Online testing is critical to ensuring reliable operations of the next generation of supercomputers based on a kilo-core network-on-chip (NoC) interconnection fabric. We present a parallel software-based self-testing (SBST) solution that makes use of the bounded model checking (BMC) technique to generate test sequences and parallel packets. In this method, the parallel SBST with BMC derives the leading sequence for each router’s internal function and detects all functionally-testable faults related to the function. A Monte-Carlo simulation algorithm is then used to search for the approximately optimum configuration of the parallel packets, which guarantees the test quality and minimizes the test cost. Finally, a multi-threading technology is used to ensure that the Monte-Carlo simulation can reach the approximately optimum configuration in a large random space and reduce the generating time of the parallel test. Experimental results show that the proposed method achieves a high fault coverage with a reduced test overhead. Moreover, by performing online testing in the functional mode with SBST, it effectively avoids the over-testing problem caused by functionally untestable turns in kilo-core NoCs.

Mining from simulation data of the golden model in hardware design verification is an effective solution to assertion generation. While the simulation data is inherently incomplete, it is necessary to evaluate the truth values of the mined assertions. This paper presents an approach to evaluating and constraining hardware assertions with absent scenarios. A Belief-failRate metric is proposed to predict the truth/falseness of generated assertions. By considering both the occurrences of free variable assignments and the conflicts of absent scenarios, we use the metric to sort true assertions in higher ranking and false assertions in lower ranking. Our Belief-failRate guided assertion constraining method leverages the quality of generated assertions. The experimental results show that the Belief-failRate framework performs better than the existing methods. In addition, the assertion evaluating and constraining procedure can find more assertions that cover new design functionality in comparison with the previous methods.

Hardware Trojans (HTs) have drawn increasing attention in both academia and industry because of their significant potential threat. In this paper, we propose HTDet, a novel HT detection method using information entropy-based clustering. To maintain high concealment, HTs are usually inserted in the regions with low controllability and low observability, which will result in that Trojan logics have extremely low transitions during the simulation. This implies that the regions with the low transitions will provide much more abundant and more important information for HT detection. The HTDet applies information theory technology and a density-based clustering algorithm called Density-Based Spatial Clustering of Applications with Noise (DBSCAN) to detect all suspicious Trojan logics in the circuit under detection. The DBSCAN is an unsupervised learning algorithm, that can improve the applicability of HTDet. In addition, we develop a heuristic test pattern generation method using mutual information to increase the transitions of suspicious Trojan logics. Experiments on circuit benchmarks demonstrate the effectiveness of HTDet.

The poor energy proportionality of server is seen as the principal source for low energy efficiency of modern data centers. We find that different resource configurations of an application lead to similar performance, but have distinct energy consumption. We call this phenomenon as “performance-equivalent resource configurations (PERC)”, and its performance range is called equivalent region (ER). Based on PERC, one basic idea for improving energy efficiency is to select the most efficient configuration from PERC for each application. However, it cannot support every application to obtain optimal solution when thousands of applications are run simultaneously on resource-bounded servers. Here we propose a heuristic scheme, CPicker, based on genetic programming to improve energy efficiency of servers. To speed up convergence, CPicker initializes a high quality population by first choosing configurations from regions that have high energy variation. Experiments show that CPicker obtains above 17% energy efficiency improvement compared with the greedy approach, and less than 4% efficiency loss compared with the oracle case.