Japan’s Rapidus Preps 2nm Foundry Process And Chiplets
An executive from the Japanese foundry startup discusses the company’s strategy, including its efforts to develop a 2nm gate-all-around (GAA) process.
By Mark LaPedus, Semiecosystem
Henri Richard, general manager and president of Rapidus Design Solutions, sat down with Semiecosystem to discuss the company’s foundry strategy and its efforts to develop its first process--a 2nm gate-all-around (GAA) technology. Rapidus Design Solutions is the U.S. subsidiary of Japanese foundry startup Rapidus Corp.
What you’ll learn:
- Who is Rapidus and what is the company’s charter?
- Where is your fab located and what is the status of your fab? And what are the company’s capital spending plans for 2025 and perhaps beyond?
- Can you discuss your roadmap? Who is your technology partner?
- Will Rapidus integrate a backside power delivery network (BSPDN) technology for the first version of your 2nm GAA process? Or will you bring up BSPDN later?
- Why does the semiconductor industry need another leading-edge foundry vendor? Is there room for another vendor like Rapidus in the marketplace? After all, TSMC provides a large percentage of the world’s leading-edge foundry business. Samsung also competes in this segment with Intel waiting in the wings.
- Years ago, Japanese semiconductor companies were among the leaders in both logic and memory technology. With Kioxia, Japan has a strong presence in NAND flash memory. But today, Japan appears to be behind in logic—its most advanced logic technology is 40nm. So, I assume that Rapidus is important in terms of national security for Japan’s semiconductor industry, right?
- Intel, Samsung, TSMC and others have been working on GAA for many years. GAA provides more performance at lower power than today’s finFET transistor technology. GAA shares many of the same process steps as finFETs. Yet, GAA is a difficult technology and a challenge when ramping up high yields. With that in mind, there is some skepticism among many that Rapidus will be able to bring up GAA technology into production promptly. Rapidus has no track record in chip manufacturing. Any comments here?
- What are some of the main technical challenges with GAA?
- The foundry business is also challenging. For one thing, a given foundry vendor must ramp up a given process on time. Then, a foundry vendor must find customers and develop a certain level of trust with those customers. Then, a foundry must deliver chips to customers on time with good yields. Rapidus is a newcomer here. Why should potential foundry customers work with Rapidus? What are the company’s competitive advantages?
- Foundries also require an EDA and IP ecosystem. How far along is Rapidus in developing this ecosystem?
- Rapidus has developed a technology called RUMS (Rapid and Unified Manufacturing Service). What is RUMS and what are the benefits?
- Rapidus will also provide customers with packaging technology, right? What is Rapidus Chiplet Solutions (RCS) and what does that involve?
To read the full article, click here
Related Chiplet
- Automotive AI Accelerator
- 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
Related News
- Eliyan Ports Industry’s Highest Performing PHY to Samsung Foundry SF4X Process Node, Achieving up to 40 Gbps Bandwidth at Unprecedented Power Levels with UCIe-Compliant Chiplet Interconnect Technology
- DreamBig Semiconductor Announces Partnership with Samsung Foundry to Launch Chiplets for World Leading MARS Chiplet Platform on 4nm FinFET Process Technology Featuring 3D HBM Integration to Solve Scale-up and Scale-out Limitations of AI for the Masses
- Rapidus and IBM Expand Collaboration to Chiplet Packaging Technology for 2nm-Generation Semiconductors
- Expanding the Chiplet Market: Processing Any Wafer from Any Foundry
Latest News
- BOS Semiconductors to Partner with Intel to Accelerate Automotive AI Innovation
- NHIZ promotes chiplet industry's development and cooperation
- Cadence and TSMC Advance AI and 3D-IC Chip Design with Certified Design Solutions for TSMC’s A16 and N2P Process Technologies
- Breaking the Memory Wall: How d-Matrix Is Redefining AI Inference with Chiplets
- Alphawave Semi Delivers Foundational AI Platform IP for Scale-Up and Scale-Out Networks