Learn about the advancement of coherent connectivity in this 16-minute technical talk from Mahesh Wagh of the CXL Consortium (AMD) at Open Compute Project. Explore how CXL™ (Compute Express Link™), an open interconnect standard, enables high-performance computational infrastructures through coherency and memory semantics, utilizing high-bandwidth and low-latency connections between host processors and various components. Discover the enhanced features of CXL 3.0, including improved scalability, advanced switching and fabric capabilities, efficient peer-to-peer communications, and fine-grained resource sharing across multiple compute domains. Gain insights into memory pooling and sharing capabilities that enable system architects to upgrade existing systems, and understand how CXL 3.0's fabric capabilities extend beyond traditional PCIe® tree-based architectural structures.
Overview
Syllabus
CXL™ (Compute Express Link™): Advancing coherent connectivity
Taught by
Open Compute Project
Related Courses
-
Introduction to Compute Express Link (CXL) 3.0 - Features and Fabric Management
-
CXL Enabling an Interoperable Ecosystem for Heterogeneous Memory and Computing Solutions
-
CXL 3.0 - Expanded Capabilities for Memory Pooling and Resource Optimization
-
Server Fabrics and the Evolution to CXL 3.0 - Memory and Resource Management in Heterogeneous Computing
-
Introducing CXL 3.0 - Expanded Capabilities for Scale and Resource Optimization
-
Messing Up Your NUMA Topology with CXL - Implications for Advanced Interconnects
