Xi Zeng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Xi Zeng has a total of 24 co-authors. Here are the top co-authors by number of shared publications:
- Yunji Chen
State Key Lab of Processors, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China
3 shared publications - Zidong Du
Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China
3 shared publications - Ling Li
University of Chinese Academy of Sciences
2 shared publications - Qi Guo
Institute of Computing Technology, Chinese Academy of Sciences
2 shared publications Bingrui Wang
Cambricon Technologies
1 shared publication- Chao Wang
University of Science and Technology of China
1 shared publication
Latest Publications
- 18 January 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
- Vol. 41 (1) , 116-128
Cambricon-G: A Polyvalent Energy-Efficient Accelerator for Dynamic Graph Neural Networks
Graph neural networks (GNNs), which extend traditional neural networks for processing graph-structured data, have been widely used in many fields. The GNN computation mainly consists of the edge processing to generate messages by combining the edge/vertex features and the vertex processing to update the vertex features with aggregated messages. In addition to nontrivial vector operations in the edge processing, huge random accesses and neural network operations in the vertex processing, the graph topology of GNNs may also vary during the computation (i.e., dynamic GNNs). The above characteristics pose significant challenges on existing architectures. In this article, we propose a novel accelerator named CAMBRICON-G for efficient processing of both dynamic and static GNNs. The key of CAMBRICON-G is to abstract the irregular computation of a broad range of GNN variants to the process of regularly tiled adjacent cuboid (which extends the traditional adjacent matrix of graph by adding the dimension of vertex features). The intuition is that the adjacent cuboid facilitates exploitation of both data locality and parallelism by offering multidimensional multilevel tiling (including spatial and temporal tiling) opportunities. To perform the multidimensional spatial tiling , the CAMBRICON-G architecture mainly consists of the cuboid engine (CE) and hybrid on-chip memory. The CE has multiple vertex processing units (VPUs) working in a coordinated manner to efficiently process the sparse data and dynamically update the graph topology with dedicated instructions. The hybrid on-chip memory contains the topology-aware cache and multiple scratchpad memory to reduce off-chip memory access. To perform the multidimensional temporal tiling , an easy-to-use programming model is provided to flexibly explore different tiling options for large graphs. Experimental results show that compared against Nvidia P100 GPU, the performance and energy efficiency can be improved by$7.14\times $ and$20.18\times $ , respectively, on various GNNs, which validates both the versatility and energy efficiency of CAMBRICON-G.- 18 January 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
- Vol. 41 (1) , 116-128
Cambricon-G: A Polyvalent Energy-Efficient Accelerator for Dynamic Graph Neural Networks
Graph neural networks (GNNs), which extend traditional neural networks for processing graph-structured data, have been widely used in many fields. The GNN computation mainly consists of the edge processing to generate messages by combining the edge/vertex features and the vertex processing to update the vertex features with aggregated messages. In addition to nontrivial vector operations in the edge processing, huge random accesses and neural network operations in the vertex processing, the graph topology of GNNs may also vary during the computation (i.e., dynamic GNNs). The above characteristics pose significant challenges on existing architectures. In this article, we propose a novel accelerator named CAMBRICON-G for efficient processing of both dynamic and static GNNs. The key of CAMBRICON-G is to abstract the irregular computation of a broad range of GNN variants to the process of regularly tiled adjacent cuboid (which extends the traditional adjacent matrix of graph by adding the dimension of vertex features). The intuition is that the adjacent cuboid facilitates exploitation of both data locality and parallelism by offering multidimensional multilevel tiling (including spatial and temporal tiling) opportunities. To perform the multidimensional spatial tiling , the CAMBRICON-G architecture mainly consists of the cuboid engine (CE) and hybrid on-chip memory. The CE has multiple vertex processing units (VPUs) working in a coordinated manner to efficiently process the sparse data and dynamically update the graph topology with dedicated instructions. The hybrid on-chip memory contains the topology-aware cache and multiple scratchpad memory to reduce off-chip memory access. To perform the multidimensional temporal tiling , an easy-to-use programming model is provided to flexibly explore different tiling options for large graphs. Experimental results show that compared against Nvidia P100 GPU, the performance and energy efficiency can be improved by$7.14\times $ and$20.18\times $ , respectively, on various GNNs, which validates both the versatility and energy efficiency of CAMBRICON-G.- 14 December 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computers
- Vol. 71 (1) , 209-222
Breaking the Interaction Wall: A DLPU-Centric Deep Learning Computing System
Due to the broad successes of deep learning, many CPU-centric artificial intelligent computing systems employ specialized devices such as GPUs, FPGAs, and ASICs, which can be named as Deep Learning Processing Units (DLPUs), for processing computation-intensive deep learning tasks. The separation between the scalar control operations mapped on CPUs and the vector computation operations mapped on DLPUs causes the frequent and costly interactions between CPUs and DLPUs, leading to the Interaction Wall. Moreover, the increasing algorithm complexity and DLPU computation speed would further aggravate the interaction wall substantially.
- 14 December 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computers
- Vol. 71 (1) , 209-222
Breaking the Interaction Wall: A DLPU-Centric Deep Learning Computing System
Due to the broad successes of deep learning, many CPU-centric artificial intelligent computing systems employ specialized devices such as GPUs, FPGAs, and ASICs, which can be named as Deep Learning Processing Units (DLPUs), for processing computation-intensive deep learning tasks. The separation between the scalar control operations mapped on CPUs and the vector computation operations mapped on DLPUs causes the frequent and costly interactions between CPUs and DLPUs, leading to the Interaction Wall. Moreover, the increasing algorithm complexity and DLPU computation speed would further aggravate the interaction wall substantially.
- 5 March 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computers
- Vol. PP (00189340) , 1
Addressing Irregularity in Sparse Neural Networks through a Cooperative Software/Hardware Approach
Neural networks have become the dominant algorithms rapidly as they achieve state-of-the-art performance in a broad range of applications such as image recognition, speech recognition and natural language processing. However, neural networks keep moving towards deeper and larger architectures, posing a great challenge to hardware systems due to the huge amount of data and computations. Although sparsity has emerged as an effective solution for reducing the intensity of computation and memory accesses directly, irregularity caused by sparsity (including sparse synapses and neurons) prevents accelerators from completely leveraging the benefits, i.e., it also introduces costly indexing module in accelerators. In this paper, we propose a cooperative software/hardware approach to address the irregularity of sparse neural networks efficiently. Initially, we observe the local convergence, namely larger weights tend to gather into small clusters during training. Based on that key observation, we propose a software-based coarse-grained pruning technique to reduce the irregularity of sparse synapses drastically. The coarse-grained pruning technique, together with local quantization, significantly reduces the size of indexes and improves the network compression ratio. We further design a multi-core hardware accelerator, Cambricon-SE, to address the remaining irregularity of sparse synapses and neurons efficiently. The novel accelerator have three key features: 1) selector modules to filter unnecessary synapses and neurons, 2) compress/decompress modules for exploiting the sparsity in data transmission (which is rarely studied in previous work), and 3) a multi-core architecture with elevated throughput to meet the real-time processing requirement. Compared against a state-of-the-art sparse neural network accelerator, our accelerator is 1:20× and 2:72× better in terms of performance and energy efficiency, respectively. Moreover, for real-time video analysis tasks, Cambricon-SE can process 1080p video at the speed of 76.59 fps.
- 5 March 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computers
- Vol. PP (00189340) , 1
Addressing Irregularity in Sparse Neural Networks through a Cooperative Software/Hardware Approach
Neural networks have become the dominant algorithms rapidly as they achieve state-of-the-art performance in a broad range of applications such as image recognition, speech recognition and natural language processing. However, neural networks keep moving towards deeper and larger architectures, posing a great challenge to hardware systems due to the huge amount of data and computations. Although sparsity has emerged as an effective solution for reducing the intensity of computation and memory accesses directly, irregularity caused by sparsity (including sparse synapses and neurons) prevents accelerators from completely leveraging the benefits, i.e., it also introduces costly indexing module in accelerators. In this paper, we propose a cooperative software/hardware approach to address the irregularity of sparse neural networks efficiently. Initially, we observe the local convergence, namely larger weights tend to gather into small clusters during training. Based on that key observation, we propose a software-based coarse-grained pruning technique to reduce the irregularity of sparse synapses drastically. The coarse-grained pruning technique, together with local quantization, significantly reduces the size of indexes and improves the network compression ratio. We further design a multi-core hardware accelerator, Cambricon-SE, to address the remaining irregularity of sparse synapses and neurons efficiently. The novel accelerator have three key features: 1) selector modules to filter unnecessary synapses and neurons, 2) compress/decompress modules for exploiting the sparsity in data transmission (which is rarely studied in previous work), and 3) a multi-core architecture with elevated throughput to meet the real-time processing requirement. Compared against a state-of-the-art sparse neural network accelerator, our accelerator is 1:20× and 2:72× better in terms of performance and energy efficiency, respectively. Moreover, for real-time video analysis tasks, Cambricon-SE can process 1080p video at the speed of 76.59 fps.