PuDHammer: Experimental Analysis of Read Disturbance Effects of Processing-using-DRAM in Real DRAM Chips

• URL: http://arxiv.org/abs/2506.12947v1
• Date: Sun, 15 Jun 2025 19:17:50 GMT
• Title: PuDHammer: Experimental Analysis of Read Disturbance Effects of Processing-using-DRAM in Real DRAM Chips
• Authors: Ismail Emir Yuksel, Akash Sood, Ataberk Olgun, Oğuzhan Canpolat, Haocong Luo, F. Nisa Bostancı, Mohammad Sadrosadati, A. Giray Yağlıkçı, Onur Mutlu,
• Abstract summary: 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.<n>PuDHammer significantly exacerbates the read disturbance vulnerability, causing up to 158.58x reduction in the minimum hammer count required to induce the first bitflip.
• Score: 6.537810647501026
• License: http://creativecommons.org/licenses/by/4.0/
• 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).

Related papers

• Understanding RowHammer Under Reduced Refresh Latency: Experimental Analysis of Real DRAM Chips and Implications on Future Solutions [6.157443107603247]
  RowHammer is a read disturbance mechanism in DRAM where repeatedly accessing (hammering) a row of DRAM cells (DRAM row) induces bitflips in physically nearby DRAM rows (victim rows)<n>With newer DRAM chip generations, these mechanisms perform preventive refresh more aggressively and cause larger performance, energy, or area overheads.<n>We present the first rigorous experimental study on the interactions between refresh latency and RowHammer characteristics in real DRAM chips.<n>Our results show that Partial Charge Restoration for Aggressive Mitigation (PaCRAM) reduces the performance and energy overheads induced by five state-of-the-art RowHammer mitigation mechanisms with
  arXiv  Detail & Related papers  (2025-02-17T12:39:03Z)
• Mixture of Hidden-Dimensions Transformer [50.40325486463241]
  We study hidden dimension sparsity and observe that trained Transformers utilize only a small fraction of token dimensions.<n>We propose MoHD (Mixture of Hidden Dimensions), a sparse conditional activation architecture.<n>It achieves 1.7% higher performance with 50% fewer activation parameters and 3.7% higher performance with a 3x parameter expansion at constant activation cost.
  arXiv  Detail & Related papers  (2024-12-07T13:15:22Z)
• Enabling Efficient and Scalable DRAM Read Disturbance Mitigation via New Experimental Insights into Modern DRAM Chips [0.0]
  Storage density exacerbates DRAM read disturbance, a circuit-level vulnerability exploited by system-level attacks. Existing defenses are either ineffective or prohibitively expensive. This dissertation tackles two problems: 1) protecting DRAM-based systems becomes more expensive as technology scaling increases read disturbance vulnerability, and 2) many existing solutions depend on proprietary knowledge of DRAM internals.
  arXiv  Detail & Related papers  (2024-08-27T13:12:03Z)
• An Experimental Characterization of Combined RowHammer and RowPress Read Disturbance in Modern DRAM Chips [7.430668228518989]
  We characterize a pattern that combines RowHammer and RowPress in 84 real DDR4 DRAM chips from all three major DRAM manufacturers. Our results show that this combined RowHammer and RowPress pattern takes significantly smaller amount of time (up to 46.1% faster) to induce the first bitflip compared to the state-of-the-art RowPress pattern. Based on our results, we provide a key hypothesis that the read disturbance effect caused by RowPress from one of the two aggressor rows in a double-sided pattern is much more significant than the other.
  arXiv  Detail & Related papers  (2024-06-18T21:57:45Z)
• RelayAttention for Efficient Large Language Model Serving with Long System Prompts [59.50256661158862]
  This paper aims to improve the efficiency of LLM services that involve long system prompts. handling these system prompts requires heavily redundant memory accesses in existing causal attention algorithms. We propose RelayAttention, an attention algorithm that allows reading hidden states from DRAM exactly once for a batch of input tokens.
  arXiv  Detail & Related papers  (2024-02-22T18:58:28Z)
• HiRE: High Recall Approximate Top-$k$ Estimation for Efficient LLM Inference [68.59839755875252]
  HiRE comprises of two novel components: (i) a compression scheme to cheaply predict top-$k$ rows/columns with high recall, followed by full computation restricted to the predicted subset, and (ii) DA-TOP-$k$: an efficient multi-device approximate top-$k$ operator. We demonstrate that on a one billion parameter model, HiRE applied to both the softmax as well as feedforward layers, achieves almost matching pretraining and downstream accuracy, and speeds up inference latency by $1.47times$ on a single TPUv5e device.
  arXiv  Detail & Related papers  (2024-02-14T18:04:36Z)
• Read Disturbance in High Bandwidth Memory: A Detailed Experimental Study on HBM2 DRAM Chips [6.501197729222095]
  We experimentally demonstrate the effects of read disturbance (RowHammer and RowPress) and uncover the inner workings of undocumented read disturbance defense mechanisms in High Bandwidth Memory (HBM) Detailed characterization of six real2 DRAM chips in two different FPGA boards shows that the read disturbance vulnerability significantly varies between different2 chips. We describe how our findings could be leveraged to develop more powerful read disturbance attacks and more efficient defense mechanisms.
  arXiv  Detail & Related papers  (2023-10-23T08:01:48Z)
• HyperAttention: Long-context Attention in Near-Linear Time [78.33061530066185]
  We present an approximate attention mechanism named HyperAttention to address the computational challenges posed by the growing complexity of long contexts. Empirically, employing Locality Sensitive Hashing (LSH) to identify large entries, HyperAttention outperforms existing methods. We validate the empirical performance of HyperAttention on a variety of different long-context length datasets.
  arXiv  Detail & Related papers  (2023-10-09T17:05:25Z)
• DISTFLASHATTN: Distributed Memory-efficient Attention for Long-context LLMs Training [82.06732962485754]
  FlashAttention effectively reduces the quadratic peak memory usage to linear in training transformer-based large language models (LLMs) on a single GPU. We introduce DISTFLASHATTN, a memory-efficient attention mechanism optimized for long-context LLMs training. It achieves 1.67x and 1.26 - 1.88x speedup compared to recent Ring Attention and DeepSpeed-Ulysses.
  arXiv  Detail & Related papers  (2023-10-05T03:47:57Z)
• RowPress: Amplifying Read Disturbance in Modern DRAM Chips [7.046976177695823]
  RowPress breaks memory isolation by keeping a DRAM row open for a long period of time. In extreme cases, RowPress induces bitflips in a DRAM row when an adjacent row is activated only once. Our detailed characterization of 164 real DDR4 DRAM chips shows that RowPress affects chips from all three major DRAM manufacturers.
  arXiv  Detail & Related papers  (2023-06-29T16:09:56Z)
• DBA: Efficient Transformer with Dynamic Bilinear Low-Rank Attention [53.02648818164273]
  We present an efficient yet effective attention mechanism, namely the Dynamic Bilinear Low-Rank Attention (DBA) DBA compresses the sequence length by input-sensitive dynamic projection matrices and achieves linear time and space complexity. Experiments over tasks with diverse sequence length conditions show that DBA achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2022-11-24T03:06:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.