collaborators

6 papers

cs.AR2026

From Characterization to Microarchitecture: Designing an Elegant and Reliable BFP-Based NPU

Jie Zhang, Jiapeng Guan, Hao Zhou +4

Block Floating-Point (BFP) is emerging as an attractive data format for edge Neural Processing Units (NPUs), combining wide dynamic range with high hardware efficiency. However, it…

cs.LG2026

NLI:Non-uniform Linear Interpolation Approximation of Nonlinear Operations for Efficient LLMs Inference

Jiangyong Yu, Xiaomeng Han, Xing Hu +3

Large Language Models (LLMs) have demonstrated remarkable performance across a wide range of tasks, but their deployment is often constrained by substantial memory footprints and c…

cs.AR2025

Re-thinking Memory-Bound Limitations in CGRAs

Xiangfeng Liu, Zhe Jiang, Anzhen Zhu +4

Coarse-Grained Reconfigurable Arrays (CGRAs) are specialized accelerators commonly employed to boost performance in workloads with iterative structures. Existing research typically…

cs.AR2025

BBAL: A Bidirectional Block Floating Point-Based Quantisation Accelerator for Large Language Models

Xiaomeng Han, Yuan Cheng, Jing Wang +6

Large language models (LLMs), with their billions of parameters, pose substantial challenges for deployment on edge devices, straining both memory capacity and computational resour…

cs.AR2025

NVR: Vector Runahead on NPUs for Sparse Memory Access

Hui Wang, Zhengpeng Zhao, Jing Wang +11

Deep Neural Networks are increasingly leveraging sparsity to reduce the scaling up of model parameter size. However, reducing wall-clock time through sparsity and pruning remains c…

cs.AR2025

Pushing the Limits of BFP on Narrow Precision LLM Inference

Hui Wang, Yuan Cheng, Xiaomeng Han +3

The substantial computational and memory demands of Large Language Models (LLMs) hinder their deployment. Block Floating Point (BFP) has proven effective in accelerating linear ope…