Marvell introduces 2nm IP Platform Empowering Tailored Datacenter Silicon

Marvell has launched its latest IP technology platform designed specifically for custom chips used in accelerated infrastructure. This platform is tailored for TSMC’s advanced 2nm-class process technologies, potentially including N2 and N2P. It encompasses essential technologies for developing cloud-optimized accelerators, Ethernet switches, and digital signal processors.

Sandeep Bharathi, Marvell’s chief development officer, highlighted the significance of the 2nm platform, stating that it will enable the company to deliver highly differentiated analog, mixed-signal, and foundational IP for building accelerated infrastructure. Marvell’s collaboration with TSMC on previous platforms, including 5nm and 3nm, has played a crucial role in pushing the boundaries of silicon capabilities.

The foundation of the 2nm platform lies in Marvell’s extensive IP portfolio, which features advanced SerDes capable of speeds exceeding 200 Gbps, processor subsystems, encryption engines, SoC fabrics, and high-bandwidth physical layer interfaces. These IPs are essential for developing various devices like custom compute accelerators and optical interconnect digital signal processors. These components serve as fundamental building blocks for AI clusters, cloud data centers, and other infrastructures supporting AI and HPC workloads.

Developing these IPs from scratch, especially for TSMC’s 2nm-class process technologies that rely on gate-all-around Nanosheet transistors, can be challenging, time-consuming, and inefficient. However, Marvell’s IP portfolio aims to address these obstacles effectively.

While Marvell does not explicitly state that its TSMC 2nm-certified platform is silicon-proven, it is reasonable to assume that some of its popular IPs are compatible with TSMC’s N2 process technology. TSMC has been collaborating with IP providers on N2-compatible IPs for a considerable period.

Marvell adopts a modular approach to semiconductor design R&D, prioritizing the qualification of foundational analog, mixed-signal IP, and advanced packaging that can be utilized across a wide range of devices. This strategy allows the company to bring process manufacturing advancements to market more swiftly.

It is worth noting that Marvell is not currently part of TSMC’s Open Innovation Platform and IP Alliance. Consequently, it remains uncertain whether Marvell’s N2-compatible IPs will be included in TSMC’s TSMC9000 IP program, which simplifies IP choices for chip designers.

Kevin Zhang, senior vice president of business development at TSMC, expressed enthusiasm about collaborating with Marvell on advancing accelerated infrastructure using TSMC’s 2nm process technology. The partnership aims to develop connectivity and compute products that leverage TSMC’s industry-leading process and packaging technologies.

Source: Marvell

Background Information

---

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

---

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

---

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