München, Univ., Diss., 2002. / Computerdatei im Fernzugriff.

München, Univ., Diss., 2002. / Computerdatei im Fernzugriff.

Chip Multi-Processor (CMP) architectures have become mainstream for designing processors. With a large number of cores, Network-On-Chip (NOC) provides a scalable communication method for CMP architectures. NOC must be carefully designed to meet constraints of power and area, and provide ultra low latencies and high throughput. In this research, we explore different techniques to design high performance NOC. First, existing NOCs mostly use Dimension Order Routing (DOR) to determine the route taken by a packet in unicast traffic. However, with the development of diverse applications in CMPs, one-to-many (multicast) and one-to-all (broadcast) traffic are becoming more common. Current unicast routing cannot support multi-cast and broadcast traffic efficiently. We propose Recursive Partitioning Multicast (RPM) routing and a detailed multicast wormhole router design for NOCs. RPM allows routers to select intermediate replication nodes based on the global distribution of destination nodes. This provides more path diversities, thus achieves more bandwidth-efficiency and finally improves the performance of the whole network. Second, as feature size is shrinking, wires are becoming abundant resources available in NOC. Since NOC can benefit from high wire density due to no limits on the number of pins and faster signaling rates, it is very critical in the NOC router design to find a way that fully utilizes the wire resources to provide high performance. We propose an Adaptive Physical Channel Regulator (APCR) for NOC routers to exploit huge wiring resources. The flit size in an APCR router is less than the physical channel width (phit size) to provide finer granularity flow control. An APCR router allows flits from different packets or flows to share the same physical channel in a single cycle. The three regulation schemes (Monopolizing, Fair-sharing and Channel-stealing) intelligently allocate the output channel resources considering not only the availability of physical channels but the occupancy of input buffers. In an APCR router, each Virtual Channel can forward a dynamic number of flits every cycle depending on the run-time network status. Third, nanophotonics has been proposed to design low latency and high band- width NOC for future CMPs. Recent nanophotonic NOC designs adopt the token- based arbitration coupled with credit-based flow control, which leads to low band- width utilization. We propose two handshake schemes for nanophotonic interconnects in CMPs, Global Handshake (GHS) and Distributed Handshake (DHS), which get rid of the traditional credit-based flow control, reduce the average token waiting time, and finally improve the network throughput. Furthermore, we enhance the basic handshake schemes with setaside buffer and circulation techniques to overcome the Head-Of-Line (HOL) blocking.

The Network on Chip (NoC) paradigm was introduced as a scalable communication infrastructure for future System-on-Chip applications. Designing application specific customized communication architectures is critical for obtaining low power, high performance solutions. Two significant design automation problems are the creation of an optimized configuration, given application requirement the implementation of this on-chip network. Automating the design of on-chip networks requires models for estimating area and energy, algorithms to effectively explore the design space and network component libraries and tools to generate the hardware description. Chip architects are faced with managing a wide range of customization options for individual components, routers and topology. As energy is of paramount importance, the effectiveness of any custom NoC generation approach lies in the availability of good energy models to effectively explore the design space. This thesis describes a complete NoC synthesis ???ow, called NoCGEN, for creating energy-efficient custom NoC architectures. Three major automation problems are addressed: custom topology generation, energy modeling and generation. An iterative algorithm is proposed to generate application specific point-to-point and packet-switched networks. The algorithm explores the design space for efficient topologies using characterized models and a system-level ???oorplanner for evaluating placement and wire-energy. Prior to our contribution, building an energy model required careful analysis of transistor or gate implementations. To alleviate the burden, an automated linear regression-based methodology is proposed to rapidly extract energy models for many router designs. The resulting models are cycle accurate with low-complexity and found to be within 10% of gate-level energy simulations, and execute several orders of magnitude faster than gate-level simulations. A hardware description of the custom topology is generated using a parameterizable library and custom HDL generator. Fully reusable and scalable network components (switches, crossbars, arbiters, routing algorithms) are described using a template approach and are used to compose arbitrary topologies. A methodology for building and composing routers and topologies using a template engine is described. The entire flow is implemented as several demonstrable extensible tools with powerful visualization functionality. Several experiments are performed to demonstrate the design space exploration capabilities and compare it against a competing min-cut topology generation algorithm.

The Network on Chip (NoC) paradigm was introduced as a scalable communication infrastructure for future System-on-Chip applications. Designing application specific customized communication architectures is critical for obtaining low power, high performance solutions. Two significant design automation problems are the creation of an optimized configuration, given application requirement the implementation of this on-chip network. Automating the design of on-chip networks requires models for estimating area and energy, algorithms to effectively explore the design space and network component libraries and tools to generate the hardware description. Chip architects are faced with managing a wide range of customization options for individual components, routers and topology. As energy is of paramount importance, the effectiveness of any custom NoC generation approach lies in the availability of good energy models to effectively explore the design space. This thesis describes a complete NoC synthesis ???ow, called NoCGEN, for creating energy-efficient custom NoC architectures. Three major automation problems are addressed: custom topology generation, energy modeling and generation. An iterative algorithm is proposed to generate application specific point-to-point and packet-switched networks. The algorithm explores the design space for efficient topologies using characterized models and a system-level ???oorplanner for evaluating placement and wire-energy. Prior to our contribution, building an energy model required careful analysis of transistor or gate implementations. To alleviate the burden, an automated linear regression-based methodology is proposed to rapidly extract energy models for many router designs. The resulting models are cycle accurate with low-complexity and found to be within 10% of gate-level energy simulations, and execute several orders of magnitude faster than gate-level simulations. A hardware description of the custom topology is generated using a parameterizable library and custom HDL generator. Fully reusable and scalable network components (switches, crossbars, arbiters, routing algorithms) are described using a template approach and are used to compose arbitrary topologies. A methodology for building and composing routers and topologies using a template engine is described. The entire flow is implemented as several demonstrable extensible tools with powerful visualization functionality. Several experiments are performed to demonstrate the design space exploration capabilities and compare it against a competing min-cut topology generation algorithm.

Berlin, Techn. Univ., Diss., 2004. / Computerdatei im Fernzugriff.

München, Techn. Universiẗat, Diss., 2003.

München, Techn. University, Diss., 2003.

No description available.

Due to the ever-shrinking feature size in CMOS process technology, it is expected that future chip multiprocessors (CMPs) will have hundreds or thousands of processing cores. To support a massively large number of cores, packet-switched on-chip interconnection networks have become a de facto communication paradigm in CMPs. However, the on-chip networks have several drawbacks, such as limited on-chip resources, increasing communication latency, and insufficient communication bandwidth. In this dissertation, several schemes are proposed to accelerate communication in on-chip interconnection networks within area and cost budgets to overcome the problems. First, an early transition scheme for fully adaptive routing algorithms is proposed to improve network throughput. Within a limited number of resources, previously proposed fully adaptive routing algorithms have low utilization in escape channels. To increase utilization of escape channels, it transfers packets earlier before the normal channels are full. Second, a pseudo-circuit scheme is proposed to reduce network latency using communication temporal locality. Reducing per-hop router delay becomes more important for communication latency reduction in larger on-chip interconnection networks. To improve communication latency, the previous arbitration information is reused to bypass switch arbitration. For further acceleration, we also propose two aggressive schemes, pseudo-circuit speculation and buffer bypassing. Third, two handshake schemes are proposed to improve network throughput for nanophotonic interconnects. Nanophotonic interconnects have been proposed to replace metal wires with optical links in on-chip interconnection networks for low latency and power consumptions as well as high bandwidth. To minimize the average token waiting time of the nanophotonic interconnects, the traditional credit-based flow control is removed. Thus, the handshake schemes increase link utilization and enhance network throughput.