Published papers

High-end network standards, such as 400GbE, have been introduced Forwarding Error Correction (FEC) for maintaining the same bit error rate (BER) as that in traditional low-bandwidth interconnection networks. However, FEC operation latency overhead surprisingly becomes higher than the sum of all the other switch operation overheads, e.g., routing computation and switch allocation. FEC operation latency overhead significantly degrades the performance of parallel applications in HPC systems. Instead, in this study, we exploit the low-latency network design using a Hamming code that does not provide rigid error-free communication. Since it is consistent with existing frame format based on standard Reed-Solomon RS(544,514) with DC(64b/66b) direct linecode and TC(256b/257b) transcode, respectively, the influences upon the other network layer design are limited. Interestingly, a large number of parallel applications can accept the BER in such a Hamming code. Since lowering such a BER improves switch operation latency, the proposed network using the Hamming code improves the execution time of NAS Parallel Benchmarks by 56% on average when compared to the counterpart RS-FEC networks.

Toward machine learning based prediction services, the prediction server has multiple predictors and selects an appropriate one based on past feedbacks from the clients. In this case, three messages including request, reply, and feedback, are required for each prediction request. Packets are typically transmitted and received via a network protocol stack in OS kernel, and performance improvement can be expected by avoiding the protocol stack since it degrades the communication performance especially for small packets. We implement the prediction server using network optimization approaches including kernel-bypassing and in-NIC processing approaches. Evaluation results show that these network optimizations are beneficial to improve the prediction server performance compared to a baseline prediction server using a standard network protocol stack.

Autoencoder, a neural-network based dimensionality reduction algorithm has demonstrated its effectiveness in anomaly detection. It can detect whether an input sample is normal or abnormal by just training only with normal data. In general, Autoencoder is built on backpropagation-based neural networks (BP-NNs). When BP-NNs are implemented in edge devices, they are typically specialized only for prediction with weight matrices precomputed offline due to the high computational cost. However, such devices cannot be immediately adapted to time-series trend changes of input data. In this paper, we propose an FPGA-based unsupervised anomaly detector, called OS-ELM-FPGA, that combines Autoencoder and an online sequential learning algorithm OS-ELM. Based on our theoretical analysis of the algorithm, the proposed OS-ELM-FPGA completely eliminates matrix pseudoinversions while improving the learning throughput. Simulation results using open-source datasets show that OS-ELM-FPGA achieves favorable anomaly detection accuracy compared to CPU and GPU implementations of BP-NNs. Learning throughput of OS-ELM-FPGA is 3.47x to 27.99x and 5.22x to 78.06x higher than those of CPU and GPU implementations of OS-ELM. It is also 3.62x to 36.15x and 1.53x to 43.44x higher than those of CPU and GPU implementations of BP-NNs.

Toward on-device learning on IoT devices, this paper implements an online sequential learning and unsupervised anomaly detection core and explores its design options, such as pipeline structure. They are evaluated in terms of performance and cost.

In parallel processing applications, a few worker nodes called "stragglers", which execute their tasks significantly slower than other tasks, increase the execution time of the job. In this paper, we propose a network switch based straggler handling system to mitigate the burden of the compute nodes. We also propose how to offload detecting stragglers and computing their results in the network switch with no additional communications between worker nodes. We introduce some approximate techniques for the proxy computation and response at the switch; thus our switch is called "ApproxSW." As a result of a simulation experiment, the proposed approximation based on task similarity achieves the best accuracy in terms of quality of generated Map outputs. We also analyze how to suppress unnecessary proxy computation by the ApproxSW. We implement ApproxSW on NetFPGA-SUME board that has four 10Gbit Ethernet (10GbE) interfaces and a Virtex-7 FPGA. Experimental results shows that the ApproxSW functions do not degrade the original 10GbE switch performance.

The emerging field of NoC with Wireless interconnects is actively being pursued by a number of researchers worldwide, from a variety of different perspectives, ranging from very high levels of abstraction (e.g., system architecture) to very low levels (physical layer and transceiver design). Successful solutions will likely adopt and encompass elements from all or at least several levels of abstraction and rely on interdisciplinary concepts from multi-core architectures, integrated circuits, 3D ICs, digital communications, complex networks, and optimization techniques. This special session will provide a timely and insightful journey into various challenges and emerging solutions regarding the design of future NoC architectures. By scope and contents, this special session represents an engaging proposition to attendees belonging to both academia and industry.

Recently proposed irregular networks can reduce the latency for both on-chip and off-chip systems with a large number of computing nodes and thus can improve the performance of parallel applications. However, these networks usually suffer from deadlocks in routing packets when using a naive minimal path routing algorithm. To solve this problem, we focus attention on a lately proposed theory that generalizes the turn model to maintain the network performance with deadlock-freedom. The theorems remain a challenge of applying themselves to arbitrary topologies including fully irregular networks. In this paper, we advance the theorems to completely general ones. Moreover, we provide a feasible implementation of a deadlock-free routing method based on our advanced theorem. Experimental results show that the routing method based on our proposed theorem can improve the network throughput by up to 138 % compared to a conventional deterministic minimal routing method. Moreover, when utilized as the escape path in Duato’s protocol, it can improve the throughput by up to 26.3 % compared with the conventional up*/down* routing.

Engineers and researchers have recently paid attention to Blockchain. Blockchain is a fault-tolerant distributed ledger without administrators. Blockchain is originally derived from cryptocurrency, but it is possible to be applied to other industries. Transferring digital asset is called a transaction. Blockchain holds all transactions, so the total amount of Blockchain data will increase as time proceeds. On the other hand, the number of Internet of Things (IoT) products has been increasing. It is difficult for IoT products to hold all Blockchain data because of their storage capacity. Therefore, they access Blockchain data via servers that have Blockchain data. However, if a lot of IoT products access Blockchain network via servers, server overloads will occur. Thus, it is useful to reduce workloads and improve throughput. In this paper, we propose a caching technique using a Field Programmable Gate Array-based (FPGA) Network Interface Card (NIC) which possesses four 10Gigabit Ethernet (10GbE) interfaces. The proposed system can reduce server overloads, because the FPGA NIC instead of the server responds to requests from IoT products if cache hits. We implemented the proposed hardware cache to achieve high throughput on NetFPGA-10G board. We counted the number of requests that the server or the FPGA NIC processed as an evaluation. As a result, the throughput improved by on average 1.97 times when hitting the cache.