Publications

[1]. Alen Sabu, Harish Patil, Wim Heirman, Liu Changxi, Trevor E. Carlson. XPU-Point: Simulator-Agnostic Sample Selection Methodology for Heterogeneous CPU-GPU Applications. in International Conference on Parallel Architectures and Compilation Techniques (PACT 2025).

[2]. Liu Changxi, Yu Miao, Sun Yifan, Trevor E. Carlson. The Sparsity-Aware LazyGPU Architecture in International Symposium on Computer Architecture (ISCA 2025).

[3]. Liu Changxi, Sun Yifan, Trevor E. Carlson. Photon: A Fine-grained Sampled Simulation Methodology for GPU Workloads in International Symposium on Microarchitecture (MICRO 2023).

[4]. You Xin*, Liu Changxi*, Yang Hailong, Wang Pengbo, Luan Zhongzhi, and Qian Depei Vectorizing SpMV by Exploiting Dynamic Regular Patterns. in International Conference on Parallel Processing (ICPP 2022).

[5]. Liu Changxi, Xie Biwei, Liu Xin, Xue Wei, Yang Hailong, and Liu Xu. Towards efficient spmv on sunway manycore architectures in International Conference on Supercomputing (ICS 2018).

[1]. Alen Sabu, Qiu Zhantong, Patil Harish, Liu Changxi, Heirman Wim, Jason Lowe-Power, Trevor E. Carlson. Accelerating the Simulation of Parallel Workloads using Loop-Bounded Checkpoints. in ACM Transactions on Architecture and Code Optimization (TACO 2026).

[2]. Liu Changxi*, Alen Sabu*, Akanksha Chaudhari, Qingxuan Kang, Trevor E. Carlson. Pac-Sim: Simulation of Multi-threaded Workloads using Intelligent, Live Sampling in ACM Transactions on Architecture and Code Optimization (TACO 2024).

[3]. Li Mingzhen*, Liu Changxi*, Liao Jianjin, Zheng Xuegui, Yang Hailong, Sun Rujun, Xu Jun, Gan Lin, Yang Guangwen, Luan Zhongzhi, Qian Depei. Towards optimized tensor code generation for deep learning on sunway many-core processor in Frontiers of Computer Science (FCS 2024).

[4]. Liu Changxi, Yang Hailong, Wang Rui, Luan Zhongzhi, and Qian Depei. T1000: Mitigating the memory footprint of convolution neural networks with decomposition and re-fusion in Future Generation Computer Systems (FGCS 2018).