Network Design for Wafer-Scale Systems with Wafer-on-Wafer Hybrid Bonding
By Patrick Iff, Tommaso Bonato, Maciej Besta, Luca Benini, Torsten Hoefler
ETH Zurich
Abstract
Transformer-based large language models are increasingly constrained by data movement as communication bandwidth drops sharply beyond the chip boundary. Wafer-scale integration using wafer-on-wafer hybrid bonding alleviates this limitation by providing ultra-high bandwidth between reticles on bonded wafers. In this paper, we investigate how the physical placement of reticles on wafers influences the achievable network topology and the resulting communication performance. Starting from a 2D mesh-like baseline, we propose four reticle placements (Aligned, Interleaved, Rotated, and Contoured) that improve throughput by up to 250%, reduce latency by up to 36%, and decrease energy per transmitted byte by up to 38%.
To read the full article, click here
Related Chiplet
- DPIQ Tx PICs
- IMDD Tx PICs
- Near-Packaged Optics (NPO) Chiplet Solution
- High Performance Droplet
- Interconnect Chiplet
Related Technical Papers
- Revamping the Semiconductor Industry with Hybrid Bonding
- Co-Optimization of Power Delivery Network Design for 3-D Heterogeneous Integration of RRAM-Based Compute In-Memory Accelerators
- Hybrid Bonding With Polymeric Interlayer Dielectric Layers Patterned by Nanoimprint Lithography
- PICNIC: Silicon Photonic Interconnected Chiplets with Computational Network and In-memory Computing for LLM Inference Acceleration
Latest Technical Papers
- CHICO-Agent: An LLM Agent for the Cross-layer Optimization of 2.5D and 3D Chiplet-based Systems
- A PPA-Driven 3D-IC Partitioning Selection Framework with Surrogate Models
- Fleet: Hierarchical Task-based Abstraction for Megakernels on Multi-Die GPUs
- ChipLight: Cross-Layer Optimization of Chiplet Design with Optical Interconnects for LLM Training
- ELMoE-3D: Leveraging Intrinsic Elasticity of MoE for Hybrid-Bonding-Enabled Self-Speculative Decoding in On-Premises Serving