mlsanityData to 14 Oct 2026

TensorDIMM: A Practical Near-Memory Processing Architecture for Embeddings and Tensor Operations in Deep Learning

arXiv 1908.03072 ↗First posted 8 Aug 2019cs.LG cs.AR cs.DCcited by 43

Not on the map. Why?

Abstract (arXiv)

Recent studies from several hyperscalars pinpoint to embedding layers as the most memory-intensive deep learning (DL) algorithm being deployed in today's datacenters. This paper addresses the memory capacity and bandwidth challenges of embedding layers and the associated tensor operations. We present our vertically integrated hardware/software co-design, which includes a custom DIMM module enhanced with near-data processing cores tailored for DL tensor operations. These custom DIMMs are populated inside a GPU-centric system interconnect as a remote memory pool, allowing GPUs to utilize for scalable memory bandwidth and capacity expansion. A prototype implementation of our proposal on real DL systems shows an average 6.2-17.6x performance improvement on state-of-the-art recommender systems.

Key facts. Cited by 43 papers in the map (data through 14 Oct 2026). First posted on arXiv 8 Aug 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 5; 2022: 10; 2023: 7; 2024: 12; 2025: 4; 2026: 5.

43 papers.

Sort:

By area:

  1. 2021RecSSD: Near Data Processing for Solid State Drive Based Recommendation Inferencecited by 35
  2. 2022A Comprehensive Survey on Trustworthy Recommender Systemscited by 32
  3. 2024Tender: Accelerating Large Language Models via Tensor Decomposition and Runtime Requantizationcited by 28
  4. 2024Smart-Infinity: Fast Large Language Model Training using Near-Storage Processing on a Real Systemcited by 15
  5. 2023MAD Max Beyond Single-Node: Enabling Large Machine Learning Model Acceleration on Distributed Systemscited by 14
  6. 2022Heterogeneous Acceleration Pipeline for Recommendation System Trainingcited by 13
  7. 2022SmartSAGE: Training Large-scale Graph Neural Networks using In-Storage Processing Architecturescited by 13
  8. 2022Sparse Attention Acceleration with Synergistic In-Memory Pruning and On-Chip Recomputationcited by 12
  9. 2022Training Personalized Recommendation Systems from (GPU) Scratch: Look Forward not Backwardscited by 11
  10. 2021GradPIM: A Practical Processing-in-DRAM Architecture for Gradient Descentcited by 10
  11. 2023G10: Enabling An Efficient Unified GPU Memory and Storage Architecture with Smart Tensor Migrationscited by 10
  12. 2023MP-Rec: Hardware-Software Co-Design to Enable Multi-Path Recommendationcited by 9
31 more
  1. 2021RecPipe: Co-designing Models and Hardware to Jointly Optimize Recommendation Quality and Performancecited by 8
  2. 2021GNNear: Accelerating Full-Batch Training of Graph Neural Networks with Near-Memory Processingcited by 6
  3. 2023Instant-NeRF: Instant On-Device Neural Radiance Field Training via Algorithm-Accelerator Co-Designed Near-Memory Processingcited by 6
  4. 2022GROW: A Row-Stationary Sparse-Dense GEMM Accelerator for Memory-Efficient Graph Convolutional Neural Networkscited by 5
  5. 2024PIM-Opt: Demystifying Distributed Optimization Algorithms on a Real-World Processing-In-Memory Systemcited by 5
  6. 2022DiVa: An Accelerator for Differentially Private Machine Learningcited by 4
  7. 2023ACCL+: an FPGA-Based Collective Engine for Distributed Applicationscited by 3
  8. 2024PyGim: An Efficient Graph Neural Network Library for Real Processing-In-Memory Architecturescited by 3
  9. 2025Toward Robust and Efficient ML-Based GPU Caching for Modern Inferencecited by 3
  10. 2022An Experimental Evaluation of Machine Learning Training on a Real Processing-in-Memory Systemcited by 2
  11. 2024PreSto: An In-Storage Data Preprocessing System for Training Recommendation Modelscited by 2
  12. 2024Debunking the CUDA Myth Towards GPU-based AI Systemscited by 2
  13. 2022EcoFlow: Efficient Convolutional Dataflows for Low-Power Neural Network Acceleratorscited by 1
  14. 2022Heterogeneous Data-Centric Architectures for Modern Data-Intensive Applications: Case Studies in Machine Learning and Databasescited by 1
  15. 2023Failure Tolerant Training with Persistent Memory Disaggregation over CXLcited by 1
  16. 2024PIFS-Rec: Process-In-Fabric-Switch for Large-Scale Recommendation System Inferencescited by 1
  17. 2024Disaggregating Embedding Recommendation Systems with FlexEMRcited by 1
  18. 2025Cocoon: A System Architecture for Differentially Private Training with Correlated Noisescited by 1
  19. 2026LOCALUT: Harnessing Capacity-Computation Tradeoffs for LUT-Based Inference in DRAM-PIMcited by 1
  20. 2021Continual Learning Approach for Improving the Data and Computation Mapping in Near-Memory Processing Systemcited by 0
  21. 2023Hera: A Heterogeneity-Aware Multi-Tenant Inference Server for Personalized Recommendationscited by 0
  22. 2024ProactivePIM: Accelerating Weight-Sharing Embedding Layer with PIM for Scalable Recommendation Systemcited by 0
  23. 2024ElasticRec: A Microservice-based Model Serving Architecture Enabling Elastic Resource Scaling for Recommendation Modelscited by 0
  24. 2024The Function-Representation Model of Computationcited by 0
  25. 2024Pushing the Performance Envelope of DNN-based Recommendation Systems Inference on GPUscited by 0
  26. 2025SCRec: A Scalable Computational Storage System with Statistical Sharding and Tensor-train Decomposition for Recommendation Modelscited by 0
  27. 2025DCC: Data-Centric Compilation of Machine Learning Kernels for Processing-In-Memory Architecturescited by 0
  28. 2026A Scheduling Framework for Efficient MoE Inference on Edge GPU-NDP Systemscited by 0
  29. 2026AMMA: A Multi-Chiplet Memory-Centric Architecture for Low-Latency 1M Context Attention Servingcited by 0
  30. 2026TokenStack: A Heterogeneous HBM-PIM Architecture and Runtime for Efficient LLM Inferencecited by 0
  31. 2026PATTON: Enabling Commodity PIM for Production LLM Servingcited by 0