3 papers
cs.AR2026
Accelerating MoE with Dynamic In-Switch Computing on Multi-GPUs
Qijun Zhang, Chen Zhang, Zhuoshan Zhou +10
Mixture-of-Experts (MoE) has been adopted by many leading large models to reduce computational requirements. However, frequent inter-GPU communication in MoE expert parallelism (EP…
cs.LG2025
DAPO: Design Structure-Aware Pass Ordering in High-Level Synthesis with Graph Contrastive and Reinforcement Learning
Jinming Ge, Linfeng Du, Likith Anaparty +8
High-Level Synthesis (HLS) tools are widely adopted in FPGA-based domain-specific accelerator design. However, existing tools rely on fixed optimization strategies inherited from s…
cs.LG2024
Accel-NASBench: Sustainable Benchmarking for Accelerator-Aware NAS
Afzal Ahmad, Linfeng Du, Zhiyao Xie +1
One of the primary challenges impeding the progress of Neural Architecture Search (NAS) is its extensive reliance on exorbitant computational resources. NAS benchmarks aim to simul…