Ping Chen
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
Ping Chen has a total of 34 co-authors. Here are the top co-authors by number of shared publications:
- Shuibing He
Zhejiang University
6 shared publications - Xuechen Zhang
Kennesaw State University
5 shared publications - Siling Yang
Zhejiang University
4 shared publications - Weijian Chen
Zhejiang University
3 shared publications - Xian-He Sun
Illinois Institute of Technology
3 shared publications - Gang Chen
Zhejiang University
2 shared publications
Latest Publications
- 1 December 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computers
- Vol. 75 (12) , 4091-4105
HyperInfer: Accelerating Large Language Model Inference via Importance-Informed Prefix-KV Caching and Prefetching
- 1 December 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computers
- Vol. 75 (12) , 4091-4105
HyperInfer: Accelerating Large Language Model Inference via Importance-Informed Prefix-KV Caching and Prefetching
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 956-967
Road-Constrained Vehicle Trajectory Recovery from Traffic Video Using Spatio-Temporal Voxel Representation
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 956-967
Open AccessRoad-Constrained Vehicle Trajectory Recovery from Traffic Video Using Spatio-Temporal Voxel Representation
- Open Access
- 8 July 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Storage
NVREC: A High-Performance Recoverable Recommendation System for Non-Volatile Memory
Current recommendation systems are designed with the assumption that computer memory is volatile. Thus, they periodically execute checkpointing operations to save model weights and embeddings to slower solid-state drives (SSDs) for failure recovery. Such designs cannot leverage the unique characteristics of non-volatile memory (NVM). This paper proposes a new recommendation model training framework called NVrec , which uses a hybrid memory system consisting of DRAM and NVM to support computing and in-memory checkpointing. NVrec proposes three recommendation-oriented techniques. (1) It partitions embeddings so that only popular vectors are placed in DRAM to hide NVM-induced latency. (2) It maintains a dual-version scheme for in-memory checkpointing: each vector in NVM alternates between a persistent version for crash recovery and a runtime version for training updates. (3) It employs fine-grained parallelism to hide the checkpointing overhead of model parameters in DRAM and GPU. Our experiments demonstrate that NVrec improves recommendation-model training throughput by 1.05 × -6.85 × and the checkpointing process by more than 5 × compared to existing models when evaluated on the synthetic and real-world datasets.
- 8 July 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Storage
Open AccessNVREC: A High-Performance Recoverable Recommendation System for Non-Volatile Memory
Current recommendation systems are designed with the assumption that computer memory is volatile. Thus, they periodically execute checkpointing operations to save model weights and embeddings to slower solid-state drives (SSDs) for failure recovery. Such designs cannot leverage the unique characteristics of non-volatile memory (NVM). This paper proposes a new recommendation model training framework called NVrec , which uses a hybrid memory system consisting of DRAM and NVM to support computing and in-memory checkpointing. NVrec proposes three recommendation-oriented techniques. (1) It partitions embeddings so that only popular vectors are placed in DRAM to hide NVM-induced latency. (2) It maintains a dual-version scheme for in-memory checkpointing: each vector in NVM alternates between a persistent version for crash recovery and a runtime version for training updates. (3) It employs fine-grained parallelism to hide the checkpointing overhead of model parameters in DRAM and GPU. Our experiments demonstrate that NVrec improves recommendation-model training throughput by 1.05 × -6.85 × and the checkpointing process by more than 5 × compared to existing models when evaluated on the synthetic and real-world datasets.
- 9 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computers
- Vol. 74 (8) , 2649-2662
ImPACT: Importance-Informed Prefetching and Caching for I/O-Bound DNN Training
Fetching large amounts of DNN training data from storage systems causes high I/O latency and GPU stalls. Importance sampling can reduce data processing on GPUs while maintaining model accuracy, but current frameworks lack a prefetching and caching layer to optimize data fetches and cache management based on sample importance. This leads to unnecessary fetches, poor cache hit ratios, and random I/Os. We present ImPACT, an importance-informed prefetching and caching system, to accelerate I/O-bound DNN training. First, we propose an importance-informed prefetching technique to reduce the prefetching of unimportant data. Then, we introduce an importance-aware caching layer, partitioned into two regions: H-cache and L-cache, which store samples of high importance and low importance respectively. Rather than using recency or frequency, we manage data items in H-cache according to their corresponding sample importance. When there is a cache miss in L-cache, we use sample substitutability and dynamic packaging to improve the cache hit ratio and reduce the number of random I/Os. Our experimental results show that ImPACT has a negligible impact on training accuracy while speeding up DNN training by up to 3.5$ \times $ compared to state-of-the-art prefetching and caching systems.- 9 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computers
- Vol. 74 (8) , 2649-2662
ImPACT: Importance-Informed Prefetching and Caching for I/O-Bound DNN Training
Fetching large amounts of DNN training data from storage systems causes high I/O latency and GPU stalls. Importance sampling can reduce data processing on GPUs while maintaining model accuracy, but current frameworks lack a prefetching and caching layer to optimize data fetches and cache management based on sample importance. This leads to unnecessary fetches, poor cache hit ratios, and random I/Os. We present ImPACT, an importance-informed prefetching and caching system, to accelerate I/O-bound DNN training. First, we propose an importance-informed prefetching technique to reduce the prefetching of unimportant data. Then, we introduce an importance-aware caching layer, partitioned into two regions: H-cache and L-cache, which store samples of high importance and low importance respectively. Rather than using recency or frequency, we manage data items in H-cache according to their corresponding sample importance. When there is a cache miss in L-cache, we use sample substitutability and dynamic packaging to improve the cache hit ratio and reduce the number of random I/Os. Our experimental results show that ImPACT has a negligible impact on training accuracy while speeding up DNN training by up to 3.5$ \times $ compared to state-of-the-art prefetching and caching systems.- Open Access
- 12 August 2024
- Published by Association for Computing Machinery (ACM)
- p. 1052-1061
AUTOHET: An Automated Heterogeneous ReRAM-Based Accelerator for DNN Inference
ReRAM-based accelerators have become prevalent in accelerating deep neural network inference owing to their in-situ computing capability of ReRAM crossbars. However, most existing ReRAM-based accelerators are designed with homogeneous crossbars, leading to either low resource utilization or sub-optimal energy efficiency. In this paper, we propose AutoHet, an automated heterogeneous ReRAM-based accelerator with varied-size crossbars for different DNN layers. To achieve both high crossbar utilization and energy efficiency, AutoHet uses a reinforcement learning algorithm to automatically determine the proper crossbar configuration for each DNN layer. Additionally, AutoHet introduces rectangle crossbars and a tile-shared crossbar allocation scheme to reduce crossbar wastage and energy consumption. Experiment results show that AutoHet effectively improves crossbar utilization by up to 3.1 × and reduces energy consumption by up to 94.6%, compared to approaches with homogeneous ReRAM crossbars.
- 12 August 2024
- Published by Association for Computing Machinery (ACM)
- p. 1052-1061
Open AccessAUTOHET: An Automated Heterogeneous ReRAM-Based Accelerator for DNN Inference
ReRAM-based accelerators have become prevalent in accelerating deep neural network inference owing to their in-situ computing capability of ReRAM crossbars. However, most existing ReRAM-based accelerators are designed with homogeneous crossbars, leading to either low resource utilization or sub-optimal energy efficiency. In this paper, we propose AutoHet, an automated heterogeneous ReRAM-based accelerator with varied-size crossbars for different DNN layers. To achieve both high crossbar utilization and energy efficiency, AutoHet uses a reinforcement learning algorithm to automatically determine the proper crossbar configuration for each DNN layer. Additionally, AutoHet introduces rectangle crossbars and a tile-shared crossbar allocation scheme to reduce crossbar wastage and energy consumption. Experiment results show that AutoHet effectively improves crossbar utilization by up to 3.1 × and reduces energy consumption by up to 94.6%, compared to approaches with homogeneous ReRAM crossbars.
- 1 December 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Parallel and Distributed Systems
- Vol. 33 (12) , 4484-4498
Accelerating Tensor Swapping in GPUs With Self-Tuning Compression
Data swapping between CPUs and GPUs is widely used to address the GPU memory shortage issue when training deep neural networks (DNNs) requiring a larger amount of memory than that a GPU may have. Data swapping may become a bottleneck when its latency is longer than the latency of DNN computations. Tensor compression in GPUs can reduce the data swapping time. However, existing works on compressing tensors in the virtual memory of GPUs have three major issues: lack of portability because its implementation requires additional (de)compression units in memory controllers, sub-optimal compression performance for varying tensor compression ratios and sizes, and poor adaptation to dense tensors because they only focus on sparse tensors. We propose a self-tuning tensor compression framework, named CSwap+ , for improving the virtual memory management of GPUs. It uses GPUs for (de)compression directly and thus has high portability and is minimally dependent on GPU architecture features. Furthermore, it only applies compression on tensors that are deemed to be cost-effective considering their compression ratio, size, and the characteristics of compression algorithms at runtime. Finally, to adapt to DNN models with dense tensors, it also supports cost-effective lossy compression for dense tensors with nearly no model training accuracy degradation. We conduct the experiments through six representative memory-intensive DNN models. Compared to vDNN, CSwap+ reduces tensor swapping latency by up to 50.9% and 46.1% with NVIDIA V100 GPU, for DNN models with sparse and dense tensors, respectively.
- 1 December 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Parallel and Distributed Systems
- Vol. 33 (12) , 4484-4498
Accelerating Tensor Swapping in GPUs With Self-Tuning Compression
Data swapping between CPUs and GPUs is widely used to address the GPU memory shortage issue when training deep neural networks (DNNs) requiring a larger amount of memory than that a GPU may have. Data swapping may become a bottleneck when its latency is longer than the latency of DNN computations. Tensor compression in GPUs can reduce the data swapping time. However, existing works on compressing tensors in the virtual memory of GPUs have three major issues: lack of portability because its implementation requires additional (de)compression units in memory controllers, sub-optimal compression performance for varying tensor compression ratios and sizes, and poor adaptation to dense tensors because they only focus on sparse tensors. We propose a self-tuning tensor compression framework, named CSwap+ , for improving the virtual memory management of GPUs. It uses GPUs for (de)compression directly and thus has high portability and is minimally dependent on GPU architecture features. Furthermore, it only applies compression on tensors that are deemed to be cost-effective considering their compression ratio, size, and the characteristics of compression algorithms at runtime. Finally, to adapt to DNN models with dense tensors, it also supports cost-effective lossy compression for dense tensors with nearly no model training accuracy degradation. We conduct the experiments through six representative memory-intensive DNN models. Compared to vDNN, CSwap+ reduces tensor swapping latency by up to 50.9% and 46.1% with NVIDIA V100 GPU, for DNN models with sparse and dense tensors, respectively.
- 9 June 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computers
- Vol. PP (00189340) , 1-13
HOME: A Holistic GPU Memory Management Framework for Deep Learning
We propose HOlistic MEmory management (HOME), a new framework for performing tensor placements in large DNN training when GPU memory space is not enough. HOME combines tensor swapping with tensor recomputation to reduce GPU memory footprint. Different from existing work that only considers partial DNN model information, HOME takes the holistic DNN model information into account in tensor placement decisions. More specifically, HOME uses a custom-designed particle swarm optimization algorithm to achieve the globally optimized placement for each tensor of the DNN model with a greatly reduced searching space. This holistic awareness of the whole model information enables HOME to obtain high performance under the given GPU memory constraint. We implement HOME in PyTorch and conduct our experiments using six popular DNN models. Experimental results show that HOME can outperform vDNN and Capuchin by up to 5.7× and 1.3× in throughput. Furthermore, HOME can improve the maximum batch size by up to 2.8× than the original PyTorch and up to 1.3× than Capuchin.
- 9 June 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computers
- Vol. PP (00189340) , 1-13
HOME: A Holistic GPU Memory Management Framework for Deep Learning
We propose HOlistic MEmory management (HOME), a new framework for performing tensor placements in large DNN training when GPU memory space is not enough. HOME combines tensor swapping with tensor recomputation to reduce GPU memory footprint. Different from existing work that only considers partial DNN model information, HOME takes the holistic DNN model information into account in tensor placement decisions. More specifically, HOME uses a custom-designed particle swarm optimization algorithm to achieve the globally optimized placement for each tensor of the DNN model with a greatly reduced searching space. This holistic awareness of the whole model information enables HOME to obtain high performance under the given GPU memory constraint. We implement HOME in PyTorch and conduct our experiments using six popular DNN models. Experimental results show that HOME can outperform vDNN and Capuchin by up to 5.7× and 1.3× in throughput. Furthermore, HOME can improve the maximum batch size by up to 2.8× than the original PyTorch and up to 1.3× than Capuchin.
- 27 September 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 191-195
SQL Injection Teaching Based on SQLi-labs
SQL injection attack is one of the most common methods of hacker attack, which is very harmful. In the course of information system security in our school, SQL injection attack and prevention is one of the most important and difficult contents in teaching. SQLi-labs is a teaching assistant software with various SQL injection vulnerabilities. With the help of this software, teacher can carry out SQL injection attacks in class, which help students better master the principle of SQL injection attack and prevention. This paper takes Union SQL injection as an example to introduce the teaching implementation process based on SQLi-labs. Teaching practice shows that this teaching mode increases the interest of students' learning and achieves good learning effect.
- 27 September 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 191-195
SQL Injection Teaching Based on SQLi-labs
SQL injection attack is one of the most common methods of hacker attack, which is very harmful. In the course of information system security in our school, SQL injection attack and prevention is one of the most important and difficult contents in teaching. SQLi-labs is a teaching assistant software with various SQL injection vulnerabilities. With the help of this software, teacher can carry out SQL injection attacks in class, which help students better master the principle of SQL injection attack and prevention. This paper takes Union SQL injection as an example to introduce the teaching implementation process based on SQLi-labs. Teaching practice shows that this teaching mode increases the interest of students' learning and achieves good learning effect.
- Open Access
- 1 October 2017
- Published by Wolters Kluwer Health in Medicine
- Vol. 96 (42) , e8246
Complete transmural migration of a retained surgical sponge
Intraluminal migration of a retained surgical sponge causing intestinal obstruction and fistula is extremely rare occurrence. A case of a 35-year-old male, who complaining a diffuse abdominal pain beginning three days earlier. He also complained of occasional vomiting, nonspecific abdominal pain, and an unintentional 15 kg weight loss during the past 2 years. However, there were no clear findings in previous laboratory work. He had received an open appendectomy approximately 4 years earlier. Retained surgical sponge. A contrast-enhanced CT of the abdomen showed a clear invagination of the small intestine. However, intraoperatively, we could not find an intestinal segment with intussusception. After the adhesive intestine was detached, a jejunal−ileal cross-linked fistula was found. More surprisingly, a retained surgical sponge was found inside the ileal fistula when the cross-linked fistula was detached. The patient was discharged 7 days after surgery. This is the first report showing an atypical image of a complete transmural migration of a retained surgical sponge mimicking intussusception.
- 1 October 2017
- Published by Wolters Kluwer Health in Medicine
- Vol. 96 (42) , e8246
Open AccessComplete transmural migration of a retained surgical sponge
Intraluminal migration of a retained surgical sponge causing intestinal obstruction and fistula is extremely rare occurrence. A case of a 35-year-old male, who complaining a diffuse abdominal pain beginning three days earlier. He also complained of occasional vomiting, nonspecific abdominal pain, and an unintentional 15 kg weight loss during the past 2 years. However, there were no clear findings in previous laboratory work. He had received an open appendectomy approximately 4 years earlier. Retained surgical sponge. A contrast-enhanced CT of the abdomen showed a clear invagination of the small intestine. However, intraoperatively, we could not find an intestinal segment with intussusception. After the adhesive intestine was detached, a jejunal−ileal cross-linked fistula was found. More surprisingly, a retained surgical sponge was found inside the ileal fistula when the cross-linked fistula was detached. The patient was discharged 7 days after surgery. This is the first report showing an atypical image of a complete transmural migration of a retained surgical sponge mimicking intussusception.