Assaf Shacham

Learn More
The design and performance of next-generation chip multiprocessors (CMPs) will be bound by the limited amount of power that can be dissipated on a single die. We present photonic networks-on-chip (NoC) as a solution to reduce the impact of intrachip and off-chip communication on the overall power budget. The low loss properties of optical waveguides,(More)
As multicore architectures prevail in modern highperformance processor chip design, the communications bottleneck has begun to penetrate on-chip interconnects. With vastly growing numbers of cores and on-chip computation, a high-bandwidth, low-latency, and, perhaps most importantly, low-power communication infrastructure is critically required for next(More)
We experimentally validate a complete optical packet switched interconnection network, implementing the SPINet architecture. The scalable photonic integrated network (SPINet) architecture capitalizes on wavelength division multiplexing (WDM) to provide very large transmission bandwidths, simplify network design, and reduce the network’s power dissipation.(More)
Packet-switched networks on chip (NoC) have been advocated as a natural communication mechanism among the processing cores in future chip multiprocessors (CMP). However, electronic NoCs do not directly address the power budget problem that limits the design of high-performance chips in nanometer technologies. We make the case for a hybrid approach to NoC(More)
As high-performance processors move towards multicore architectures, packet-switched on-chip networks are gaining wide acceptance as interconnect solutions that can directly address the bandwidth and latency requirements as well as provide partial relief to the broader challenge of power dissipation. Still, studies show that the power consumed by on-chip(More)
Alternative contention resolution techniques are studied in the data vortex interconnection network, namely, the insertion of fiber-delay-line (FDL) buffers into the switching nodes. The performance of each technique is evaluated according to relevant performance metrics: acceptance rate, mean latency, and latency variance. A detailed discussion concludes(More)
We report on the implementation of a complete 12-port Data Vortex optical packet switching fabric containing 36 fully-interconnected nodes. Correct routing behavior is verified for 14-channel WDM packets, and latencies below 60 ns are achieved. ©2005 Optical Society of America OCIS codes: (060.2310) Fiber optics; (060.4250) Networks
We present SPINet (Scalable Photonic Integrated Network), an optical switching architecture particularly designed for photonic integration. The performance of SPINet-based networks is investigated through simulations, and it is shown that SPINet can provide the bandwidth demanded by high performance computing systems while meeting the ultra-low latency and(More)