18591718. RECALL PENDING CACHE LINE EVICTION simplified abstract (Micron Technology, Inc.)
Contents
RECALL PENDING CACHE LINE EVICTION
Organization Name
Inventor(s)
Dean E. Walker of Allen TX (US)
Tony M. Brewer of Plano TX (US)
RECALL PENDING CACHE LINE EVICTION - A simplified explanation of the abstract
This abstract first appeared for US patent application 18591718 titled 'RECALL PENDING CACHE LINE EVICTION
The abstract describes a system and techniques for recalling pending cache line eviction in a computer system.
- A queue is maintained for a cache line containing a deferred memory request.
- Metadata for the queue is stored in the cache line tag.
- When a recall is required, the metadata is transferred from the tag to a first recall storage, referenced by a memory request ID.
- The memory request ID is then written to a second recall storage, referenced by the message ID of the recall request.
- Upon receiving a response to the recall request, the queue for the cache line can be restored by using the message ID in the response to look up the memory request ID from the second recall storage, then retrieving the metadata from the first recall storage using the memory request ID, and finally writing the metadata back into the tag for the cache line.
Potential Applications: - This technology can be applied in computer systems where efficient cache management is crucial. - It can be used in high-performance computing environments to optimize memory access.
Problems Solved: - Efficiently managing cache line eviction in computer systems. - Streamlining memory access and recall processes.
Benefits: - Improved performance and efficiency in cache management. - Enhanced memory access optimization in high-performance computing environments.
Commercial Applications: Title: Advanced Cache Line Recall System for High-Performance Computing This technology can be utilized in data centers, cloud computing environments, and supercomputing facilities to enhance memory access efficiency and overall system performance.
Questions about the technology: 1. How does this system improve cache management in computer systems? 2. What are the key benefits of using this technology in high-performance computing environments?
Original Abstract Submitted
System and techniques for recall pending cache line eviction are described herein. A queue that includes a deferred memory request is kept for a cache line. Metadata for the queue is stored in a cache line tag. When a recall is needed, the metadata is written from the tag to a first recall storage, referenced by a memory request ID. After the recall request is transmitted, the memory request ID is written to a second recall storage referenced by the message ID of the recall request. Upon receipt of a response to the recall request, the queue for the cache line can be restored by using the message ID in the response to lookup the memory request ID from the second recall storage, then using the memory request ID to lookup the metadata from the first recall storage, and then writing the metadata into the tag for the cache line.
