Author :
Passas, Giorgos ; Katevenis, Manolis ; Pnevmatikatos, Dionisios
Abstract :
High-radix, single-chip routers have emerged as efficient building blocks for interconnection networks. Researchers believe that hierarchical switch architectures are needed at high radices as crossbars scale with the square of the router radix. This article proposes a novel microarchitecture that allows flat crossbar switches to scale to 128 ports, supporting 32 Gbits per second per port (Gbps/port) while occupying 4.9 mm^2 and consuming 4.2 W, or supporting 64 Gbps/port at 7.5 mm^2 and 7.5 W, in 45-nm CMOS. Key features include deep crossbar pipelining to cope with wire delay, a novel cross-scheduler architecture to reduce wiring complexity, and catalytic custom gate placement within standard electronic design automation (EDA) flows. Furthermore, on a chip, crossbar speedup and combined I/O queuing (CIOQ) is better than hierarchical queueing, providing top performance with orders of magnitude lower memory cost. Finally, the authors compare CIOQ with Swizzle Switch prototypes and demonstrate high-radix crossbars´ potential for system-on-chip interconnects.
Keywords :
VLSI; electronic design automation; interconnections; logic gates; network routing; pipeline processing; switching circuits; system-on-chip; wires (electric); wiring; CIOQ; VLSI microarchitecture; catalytic custom gate placement; combined I/O queuing; combined input-output queued crossbar architecture; cross-scheduler architecture; high-radix on-chip switches; high-radix single-chip routers; interconnection networks; standard electronic design automation; system-on-chip interconnects; wire delay; wiring complexity; Delays; Interconnection networks; Logic gates; Multiplexing; Packet switching; Very large scale integration; Wiring; VLSI; on-chip interconnection network; packet-switching network;