Memory Machine™ for CXL
Big Memory Platform for the AI Era
Optimizes the cost and performance of AI and other data-intensive workloads by intelligently managing the memory-storage hierarchy and fabric-attached memory to overcome the memory wall.
Employs intelligent placement policies and memory page movement to optimize latency or bandwidth.
Allows multiple servers to access shared memory with software-enabled cache coherence.
Memory Machine for CXL Overview
Memory Machine for CXL Partners
Use Cases
MySQL
Memory Machine for CXL improves performance with intelligent tiering
Ray AI Framework
Memory Machine for CXL accelerates shuffles with shared memory objects
FlexGen LLM Inference
Memory Machine for CXL boots NVIDIA GPU utilization by 77%
½ Cost, 3x capacity with CXL
Memory Machine for CXL tiering enables use of lower cost and higher capacity CXL memory
Weaviate AI Vector Database
Memory Machine for CXL accelerates shuffles with shared memory objects