HE-PIM: Demystifying Homomorphic Operations on a Real-world Processing-in-Memory System

• URL: http://arxiv.org/abs/2605.12841v1
• Date: Wed, 13 May 2026 00:36:03 GMT
• Title: HE-PIM: Demystifying Homomorphic Operations on a Real-world Processing-in-Memory System
• Abstract summary: Homomorphic encryption (HE) enables computation over encrypted data, offering strong privacy guarantees for untrusted computing environments.<n>Practical adoption remains limited by high computational complexity, large ciphertext sizes, and substantial data movement.<n>Processing-In-Memory (PIM) is a promising mitigation by computing near or inside memory.
• Score: 12.932284199913944
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Homomorphic encryption (HE) enables computation over encrypted data, offering strong privacy guarantees for untrusted computing environments. Practical adoption remains limited by high computational complexity, large ciphertext sizes, and substantial data movement. Processor-centric architectures (CPUs, GPUs, ASICs) hit fundamental bottlenecks on HE workloads because ciphertexts are large, data locality is low, and primitives such as relinearization and bootstrapping repeatedly access large auxiliary metadata. Processing-In-Memory (PIM) is a promising mitigation by computing near or inside memory. Prior PIM proposals for HE either do not target real-world PIM systems or cover only a narrow set of operations. We comprehensively characterize HE operations on a real-world, general-purpose PIM system. We implement a complete set of HE kernels used by emerging applications (databases, machine learning) on the UPMEM PIM system, evaluate performance and scalability, compare against CPU and GPU baselines, and discuss implications for future PIM hardware. Our results demonstrate four major findings. (1) HE-based applications expose distinct bottlenecks across execution stages: some kernels are compute-bound due to modular arithmetic, while others are memory-bound due to large ciphertexts and intermediate data. These bottlenecks are exacerbated by limited per-core compute and per-bank capacity, which force frequent data movement. (2) The dominant compute bottleneck is the lack of native 64-bit modular integer multiplication, a key HE primitive. (3) Limited per-bank memory capacity is the second major bottleneck, since HE ciphertexts and auxiliary metadata do not fit and require inter-bank movement. (4) Despite these limits, PIM can be a viable alternative to state-of-the-art CPU and GPU systems for HE when equipped with native modular multiplication and efficient inter-PIM data movement.

Related papers

• LLM Inference in a Flash! [66.43896490006965]
  Large Language Models (LLMs) have shown impressive capabilities across a range of natural language processing tasks.<n>We present an end-to-end integer-only quantization approach to eliminate expensive floating-point computations.
  arXiv  Detail & Related papers  (2026-09-14T18:04:30Z)
• Taking Cryptography Out of the Data Path via Near-Memory Processing in DRAM [6.779726319389449]
  cryptographic algorithms such as AES-128 and SHA-256 are fundamental to ensuring data security and integrity.<n>Processing-in-Memory (PIM) has emerged as a promising architectural paradigm.<n>We investigate the potential and limitations of real-world PIM in accelerating cryptographic algorithms.
  arXiv  Detail & Related papers  (2026-05-19T16:06:03Z)
• CODA: Rewriting Transformer Blocks as GEMM-Epilogue Programs [48.961770224590204]
  CODA is a GPU kernel abstraction that expresses these computations as GEMM-plus-epilogue programs.<n>We show that CODA offers a practical path toward combining framework-level productivity with hardware-level efficiency.
  arXiv  Detail & Related papers  (2026-05-19T02:30:43Z)
• Understand and Accelerate Memory Processing Pipeline for Disaggregated LLM Inference [45.78442013449325]
  Large language models rely on efficient long-context processing and generation mechanisms to support complex reasoning.<n>We show that these optimizations can be unified into a four-step memory processing pipeline: Prepare Memory, Compute Relevancy, Retrieval, and Apply to Inference.<n>Motivated by this insight, we argue that textbfheterogeneous systems are well-suited to accelerate memory processing and thus end-to-end inference.
  arXiv  Detail & Related papers  (2026-03-30T21:03:39Z)
• DRAMatic Speedup: Accelerating HE Operations on a Processing-in-Memory System [4.464102544889846]
  Homomorphic encryption (HE) is a promising technology for confidential cloud computing.<n> processing-in-Memory (PIM) is an alternative hardware architecture that integrates processing units and memory on the same chip or memory module.<n>We present DRAMatic, which implements operations foundational to HE on UPMEM's programmable, general-purpose PIM system.
  arXiv  Detail & Related papers  (2026-02-12T21:45:15Z)
• Space Filling Curves is All You Need: Communication-Avoiding Matrix Multiplication Made Simple [42.09057806159106]
  General Matrix multiplication is the cornerstone of Deep Learning and HPC workloads.<n>Modern platforms with matrix multiplication accelerators exhibit high FLOP/Byte machine balance.<n>In this work we revisit space filling curves (SFC) to alleviate the problem of this cumbersome tuning.<n>We obtain platform-oblivious and shape-oblivious matrix-multiplication schemes that exhibit inherently high degree of data locality.
  arXiv  Detail & Related papers  (2026-01-22T19:56:16Z)
• Intra-DP: A High Performance Collaborative Inference System for Mobile Edge Computing [67.98609858326951]
  Intra-DP is a high-performance collaborative inference system optimized for deep neural networks (DNNs) on mobile devices.<n>It reduces per-inference latency by up to 50% and energy consumption by up to 75% compared to state-of-the-art baselines.<n>The evaluation demonstrates that Intra-DP reduces per-inference latency by up to 50% and energy consumption by up to 75% compared to state-of-the-art baselines.
  arXiv  Detail & Related papers  (2025-07-08T09:50:57Z)
• BiVM: Accurate Binarized Neural Network for Efficient Video Matting [56.000594826508504]
  Deep neural networks for real-time video matting suffer significant computational limitations on edge devices.<n>We present BiVM, an accurate and resource-efficient Binarized neural network for Video Matting.<n>BiVM surpasses alternative binarized video matting networks, including state-of-the-art (SOTA) binarization methods, by a substantial margin.
  arXiv  Detail & Related papers  (2025-07-06T16:32:37Z)
• Evaluating the Potential of In-Memory Processing to Accelerate Homomorphic Encryption [1.5707609236065612]
  homomorphic encryption (HE) allows computation without the need for decryption.<n>The high computational and memory overhead associated with the underlying cryptographic operations has hindered the practicality of HE-based solutions.<n> processing in-memory (PIM) presents a promising solution to this problem by bringing computation closer to data, thereby reducing the overhead resulting from processor-memory data movements.
  arXiv  Detail & Related papers  (2024-12-12T10:28:58Z)
• PhD Forum: Efficient Privacy-Preserving Processing via Memory-Centric Computing [0.0]
  Homomorphic encryption (HE) and secure multi-party computation (SMPC) enhance data security by enabling processing on encrypted data. Existing approaches focus on improving computational overhead using specialized hardware. We propose a framework that uses recently available PIM hardware to achieve efficient privacy-preserving computation.
  arXiv  Detail & Related papers  (2024-09-25T09:37:50Z)
• PIM-Opt: Demystifying Distributed Optimization Algorithms on a Real-World Processing-In-Memory System [21.09681871279162]
  Modern Machine Learning (ML) training on large-scale datasets is a time-consuming workload. It relies on the optimization algorithm Gradient Descent (SGD) due to its effectiveness, simplicity, and generalization performance. processor-centric architectures suffer from low performance and high energy consumption while executing ML training workloads. Processing-In-Memory (PIM) is a promising solution to alleviate the data movement bottleneck.
  arXiv  Detail & Related papers  (2024-04-10T17:00:04Z)
• FusionAI: Decentralized Training and Deploying LLMs with Massive Consumer-Level GPUs [57.12856172329322]
  We envision a decentralized system unlocking the potential vast untapped consumer-level GPU. This system faces critical challenges, including limited CPU and GPU memory, low network bandwidth, the variability of peer and device heterogeneity.
  arXiv  Detail & Related papers  (2023-09-03T13:27:56Z)
• Faster Secure Data Mining via Distributed Homomorphic Encryption [108.77460689459247]
  Homomorphic Encryption (HE) is receiving more and more attention recently for its capability to do computations over the encrypted field. We propose a novel general distributed HE-based data mining framework towards one step of solving the scaling problem. We verify the efficiency and effectiveness of our new framework by testing over various data mining algorithms and benchmark data-sets.
  arXiv  Detail & Related papers  (2020-06-17T18:14:30Z)

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.