Reducing power and latency in 2-D mesh NoCs using globally pseudochronous locally synchronous clocking

One of the main problems when designing large ASICs today is to distribute a low power synchronous clock over the whole chip and a lot of remedies to this problem have been proposed over the years. For networks-on-chip (NoC), where computational resources are organised in a 2-D mesh connected together through switches in an on-chip interconnection network, another possibility exists: globally pseudochronous locally synchronous clock distribution. We present a clocking scheme for NoCs that we call globally pseudochronous locally synchronous, in which we distribute a clock with a constant phase difference between the switches. As a consequence of the phase difference, some paths along the NoC switch network become faster than the others. We call these paths data motorways. By adapting the switching policy in the switches to prefer data to use the motorways, we show that the latency within the network is reduced with up to 40% compared to a synchronous reference case. The phase difference between the resources also makes the circuit more tolerant to clock skew. It also distributes the current peaks more evenly across the clock period, which leads to a reduction in peak power, which in turn further reduces the clock skew and the jitter in the clock network.

[1]  Christer Svensson,et al.  Self-tested self-synchronization circuit for mesochronous clocking , 2001 .

[2]  Ken Mai,et al.  The future of wires , 2001, Proc. IEEE.

[3]  Pong-Fei Lu,et al.  Physical design of a fourth-generation POWER GHz microprocessor , 2001, 2001 IEEE International Solid-State Circuits Conference. Digest of Technical Papers. ISSCC (Cat. No.01CH37177).

[4]  William J. Dally,et al.  Digital systems engineering , 1998 .

[5]  S. Lipa,et al.  Rotary traveling-wave oscillator arrays: a new clock technology , 2001 .

[6]  I. Soderquist Globally updated mesochronous design style , 2003 .

[7]  Johnny Öberg,et al.  Lowering power consumption in clock by using globally asynchronous locally synchronous design style , 1999, DAC '99.

[8]  Behzad Razavi,et al.  Rotary TravelingWave Oscillator Arrays: A New Clock Technology , 2003 .

[9]  Jian Liu,et al.  A global wire planning scheme for Network-on-Chip , 2003, Proceedings of the 2003 International Symposium on Circuits and Systems, 2003. ISCAS '03..

[10]  Qing K. Zhu High-speed clock network design , 2002 .

[11]  Jiang Xu,et al.  Wave pipelining for application-specific networks-on-chips , 2002, CASES '02.

[12]  C. Patrick Yue,et al.  Design of a 10GHz clock distribution network using coupled standing-wave oscillators , 2003, Proceedings 2003. Design Automation Conference (IEEE Cat. No.03CH37451).

[13]  Johnny Öberg Clocking Strategies for Networks-on-Chip , 2003, Networks on Chip.

[14]  Axel Jantsch,et al.  Load distribution with the proximity congestion awareness in a network on chip , 2003, 2003 Design, Automation and Test in Europe Conference and Exhibition.

[15]  Eby G. Friedman,et al.  Clock distribution networks in synchronous digital integrated circuits , 2001, Proc. IEEE.