The Rambus PCI Express (PCIe) 5.0 and Compute Express Link (CXL) PHY is a low-power, area-optimized, silicon IP core designed with a system-oriented approach to maximize flexibility and ease of integration. It delivers up to 32 GT/s data rates in performance-intensive applications for artificial intelligence (AI), data center, edge, 5G infrastructure and graphics. With the Northwest Logic Expresso 5.0 controller core it comprises a complete PCIe 5.0 SerDes subsystem. Alternatively, it can be integrated with PIPE 5.1-compliant 3rd-party controllers. The PCIe 5 SerDes PHY supports PCIe 5.0, 4.0, 3.0 and 2.0, and has full support for manufacturability.
For Ultra-Low Power PCIe 5.0 Designs
Rambus also offers an ultra-low power PCIe 5.0 SerDes PHY (formerly AnalogX AXLinkIO MP) for channels up to 25dB insertion loss. This PHY solution supports PCIe 5.0 and earlier generations to PCIe 1.0. It offers the industry’s best power, area and latency in its class for next-generation computing and networking applications with the most demanding PPA requirements. It is available on advanced FinFET process nodes.
The Rambus PCI express 5 PHY with the Expresso 5.0 digital controller comprise a high-performance serial link subsystem. Optimized for power in challenging, high-loss channels, our PCIe 5.0 interface solution is ideal for performance-intensive AI, data center, edge, 5G infrastructure and graphics applications.
The PHY consists of a PMA hard macro that supports PCIe 5.0, 4.0, 3.0 and 2.0 protocols and a physical coding sublayer (PCS) soft macro for PCIe that is PIPE 5.1 compliant. Co-verified with the Northwest Logic Expresso 5.0 digital controller, the PHY can also be integrated with 3rd-party PIPE 5.1-compliant controllers.
Designed with a minimal set of broadside controls, the PHY is configurable in x2, x4, x8 and x16 lane configurations with bifurcation support. This gives the PHY improved flexibility and support for a wide range of applications. Multi-tap transmitter and adaptive receiver equalization supports more than 36dB of channel insertion loss.
The PCIe 5 SerDes PHY is available on an advanced 7nm FinFET process node.
The PCI Express® (PCIe) interface is the critical backbone that moves data at high bandwidth between various compute nodes such as CPUs, GPUs, FPGAs, and workload-specific accelerators. The rise of cloud-based computing and hyperscale data centers, along with high-bandwidth applications like artificial intelligence (AI) and machine learning (ML), require the new level of performance of PCI Express 5.0.
|Protocol||Data Rate (Gbps)||Application|
|PCIe 2.0||5||High bandwidth peripherals and graphics|
|PCIe 3.0||8||Servers, storage, networking devices|
|PCIe 4.0||16||Servers, storage, networking devices|
|PCIe 5.0||32||AI, servers, storage, networking, 5G infrastructure|
Maintaining signal integrity has become increasingly difficult as data rates moves past 28Gbps to 56Gbps and beyond. Up to 28Gbps rates, NRZ is the preferred and standardized encoding scheme which consists of 1’s and 0’s. NRZ is also referred to as PAM2 (pulse amplitude modulation, 2-level), due to its two amplitude levels which contain 1 bit of information in every symbol. With serial data rates hitting 56 Gb/s per channel, signal impairments caused by increased bandwidth has prompted the high-speed serial data industry to adopt PAM4, or 4-level pulse amplitude modulation.