The die-stacking structure of 3D network-on-chips (3D NoC) leads to high power density and unequal thermal conductance between different layers, which results in low reliability and performance degradation of 3D NoCs. Congestion-aware adaptive routing, which is capable of balancing the network’s traffic load, can alleviate congestion and thermal problems so as to improve the performance of the network. In this study, we propose a traffic- and thermal-aware Q-routing algorithm (TTQR) based on Q-learning, a reinforcement learning method. The proposed algorithm saves the local traffic status and the global temperature information to the Q1-table and Q2-table, respectively. The values of two tables are updated by the packet header and saved in a small size, which saves the hardware overhead. Based on the ratio of the Q1-value to the Q2-value corresponding to each direction, the packet’s output port is selected. As a result, packets are transferred to the chosen path to alleviate thermal problems and achieve more balanced inter-layer traffic. Through the Access Noxim simulation platform, we compare the proposed routing algorithm with the TAAR routing algorithm. According to experimental results using synthetic traffic patterns, our proposed methods outperform the TAAR routing algorithm by an average of 63.6% and 41.4% in average latency and throughput, respectively.

The reliability of memory is an important issue. The rapid development of transistor technology makes the memory more prone to soft errors. Several recent efforts have proposed various designs to avoid the corruption of stored data by using Error Correction Codes (ECC). However, these designs tend to focus on one indicator, which means they cannot balance the electrical timing, area and power consumption constraints with the increasing of the chip-scale and the operating frequency. In this paper, we propose a design named TECED: A Two-Dimensional Error-Correction Codes Based Energy-Efficiency SRAM Design. We achieve higher energy-efficiency and lower hardware cost by using a two-dimensional error correction codes, and evaluate the design by considering the overall system performance. Comparing with the traditional Hamming code, the evaluation shows that the TECED reduces most of fifty percent of the area overhead and twenty-eight point five percent power consumption of the memory at a specific storage capacity.

Due to the high throughput and high computing capability of convolutional neural networks (CNNs), researchers are paying increasing attention to the design of CNNs hardware accelerator architecture. Accordingly, in this paper, we propose a block parallel computing algorithm based on the matrix transformation computing algorithm (MTCA) to realize the convolution expansion and resolve the block problem of the intermediate matrix. It enables high parallel implementation on hardware. Moreover, we also provide a specific calculation method for the optimal partition of matrix multiplication to optimize performance. In our evaluation, our proposed method saves more than 60% of hardware storage space compared with the im2col(image to column) approach. More specifically, in the case of large-scale convolutions, it saves nearly 82% of storage space. Under the accelerator architecture framework designed in this paper, we realize the performance of 26.7GFLOPS-33.4GFLOPS (depending on convolution type) on FPGA(Field Programmable Gate Array) by reducing bandwidth and improving data reusability. It is 1.2×–4.0× faster than memory-efficient convolution (MEC) and im2col, respectively, and represents an effective solution for a large-scale convolution accelerator.

Deep Neural Networks (DNNs) have achieved great progress in academia and industry. But they have become computational and memory intensive with the increase of network depth. Previous designs seek breakthroughs in software and hardware levels to mitigate these challenges. At the software level, neural network compression techniques have effectively reduced network scale and energy consumption. However, the conventional compression algorithm is complex and energy intensive. At the hardware level, the improvements in the semiconductor process have effectively reduced power and energy consumption. However, it is difficult for the traditional Von-Neumann architecture to further reduce the power consumption, due to the memory wall and the end of Moore’s law. To overcome these challenges, the spintronic device based DNN machines have emerged for their non-volatility, ultra low power, and high energy efficiency. However, there is no spin-based design that has achieved innovation at both the software and hardware level. Specifically, there is no systematic study of spin-based DNN architecture to deploy compressed networks. In our study, we present an ultra-efficient Spin-based Architecture for Compressed DNNs (SAC), to substantially reduce power consumption and energy consumption. Specifically, we propose a One-Step Compression algorithm (OSC) to reduce the computational complexity with minimum accuracy loss. We also propose a spin-based architecture to realize better performance for the compressed network. Furthermore, we introduce a novel computation flow that enables the reuse of activations and weights. Experimental results show that our study can reduce the computational complexity of compression algorithm from 𝒪( Tk ³ to 𝒪( k ² log k ), and achieve 14× ∼ 40× compression ratio. Furthermore, our design can attain a 2× enhancement in power efficiency and a 5× improvement in computational efficiency compared to the Eyeriss. Our models are available at an anonymous link https://bit.ly/39cdtTa .

As the Convolutional Neural Network (CNN) goes deeper and more complex, the network becomes memory-intensive and computation-intensive. To address this issue, the lightweight neural network reduces parameters and Multiplication-and-Accumulation (MAC) operations by using the Depthwise Separable Convolution (DSC) to improve speed and efficiency. Nonetheless, the energy efficiency of classical Von Neumann architectures for CNNs is limited due to the memory wall challenge. Spin-based architectures have the potential to address this challenge thanks to the integration of memory and computing with ultra-high energy efficiency. However, deploying the DSC on spin-based architectures with the traditional dataflow leads to huge activation movements and low hardware utilization. Moreover, the inter-layer data dependency of neural networks increases latency. These factors become the bottleneck of improving energy efficiency and performance.Inspired by these challenges, we propose a novel dataflow on Spin-based Architectures for Lightweight neural networks (SAL). The novel dataflow replaces convolution unrolling by selecting activations in the crossbar according to the convolution window and also realizes the inter-layer data reuse. Moreover, the novel dataflow also reduces the latency due to the data dependency between layers, realizing higher performance. To the best of our knowledge, this is the first design to use hybrid dataflow for the PIM architecture. We also optimize the structure of the spin-based crossbar and the pipeline based on the dataflow to achieve better data reuse and computational parallelism. For deploying the MobileNet V1, the novel dataflow improves the hardware utilization by 23×∼ 105× and reduces the data traffic by 1.09×∼ 18.6×. Compared with the NEBULA, a spin-based non-Von Neumann architecture, the SAL reduces the energy consumption by 4× and improves the performance by 7.3×, which are 0.32mJand 10.43GOPs^-1, respectively. Moreover, the SAL improves power efficiency over 29 times more than the NEBULA. Compared with the Eyeriss, the SAL improves the energy efficiency by four orders of magnitude.

The processing-in-memory (PIM) architecture becomes a promising candidate for deep learning accelerators by integrating computation and memory. Most PIM-based studies improve the performance and energy efficiency by using the weight stationary (WS) data flow due to its high parallelism. However, the WS data flow has some fundamental limitations. First, the WS data flow has huge activation movements between on-chip memory and off-chip memory due to the limited memory space of the resistive random-access memory (ReRAM) array. Second, the WS data flow needs to read the input activation repeatedly according to the convolution window. These data movements decrease the energy efficiency and performance of the PIM architecture. To address these issues, the input stationary (IS) data flow stores activations instead of weights to reduce data movements. But the IS data flow faces some challenges. First, the data dependency between adjacent layers limits the performance. Second, there are huge across-array computations due to the special mapping method. Third, the previous IS data flow cannot realize the high parallelism. Fourth, the IS data flow depends on the 3-D ReRAM structure. To address these issues, we propose a novel data flow for PIM architectures. We optimize the IS data flow to decrease the activation movement and propose a parallel computing method to realize high parallelism and reduce the across-array computations. We identify and analyze the fundamental limitations and impact of different interlayer data flows, including the WS-WS, IS-IS, WS-IS, and IS-WS. We also propose a method to build a hybrid data flow by combining these interlayer data flows to tradeoff performance and energy consumption. Our experimental results and analysis demonstrate the potential of our design. The performance and energy efficiency of our design reach 0.13–1.77 TFLOPS and 61–85 TOPS/J, respectively. Compared to the state-of-the-art design, the NEBULA, our design can improve performance by $1.4\times $ , $2.3\times $ , and $3.5\times $ for deploying the MobileNet-V1, ResNet-18, and VGG-16, and also can improve energy efficiency by $3.3\times $ , $2\times $ , and $2\times $ , respectively.