PuDHammer: Experimental Analysis of Read Disturbance Effects of Processing-using-DRAM in Real DRAM Chips
Authors:
- Ismail Emir YukselIYIsmail Emir Yuksel
- Akash SoodASAkash Sood
- Ataberk OlgunAOAtaberk Olgun
- Oğuzhan CanpolatOCOğuzhan Canpolat
- Haocong LuoHLHaocong Luo
- F. Nisa BostancıFBF. Nisa Bostancı
- A. Giray YağlıkçıAYA. Giray Yağlıkçı
- Onur MutluOMOnur Mutlu
Preprint
Abstract
Processing-using-DRAM (PuD) is a promising paradigm for alleviating the data movement bottleneck using DRAM's massive internal parallelism and bandwidth to execute very wide operations. Performing a PuD operation involves activating multiple DRAM rows in quick succession or simultaneously, i.e., multiple-row activation. Multiple-row activation is fundamentally different from conventional memory access patterns that activate one DRAM row at a time. However, repeatedly activating even one DRAM row (e.g., RowHammer) can induce bitflips in unaccessed DRAM rows because modern DRAM is subject to read disturbance. Unfortunately, no prior work investigates the effects of multiple-row activation on DRAM read disturbance. In this paper, we present the first characterization study of read disturbance effects of multiple-row activation-based PuD (which we call PuDHammer) using 316 real DDR4 DRAM chips from four major DRAM manufacturers. Our detailed characterization show that 1) PuDHammer significantly exacerbates the read disturbance vulnerability, causing up to 158.58x reduction in the minimum hammer count required to induce the first bitflip ($HC_{first}$), compared to RowHammer, 2) PuDHammer is affected by various operational conditions and parameters, 3) combining RowHammer with PuDHammer is more effective than using RowHammer alone to induce read disturbance error, e.g., doing so reduces $HC_{first}$ by 1.66x on average, and 4) PuDHammer bypasses an in-DRAM RowHammer mitigation mechanism (Target Row Refresh) and induces more bitflips than RowHammer. To develop future robust PuD-enabled systems in the presence of PuDHammer, we 1) develop three countermeasures and 2) adapt and evaluate the state-of-the-art RowHammer mitigation standardized by industry, called Per Row Activation Counting (PRAC). We show that the adapted PRAC incurs large performance overheads (48.26%, on average).
Keywords
All Related Versions
This publication has 151 references indexed in Scilit:
- Defeating Software Mitigations Against Rowhammer: A Surgical Precision Hammer2018
- GuardION: Practical Mitigation of DMA-Based Rowhammer Attacks on ARM2018
- Study of proton radiation effect to row hammer fault in DDR4 SDRAMsMicroelectronics Reliability, 2018
- Simple Operations in Memory to Reduce Data Movement2017
- Statistical distributions of row-hammering induced failures in DDR3 componentsMicroelectronics Reliability, 2016
- Curious Case of Rowhammer: Flipping Secret Exponent Bits Using Timing Analysis2016
- Experiments and root cause analysis for active-precharge hammering fault in DDR3 SDRAM under 3 × nm technologyMicroelectronics Reliability, 2016
- MediaBench II video: Expediting the next generation of video systems researchMicroprocessors and Microsystems, 2009
- XOR-based Visual Cryptography SchemesDesigns, Codes and Cryptography, 2005
- VLSI Memory Chip Design2001