TSMC Prepares Massive 8x Reticle Super Carrier Interposer for Next-Gen Chips, Significantly Larger than Current Models

TSMC plans to develop larger interposers and substrates to meet the demand for more powerful processors in the high-performance computing and artificial intelligence industries, with their next-generation CoWoS_L product expected to offer 5.5 times the area of current solutions and their future CoWoS technology projected to double performance once again.

Allows for larger chips with more logic chiplets and memory stacks
Potential for significant increase in compute performance
Pushes the boundaries of chip size and offers a solution for Moore's Law slowdown

TSMC, the chip manufacturer, is no stranger to pushing the boundaries of chip size. With their chip-on-wafer-on-Substrate (CoWoS) technology, they have already been able to produce larger chips by fitting multiple dies onto a single silicon interposer. However, in response to the growing demand from the high-performance computing (HPC) and artificial intelligence (AI) industries, TSMC is now planning to go even bigger.

During their recent North American Technology Symposium, TSMC announced their plans to develop super-sized interposers that can reach over 8 times the reticle limit. Currently, their CoWoS technology allows for interposers up to 2831 mm², and they are already seeing customers designing chips that utilize the full capacity. Examples of such chips include AMD’s Instinct MI300X accelerator and nVidia’s upcoming B200 accelerator, both of which incorporate large logic chiplets and multiple HBM3/HBM3E memory stacks.

However, chip developers are aiming for even more powerful processors. To achieve this, they need to go bigger by incorporating more logic chiplets and memory stacks. TSMC’s next-generation CoWoS product, set to launch in 2026, will be called CoWoS_L and will offer a maximum interposer size of approximately 4719 mm², which is 5.5 times that of a photomask. This new package will support up to 12 HBM memory stacks and will require a larger substrate measuring at 100×100 mm. With process node improvements, TSMC expects chips based on CoWoS_L to deliver more than 3.5 times the compute performance of current-generation CoWoS chips.

Looking further ahead, in 2027, TSMC plans to introduce a version of CoWoS that allows for interposers up to 8 times larger than the reticle limit. This will provide a generous 6864 mm² of space for chiplets on a substrate measuring 120×120 mm. TSMC envisions utilizing this technology for designs that integrate four stacked systems-on-integrated chips (SoICs), along with 12 HBM4 memory stacks and additional I/O dies. This advancement is projected to double the performance once again, surpassing 7 times the performance of current-generation chips.

However, building such large chips comes with its own challenges. It will impact system design and how data centers accommodate these systems. TSMC’s 100×100 mm substrate will push the limits of the OAM 2.0 form factor, which already measures 102×165 mm. And if the next generation of CoWoS doesn’t break the current form factor, then the 120×120 mm chips certainly will. Additionally, the larger size requires more power and cooling, leading hardware vendors to explore liquid and immersion cooling solutions for these multi-kilowatt chips.

While Moore’s Law may have slowed down in terms of transistor density improvements, CoWoS technology offers a way to produce chips with an increasing number of transistors. With TSMC’s plans to offer interposers and substrates with more than twice the area of current solutions, we can expect big chips for HPC systems to continue growing in both performance and size.

About Our Team

Our team comprises industry insiders with extensive experience in computers, semiconductors, games, and consumer electronics. With decades of collective experience, we’re committed to delivering timely, accurate, and engaging news content to our readers.

Background Information

About AMD:

AMD, a large player in the semiconductor industry is known for its powerful processors and graphic solutions, AMD has consistently pushed the boundaries of performance, efficiency, and user experience. With a customer-centric approach, the company has cultivated a reputation for delivering high-performance solutions that cater to the needs of gamers, professionals, and general users. AMD's Ryzen series of processors have redefined the landscape of desktop and laptop computing, offering impressive multi-core performance and competitive pricing that has challenged the dominance of its competitors. Complementing its processor expertise, AMD's Radeon graphics cards have also earned accolades for their efficiency and exceptional graphical capabilities, making them a favored choice among gamers and content creators. The company's commitment to innovation and technology continues to shape the client computing landscape, providing users with powerful tools to fuel their digital endeavors.

Latest Articles about AMD

About nVidia:

NVIDIA has firmly established itself as a leader in the realm of client computing, continuously pushing the boundaries of innovation in graphics and AI technologies. With a deep commitment to enhancing user experiences, NVIDIA's client computing business focuses on delivering solutions that power everything from gaming and creative workloads to enterprise applications. for its GeForce graphics cards, the company has redefined high-performance gaming, setting industry standards for realistic visuals, fluid frame rates, and immersive experiences. Complementing its gaming expertise, NVIDIA's Quadro and NVIDIA RTX graphics cards cater to professionals in design, content creation, and scientific fields, enabling real-time ray tracing and AI-driven workflows that elevate productivity and creativity to unprecedented heights. By seamlessly integrating graphics, AI, and software, NVIDIA continues to shape the landscape of client computing, fostering innovation and immersive interactions in a rapidly evolving digital world.

Latest Articles about nVidia

About TSMC:

TSMC, or Taiwan Semiconductor Manufacturing Company, is a semiconductor foundry based in Taiwan. Established in 1987, TSMC is a important player in the global semiconductor industry, specializing in the manufacturing of semiconductor wafers for a wide range of clients, including technology companies and chip designers. The company is known for its semiconductor fabrication processes and plays a critical role in advancing semiconductor technology worldwide.

Latest Articles about TSMC

Technology Explained

chiplets: Chiplets are a new type of technology that is revolutionizing the computer industry. They are small, modular components that can be used to build a variety of computer systems. Chiplets are designed to be highly efficient and cost-effective, allowing for the creation of powerful and complex systems without the need for large, expensive components. They are also highly customizable, allowing for the creation of systems tailored to specific needs. Chiplets are being used in a variety of applications, from high-end gaming PCs to embedded systems and even supercomputers. They are also being used to create powerful AI systems, allowing for the development of more advanced and intelligent machines. Chiplets are revolutionizing the computer industry, allowing for the creation of powerful and efficient systems at a fraction of the cost.

Latest Articles about chiplets

CoWoS: CoWoS, or Chip-on-Wafer-on-Substrate, is a recent advancement in chip packaging that allows for more powerful processors in a compact size. This technology stacks multiple chips on a silicon interposer, enabling denser connections and improved performance. Developed for high-performance computing, CoWoS promises faster processing, lower power consumption, and the ability to pack more processing power into smaller devices.

Latest Articles about CoWoS

HBM3E: HBM3E is the latest generation of high-bandwidth memory (HBM), a type of DRAM that is designed for artificial intelligence (AI) applications. HBM3E offers faster data transfer rates, higher density, and lower power consumption than previous HBM versions. HBM3E is developed by SK Hynix, a South Korean chipmaker, and is expected to enter mass production in 2024. HBM3E can achieve a speed of 1.15 TB/s and a capacity of 64 GB per stack. HBM3E is suitable for AI systems that require large amounts of data processing, such as deep learning, machine learning, and computer vision.

Latest Articles about HBM3E

HPC: HPC, or High Performance Computing, is a type of technology that allows computers to perform complex calculations and process large amounts of data at incredibly high speeds. This is achieved through the use of specialized hardware and software, such as supercomputers and parallel processing techniques. In the computer industry, HPC has a wide range of applications, from weather forecasting and scientific research to financial modeling and artificial intelligence. It enables researchers and businesses to tackle complex problems and analyze vast amounts of data in a fraction of the time it would take with traditional computing methods. HPC has revolutionized the way we approach data analysis and has opened up new possibilities for innovation and discovery in various fields.

Latest Articles about HPC

Substrate: The technology substrate is a layer of material that provides a foundation for the components of a computer system. It is the foundation upon which the components of a computer system are built. It is usually made of a material such as silicon, which is a semiconductor material. The technology substrate is used to create the circuits and pathways that allow the components of a computer system to communicate with each other. It is also used to create the physical structure of the computer system, such as the motherboard, memory, and other components. The technology substrate is essential for the functioning of a computer system, as it provides the necessary pathways for the components to communicate with each other. It is also used to create the physical structure of the computer system, such as the motherboard, memory, and other components.