Scaling High-Performance Interconnect Architectures to Many-Core Systems.

The ever-increasing demand for performance scaling has made multi-core (2-8 cores) chips prevalent in today’s computing systems and foreshadows the shift toward many-core (10s- 100s of cores) chips in the near future. Although the potential performance gains from many-core systems remain appealing, the widespread adoption of these systems hinges on their ability to scale performance while simultaneously satisfying Quality-of-Service (QoS) and energy-efficiency constraints. This work makes the case that the interconnect for these many-core systems has a significant impact on the aforementioned scalability issues. The impact of interconnects on many-core systems is illustrated by observing that the degree of the interconnect has a signicant effect on system scalability and demonstrating that the architecture of high-radix, many-core systems are feasible, energy-efficient, and high-performance. The feasibility of high-radix crossbars for many-core systems is first shown through a new circuit-level building block called the Swizzle-Switch which can operate at frequencies up to 1.5GHz for 128-bit, radix-64 crossbars. This work then shows how a many-core system called the Swizzle-Switch Network (SSN) can use the Swizzle-Switch as the central building block for a flat crossbar interconnect. The SSN is shown to be advantageous to traditional Network-on-Chip (NoC) for systems up to 64 cores. The SSN performance by 21% relative to a Mesh while also providing a 25% energy savings over the Mesh. The Swizzle-Switch is also leveraged as a building block for high-radix NoC topologies that can support many-core architectures. The Swizzle-Switch-based Flattened Butterfly topology is demonstrated to provide a 15% speedup and 10% energy savings over the Mesh. Finally, the impact that 3D stacking technology has on many-core scalability is evaluated for bus and crossbar interconnects. A 3D-optimized Swizzle-Switch Network is able to leverage frequency gains to achieve a 15-28% speedup over a 2D-Swizzle-Switch Network when using memory- intensive benchmarks. Additionally, a bus-based 64-core architecture is shown to provide an average speedup of 49× over a baseline uniprocessor system when using 3D technology.PhDComputer Science & EngineeringUniversity of Michigan, Horace H. Rackham School of Graduate Studieshttp://deepblue.lib.umich.edu/bitstream/2027.42/93980/1/ksewell_1.pd