HiFi-DRAM: Enabling High-fidelity DRAM Research by Uncovering Sense Amplifiers with IC Imaging
Michele Marazzi, Tristan Sachsenweger, Flavien Solt, Peng Zeng, Kubo Takashi, Maksym Yarema, Kaveh Razavi
摘要
DRAM vendors do not disclose the architecture of the sense amplifiers deployed in their chips. Unfortunately, this hinders academic research that focuses on studying or improving DRAM. Without knowing the circuit topology, transistor dimensions, and layout of the sense amplifiers, researchers are forced to rely on best guesses, impairing the fidelity of their studies. We aim to fill this gap between academia and industry for the first time by performing Scanning Electron Microscopy (SEM) with Focused Ion Beam (FIB) on recent commodity DDR4 and DDR5 DRAM chips from the three major vendors. This required us to adequately prepare the samples, identify the sensing area, and align images from the different FIB slices. Using the acquired images, we reverse engineer the circuits, measure transistor dimensions and extract physical layouts of sense amplifiers - all previously unavailable to researchers. Our findings show that the commonly assumed classical sense amplifier topology has been replaced with the more sophisticated offset-cancellation design by two of the three major DRAM vendors. Furthermore, the transistor dimensions of sense amplifiers and their revealed physical layouts are significantly different than what is assumed in existing literature. Given commodity DRAM, our analysis shows that the public DRAM models are up to 9 x inaccurate, and existing research has up to error when estimating the impact of the proposed changes. To enable high-fidelity DRAM research in the future, we open source our data, including the reverse engineered circuits and layouts.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了最后一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper4
- DRAMScope: Uncovering DRAM Microarchitecture and Characteristics by Issuing Memory CommandsHwayong Nam, Seungmin Baek, Minbok Wi, Michael Jaemin Kim 等ISCA 2024 · 被引用 19 次
- DejaVu: Why You Should Write to Your DRAM Rows Twice, CarefullyHaocong Luo, Ismail Emir Yüksel, Ataberk Olgun, Nisa Bostanci 等ISCA 2026 · 被引用 4 次
- PuDghost: Experimental Analysis of Computation Result Corruption in Processing-Using-Dram Operations on Real Dram Chips and Implications for Future SystemsDaichi Tokuda, Ismail Emir Yüksel, Tatsuya Kubo, Ataberk Olgun 等ISCA 2026 · 被引用 4 次
- Assassyn: A Unified Abstraction for Architectural Simulation and ImplementationJian Weng, Boyang Han, Derui Gao, Ruijie Gao 等ISCA 2025 · 被引用 1 次
它引用的顶会 Paper12
- SIMDRAM: a framework for bit-serial SIMD processing using DRAMNastaran Hajinazar, Geraldo F. Oliveira, Sven Gregorio, João Dinis Ferreira 等ASPLOS 2021 · 被引用 182 次
- ProTRR: Principled yet Optimal In-DRAM Target Row RefreshMichele Marazzi, Patrick Jattke, Flavien Solt, Kaveh RazaviS&P 2022 · 被引用 101 次
- ELP2IM: Efficient and Low Power Bitwise Operation Processing in DRAMXin Xin, Youtao Zhang, Jun YangHPCA 2020 · 被引用 84 次
- Uncovering In-DRAM RowHammer Protection Mechanisms: A New Methodology, Custom RowHammer Patterns, and ImplicationsHasan Hassan, Yahya Can Tugrul, Jeremie S. Kim, Victor van der Veen 等MICRO 2021 · 被引用 79 次
- CLR-DRAM: A Low-Cost DRAM Architecture Enabling Dynamic Capacity-Latency Trade-OffHaocong Luo, Taha Shahroodi, Hasan Hassan, Minesh Patel 等ISCA 2020 · 被引用 64 次
相关 Paper
- TRRespass: Exploiting the Many Sides of Target Row RefreshPietro Frigo, Emanuele Vannacci, Hasan Hassan, Victor van der Veen 等S&P 2020 · 被引用 274 次
- BLACKSMITH: Scalable Rowhammering in the Frequency DomainPatrick Jattke, Victor van der Veen, Pietro Frigo, Stijn Gunter 等S&P 2022 · 被引用 140 次
- Variable Read Disturbance: An Experimental Analysis of Temporal Variation in DRAM Read DisturbanceAtaberk Olgun, F. Nisa Bostanci, Ismail Emir Yüksel, Oguzhan Canpolat 等HPCA 2025 · 被引用 15 次
- REGA: Scalable Rowhammer Mitigation with Refresh-Generating ActivationsMichele Marazzi, Flavien Solt, Patrick Jattke, Kubo Takashi 等S&P 2023
- Predicting Future-System Reliability with a Component-Level DRAM Fault ModelJeageun Jung, Mattan ErezMICRO 2023 · 被引用 9 次
