C2C-Explorer: An Exploration Framework for Chip-to-Chip Interconnect Architectures in LLM Cloud Computing Systems
By Jiayi Li 1,2,3,4, Di Wu 3,4, Qingxu Li 5, Hongxiao Zhao 1,2, Jiaqi Yang 1,2, Anjunyi Fan 1,2, Wenbin Zhang 3,4, Boqiang Wu 3,4, Shuting Liu 3,4, Shifeng Fang 3,4, Jianbo Dong 5, Dimin Niu 3,4 and Bonan Yan 1,2,5
1 Institute for Artificial Intelligence, Peking University, Beijing, China;
2 Beijing Advanced Innovation Center for Integrated Circuits, School of Integrated Circuits, Peking University, Beijing, China;
3 Hupan Lab, Hangzhou, China;
4 Damo Academy, Alibaba Group, Hangzhou, China;
5 Alibaba Cloud, Alibaba Group, Beijing, China
Abstract
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× 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.
Keywords: chip-to-chip communication, supernode, scale out, LLM simulator, scale up, large language model, cloud computing system
To read the full article, click here
Related Chiplet
- Integrated voltage regulator (IVR) chiplet
- High-performance connectivity chiplets
- eFPGA Chiplet
- DPIQ Tx PICs
- IMDD Tx PICs
Related Technical Papers
- 3D Electronic-Photonic Heterogenous Interconnect Platforms Enabling Energy-Efficient Scalable Architectures For Future HPC Systems
- PICNIC: Silicon Photonic Interconnected Chiplets with Computational Network and In-memory Computing for LLM Inference Acceleration
- FoldedHexaTorus: An Inter-Chiplet Interconnect Topology for Chiplet-based Systems using Organic and Glass Substrates
- CHICO-Agent: An LLM Agent for the Cross-layer Optimization of 2.5D and 3D Chiplet-based Systems
Latest Technical Papers
- C2C-Explorer: An Exploration Framework for Chip-to-Chip Interconnect Architectures in LLM Cloud Computing Systems
- ReVolt: Power Delivery Network-Aware Voltage Droop Control for 2.5D PIM Chiplet Architectures
- Innovative FA hardware solution to enable system-level debug of 3D ICs
- Hardware Design and Security in the Era of Chiplets and LLMs
- DICE: Detailed Inter-Chiplet End-to-End PHY Modeling for Accurate Chiplet Simulation