Sarcina Technology introduces AI Chiplet Platform for Compact 100×100 mm Systems

Sarcina Technology introduces Game-Changing AI Platform

Sarcina Technology, a trailblazer in the world of semiconductor packaging, is making waves with the launch of its innovative AI platform. This solution is designed to offer advanced packaging options that can be tailored to meet the unique needs of customers. By leveraging ASE’s FOCoS-CL (Fan-Out Chip-on-Substrate-Chip Last) assembly technology, Sarcina’s platform includes a sophisticated interposer that supports chiplets using UCIe-A for die-to-die interconnects. The result? Cost-effective, customizable, and state-of-the-art solutions that are ready to take the industry by storm.

Pushing the Boundaries of AI Computing

At Sarcina, the mission is clear: to redefine what’s possible in AI computing system development. With the ever-evolving demands of AI workloads, there’s a pressing need for packaging solutions that can keep up with higher computational needs. Sarcina’s novel interposer packaging technology seamlessly integrates leading memory solutions with high-efficiency interconnects. Whether you’re focused on cost, performance, or power efficiency, Sarcina’s new AI platform is equipped to deliver.

Dr. Larry Zu, the CEO of Sarcina Technology, reflects on the journey: “Six years ago, we prototyped a 2.5D silicon TSV interposer package that combined one ASIC and two HBMs. We believed this tech would pave the way for complex compute solutions. Today, that vision is coming to life, fueled by RDL die-to-die interconnects like UCIe.”

A New Era of AI Computing

Dr. Zu elaborates, “With FOCoS assembly technology, we are entering a new era of AI computing. Our AI platform not only offers greater efficiency and customization but also the lowest costs in the industry for generative AI chips. This ensures our customers remain competitive in the fast-paced AI landscape.”

Sarcina’s team has achieved impressive feats, developing an interposer that boasts up to 64 bits of data interface per module and reaching data rates of up to 32 GT/s. This performance is top-notch, aligning with the UCIe 2.0 standard for both bandwidth and data rate. And if that’s not enough, multiple modules can be arranged in parallel along the silicon die edge to further enhance data transfer throughput. Plus, customers can choose between LPDDR5X/6 packaged memory chips and HBMs for their specific needs.

Empowering Startups and Innovators

Sarcina’s extensive expertise in designing high-power, high-performance semiconductor packages means that startups can focus on what they do best: developing efficient algorithms for generative AI and edge AI training. There’s no need for an expensive post-silicon design and manufacturing team. Instead, startups can simply develop their silicon and hand it over to Sarcina for streamlined post-silicon packaging. This not only reduces costs but also maintains high performance.

Sarcina’s die-to-die interposer solution empowers AI customers to utilize chiplets to create larger silicon areas, supporting high-performance computing while ensuring satisfactory wafer yields. This larger package design is crucial for generative AI applications that demand rapid, parallel data processing.

Key Features of Sarcina’s AI Platform

So, what can we expect from Sarcina’s new AI platform? Here are some standout features:

–

Cost-effective chiplet design

: A budget-friendly alternative to pricey SoC solutions.
–

Fast die-to-die interconnection with UCIe-A standard

: Up to 64-bit data interface per module and 32 GT/s transmission speed per lane, supporting multi-module configurations and interconnect redundancy.
–

FOCoS-CL advanced packaging technology

: A cost-effective replacement for expensive 2.5D TSV silicon interposer technology.
–

LPDDR5X/6 and HBM options

: Delivering superior memory bandwidth and efficiency for various AI workloads, with LPDDR6 memory utilizing 3D stacking technology akin to HBM.
–

Scalable package size

: Supporting package sizes up to 100 mm x 100 mm, allowing for scalability across diverse AI applications.
–

Power specifications

: Under 500 W for forced air cooling and up to 1000 W with Liquid Cooling, offering flexible deployment options.
–

Memory integration

: Supporting up to 20 LPDDR5X/6 memory chips or up to 8 HBM3E chips for high-speed data processing.

Transforming Industries with AI

The launch of Sarcina’s AI platform is poised to revolutionize AI computing capabilities across various sectors, from autonomous systems to data centers and scientific computing. With such innovative solutions on the horizon, one can’t help but wonder: how will this technology reshape our future? As Sarcina continues to push the envelope, the possibilities seem endless.

Technology Explained

---

chiplet: Chiplets are a new type of technology that is revolutionizing the computer industry. They are small, modular components that can be used to build powerful computing systems. Chiplets are designed to be used in combination with other components, such as processors, memory, and storage, to create a complete system. This allows for more efficient and cost-effective production of computers, as well as more powerful and versatile systems. Chiplets can be used to create powerful gaming PCs, high-end workstations, and even supercomputers. They are also being used in the development of artificial intelligence and machine learning applications. Chiplets are an exciting new technology that is changing the way we build and use computers.

Latest Articles about chiplet

---

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

---

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

---

Liquid Cooling: Liquid cooling is a technology used to cool down computer components, such as processors, graphics cards, and other components that generate a lot of heat. It works by circulating a liquid coolant, such as water or a special coolant, through a series of pipes and radiators. The liquid absorbs the heat from the components and then dissipates it into the air. This technology is becoming increasingly popular in the computer industry due to its ability to provide more efficient cooling than traditional air cooling methods. Liquid cooling can also be used to overclock components, allowing them to run at higher speeds than their rated speeds. This technology is becoming increasingly popular in the gaming industry, as it allows gamers to get the most out of their hardware.

Latest Articles about Liquid Cooling

---

LPDDR5X: LPDDR5X is a type of computer memory technology that is used in many modern computers. It stands for Low Power Double Data Rate 5X and is a type of Random Access Memory (RAM). It is designed to be more efficient than its predecessors, allowing for faster data transfer speeds and lower power consumption. This makes it ideal for use in laptops, tablets, and other mobile devices. It is also used in gaming consoles and other high-end computers. LPDDR5X is capable of transferring data at up to 8400 megabits per second, making it one of the fastest types of RAM available. This makes it ideal for applications that require high performance, such as gaming, video editing, and 3D rendering.

Latest Articles about LPDDR5X

---

SoC: A System-on-Chip (SoC) is a highly integrated semiconductor device that encapsulates various electronic components, including processors, memory, input/output interfaces, and often specialized hardware components, all on a single chip. SoCs are designed to provide a complete computing system or subsystem within a single chip package, offering enhanced performance, power efficiency, and compactness. They are commonly used in a wide range of devices, from smartphones and tablets to embedded systems and IoT devices, streamlining hardware complexity and facilitating efficient integration of multiple functions onto a single chip.

Latest Articles about SoC

---

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.

Latest Articles about Substrate