Marvell Introduces PCIe Gen 6 Retimer Line, Expanding Connectivity Portfolio

Marvell Technology, a important player in the semiconductor industry, has announced the expansion of its connectivity portfolio with the introduction of the Alaska P PCIe retimer product line. These retimers are designed to enhance data center compute fabrics within accelerated servers, general-purpose servers, CXL systems, and disaggregated infrastructure. The initial products in this product line include 8- and 16-lane PCIe Gen 6 retimers that facilitate connections between AI accelerators, GPUs, CPUs, and other components within server systems.

The increasing demand for artificial intelligence (AI) and machine learning (ML) applications has led to higher data flows and connections within server systems, requiring PCIe retimers to meet the growing bandwidth requirements. PCIe has become the industry standard for connecting AI accelerators, GPUs, CPUs, and other server components within a system. With AI models doubling their computation requirements every six months, PCIe Gen 6 has become a necessity. This latest PCIe standard operates at 64 gigatransfers-per-second (GT/s) and utilizes four-level pulse-amplitude modulation (PAM4) signaling, replacing the non-return to zero (NRZ) modulation used for the past two decades. The higher bandwidth and faster data rate of PCIe Gen 6 limit the distance signals can reliably travel, which is where Marvell’s Alaska P retimers come into play. These retimers compensate for signal degradations and regenerate the signal, enabling reliable communication over the required physical distances between GPUs and CPUs in AI servers, between GPUs on different boards, or between CPUs and a shared memory pool enabled by CXL.

According to Alan Weckel, co-founder of 650 Group, “Signal distance is a real dilemma for service providers. We estimate over 75% of cloud and AI servers shipping two years from now will rely on retimers, and these servers will contain multiple retimers. An eight GPU server might contain 16 or more of these devices. Retimers will even percolate into enterprise servers.” Marvell’s expertise in PAM4 technology positions the company well to drive the evolution of this emerging market.

Marvell’s Alaska P PCIe retimer product line builds upon the company’s leadership in PAM4 technology, which it pioneered over a decade ago. Marvell’s PAM4 technology has been instrumental in enabling data center backend and frontend networks, with most data center optical interconnects now based on PAM4. The new product line extends Marvell’s connectivity portfolio beyond Ethernet and InfiniBand interconnects to include copper and optical PCIe, CXL, and proprietary compute fabric links. This expansion allows Marvell to address connections within AI and general-purpose server systems, broadening its market reach.

Leveraging its PAM4 SerDes technology leadership and data infrastructure IP platform, Marvell has developed a connectivity platform that empowers leading cloud data center operators to optimize their infrastructure for their unique architectures and workloads. In 2023, Marvell introduced Nova, the industry’s first 1.6T PAM4 DSP. Marvell has also introduced integrated PAM4 DSPs (Perseus) and DSPs optimized for efficiency (Spica Gen 2-T) to cater to the diverse range of cloud data center link types and use cases. PAM4 technology is also the foundation of Marvell’s Alaska A DSP chips, which are optimized for active electrical cable (AEC) applications.

The Alaska P PCIe retimers offer several benefits and features that make them stand out in the market. The 16-lane PCIe 6 retimer, built on a 5 nm process node, boasts industry-leading power efficiency, consuming only 10 watts of power. It can compensate for 40dB of channel loss, surpassing the specification of 32dB at PCIe 6. These retimers can be used for both on-board or cable copper connections, or they can be combined with electrical-to-optical components to create optical PCIe modules, catering to different cloud customer data center architectures. Marvell is collaborating with cable and optical module partners to integrate these products into cloud-optimized interconnect solutions for various data center applications.

Marvell has garnered strong support from key ecosystem partners who recognize the value of its PCIe retimer products. Raghu Nambiar, corporate vice president at AMD, emphasizes the importance of PCIe technologies in meeting the increased connectivity demands of next-generation AI and HPC workloads. Dermot O’Driscoll, vice president of product solutions at ARM, highlights the need for efficient interconnect technology with faster data rates as AI and ML applications consume more power. Osa Mok, chief marketing officer at InnoLight, acknowledges the collaboration between Marvell and InnoLight in advancing the optical PCIe ecosystem to support evolving data center workloads and architectures. Jim Pappas, director of Technology Initiatives at Intel, emphasizes the critical role of PCIe retimers in delivering platforms that meet customers’ ever-increasing performance requirements for AI and high-performance compute workloads. Vishwas Rao, vice president of product management at TE Connectivity, applauds Marvell’s PCIe retimer product portfolio launch and highlights the powerful combination of Alaska P PCIe retimers with TE’s advanced cabling solution in meeting the performance requirements of mission-critical data center applications.

The Marvell Alaska P PCIe 16-lane retimer is currently being sampled to customers and ecosystem partners, while the 8-lane product will be available for sampling in the next quarter. For more information about these products, visit Marvell’s product page.

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 ARM:

ARM, originally known as Acorn RISC Machine, is a British semiconductor and software design company that specializes in creating energy-efficient microprocessors, system-on-chip (SoC) designs, and related technologies. Founded in 1990, ARM has become a important player in the global semiconductor industry and is widely recognized for its contributions to mobile computing, embedded systems, and Internet of Things (IoT) devices. ARM's microprocessor designs are based on the Reduced Instruction Set Computing (RISC) architecture, which prioritizes simplicity and efficiency in instruction execution. This approach has enabled ARM to produce highly efficient and power-saving processors that are used in a vast array of devices, ranging from smartphones and tablets to IoT devices, smart TVs, and more. The company does not manufacture its own chips but licenses its processor designs and intellectual property to a wide range of manufacturers, including Qualcomm, Apple, Samsung, and NVIDIA, who then integrate ARM's technology into their own SoCs. This licensing model has contributed to ARM's widespread adoption and influence across various industries.

  

Latest Articles about ARM

---

About Intel:

Intel Corporation, a global technology leader, is for its semiconductor innovations that power computing and communication devices worldwide. As a pioneer in microprocessor technology, Intel has left an indelible mark on the evolution of computing with its processors that drive everything from PCs to data centers and beyond. With a history of advancements, Intel's relentless pursuit of innovation continues to shape the digital landscape, offering solutions that empower businesses and individuals to achieve new levels of productivity and connectivity.

  

Latest Articles about Intel

Technology Explained

---

GPU: GPU stands for Graphics Processing Unit and is a specialized type of processor designed to handle graphics-intensive tasks. It is used in the computer industry to render images, videos, and 3D graphics. GPUs are used in gaming consoles, PCs, and mobile devices to provide a smooth and immersive gaming experience. They are also used in the medical field to create 3D models of organs and tissues, and in the automotive industry to create virtual prototypes of cars. GPUs are also used in the field of artificial intelligence to process large amounts of data and create complex models. GPUs are becoming increasingly important in the computer industry as they are able to process large amounts of data quickly and efficiently.

Latest Articles about GPU

---

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

---

PCIe: PCIe (Peripheral Component Interconnect Express) is a high-speed serial computer expansion bus standard for connecting components such as graphics cards, sound cards, and network cards to a motherboard. It is the most widely used interface in the computer industry today, and is used in both desktop and laptop computers. PCIe is capable of providing up to 16 times the bandwidth of the older PCI standard, allowing for faster data transfer speeds and improved performance. It is also used in a variety of other applications, such as storage, networking, and communications. PCIe is an essential component of modern computing, and its applications are only expected to grow in the future.

Latest Articles about PCIe