Shaoqiang Lu

Shaoqiang Lu

Auto-generated profile, based on publicly available information

Shaoqiang Lu

Shanghai Jiao Tong University, Shanghai, China and Eastern Institute of Technology, Ningbo, Zhejiang, China

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications

18 August 2025 in ACM Transactions on Reconfigurable Technology and Systems
Verified
Journal Article
Open access
SLShaoqiang Lu
Shaoqiang Lu
TZTiandong Zhao
Tiandong Zhao
TLTing-Jung Lin
Ting-Jung Lin
RZRumin Zhang
Rumin Zhang
CWChen Wu
Chen Wu
LHLei He
Lei He
Transformer-based models have achieved extensive success with increasingly large numbers of parameters and computations, for which many multi-core accelerators have been developed. Nevertheless, they suffer from limited throughput due to either low operating frequency or high communication overhead between cores. This article proposes an FPGA-based multi-core overlay processor, named MCoreOPU, to optimize intra-core computation and inter-core communication. First, we boost the operating frequency of the processing element (PE) array to double the rest of the processor to improve the intra-core throughput. Second, we develop on-chip synchronization routers to reduce off-chip memory traffic, where only the partial sum and maximum are communicated between cores rather than entire vectors for layer normalization and softmax. Moreover, we pipeline synchronization to reduce synchronization latency and develop a bypass of the interconnect bus to reduce the off-chip memory access latency. Finally, we optimize the multi-core model allocation and scheduling to minimize the inter-core communications and maximize the intra-core computation efficiency. The MCoreOPU is implemented in 8-bit fixed-point precision with four cores and four DDRs on the Xilinx U200 FPGA, where the PE array runs at 600 MHz while the rest runs at 300 MHz. Experimental results show that the throughput per MAC of MCoreOPU for BERT, ViT, GPT-2, and LLaMA inference is 1.31 \(\times\) –7.18 \(\times\) higher than other FPGA-based accelerators. Compared with the A100 GPU, the throughput per equivalent MAC efficiency is improved by 22.52 \(\times\) –27.12 \(\times\) .