Strategies for Addressing More Complex Custom Chip Design
By Abhishek Jadhav, EETimes | March 21, 2025
Unprecedented growth and demand for edge computing and high-performance computing (HPC) is creating new opportunities and significant challenges for custom chips. We spoke to Sondrel CEO Oliver Jones to discuss some of the approaches to addressing these needs.
Custom chip design is a multifaceted process involving many considerations, from power efficiency and performance trade-offs to manufacturing and packaging complexities. One of the primary challenges in this domain is managing power, performance and area (PPA) trade-offs.
Designers must carefully balance these factors to ensure that the final product meets the strict requirements of modern applications like AI at the edge or HPC workloads. Additionally, the process involves navigating geopolitical disruptions and supply chain constraints, which can delay production and increase costs.
To read the full article, click here
Related Semiconductor IP
- NPU IP Core for Mobile
- NPU IP Core for Edge
- Specialized Video Processing NPU IP
- HYPERBUS™ Memory Controller
- AV1 Video Encoder IP
Related News
- Cadence and TSMC Advance AI and 3D-IC Chip Design with Certified Design Solutions for TSMC’s A16 and N2P Process Technologies
- sureCore extends its sureFIT design service to include custom memory solutions for AI applications
- ICE-G3 EPU Adds Cluster Controller to Save More Energy For Complex Chip Power Architectures
- Imec pioneers unique, low-power UWB receiver chip: 10x more resilient against Wi-Fi and (beyond) 5G interference
Latest News
- Jim Keller: ‘Whatever Nvidia Does, We’ll Do The Opposite’
- FlexGen Streamlines NoC Design as AI Demands Grow
- IntoPIX Presents Its New Titanium Software Suite: Empowering AV-Over-IP Workflows With Speed, Quality & Interoperability
- Global Semiconductor Sales Increase 2.5% Month-to-Month in April
- Speedata Raises $44M to Launch First-Ever Chip Designed Specifically for Accelerating Big Data Analytics - Compute's Second Largest Workload