Guangjun Li

Non-Blocking Testing for Network-on-Chip

To achieve high reliability in on-chip networks, it is necessary to test the network as frequently as possible to detect physical failures before they lead to system-level failures. A main obstacle is that the circuit under test has to be isolated, resulting in network cuts and packet blockage which limit the testing frequency. To address this issue, we propose a comprehensive network-level approach which could test multiple routers simultaneously at high speed without blocking or dropping packets. We first introduce a reconfigurable router architecture allowing the cores to keep their connections with the network while the routers are under test. A deadlock-free and highly adaptive routing algorithm is proposed to support reconfigurations for testing. In addition, a testing sequence is defined to allow testing multiple routers to avoid dropping of packets. A procedure is proposed to control the behavior of the affected packets during the transition of a router from the normal to the testing mode and vice versa. This approach neither interrupts the execution of applications nor has a significant impact on the execution time. Experiments with the PARSEC benchmarks on an 8x8 NoC-based chip multiprocessors show only 3 percent execution time increase with four routers simultaneously under test.

Tolerating transient illegal turn faults in NoCs

Network-on-Chip (NoC) is becoming a competitive solution to connect hundreds of processing elements in modern computing platforms. Under the trend of shrinking feature sizes, circuits are likely to suffer from faults which lead to degraded performance and erroneous behaviour. Compared to permanent faults, transient faults happen even more frequently and seriously while they are hidden within complex on-chip behaviours. One of the serious consequences caused by transient faults is taking illegal turns by the packets after the damage of control logic in on-chip routers which may lead to a deadlock situation and eventually crashing the entire system. To avoid this situation, in this paper, we propose a comprehensive scheme called ODT including an improved router architecture, an illegal-turn-resilient routing algorithm, online fault-detect units and a fault classification method. By applying ODT, more turns are supported on routing level and the deadlock situations can be significantly reduced. Experimental results indicate up to 22% increase of the survived packets in the network when 4% of routing computation units in failure. The extra area overhead and power consumption of ODT method is around 9.22% and 9.63%.

A Routing-Level Solution for Fault Detection, Masking, and Tolerance in NoCs

Faults may occur in numerous locations of a router in a NoC platform. Compared with the faults in the data path, faults in the control path may cause more severe effects which may result in crashing the entire system. Most of the current efforts in literature focus on disabling a router when a fault is detected. Considering this level of coarse-granularity, the functioning parts of a router have to be unnecessarily disabled which may severely affect the performance or functionality of the on-chip network. To cope with this problem, in this paper we propose a mechanism to tolerate faults in the control path which largely avoid disabling a router as long as the fault is not severe. This mechanism is called DMT, standing for three distinguishing characteristics of the proposed method as fault Detection, fault Masking and fault Tolerance. The proposed mechanism can efficiently detect the faults expressed as illegal turns while it has the capability to tolerate faults without a prior knowledge on where and why a fault has happened.

A Fault-Tolerant Routing Algorithm for NoC Using Farthest Reachable Routers

As technology scaling, reliability has became one of the key challenges of Network-on-Chip (NoC). Many fault-tolerant routing algorithms for NoC are developed to overcome fault components and provide reliable transmission. But proposed routing algorithms do not pay enough attention to find the shortest paths, which increases latency and power consumption. In this paper, a fault-tolerant routing algorithm using new component states diffusion method based on Farthest Reachable Router (FRR) is proposed. This algorithm can reduce latency by finding the shortest paths between source and destination routers. Experiment results verify that FRR routing algorithm can tolerate 79% fault patterns within 3 × 3 and reduce latency by 16-44% compared with FON.

VisualNoC: A Visualization and Evaluation Environment for Simulation and Mapping

Simulation is the most common approach to evaluate Network on Chip (NoC) designs and many simulators at different abstraction levels have been developed so far. However, researchers have to spend a considerable amount of time and effort to debug, analyze, and extract meaningful information from the simulator reports. In this work, we propose a full-system visualization framework, called VisualNoC, that support both network simulation and task mapping. VisualNoC operates in a cycle-accurate mode and is based on an event-based trace model which can record the behaviors of routers, processing elements and packets. The visualization interface can provide efficient debugging and analysis platform by representing the simulation process and results in a variety of ways. One of the main features of VisualNoC is providing an intuitive way of analyzing the efficiency of different mapping algorithms that helps in finding bottlenecks and optimizing the design.

Design of Fault-Tolerant and Reliable Networks-on-Chip

Networks-on-Chips (NoCs) are at the core of high performance multi-processor systems-on-chips. As the number of cores and sub-systems on chip grows, the size and complexity of NoCs increase as well. Due to the process variation, aging effects and soft-errors in current and expected future process generations, the probability of failure in the NoCs rises and has to be fought at all levels: circuit, architecture, and communication protocols. This paper discusses appropriate fault models for NoCs and their effects on the architecture and network levels. A method to design fault-tolerant NoCs comprising of techniques at the link level, the routing level, and the end-to-end level of the communication is presented. In addition, the proposed method offers an isolation technique where the computing cores are decoupled from the faults in the network. This technique avoids or at least attenuates the severe impacts of faults on the network performance and functionality. These point techniques are combined together to design fault-tolerant and reliable NoCs.

WeNA: Deterministic Run-time Task Mapping for Performance Improvement in Many-core Embedded Systems

Many-core embedded systems will feature an extremely dynamic workload distribution where massive applications arranged as an unpredictable sequence enter and leave the system at run-time. Efficient mapping strategy is required to allocate system resources to the incoming application. Noncontiguous mapping improves system throughput by utilizing disjoint nodes, however, the increasing communication distance and external congestion lead to high power consumption and network delay. This paper thus presents an enhanced noncontiguous dynamic mapping algorithm, aiming at decreasing interprocessor communication overhead and improving both network and application performance. Communication volumes are utilized to arrange the mapping order of tasks belong to the same application. Moreover, expanding parameter of each task is developed which directs the optimized mapping decision comparing to the current neighborhood and occupancy information. Experimental results show that our modified mapping algorithm Weighted-based Neighborhood Allocation (WeNA) makes considerable improvements on Average Weighted Manhattan Distance (8.06%) and network latency (9.8%) in comparison with the state-of-the-art algorithm.

Fault-resilient routing unit in NoCs

With aggressive technology scaling in deep submicron era, burgeoning transistors make chips more susceptible to failures. It is inevitable that process variation is gradually becoming a crucial challenge in the IC design. In addition, aging leads to faults, shortening the lifetime of the circuits. Networks-on-chip also come to the problems caused by variations and aging, leading to degraded performance and erroneous behaviors. Faults may occur in numerous locations of the on-chip networks and once they occur in the control path, more severe effects such as deadlock and livelock are expected. In this paper, we present a fine-grained mechanism to tolerate faults in the routing computation units without disabling the faulty routers. By applying this mechanism, routing and packet-receiving services are separated. The faulty routing computation unit is replaced by a light-weight redundant circuit, providing static but reliable routing services. The other components in this router are still functional retaining the on-chip performance. Experimental results indicate that the on-chip network with the proposed mechanism is fault-tolerant when 14% of all routing computation modules are suffering from faults. The area overhead and power consumption of the proposed method is around 7.29% and 6.20% over the baseline approach.

Non-blocking BIST for continuous reliability monitoring of Networks-on-Chip

To achieve high reliability in on-chip networks, frequent runs of Built-in Self-Test allow the detection of and recovery from faults before they affect packets and the system functionality. However, to test routers, wrappers isolate cores from the network which leads to execution blocking and performance loss. In this paper, we propose a design-for-test reconfigurable router with two alternative bypassing channels. The router architecture allows maintaining the connection between cores and the network during the testing procedure by utilizing the bypassing channels. With the help of an adaptive routing algorithm and a testing strategy, networks can be fully tested at a high testing frequency with <15% increase of execution time.

Minimizing the system impact of router faults by means of reconfiguration and adaptive routing

Abstract To tolerate faults in Networks-on-Chip (NoC), routers are often disconnected from the NoC, which affects the system integrity. This is because cores connected to the disabled routers cannot be accessed from the network, resulting in loss of function and performance. We propose E-Rescuer , a technique offering a reconfigurable router architecture and a fault-tolerant routing algorithm. By taking advantage of bypassing channels, the reconfigurable router architecture maintains the connection between the cores and the network regardless of the router status. The routing algorithm allows the core to access the network when the local router is disabled.Our analysis and experiments show that the proposed technique provides 100% packet delivery in 100%, 92.56%, and 83.25% of patterns when 1, 2 and 3 routers are faulty, respectively. Moreover, the throughput increases up to 80%, 46% and 33% in comparison with FTLR, HiPFaR, and CoreRescuer, respectively.