Memory Interface Chips icon

Memory Interface Chips

CXL Memory Interconnect Initiative

A research program focused on improving performance, efficiency and TCO for a new era of data center architecture.

Improved Performance icon

Improved Performance

Effectively expands main memory for high-capacity workloads

Enhanced Efficiency icon

Enhanced Efficiency

Matches memory resources to the specific needs of varying workloads
Lower TCO icon

Lower TCO

Shares memory resources across processors for greater utilization

Disaggregation and Composability

The data center is moving from a model where each server has dedicated processing and memory, as well as other resources like networking and accelerators, to a disaggregated model that employs pools of shared resources which can be efficiently composed to the needs of specific workloads whatever their requirements. Disaggregation and composability tailor computing resources to the workload, bringing many benefits including higher performance, greater efficiency and reduced total cost of ownership (TCO) for the data center.

CXL Memory Expansion and Pooling

CXL 2.0 enables a host, such a as a processor, to access device attached memory using load/store commands. This enables a memory expansion use model wherein significant additional capacity, above and beyond direct-attached main memory, can be added to a CPU host via a CXL-attached device. A further use model is memory pooling, where many-to-many connections between hosts and devices are possible. With CXL 2.0, a host can access all or part of the memory across multiple devices. A device can act as multiple logical devices simultaneously accessible by up to 16 hosts. Memory pooling with CXL 2.0 allows for the tailored matching of workloads to the available memory in the pool leading to improved performance, higher memory use efficiency, and improved utilization and TCO.
Diagram of CXL Memory Pooling Through Direct Connect
CXL Memory Pooling Through Direct Connect

Rambus CXL Memory Interconnect Initiative

Through the CXL Memory Interconnect Initiative, Rambus is researching and developing solutions to enable a new era of data center performance and efficiency. Announced on June 16, 2021, this initiative is the latest chapter in the 30-year history of Rambus leadership in the development of breakthrough memory and chip-to-chip interconnect technology and products.

Realization of the chip solutions needed for the memory expansion and pooling use cases, and further those needed for server disaggregation and composability, will require the synthesis of a number of critical technologies. Rambus has been researching memory solutions for disaggregated architectures for close to a decade and leverages a system-aware design approach to solve these next-generation challenges. This initiative brings together our expertise in memory and SerDes subsystems, semiconductor and network security, high-volume memory interface chips and compute system architectures to develop breakthrough interconnect solutions for the future data center.

CXL Memory Interconnect Initiative: Enabling a New Era of Data Center Architecture

CXL Memory Interconnect Initiative: Enabling a New Era of Data Center Architecture

In response to an exponential growth in data, the industry is on the threshold of a groundbreaking architectural shift that will fundamentally change the performance, efficiency and cost of data centers around the globe. Server architecture, which has remained largely unchanged for decades, is taking a revolutionary step forward to address the growing demand for data and the voracious performance requirements of advanced workloads. 

Data Center Evolution: DDR5 DIMMs Advance Server Performance cover

Data Center Evolution: DDR5 DIMMs Advance Server Performance

Driven by a confluence of megatrends, global data traffic is increasing at an exponential rate. For example, 5G networks are enabling billions of AI-powered IoT devices untethered from wired networks. Nowhere is the impact of all this growth being felt more intensely than in data centers. Indeed, hyperscale data centers have become the critical hubs of the global data network. DDR5 DRAM will enable the next generation of server systems providing the massive computing power of hyperscale and enterprise data centers. Learn about the benefits of DDR5 memory and the design considerations for implementing DDR5 DIMMs.