Systems (IWIA ‘05), Oahu, Hawaii, USA, January 19-21, 2005