Strong, thorough, and efficient memory protection against existing and emerging DRAM errors

Date

2016-12

Authors

Kim, Jungrae

Journal Title

Journal ISSN

Volume Title

Publisher

Abstract

Memory protection is necessary to ensure the correctness of data in the presence of unavoidable faults. As such, large-scale systems typically employ Error Correcting Codes (ECC) to trade off redundant storage and bandwidth for increased reliability. Single Device Data Correction (SDDC) ECC mechanisms are required to meet the reliability demands of servers and large-scale systems by tolerating even severe faults that disable an entire memory chip. In the future, however, stronger memory protection will be required due to increasing levels of system integration, shrinking process technology, and growing transfer rates. The energy-efficiency of memory protection is also important as DRAM already consumes a significant fraction of system energy budget. This dissertation develops a novel set of ECC schemes to provide strong, safe, flexible, and thorough protection against existing and emerging types of DRAM errors. This research also reduces energy consumption of such protection while only marginally impacting performance. First, this dissertation develops Bamboo ECC, a technique with strongerthan-SDDC correction and very safe detection capabilities (≥ 99.999994% of data errors with any severity are detected). Bamboo ECC changes ECC layout based on frequent DRAM error patterns, and can correct concurrent errors from multiple devices and all but eliminates the risk of silent data corruption. Also, Bamboo ECC provides flexible configurations to enable more adaptive graceful downgrade schemes in which the system continues to operate correctly after even severe chip faults, albeit at a reduced capacity to protect against future faults. These strength, safety, and flexibility advantages translate to a significantly more reliable memory sub-system for future exascale computing. Then, this dissertation focuses on emerging error types from scaling process technology and increasing data bandwidth. As DRAM process technology scales down to below 10nm, DRAM cells are becoming more vulnerable to errors from an imperfect manufacturing process. At the same time, DRAM signal transfers are getting more susceptible to timing and electrical noises as DRAM interfaces keep increasing signal transfer rates and decreasing I/O voltage levels. With individual DRAM chips getting more vulnerable to errors, industry and academia have proposed mechanisms to tolerate these emerging types of errors; yet they are inefficient because they rely on multiple levels of redundancy in the case of cell errors and ad-hoc schemes with suboptimal protection coverage for transmission errors. Active Guardband ECC and All-Inclusive ECC make systematic use of ECC and existing mechanisms to provide thorough end-to-end protection without requiring redundancy beyond what is common today. Finally, this dissertation targets the energy efficiency of memory protection. Frugal ECC combines ECC with fine-grained compression to provide versatile and energy-efficient protection. Frugal ECC compresses main memory at cache-block granularity, using any left over space to store ECC information. Frugal ECC allows more energy-efficient memory configurations while maintaining SDDC protection. Its tailored compression scheme minimizes insufficiently compressed blocks and results in acceptable performance overhead. The strong, thorough, and efficient protection described by this dissertation may allow for more aggressive design of future computing systems with larger integration, finer process technology, higher transfer rates, and better energy efficiency

Description

LCSH Subject Headings

Citation