Y
Yuan Xie
Researcher at University of California, Santa Barbara
Publications - 794
Citations - 32484
Yuan Xie is an academic researcher from University of California, Santa Barbara. The author has contributed to research in topics: Computer science & Cache. The author has an hindex of 76, co-authored 739 publications receiving 24155 citations. Previous affiliations of Yuan Xie include Pennsylvania State University & Foundation University, Islamabad.
Papers
More filters
Proceedings ArticleDOI
NeuroMeter: An Integrated Power, Area, and Timing Modeling Framework for Machine Learning Accelerators Industry Track Paper
TL;DR: NeMeter as mentioned in this paper is an integrated power, area, and timing modeling framework for ML accelerators and enables the runtime analysis of system-level performance and efficiency when the runtime activity factors are provided.
Proceedings ArticleDOI
3D memory stacking for fast checkpointing/restore applications
Jing Xie,Xiangyu Dong,Yuan Xie +2 more
TL;DR: This work designs a 2-layer TSV-based SRAM/SRAM 3D-stacked chip to mimic the high-bandwidth and fast data transfer from one memory layer to another memory layer, so that the inmemory checkpointing/restartrestore scheme can be enabled for the future exascale computing.
Proceedings ArticleDOI
ILP-based scheme for timing variation-aware scheduling and resource binding
Yibo Chen,Jin Ouyang,Yuan Xie +2 more
TL;DR: This paper presents a 0-1 integer linear programming (ILP) formulation that aims at reducing the impact of timing variations in high-level synthesis, by integrating overall timing yield constraints into scheduling and resource binding.
Posted Content
Structurally Sparsified Backward Propagation for Faster Long Short-Term Memory Training.
TL;DR: It is observed that artificially inducing sparsity in the gradients of the gates in an LSTM cell has little impact on the training quality, and this performance gap can be eliminated by mixing the sparse training method and the standard dense training method.
Proceedings ArticleDOI
Leveraging nonvolatility for architecture design with emerging NVM
TL;DR: The potential benefit by leveraging nonvolatility for architecture design is pointed out and two case studies are described, which support persistency in NVM based main memory.