Xiaoyang Lu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Xiaoyang Lu has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Xian-He Sun
Illinois Institute of Technology
6 shared publications - Xiaoming Chen
Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China
5 shared publications - Yinhe Han
Chinese Academy of Sciences
5 shared publications - Boyu Long
Institute of Computing Technology, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China
2 shared publications - Liang Yan
Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China
2 shared publications - Dazhao Cheng
Wuhan University, Wuhan, China
1 shared publication
Latest Publications
- Open Access
- 22 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 962-977
I/O Analysis is All You Need: An I/O Analysis for Long-Sequence Attention
- 22 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 962-977
Open AccessI/O Analysis is All You Need: An I/O Analysis for Long-Sequence Attention
- Open Access
- 17 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 1073-1086
COSMOS: RL-Enhanced Locality-Aware Counter Cache Optimization for Secure Memory
- 17 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 1073-1086
Open AccessCOSMOS: RL-Enhanced Locality-Aware Counter Cache Optimization for Secure Memory
- Open Access
- 29 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 278-283
Concurrency-Aware Cache Miss Cost Prediction with Perceptron Learning
- 29 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 278-283
Open AccessConcurrency-Aware Cache Miss Cost Prediction with Perceptron Learning
- 14 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
- Vol. 44 (12) , 4577-4590
ProMiner: Enhancing Locality, Parallelism, and Offloading for Graph Mining on Processing-in-Memory Systems
Graph mining, critical for discovering specific patterns within complex structures, is becoming increasingly important in our data-driven world. Due to their memory-bound nature, graph mining applications encounter significant limitations with conventional processor-centric systems, like central processing units (CPUs) and graphics processing units (GPUs), stemming from the costly data movement between memory and processing units. Memory-centric computing systems, such as processing-in-memory (PIM) where computation occurs directly within or near memory modules, have the potential to accelerate graph mining. However, accelerating graph mining applications with PIM presents three primary challenges: 1) the difficulty in utilizing locality; 2) the challenge of exploring parallelism; and 3) the complexity of workload offloading between PIM and CPU. Addressing these intricate challenges, we introduce ProMiner, a novel framework that integrates three key techniques through cohesive software and hardware co-design. First, we propose a partitioning method tailored for graph mining to enhance data locality. Second, we design a coarse-fine parallelism optimization scheme to explore parallelism across different levels of memory. Third, we introduce a concurrency-aware mechanism for performance estimation, aimed at identifying the optimal computing engine for workload offloading to maximize performance. Our experimental results demonstrate that ProMiner significantly advances the state-of-the-art in graph mining, achieving 48.8% and 29.9% execution time reduction over NDMiner and DIM- Mining, respectively.
- 14 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
- Vol. 44 (12) , 4577-4590
ProMiner: Enhancing Locality, Parallelism, and Offloading for Graph Mining on Processing-in-Memory Systems
Graph mining, critical for discovering specific patterns within complex structures, is becoming increasingly important in our data-driven world. Due to their memory-bound nature, graph mining applications encounter significant limitations with conventional processor-centric systems, like central processing units (CPUs) and graphics processing units (GPUs), stemming from the costly data movement between memory and processing units. Memory-centric computing systems, such as processing-in-memory (PIM) where computation occurs directly within or near memory modules, have the potential to accelerate graph mining. However, accelerating graph mining applications with PIM presents three primary challenges: 1) the difficulty in utilizing locality; 2) the challenge of exploring parallelism; and 3) the complexity of workload offloading between PIM and CPU. Addressing these intricate challenges, we introduce ProMiner, a novel framework that integrates three key techniques through cohesive software and hardware co-design. First, we propose a partitioning method tailored for graph mining to enhance data locality. Second, we design a coarse-fine parallelism optimization scheme to explore parallelism across different levels of memory. Third, we introduce a concurrency-aware mechanism for performance estimation, aimed at identifying the optimal computing engine for workload offloading to maximize performance. Our experimental results demonstrate that ProMiner significantly advances the state-of-the-art in graph mining, achieving 48.8% and 29.9% execution time reduction over NDMiner and DIM- Mining, respectively.
- 10 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Computer Architecture Letters
- Vol. 24 (1) , 121-124
Pyramid: Accelerating LLM Inference With Cross-Level Processing-in-Memory
Integrating processing-in-memory (PIM) with GPUs accelerates large language model (LLM) inference, but existing GPU-PIM systems encounter several challenges. While GPUs excel in large general matrix-matrix multiplications (GEMM), they struggle with small-scale operations better suited for PIM, which currently cannot handle them independently. Additionally, the computational demands of activation operations exceed the capabilities of current PIM technologies, leading to excessive data movement between the GPU and memory. PIM's potential for general matrix-vector multiplications (GEMV) is also limited by insufficient support for fine-grained parallelism. To address these issues, we propose Pyramid, a novel GPU-PIM system that optimizes PIM for LLM inference by strategically allocating cross-level computational resources within PIM to meet diverse needs and leveraging the strengths of both technologies. Evaluation results demonstrate that Pyramid outperforms existing systems like NeuPIM, AiM, and AttAcc by factors of 2.31×, 1.91×, and 1.72×, respectively.
- 10 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Computer Architecture Letters
- Vol. 24 (1) , 121-124
Pyramid: Accelerating LLM Inference With Cross-Level Processing-in-Memory
Integrating processing-in-memory (PIM) with GPUs accelerates large language model (LLM) inference, but existing GPU-PIM systems encounter several challenges. While GPUs excel in large general matrix-matrix multiplications (GEMM), they struggle with small-scale operations better suited for PIM, which currently cannot handle them independently. Additionally, the computational demands of activation operations exceed the capabilities of current PIM technologies, leading to excessive data movement between the GPU and memory. PIM's potential for general matrix-vector multiplications (GEMV) is also limited by insufficient support for fine-grained parallelism. To address these issues, we propose Pyramid, a novel GPU-PIM system that optimizes PIM for LLM inference by strategically allocating cross-level computational resources within PIM to meet diverse needs and leveraging the strengths of both technologies. Evaluation results demonstrate that Pyramid outperforms existing systems like NeuPIM, AiM, and AttAcc by factors of 2.31×, 1.91×, and 1.72×, respectively.
- Open Access
- 27 April 2024
- Published by Association for Computing Machinery (ACM)
- p. 71-85
ACES: Accelerating Sparse Matrix Multiplication with Adaptive Execution Flow and Concurrency-Aware Cache Optimizations
Sparse matrix-matrix multiplication (SpMM) is a critical computational kernel in numerous scientific and machine learning applications. SpMM involves massive irregular memory accesses and poses great challenges to conventional cache-based computer architectures. Recently dedicated SpMM accelerators have been proposed to enhance SpMM performance. However, current SpMM accelerators still face challenges in adapting to varied sparse patterns, fully exploiting inherent parallelism, and optimizing cache performance. To address these issues, we introduce ACES, a novel SpMM accelerator in this study. First, ACES features an adaptive execution flow that dynamically adjusts to diverse sparse patterns. The adaptive execution flow balances parallel computing efficiency and data reuse. Second, ACES incorporates locality-concurrency co-optimizations within the global cache. ACES utilizes a concurrency-aware cache management policy, which considers data locality and concurrency for optimal replacement decisions. Additionally, the integration of a non-blocking buffer with the global cache enhances concurrency and reduces computational stalls. Third, the hardware architecture of ACES is designed to integrate all innovations. The architecture ensures efficient support across the adaptive execution flow, advanced cache optimizations, and fine-grained parallel processing. Our performance evaluation demonstrates that ACES significantly outperforms existing solutions, providing a 2.1× speedup and marking a substantial advancement in SpMM acceleration.
- 27 April 2024
- Published by Association for Computing Machinery (ACM)
- p. 71-85
Open AccessACES: Accelerating Sparse Matrix Multiplication with Adaptive Execution Flow and Concurrency-Aware Cache Optimizations
Sparse matrix-matrix multiplication (SpMM) is a critical computational kernel in numerous scientific and machine learning applications. SpMM involves massive irregular memory accesses and poses great challenges to conventional cache-based computer architectures. Recently dedicated SpMM accelerators have been proposed to enhance SpMM performance. However, current SpMM accelerators still face challenges in adapting to varied sparse patterns, fully exploiting inherent parallelism, and optimizing cache performance. To address these issues, we introduce ACES, a novel SpMM accelerator in this study. First, ACES features an adaptive execution flow that dynamically adjusts to diverse sparse patterns. The adaptive execution flow balances parallel computing efficiency and data reuse. Second, ACES incorporates locality-concurrency co-optimizations within the global cache. ACES utilizes a concurrency-aware cache management policy, which considers data locality and concurrency for optimal replacement decisions. Additionally, the integration of a non-blocking buffer with the global cache enhances concurrency and reduces computational stalls. Third, the hardware architecture of ACES is designed to integrate all innovations. The architecture ensures efficient support across the adaptive execution flow, advanced cache optimizations, and fine-grained parallel processing. Our performance evaluation demonstrates that ACES significantly outperforms existing solutions, providing a 2.1× speedup and marking a substantial advancement in SpMM acceleration.
- Open Access
- 21 June 2023
- Published by Association for Computing Machinery (ACM)
- p. 54-55
DeepSim: A Transformer Based Model For Fast Simulation And Exploring Computer System Design Space
- 21 June 2023
- Published by Association for Computing Machinery (ACM)
- p. 54-55
Open AccessDeepSim: A Transformer Based Model For Fast Simulation And Exploring Computer System Design Space