Emerging workloads, such as Multi-Agent Reinforcement Learning (MARL), large-scale neuromorphic computing, and probabilistic graphical models, intrinsically exhibit parallel-sequential computing patterns. While these tasks demand massive parallelism to achieve high throughput, they are severely bottlenecked by irregula...
Daijing Shi, Hongxiao Zhao, Yihan Fu et al.· 0 citations
DOPS (dynamic operator scheduling), a hardware-aware, closed-loop framework that jointly optimizes operator scheduling and blockwise weight layouts and supports systematic analysis of workload sensitivity and hardware scalability for LLM serving is presented.
Jiaqi Yang, Jia-Yi Li, Yihan Fu et al.· arXiv.org· 0 citations
C2C-Explorer is proposed, an adaptive Bayesian DSE framework that integrates a LLM-workload-driven traffic generator, a scalable interconnect simulator, and a metric-guided evaluator into a workload-to-hardware optimization pipeline, enabling systematic C2C architectural co-design under realistic LLM workloads.
Jia-Yi Li, Di Wu, Qingxu Li et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.