Search

Deep neural networks (DNNs) are revolutionizing machine learning, with unprecedented accuracy on many AI tasks. Energy-efficient neural acceleration is crucial in broadening DNN applications in cloud and mobile end devices. However, power-hungry clock networks limit the energy-efficiency of DNN accelerators. In this work, we propose a novel DNN hardware accelerator, called the asynchronous neural network processor (AsNNP). At the heart of AsNNP is a scalable hierarchy matrix multiply unit, with bit-serial processing elements working in parallel. It replaces the global clock networks with asynchronous handshake protocols to realize the synchronization and communication between each part, minimizing the dynamic power. Meanwhile, a fine-grain asynchronous pipeline based on weak-conditioned half-buffer (WCHB) is introduced to pipe successive computations in a data-driven manner, i.e., once data arrives computation begins, maximizing the throughput. These techniques enable AsNNP to work in a fully data-driven asynchronous communication fashion with optimized energy-efficiency. The proposed accelerator is implemented with quasi-delay-insensitive (QDI) clockless logic family and evaluated in a 65 nm process. Compared with the synchronous baseline, simulation results show that AsNNP offers $2.2\times $ higher equivalent frequency and $1.59\times $ lower power. Compared with state-of-the-art DNN accelerators, AsNNP shows $1.17\times -4.97\times $ energy-efficiency improvement.

Biothiols play an important role in living cells and are associated with many diseases. Thus, it is necessary to develop a facile, cost-effective, and convenient analytical method for the detection of biothiols. Nanozymes are functional nanomaterials with enzymatic activities. Due to their unique advantages (e.g., low cost, high stability, and multifunctionality), nanozymes have been extensively used to construct sensing systems. Previous studies demonstrated colorimetric assays for biothiol detection because they could competitively inhibit the peroxidase-like activities of nanozymes. However, few studies were able to differentiate biothiols from each other. To address these challenges, herein, we first synthesized Au alloy nanozymes with better peroxidase-like activities than gold nanoparticles (AuNPs). Then, cross-reactive sensor arrays were constructed with three alloy nanozymes. Six typical biothiols (i.e., glutathione, cysteine, dithiothreitol, mercaptoacetic acid, mercaptoethanol, and mercaptosuccinic acid) were successfully detected and discriminated by the as-prepared nanozyme sensor arrays. Moreover, the practical application of the nanozyme sensor arrays was demonstrated by discriminating biothiols in serum successfully.

Owing to the existence of power-hungry clock networks, synchronous CNN accelerators are hard to achieve further low power consumption. In this paper, we propose a novel clockless asynchronous CNN processing element, replacing clock networks with asynchronous handshake signals. And then we construct a CNN computation array based on our PE and implement it in standard ASIC design flow. In addition, compared with the synchronous version that works at 200MHz frequency, our design can realize about 5.70× power consumption saving and 5.59× power-efficiency improvement when working at 196.0MHz equivalent frequency.

VGG-16 neural network is one of the most powerful artificial intelligence algorithms widely used in computer vision. There are many accelerators proposed for VGG-16 to obtain high energy efficiency but ignoring the existence of the power-hungry clock network. In this paper, we proposed an asynchronous convolution process engine for VGG-16 whose multiplication and accumulation (MAC) are clock-free asynchronous circuits. We also proposed a novel synchronous and asynchronous interface to solve the problem of setup time and hold time violations that easily occur when synchronous and asynchronous circuits are combined. The whole design was implemented in the 4Onm process. Experimental results show that compared with the synchronous version design, our asynchronous convolution process engine can achieve a 1.5x improvement in energy efficiency.

The promise of immunotherapy for cancer therapy has not been fully fulfilled because portions of tumors are immunosuppressive. To tackle this challenge, the initiation of immune system by stimulator of interferon genes (STING) pathway is explored and multifunctional STING-activating nanoparticles are rationally designed for synergistic antitumor therapy. The STING-activating nanoparticles have a formulation of Mn

Correction for ‘Gold alloy-based nanozyme sensor arrays for biothiol detection’ by Junshu Lin et al., Analyst, 2020, DOI: 10.1039/d0an00451k.