CRAM-ER: Error-Resilient Spintronic Computational Random Access Memory for Scalable In-Memory Computation

• URL: http://arxiv.org/abs/2606.02781v1
• Date: Mon, 01 Jun 2026 18:45:05 GMT
• Title: CRAM-ER: Error-Resilient Spintronic Computational Random Access Memory for Scalable In-Memory Computation
• Abstract summary: We propose an error-resilient CRAM (CRAM-ER) architecture for scalable in-memory matrix-vector multiplications (MVMs)<n> Evaluations of the CMOS+spintronic hybrid architecture on DNN benchmarks show near-lossless accuracy while reducing CRAM latency by up to 2 orders of magnitude.
• Score: 5.851126867333842
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deep neural networks (DNNs) have achieved state-of-the-art performance across diverse domains. However, typical Von Neumann compute paradigms face severe memory bottlenecks. Emerging near-memory and compute-in-memory approaches alleviate this but incur significant peripheral overhead. Computational Random Access Memory (CRAM) based on MRAM enables in-situ logic without peripheral overhead, offering a dense, energy-efficient solution. However, probabilistic MRAM switching induces gate-level errors that limit the scalability and reliability of CRAM for accelerating DNN. Moreover, the large number of sequential MRAM writes severely constrains CRAM throughput. To address these challenges, we propose an error-resilient CRAM (CRAM-ER) architecture for scalable in-memory matrix-vector multiplications (MVMs). Our error-aware hardware-software co-design framework leverages a hybrid spintronic-CRAM + CMOS adder-tree architecture to mitigate the impact of device-level errors, demonstrating MVM functionality with high area and energy efficiency. We further develop an error-aware model fine-tuning and fine-grained error correction for enhanced error resilience. Evaluations of the CMOS+spintronic hybrid architecture on DNN benchmarks show near-lossless accuracy while reducing CRAM latency by up to 2 orders of magnitude, outperforming CPU/GPU+high-bandwidth DRAM in both energy efficiency and energy-delay product.

Related papers

• Memory Caching: RNNs with Growing Memory [56.25483647131372]
  We introduce Memory Caching (MC), a technique that enhances recurrent models by caching checkpoints of memory states (a.k.a. hidden states)<n>We propose four variants of MC, including gated aggregation and sparse selective mechanisms, and discuss their implications on both linear and deep memory modules.<n>The results indicate that while Transformers achieve the best accuracy, our MC variants show competitive performance, close the gap with Transformers, and performs better than state-of-the-art recurrent models.
  arXiv  Detail & Related papers  (2026-02-27T18:53:41Z)
• Decoder-Hybrid-Decoder Architecture for Efficient Reasoning with Long Generation [108.0657508755532]
  We introduce the Gated Memory Unit (GMU), a simple yet effective mechanism for efficient memory sharing across layers.<n>We apply it to create SambaY, a decoder-hybrid-decoder architecture that incorporates GMUs to share memory readout states from a Samba-based self-decoder.
  arXiv  Detail & Related papers  (2025-07-09T07:27:00Z)
• Hardware-software co-exploration with racetrack memory based in-memory computing for CNN inference in embedded systems [54.045712360156024]
  racetrack memory is a non-volatile technology that allows high data density fabrication.<n>In-memory arithmetic circuits with memory cells affects both the memory density and power efficiency.<n>We present an efficient in-memory convolutional neural network (CNN) accelerator optimized for use with racetrack memory.
  arXiv  Detail & Related papers  (2025-07-02T07:29:53Z)
• A distillation-teleportation protocol for fault-tolerant QRAM [95.99192129224721]
  We present a protocol for fault-tolerantly implementing the logical quantum random access memory (QRAM) operation.<n>For coherently accessing classical memories of size $2n$, our protocol consumes only $mathrmpoly(n)$ fault-tolerant quantum resources.
  arXiv  Detail & Related papers  (2025-05-26T17:42:56Z)
• Efficient and accurate neural field reconstruction using resistive memory [52.68088466453264]
  Traditional signal reconstruction methods on digital computers face both software and hardware challenges. We propose a systematic approach with software-hardware co-optimizations for signal reconstruction from sparse inputs. This work advances the AI-driven signal restoration technology and paves the way for future efficient and robust medical AI and 3D vision applications.
  arXiv  Detail & Related papers  (2024-04-15T09:33:09Z)
• Experimental demonstration of magnetic tunnel junction-based computational random-access memory [4.640906373267124]
  "Computational random-access memory (CRAM) has emerged to address this fundamental limitation" CRAM performs logic operations directly using the memory cells themselves, without having the data ever leave the memory. Technology could have a significant impact on power- and energy-demanding applications of machine intelligence.
  arXiv  Detail & Related papers  (2023-12-21T19:28:54Z)
• Evaluation of STT-MRAM as a Scratchpad for Training in ML Accelerators [9.877596714655096]
  Training deep neural networks (DNNs) is an extremely memory-intensive process. Spin-Transfer-Torque MRAM (STT-MRAM) offers several desirable properties for training accelerators. We show that MRAM provide up to 15-22x improvement in system level energy.
  arXiv  Detail & Related papers  (2023-08-03T20:36:48Z)
• TL-nvSRAM-CIM: Ultra-High-Density Three-Level ReRAM-Assisted Computing-in-nvSRAM with DC-Power Free Restore and Ternary MAC Operations [8.669532093397065]
  This work proposes an ultra-high-density three-level ReRAMs-assisted computing scheme for large NN models. The proposed TL-nvSRAM-CIM achieves 7.8x higher storage density, compared with the state-art works.
  arXiv  Detail & Related papers  (2023-07-06T01:46:06Z)
• Pex: Memory-efficient Microcontroller Deep Learning through Partial Execution [11.336229510791481]
  We discuss a novel execution paradigm for microcontroller deep learning. It modifies the execution of neural networks to avoid materialising full buffers in memory. This is achieved by exploiting the properties of operators, which can consume/produce a fraction of their input/output at a time.
  arXiv  Detail & Related papers  (2022-11-30T18:47:30Z)
• Improving Inference Lifetime of Neuromorphic Systems via Intelligent Synapse Mapping [0.2578242050187029]
  An RRAM cell can switch its state after reading its content a certain number of times. We propose an architectural solution to extend the read endurance of RRAM-based neuromorphic systems.
  arXiv  Detail & Related papers  (2021-06-16T20:12:47Z)
• Parallelising the Queries in Bucket Brigade Quantum RAM [69.43216268165402]
  Quantum algorithms often use quantum RAMs (QRAM) for accessing information stored in a database-like manner. We show a systematic method to significantly reduce the effective query time by using Clifford+T gate parallelism. We conclude that, in theory, fault-tolerant bucket brigade quantum RAM queries can be performed approximately with the speed of classical RAM.
  arXiv  Detail & Related papers  (2020-02-21T14:50:03Z)

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.