A Novel Hybrid Cache Coherence with Global Snooping for Many-core Architectures

Cache coherence ensures correctness of cached data in multi-core processors. Traditional implementations of existing protocols make them unscalable for many core architectures. While snoopy coherence requires unscalable ordered networks, directory coherence is weighed down by high area and energy overheads. In this work, we propose Wireless-enabled Share-aware Hybrid (WiSH) to provide scalable coherence in many core processors. WiSH implements a novel Snoopy over Directory protocol using on-chip wireless links and hierarchical, clustered Network-on-Chip to achieve low-overhead and highly efficient coherence. A local directory protocol maintains coherence within a cluster of cores, while coherence among such clusters is achieved through global snoopy protocol. The ordered network for global snooping is provided through low-latency and low-energy broadcast wireless links. The overheads are further reduced through share-aware cache segmentation to eliminate coherence for private blocks. Evaluations show that WiSH reduces traffic by and runtime by , while requiring smaller storage and lower energy as compared to existing hierarchical and hybrid coherence protocols. Owing to its modularity, WiSH provides highly efficient and scalable coherence for many core processors.

Sub-Milliwatt Transceiver IC for Transcutaneous Communication of an Intracortical Visual Prosthesis

An intracortical visual prosthesis plays a vital role in partially restoring the faculty of sight in visually impaired people. Reliable high date rate wireless links are needed for transcutaneous communication. Such wireless communication should receive stimulation data (downlink) and send out neural recorded data (uplink). Hence, there is a need for an implanted transceiver that is low-power and delivers sufficient data rate for both uplink and downlink. In this paper, we propose an integrated circuit (IC) solution based on impulse radio ultrawideband using on-off keying modulation (OOK IR-UWB) for the uplink transmitter, and binary phase-shift keying (BPSK) with sampling and digital detection for the downlink receiver. To make the solution low-power, predominantly digital components are used in the presented transceiver test-chip. Current-controlled oscillators and an impulse generator provide tunability and complete the on-chip integration. The transceiver test-IC is fabricated in 180 nm CMOS technology and occupies only 0.0272 mm2. At 1.3 V power supply, only 0.2 mW is consumed for the BPSK receiver and 0.3 mW for the IR-UWB transmitter in the transceiver IC, while delivering 1 Mbps and 50 Mbps, respectively. Our link budget analysis shows that this test chip is suitable for intracortical integration considering the future off-chip antennas/coils transcutaneous 3–7 mm communication with the outer side. Hence, our work will enable realistic wireless links for the intracortical visual prosthesis.

Wireless Network Optimization for Federated Learning with Model Compression in Hybrid VLC/RF Systems

In this paper, the optimization of network performance to support the deployment of federated learning (FL) is investigated. In particular, in the considered model, each user owns a machine learning (ML) model by training through its own dataset, and then transmits its ML parameters to a base station (BS) which aggregates the ML parameters to obtain a global ML model and transmits it to each user. Due to limited radio frequency (RF) resources, the number of users that participate in FL is restricted. Meanwhile, each user uploading and downloading the FL parameters may increase communication costs thus reducing the number of participating users. To this end, we propose to introduce visible light communication (VLC) as a supplement to RF and use compression methods to reduce the resources needed to transmit FL parameters over wireless links so as to further improve the communication efficiency and simultaneously optimize wireless network through user selection and resource allocation. This user selection and bandwidth allocation problem is formulated as an optimization problem whose goal is to minimize the training loss of FL. We first use a model compression method to reduce the size of FL model parameters that are transmitted over wireless links. Then, the optimization problem is separated into two subproblems. The first subproblem is a user selection problem with a given bandwidth allocation, which is solved by a traversal algorithm. The second subproblem is a bandwidth allocation problem with a given user selection, which is solved by a numerical method. The ultimate user selection and bandwidth allocation are obtained by iteratively compressing the model and solving these two subproblems. Simulation results show that the proposed FL algorithm can improve the accuracy of object recognition by up to 16.7% and improve the number of selected users by up to 68.7%, compared to a conventional FL algorithm using only RF.

Continuous-Variable Quantum Secret Sharing Based on Thermal Terahertz Sources in Inter-Satellite Wireless Links

We propose a continuous-variable quantum secret sharing (CVQSS) scheme based on thermal terahertz (THz) sources in inter-satellite wireless links (THz-CVQSS). In this scheme, firstly, each player locally preforms Gaussian modulation to prepare a thermal THz state, and then couples it into a circulating spatiotemporal mode using a highly asymmetric beam splitter. At the end, the dealer measures the quadrature components of the received spatiotemporal mode through performing the heterodyne detection to share secure keys with all the players of a group. This design enables that the key can be recovered only by the whole group players’ knowledge in cooperation and neither a single player nor any subset of the players in the group can recover the key correctly. We analyze both the security and the performance of THz-CVQSS in inter-satellite links. Results show that a long-distance inter-satellite THz-CVQSS scheme with multiple players is feasible. This work will provide an effective way for building an inter-satellite quantum communication network.