Taking 3D IC Heterogeneous Integration Mainstream
By Tony Mastroianni and Todd Burkholder, Siemens Digital Industries Software
3DIncCtes | March 26, 2025
Over the last several years, chiplet-based heterogeneous package integration has emerged as a promising alternative to traditional monolithic package solutions; the so-called homogenous SoC design. 3D IC heterogeneous integration is a system approach, wherein what typically would be implemented as an SoC is disaggregated into solid, fabricated IP blocks; i.e., chiplets.
These chiplets typically provide a specific function implemented in an optimal chip process node. Several chiplets and an optional, custom SoC device can be mounted and interconnected in a single package using high-speed/bandwidth chiplet-to-chiplet interfaces. The resulting 3D IC heterogeneously integrated packages deliver greater performance at a reduced cost, higher yield, and have only a slightly larger area than a traditional monolithic SoC package.
This system-oriented approach, known as system technology co-optimization (STCO), differs from traditional IC design. STCO spans five significant activities that are both complex and sophisticated: architectural planning and analysis, functional design and test, physical design planning and verification, and electrical and reliability analysis.
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
- Co-Optimization of Power Delivery Network Design for 3-D Heterogeneous Integration of RRAM-Based Compute In-Memory Accelerators
- A3D-MoE: Acceleration of Large Language Models with Mixture of Experts via 3D Heterogeneous Integration
- Heterogeneous Integration - Chiplets
- Reliability challenges in 3D IC semiconductor design
Latest Technical Papers
- Scope: A Scalable Merged Pipeline Framework for Multi-Chip-Module NN Accelerators
- Scaling Routers with In-Package Optics and High-Bandwidth Memories
- TDPNavigator-Placer: Thermal- and Wirelength-Aware Chiplet Placement in 2.5D Systems Through Multi-Agent Reinforcement Learning
- Towards Scalable Multi-Chip Wireless Networks with Near-Field Time Reversal
- Hybrid surface pre-treatments for enhancing copper-to-copper direct bonding