5 papers
DGNNFlow: A Streaming Dataflow Architecture for Real-Time Edge-based Dynamic GNN Inference in HL-LHC Trigger Systems
Davendra Maharaj, Tu Pham, Peter Meiring +4
Dynamic GNN inference exhibits strong capability to model interactions over time, such as complex particle collision events in High Energy Physics (HEP) experiments at High Luminos…
Efficient Mixture-of-Agents Serving via Tree-Structured Routing, Adaptive Pruning, and Dependency-Aware Prefill-Decode Overlap
Zijun Wang, Yijiahao Qi, Hanqiu Chen +5
Mixture-of-Agents (MoA) inference can suffer from dense inter-agent communication and low hardware utilization, which jointly inflate serving latency. We present a serving design t…
ForgeBench: A Machine Learning Benchmark Suite and Auto-Generation Framework for Next-Generation HLS Tools
Andy Wanna, Hanqiu Chen, Cong Hao
Although High-Level Synthesis (HLS) has attracted considerable interest in hardware design, it has not yet become mainstream due to two primary challenges. First, current HLS hardw…
ICGMM: CXL-enabled Memory Expansion with Intelligent Caching Using Gaussian Mixture Model
Hanqiu Chen, Yitu Wang, Luis Vitorio Cargnini +7
Compute Express Link (CXL) emerges as a solution for wide gap between computational speed and data communication rates among host and multiple devices. It fosters a unified and coh…
Residual-INR: Communication Efficient On-Device Learning Using Implicit Neural Representation
Hanqiu Chen, Xuebin Yao, Pradeep Subedi +1
Edge computing is a distributed computing paradigm that collects and processes data at or near the source of data generation. The on-device learning at edge relies on device-to-dev…