Netspeed Systems

Mahmud Hassan

Sailesh Kumar

Eric Norige

Joji Philip

Sundari Mitra

Joseph Rowlands

A network-on-chip configuration includes a first plurality of cores arranged in a two-dimensional mesh; a first plurality of routers, each of the first plurality of routers associated with a corresponding local one of the first plurality of cores, each of the first plurality of routers having a plurality of directional ports configured to provide connections to other ones of the first plurality of routers; a second plurality of cores disposed around a periphery of the two-dimensional mesh arrangement; and a second plurality of routers, each of the second plurality of routers associated with a corresponding local one of the second plurality of cores, and having a directional port configured to provide a connection to a neighboring one of the first plurality of routers.

Hierarchical asymmetric mesh with virtual routers

Systems and methods for automatically building a deadlock free inter-communication network in a multi-core system are described. The example embodiments described herein involve deadlock detection during the mapping of user specified communication pattern amongst blocks of the system. Detected deadlocks are then avoided by re-allocation of channel resources. An example embodiment of the deadlock avoidance scheme is presented on Network-on-chip interconnects for large scale multi-core system-on-chips.

Automatic construction of deadlock free interconnects

Systems and methods described herein are directed to solutions for NoC interconnects that provide end-to-end uniform- and weighted-fair allocation of resource bandwidths among various contenders. The example implementations are fully distributed and involve tagging the messages with meta-information when the messages are injected in the interconnection network. Example implementations may involve routers using various arbitration phases, and making local arbitration decisions based on the meta-information of incoming messages. The meta-information can be of various types based on the number of router arbitration phases, and the desired level of sophistication.

Tagging and synchronization for fairness in NOC interconnects

Systems and methods described herein are directed to solutions for Network on Chip (NoC) interconnects that automatically and dynamically determines the number of layers needed in a NoC interconnect system based on the bandwidth requirements of the system traffic flows. The number of layers is dynamically allocated and minimized by performing load balancing of the traffic flows between the channels and routes of different NoC layers as they are mapped. Additional layers may be allocated to provide the additional virtual channels that may be needed for deadlock avoidance and to maintain the isolation properties between various system flows. Layer allocation for additional bandwidth and additional virtual channels (VCs) may be performed in tandem.

Creating multiple NoC layers for isolation or avoiding NoC traffic congestion

Systems and methods for automatically building a deadlock free inter-communication network in a multi-core system are described. The example implementations described herein involve a high level specification to capture the internal dependencies of various cores, and using it along with the user specified system traffic profile to automatically detect protocol level deadlocks in the system. When all detected deadlock are resolved or no such deadlocks are present, messages in the traffic profile between various cores of the system may be automatically mapped to the interconnect channels and detect network level deadlocks. Detected deadlocks then may be avoided by re-allocation of channel resources. An example implementation of the internal dependency specification and using it for deadlock avoidance scheme is presented on Network-on-chip interconnects for large scale multi-core system-on-chips.

Automatic deadlock detection and avoidance in a system interconnect by capturing internal dependencies of IP cores using high level specification

Systems and methods described herein are directed to solutions for NoC interconnects that provide end-to-end uniform- and weighted-fair allocation of resource bandwidths among various contenders. The example implementations are fully distributed and involve computing weights for various channels in a network on chip (NoC) based on the bandwidth requirements of flows at the channels. Example implementations may involve using the weights to perform weighted arbitration between channels in the NoC to provide quality of service (QoS). The weights may be adjusted dynamically by monitoring the activity of flows at the channels. The newly adjusted weights can be used to perform the weighted arbitrations to avoid unfair bandwidth allocations.

QoS in heterogeneous NoC by assigning weights to NoC node channels and using weighted arbitration at NoC nodes

Systems and methods involving construction of a system interconnect in which different channels have different widths in numbers of bits. Example processes to construct such a heterogeneous channel NoC interconnect are disclosed herein, wherein the channel width may be determined based upon the provided specification of bandwidth and latency between various components of the system.

Heterogeneous channel capacities in an interconnect

Example implementations described herein are directed to a floor plan for a Network on Chip (NoC) topology that can include a plurality of on chip blocks of substantially non-uniform shapes and dimensions. An interconnection network is synthesized along with a plan for a physical layout of the interconnection network based on physical dimensions of the plurality of on chip blocks, the physical dimensions of the floorplan and relative placement information for placing the plurality of on chip blocks on the floorplan. Porosity information for the plurality of on chip blocks on the floorplan and required chip functionality may also be taken into consideration.

Asymmetric mesh NoC topologies

Example implementations described herein are directed to a system on chip (SoC) that can include a plurality of blocks of substantially non-uniform shapes and dimensions, a plurality of routers, and a plurality of links between routers. The plurality of blocks and the plurality of routers are interconnected by the plurality of links using a Network-on-Chip (NoC) architecture with a sparse mesh topology. The sparse mesh topology involves a sparsely populated mesh which is a subset of a full mesh having one or more of the plurality of routers or links removed. The plurality of blocks communicate among each other by routing messages over the remaining ones of the plurality of routers and links of the sparse mesh.

A method of interconnecting blocks of heterogeneous dimensions using a NoC interconnect with sparse mesh topology includes determining a size of a mesh reference grid based on dimensions of the chip, dimensions of the blocks of heterogeneous dimensions, relative placement of the blocks and a number of host ports required for each of the blocks of heterogeneous dimensions, overlaying the blocks of heterogeneous dimensions on the mesh reference grid based on based on a guidance floor plan for placement of the blocks of heterogeneous dimensions, removing ones of a plurality of nodes and corresponding ones of links to the ones of the plurality of nodes which are blocked by the overlaid blocks of heterogeneous dimensions, based on porosity information of the blocks of heterogeneous dimensions, and mapping inter-block communication of the network-on-chip architecture over remaining ones of the nodes and corresponding remaining ones of the links.

Growing community of inventors

San Carlos, CA, United States of America

Mahmud Hassan