Scaling enhances intrinsic transistor performance and degrades interconnects. As the technology steps into nanometer era, global interconnects are becoming bottleneck for overall chip performance. In this paper, we show package level interconnects are an effective alternative for on-chip global wiring. These interconnects behave as LC transmission lines and can be exploited for their near speed of light transmission and low attenuation characteristics. We compare performancebandwidth, bandwidth density, latency and power consumptionof the package level transmission lines with conventional on-chip global interconnects for different ITRS technology nodes. Based on these results, we show package level interconnects are well suited for power demanding low latency applications and we analyze different interconnect options like memory buses, long inter tile interconnects, clock and power distribution.
A 576 Mb DRAM is implemented with 16 serial links at 10.3125Gbps. Using careful memory/SerDes/package codesign, the system achieves 14.5ns latency and 24.75GByte/s read/write bandwidth. It achieves SRAM-like random access by using logic-compatible 65nm GP embedded DRAM and small 36 Kb sub-arrays with hidden refresh.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.