Publications

Communication in multi- and many-core processors has long been a bottleneck to performance due to the high cost of long-distance electrical transmission. This difficulty has been partially remedied by architectural constructs such as caches and novel interconnect topologies, albeit at a steep cost in terms of complexity. Unfortunately, even these measures are rendered ineffective by certain kinds of communication, most notably scatter and gather operations that exhibit highly non-local data access patterns. Much work has gone into examining how the increased bandwidth density afforded by chip-scale silicon photonic interconnect technologies affects computing, but photonics have additional properties that can be leveraged to greatly accelerate performance and energy efficiency under such difficult loads. This paper describes a novel synchronized global photonic bus and system architecture called P-sync that uses photonics' distance independence to greatly improve performance on many important applications previously limited by electronic interconnect. The architecture is evaluated in the context of a non-local yet common application: the distributed Fast Fourier Transform. We show that it is possible to achieve high efficiency by tightly balancing computation and communication latency in P-sync and achieve upwards of a 6x performance increase on gather patterns, even when bandwidth is equalized.

Large-scale 3D scene reconstruction using Structure from Motion (SfM) continues to be very computationally challenging despite much active research in the area. We propose an efficient, scalable processing chain designed for cluster computing and suitable for use on aerial video. The sparse bundle adjustment step, which is iterative and difficult to parallelize, is accomplished by partitioning the input image set, generating independent point clouds in parallel, and then fusing the clouds and combining duplicate points. We compare this processing chain to a leading parallel SfM implementation, which exploits fine-grained parallelism in various matrix operations and is not designed to scale beyond a multi-core workstation with GPU. We show our cluster-based approach offers significant improvement in scalability and runtime while producing comparable point cloud density and more accurate point location estimates.