mlsanityData to 14 Oct 2026

A Modern Primer on Processing in Memory

arXiv 2012.03112 ↗First posted 5 Dec 2020cs.AR cs.DCcited by 32

Not on the map. Why?

Abstract (arXiv)

This paper discusses recent research that aims to enable computation close to data, an approach we broadly call processing-in-memory (PIM). PIM places computation mechanisms in or near where the data is stored (i.e., inside memory chips or modules, in the logic layer of 3D-stacked memory, in the memory controllers, in storage devices or chips), so that data movement between the computation units and memory/storage units is reduced or eliminated. While the general idea of PIM is not new, we discuss motivating trends in applications as well as memory circuits and technology that greatly exacerbate the need for enabling it in modern computing systems. We examine at least two promising new approaches to designing PIM systems to accelerate important data-intensive applications: (1) processing-using-memory, which exploits fundamental analog operational principles of memory chips to perform massively-parallel operations in-situ in memory, (2) processing-near-memory, which exploits different logic and memory integration technologies (e.g., 3D-stacked memory technology) to place computation logic close to memory circuitry, and thereby enable high-bandwidth, low-energy, and low-latency access to data. In both approaches, we describe and tackle relevant cross-layer research, design, and adoption challenges in devices, architecture, systems, compilers, programming models, and applications. Our focus is on the development of PIM designs that can be adopted in real computing platforms at low cost. We conclude by discussing work on solving key challenges to the practical adoption of PIM. We believe that the shift from a processor-centric to a memory-centric mindset (and infrastructure) remains the largest adoption challenge for PIM, which, once overcome, can unleash a fundamentally energy-efficient, high-performance, and sustainable new way of designing, using, and programming computing systems.

Key facts. Cited by 32 papers in the map (data through 14 Oct 2026). First posted on arXiv 5 Dec 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 6; 2023: 5; 2024: 8; 2025: 7; 2026: 6.

32 papers.

Sort:

By area:

  1. 2024Demystifying Chains, Trees, and Graphs of Thoughtscited by 63
  2. 2022Parallel and Distributed Graph Neural Networks: An In-Depth Concurrency Analysiscited by 29
  3. 2025PAPI: Exploiting Dynamic Parallelism in Large Language Model Decoding with a Processing-In-Memory-Enabled Computing Systemcited by 20
  4. 2023Design Principles for Lifelong Learning AI Acceleratorscited by 9
  5. 2022Accelerating Neural Network Inference with Processing-in-DRAM: From the Edge to the Cloudcited by 5
  6. 2024Hyperdimensional Representation Learning for Node Classification and Link Predictioncited by 5
  7. 2024PIM-Opt: Demystifying Distributed Optimization Algorithms on a Real-World Processing-In-Memory Systemcited by 5
  8. 2024PIMphony: Overcoming Bandwidth and Capacity Inefficiency in PIM-based Long-Context LLM Inference Systemcited by 5
  9. 2022Machine Learning Training on a Real Processing-in-Memory Systemcited by 4
  10. 2024Demystifying Higher-Order Graph Neural Networkscited by 4
  11. 2025Open3DBench: Open-Source Benchmark for 3D-IC Backend Implementation and PPA Evaluationcited by 4
  12. 2024PyGim: An Efficient Graph Neural Network Library for Real Processing-In-Memory Architecturescited by 3
20 more
  1. 2025CHIME: Chiplet-based Heterogeneous Near-Memory Acceleration for Edge Multimodal LLM Inferencecited by 3
  2. 2022An Experimental Evaluation of Machine Learning Training on a Real Processing-in-Memory Systemcited by 2
  3. 2024SwiftRL: Towards Efficient Reinforcement Learning on Real Processing-In-Memory Systemscited by 2
  4. 2022EcoFlow: Efficient Convolutional Dataflows for Low-Power Neural Network Acceleratorscited by 1
  5. 2022Heterogeneous Data-Centric Architectures for Modern Data-Intensive Applications: Case Studies in Machine Learning and Databasescited by 1
  6. 2023TransPimLib: A Library for Efficient Transcendental Functions on Processing-in-Memory Systemscited by 1
  7. 2023Comprehensive Benchmarking of Binary Neural Networks on NVM Crossbar Architecturescited by 1
  8. 2023WWW: What, When, Where to Compute-in-Memorycited by 1
  9. 2025Assessing Tenstorrent's RISC-V MatMul Acceleration Capabilitiescited by 1
  10. 2025AIM: Software and Hardware Co-design for Architecture-level IR-drop Mitigation in High-performance PIMcited by 1
  11. 2026Physical Foundation Models: Fixed hardware implementations of large-scale neural networkscited by 1
  12. 2023NicePIM: Design Space Exploration for Processing-In-Memory DNN Accelerators with 3D-Stacked-DRAMcited by 0
  13. 2024Prospective Messaging: Learning in Networks with Communication Delayscited by 0
  14. 2025A Data Aggregation Visualization System supported by Processing-in-Memorycited by 0
  15. 2025DCC: Data-Centric Compilation of Machine Learning Kernels for Processing-In-Memory Architecturescited by 0
  16. 2026Machine Learning-Driven Intelligent Memory System Design: From On-Chip Caches to Storagecited by 0
  17. 2026NasZip: Software and Hardware Co-Design to Accelerate Approximate Nearest Neighbor Search with DIMM-Based Near-Data Processingcited by 0
  18. 2026Leveraging ECRAM for Edge Continual Learningcited by 0
  19. 2026RED-PIM: Reducing Data Movement for Transformers using Processing-in-Memorycited by 0
  20. 2026You Only Charge Once 2.0 : A End-to-End Analog Computing-in-Memory Architecture with Reconfigurable Switched Capacitorscited by 0