Performance Efficiency AI Accelerator for Mobile and Edge Devices
Industry Expert Blogs
Compute Express Link (CXL): All you need to knowRambus BlogNov. 10, 2021 |
In this blog post, we take an in-depth look at Compute Express Link ™ (CXL) 2.0, an open standard cache-coherent interconnect between processors and accelerators, smart NICs, and memory devices.
- We explore how CXL is helping data centers more efficiently handle the yottabytes of data generated by artificial intelligence (AI) and machine learning (ML) applications.
- We discuss how CXL technology maintains memory coherency between the CPU memory space and memory on attached devices to enable resource sharing (or pooling).
- We also detail how CXL builds upon the physical and electrical interfaces of PCI Express® (PCIe) 5.0 with protocols that establish coherency, simplify the software stack, and maintain compatibility with existing standards.
- Lastly, we review Rambus CXL solutions, which include the Rambus CXL 2.0 Interconnect Subsystem comprising a CXL 2.0 Controller and CXL 2.0 SerDes PHY. These solutions are now available with integrated Integrity and Data Encryption (IDE) modules which monitor and protect against cyber and physical attacks on CXL and PCIe links.
Let’s get started.
Related Blogs
- Ecosystem Collaboration Drives New AMBA Specification for Chiplets
- Semiconductor Industry 2.0
- Mitigating Side-Channel Attacks In Post Quantum Cryptography (PQC) With Secure-IC Solutions
- Rambus Demonstrates Advancing Data Center Capabilities with CXL Over Optics
- CXL 3.1: How Evolving CXL Standards are Pushing Interconnects to Even Higher Performance