Advanced Packaging and Chiplets Can Be for Everyone
By Boris Chau, Project Leader, Faraday Technology Corporation
EETimes (November 29, 2024)
The chiplet revolution is upon us. What began in laboratories as multi-die science projects has eventually evolved. A giant company like AMD, Intel or Nvidia can produce—either at TSMC or, in Intel’s case, internally—a giant, startlingly expensive CPU or GPU multi-die assembly using advanced packaging to achieve remarkable density, power efficiency and performance.
However, the real promise of chiplets is something different: to democratize the design of complex silicon systems so that even systems developers and small-fabless semiconductor companies could develop them.
Today, there are both promising signs and notable obstacles to this vision. But I believe it is already possible for a modest design team to achieve a chiplet-based design today. However, that requires a good understanding of the variables involved and how to manage these in delivering the final design. Very likely today, this will involve using an external partner with that expertise.
This advance cannot come too soon. As the package becomes a critical factor in system performance, integrating multiple semiconductor dies—often designed and manufactured by different companies—within the same package will be essential.
Related Chiplet
- Direct Chiplet Interface
- HBM3e Advanced-packaging chiplet for all workloads
- UCIe AP based 8-bit 170-Gsps Chiplet Transceiver
- UCIe based 8-bit 48-Gsps Transceiver
- UCIe based 12-bit 12-Gsps Transceiver
Related Technical Papers
- High-Bandwidth Chiplet Interconnects for Advanced Packaging Technologies in AI/ML Applications: Challenges and Solutions
- Workflows for tackling heterogeneous integration of chiplets for 2.5D/3D semiconductor packaging
- Intel Delivers Cutting-Edge Process Technologies to the Data Center with Intel 18A and Advanced Chiplet Packaging
- Challenges and Opportunities to Enable Large-Scale Computing via Heterogeneous Chiplets
Latest Technical Papers
- Performance Implications of Multi-Chiplet Neural Processing Units on Autonomous Driving Perception
- ChipAI: A scalable chiplet-based accelerator for efficient DNN inference using silicon photonics
- Advanced Packaging and Chiplets Can Be for Everyone
- Interfacing silicon photonics for high-density co-packaged optics
- System-Technology Co-Optimization for Dense Edge Architectures using 3D Integration and Non-Volatile Memory