Link Details

Link 986233 thumbnail
User 972555 avatar

By KrDe
Submitted: Jun 21 2013 / 00:44

As DRAM systems face scalability challenges, the architecture community has started investigating alternative technologies for main memory. These emerging memory technologies tend to suffer from the problem of limited write endurance. This problem is exacerbated because of the high variability in lifetime across different cells, resulting in weaker cells failing much earlier than nominal cells. Ensuring long lifetimes under high variability requires that the design can correct a large number of errors for any given memory line. Unfortunately, supporting high levels of error correction for all lines incurs significantly high overhead, often exceeding 10 percent of overall memory capacity. We propose to reduce the storage required for error correction by exploiting the observation that only a few lines require high levels of hard-error correction. Therefore, prior approaches that uniformly allocated a large number of error correction entries for all lines are inefficient, as most (more than 90 percent) of these entries remain unused. We propose Pay-As-You-Go (PAYG), an efficient hard-error resilient architecture that allocates error correction entries in proportion to the number of hard faults in the line. We describe a storage-efficient and low-latency organization for PAYG. Compared to uniform error correction, PAYG requires one third the storage overhead and yet provides 13 percent more lifetime.
  • 2
  • 0
  • 75
  • 21

Add your comment

Html tags not supported. Reply is editable for 5 minutes. Use [code lang="java|ruby|sql|css|xml"][/code] to post code snippets.

Upvoters (2)

Downvoters (0)

    Apache Hadoop
    Written by: Piotr Krewski
    Featured Refcardz: Top Refcardz:
    1. Play
    2. Akka
    3. Design Patterns
    4. OO JS
    5. Cont. Delivery
    1. Play
    2. Java Performance
    3. Akka
    4. REST
    5. Java