C2C-Explorer: An Exploration Framework for Chip-to-Chip Interconnect Architectures in LLM Cloud Computing Systems
This work addresses the challenge of efficiently designing chip-to-chip interconnect hardware for LLM cloud computing systems, which is crucial for scaling up LLMs.
The paper introduces C2C-Explorer, a framework designed to optimize chip-to-chip interconnect architectures for large language model (LLM) cloud computing systems. It integrates a traffic generator, a scalable interconnect simulator, and an evaluator to explore design spaces, achieving a 44.1% improvement in goodput and a 98.4% reduction in memory for a 32-XPU DeepSeek-R1-671B inference workload.
The scaling-up of large language models (LLMs) necessitates computing systems to have multi-processor-chip architectures, elevating the importance of chip-to-chip (C2C) communication. However, designing efficient C2C hardware architectures for LLM workloads faces three key challenges: generating realistic LLM-specific C2C traffic, accurately simulating hardware-level communication at scale, and efficiently exploring the exponentially large C2C design space. We propose C2C-Explorer, an adaptive Bayesian DSE framework that integrates a LLM-workload-driven traffic generator, a scalable interconnect simulator (switch/full-mesh, up to 512 chips), and a metric-guided evaluator into a workload-to-hardware optimization pipeline, enabling systematic C2C architectural co-design under realistic LLM workloads. Validated against FPGA-based C2C prototypes, the C2C simulator achieves 2.46-8.23% end-to-end timing error across diverse traffic patterns. Its hybrid cycle and event model further accelerates large-scale simulation by up to 7.8$\times$ over a pure cycle-accurate baseline. Applied to a 32-XPU DeepSeek-R1-671B inference workload, C2C-Explorer identifies configurations that improve goodput by 44.1% and reduce memory by 98.4%. C2C-Explorer is open-source and available at https://github.com/Selinaee/C2C-Explorer.