​    

Cheng Li

cli99@illinois.edu

Coordinated Science Laboratory
1308 W. Main Street
Urbana, IL 61801


My Projects:

 

My Publications:

"Across-Stack Profiling and Characterization of Machine Learning Models on GPUs", Cheng Li, Abdul Dakkak, Jinjun Xiong, https://arxiv.org/abs/1908.06869. [more...]
 
"TrIMS: Transparent and Isolated Model Sharing for Low Latency Deep Learning Inference in Function-as-a-Service", Abdul Dakkak, Cheng Li, Simon Garcia de Gonzalo, Jinjun Xiong, Wen-mei Hwu, IEEE International Conference on Cloud Computing, July 8-13, 2019, Milan, Italy. [more...]
 
"Accelerating Reduction and Scan Using Tensor Core Units", Abdul Dakkak, Cheng Li, Jinjun Xiong, Wen-mei Hwu, ICS 2019: International Conference on Supercomputing, June 26-28, Phoenix AZ. [more...]
 
"Frustrated with Replicating Claims of a Shared Model? A Solution", Abdul Dakkak, Cheng Li, Jinjun Xiong, https://arxiv.org/abs/1811.09737. [more...]
 
"Benchmarking and Understanding ML Inference", Cheng Li, Abdul Dakkak, Jinjun Xiong, Wen-mei Hwu, https://arxiv.org/abs/1904.12437. [more...]
 
"Evaluating Characteristics of CUDA Communication Primitives on High-Bandwidth Interconnects", Carl Pearson, Abdul Dakkak, Cheng Li, Jinjun Xiong, Wen-mei Hwu, Pearson, Carl, et al. "Evaluating Characteristics of CUDA Communication Primitives on High-Bandwidth Interconnects." Proceedings of the 10th ACM/SPEC International Conference on Performance Engineering. ACM, 2019.. (ICPE Best Paper Award) [more...]
 
"TrIMS: Transparent and Isolated Model Sharing for LowLatency Deep Learning Inference in Function as aService Environments", Abdul Dakkak, Cheng Li, Simon Garcia de Gonzalo, Jinjun Xiong, Wen-mei Hwu, Systems for ML at NIPS 2018. [more...]
 
"Accelerating Reduction and Scan Using Tensor Core Units", Abdul Dakkak, Cheng Li, Jinjun Xiong, Wen-mei Hwu, CoRR, abs/1811.09736.. [more...]
 
"MLModelScope: Evaluate and Measure ML Models within AI Pipelines", Abdul Dakkak, Cheng Li, arXiv preprint arXiv:1811.09737 (2018).. [more...]
 
"RAI: A Scalable Project Submission System for Parallel Programming Courses", Abdul Dakkak, Carl Pearson, Cheng Li, Parallel and Distributed Processing Symposium Workshops, 2017 IEEE International.. [more...]
 
"KLAP: Kernel Launch Aggregation and Promotion for Optimizing Dynamic Parallelism", Izzat El Hajj, Juan Gómez-Luna, Cheng Li, Li-Wen Chang, Dejan Milojicic, Wen-mei Hwu, Proceedings of the 49th Annual IEEE/ACM International Symposium on Microarchitecture, 2016. [more...]