UC Santa Barbara

As we approach some of the physical limits of transistor scale and performance, modern system-on-chips (SoCs) have become increasingly heterogeneous, incorporating more hardware accelerators in their designs. The general design philosophy has been to treat these accelerators simply as an off-loading co-processor, each with their own custom software drivers. This wastes system performance and kernel developer time and inherently prohibits the amount of collaboration between all of the SoC components. Our project, Pengwing, seeks to alter the current standard surrounding accelerator usage to provide powerful collaboration between hardware and software system services. We implement a novel blended operating system design that follows the idea of software-oriented acceleration. In this paradigm, robust software-hardware interactions are achieved by providing a system substrate that enables communication with accelerators using existing software abstractions like shared-memory queues. My contributions to this project revolve around incorporating Beehive, a hardware network stack, into our SoC design. By intentionally decoupling Beehive from the cores during integration, software and hardware alike can utilize various network functions provided through Beehive using our standard software queue API. This thesis will detail the versatility present in our blended OS implementation and showcase robust software-hardware interaction through various setups that leverage Beehive utilizing the same underlying hardware SoC design.