Lightweight hardware support for selective coherence in heterogeneous manycore accelerators
Alessandro Cilardoa, Mirko Gagliardi and Vincenzo Scotti
University of Naples Federico II and CeRICT, Naples, Italy
aacilardo@unina.it
ABSTRACT
Shared memory coherence is a key feature in manycore accelerators, ensuring programmability and application portability. Most established solutions for coherence in homogeneous systems cannot be simply reused because of the special requirements of accelerator architectures. This paper introduces a low-overhead hardware coherence system for heterogeneous accelerators, with customizable granularity and noncoherent region support. The coherence system has been demonstrated in operation in a full manycore accelerator, exhibiting significant improvements in terms of network load, execution time, and power consumption.
