TY - JOUR T1 - A Low-Overhead Asynchronous Interconnection Network for GALS Chip Multiprocessors JF - Computer-Aided Design of Integrated Circuits and Systems, IEEE Transactions on Y1 - 2011 A1 - Horak,M.N. A1 - Nowick,S.M. A1 - Carlberg,M. A1 - Vishkin, Uzi KW - 1.36 KW - 800 KW - 90 KW - architecture;size KW - architectures;shared KW - asynchronous KW - benchmark KW - chip KW - chips;multiprocessor KW - distribution KW - distribution;frequency KW - GALS KW - GHz;frequency KW - interconnection KW - kernel;post-layout KW - layout;clock KW - locally-synchronous KW - memory KW - MHz;globally-asynchronous KW - multiple KW - multiprocessor;clock KW - multiprocessor;interface KW - network;mixed-timing KW - network;network KW - networks;microprocessor KW - networks;network KW - nm;circuit KW - Parallel KW - routing;network-on-chip;parallel KW - routing;parallel KW - simulation;random KW - synchronous KW - systems; KW - timing;low-overhead KW - traffic;shared-memory AB - A new asynchronous interconnection network is introduced for globally-asynchronous locally-synchronous (GALS) chip multiprocessors. The network eliminates the need for global clock distribution, and can interface multiple synchronous timing domains operating at unrelated clock rates. In particular, two new highly-concurrent asynchronous components are introduced which provide simple routing and arbitration/merge functions. Post-layout simulations in identical commercial 90 nm technology indicate that comparable recent synchronous router nodes have 5.6-10.7 more energy per packet and 2.8-6.4 greater area than the new asynchronous nodes. Under random traffic, the network provides significantly lower latency and identical throughput over the entire operating range of the 800 MHz network and through mid-range traffic rates for the 1.36 GHz network, but with degradation at higher traffic rates. Preliminary evaluations are also presented for a mixed-timing (GALS) network in a shared-memory parallel architecture, running both random traffic and parallel benchmark kernels, as well as directions for further improvement. VL - 30 SN - 0278-0070 CP - 4 M3 - 10.1109/TCAD.2011.2114970 ER -