The performance shortcomings of multipurpose compute engines have stirred recent excitement in specialized processors, preempted by GPUs. Simultaneously, computational complexity theory NP 'hard' problems scaling as O(n^k) require new hardware solutions. This presents an opportunity for photonic information processors (PIP) building on photonic integration through recent foundry developments. The value proposition for PIPs exist via optical parallelism, small capacitive charging of OE devices, 10's of ps short propagation delays, a natural convolution via optical interference, and an O(n)-scaling Fourier transform. Based on a recently developed photonic NxN router, here we present two photonic processors; a) the residual arithmetic nanophotonic computer (RANC), and b) a reconfigurable graph processor, the latter being a computing-in-switching (CIS) paradigm. PIPs operate with time-of-flight, once the processor is configured (e.g. setting phase), which is on the order of 10-100 ps given the mm-scale photonic integration footprints. This high bandwidth, however challenges the electronic-optic I/O bottleneck. To address this, we further discuss an optical front-end DAC with <100 ps delay enabled by a 2x2 electro-optic switch.
|