Improving DRAM Performance, Security, and Reliability by Understanding and Exploiting DRAM Timing Parameter Margins

TL;DR

This dissertation characterizes modern DRAM devices to exploit timing margins for performance, power efficiency, security, and reliability improvements, revealing new vulnerabilities and opportunities for device identification and random number generation.

Contribution

It provides a comprehensive analysis of DRAM timing margins, introduces methods for faster device identification and true random number generation, and evaluates the security implications of RowHammer vulnerabilities.

Findings

Certain DRAM regions can be accessed faster due to manufacturing variation.

DRAM access timing can be reduced below specifications to improve performance and identify devices.

Existing RowHammer mitigations are ineffective or inefficient for future DRAM devices.

Abstract

This dissertation rigorously characterizes many modern commodity DRAM devices and shows that by exploiting DRAM access timing margins within manufacturer-recommended DRAM timing specifications, we can significantly improve system performance, reduce power consumption, and improve device reliability and security. First, we characterize DRAM timing parameter margins and find that certain regions of DRAM can be accessed faster than other regions due to DRAM cell process manufacturing variation. We exploit this by enabling variable access times depending on the DRAM cells being accessed, which not only improves overall system performance, but also decreases power consumption. Second, we find that we can uniquely identify DRAM devices by the locations of failures that result when we access DRAM with timing parameters reduced below specification values. Because we induce these failures with DRAM accesses, we can generate these unique identifiers significantly more quickly than prior work. Third, we propose a random number generator that is based on our observation that timing failures in certain DRAM cells are randomly induced and can thus be repeatedly polled to very quickly generate true random values. Finally, we characterize the RowHammer security vulnerability on a wide range of modern DRAM chips while violating the DRAM refresh requirement in order to directly characterize the underlying DRAM technology without the interference of refresh commands. We demonstrate with our characterization of real chips, that existing RowHammer mitigation mechanisms either are not scalable or suffer from prohibitively large performance overheads in projected future devices and it is critical to research more effective solutions to RowHammer. Overall, our studies build a new understanding of modern DRAM devices to improve computing system performance, reliability and security all at the same time.