- 博客(6)
- 收藏
- 关注
原创 Paper Reading: DCNN Architecture With Reconfigurable Computation Patterns
This paper is published in VLSI in 2017. Prior works on DCNN acceleration usually use a fixed computation pattern for diverse DCNN models, which leads to imbalance between power efficiency and performance. Thus, the researchers design a DCNN accele
2023-07-02 10:56:43 59 1
原创 Paper Reading: Eyeriss v2: A Flexible Accelerator for Emerging DCNNs on Mobile Devices
This paper is published in 2019. Due to the compact or sparse models are different from the traditional large ones in that there is much more variation in their layer shapes and sizes, the researchs design a flexible accelerator, called eyeriss v2, exploit
2023-07-02 10:00:10 161 1
原创 Paper Reading: Eyeriss: An Energy-Efficient Reconfigurable Accelerator for DCNNs
This paper is published in JSSC in 2017. CNNs are widely used in modern AI systems but also bring challenges on throughput and energy efficiency to the underlying hardware. Therefore, the researchers design an energy-efficient reconfigurable accelerator, c
2023-07-01 23:27:22 148
原创 Paper Reading: DNPU: An 8.1TOPS/W Reconfigurable CNN-RNN Processor for Deep Neural Networks
This paper is published in ISSCC in 2017. Recently, deep learning with convolutional neural networks (CNNs) and recurrent neural networks (RNNs) has become universal in all-around applications. But there has been no work on a combined CNN-RNN processor. He
2023-07-01 22:50:39 223
原创 Paper Reading: A 288μW Programmable Deep-Learning Processor with 270KB On-Chip Weight Storage
This paper is published in ISSCC in 2017. Recently there has been increased interest in deep learning for mobile IoT to enable intelligence at the edge. Therefore, low power is a critical design constraint. The researchers introduce a low-power, programmab
2023-07-01 22:04:45 75
原创 Paper Reading: A 1.42TOPS/W Deep Convolutional Neural Network Recognition Processor for Intelligent
This paper, published in ISSCC in 2016, addresses the challenges posed by the computational complexity and significant memory requirements of Convolutional Neural Networks (CNNs). In order to enable intelligent edge devices, the researchers implemented an
2023-07-01 16:14:15 106
空空如也
空空如也
TA创建的收藏夹 TA关注的收藏夹
TA关注的人