Data Demands Drive Co-Packaged Silicon and Optics for Switch Fabrics
By Nitin Dahad, EETimes
March 12, 2020
When we talk about having billions of connected devices, that also means massive growth in data, as well as data centers with increased performance and network bandwidth to process that data. Modern data center switches rely on pluggable optics installed in the switch faceplate that are connected to switch serializer/deserializer (SerDes) ports using an electrical trace.
But as data center switch bandwidth grows to meet demand, connecting the SerDes to pluggable optics electrically will become more complex and require more power. This is likely to present bandwidth scalability challenges in terms of density, cost, and power; challenges that require tighter integration of optics and networking silicon.
To read the full article, click here
Related Semiconductor IP
- AXI to UCIe FDI Interface IP
- 45SPCLO UCIe-Class 1-32Gbps Low Power Receiver IP (NRZ)
- 45SPCLO UCIe-Class 1-32Gbps Low Power Transmitter IP (NRZ)
- Peripheral Sensor Interface (PSI5) Host Controller
- Link Acceleration Unit
Related News
- Analogue Insight Opens Early Customer Engagement for Low-Power 1–32 Gbps NRZ Transmitter and Receiver IP in GlobalFoundries 45SPCLO for Integrated Co-Packaged Optics
- Rambus Introduces PCIe® 7.0 Switch IP with Time Division Multiplexing for Scalable AI and Data Center Infrastructure
- Alchip Leverages AWS to Enable Cloud-Based Silicon Execution for AI and Data Center Platform
- Inova Semiconductors and StarIC Announce Initial Silicon Validation, Accelerating APXpress Ecosystem for Physical AI
Latest News
- ASICLAND Selected as SK hynix’s Partner for Next-Gen eSSD Development, Establishing a ‘K-Semiconductor Win-Win’ Model
- onsemi to Acquire Synaptics to Enable the Next Generation of Intelligent Systems for Physical AI
- EdgeAI Licensed Andes Technology CPU IP to Power Next-Generation Edge AI Neuromorphic Solution
- Jim Keller: ‘AI Still Obeys the Old Laws of Compute’
- OpenAI and Broadcom unveil LLM-optimized inference chip