ReCross: Efficient Embedding Reduction Scheme for In-Memory Computing using ReRAM-Based Crossbar

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Lai, Yu-Hong, Tsai, Chieh-Lin, Lim, Wen Sheng, Hu, Han-Wen, Kuo, Tei-Wei, Chang, Yuan-Hao
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909785908051968
author Lai, Yu-Hong
Tsai, Chieh-Lin
Lim, Wen Sheng
Hu, Han-Wen
Kuo, Tei-Wei
Chang, Yuan-Hao
author_facet Lai, Yu-Hong
Tsai, Chieh-Lin
Lim, Wen Sheng
Hu, Han-Wen
Kuo, Tei-Wei
Chang, Yuan-Hao
contents Deep learning-based recommendation models (DLRMs) are widely deployed in commercial applications to enhance user experience. However, the large and sparse embedding layers in these models impose substantial memory bandwidth bottlenecks due to high memory access costs and irregular access patterns, leading to increased inference time and energy consumption. While resistive random access memory (ReRAM) based crossbars offer a fast and energy-efficient solution through in-memory embedding reduction operations, naively mapping embeddings onto crossbar arrays leads to poor crossbar utilization and thus degrades performance. We present ReCross, an efficient ReRAM-based in-memory computing (IMC) scheme designed to minimize execution time and enhance energy efficiency in DLRM embedding reduction. ReCross co-optimizes embedding access patterns and ReRAM crossbar characteristics by intelligently grouping and mapping co-occurring embeddings, replicating frequently accessed embeddings across crossbars, and dynamically selecting in-memory processing operations using a newly designed dynamic switch ADC circuit that considers runtime energy trade-offs. Experimental results demonstrate that ReCross achieves a 3.97x reduction in execution time and a 6.1x improvement in energy efficiency compared to state-of-the-art IMC approaches.
format Preprint
id arxiv_https___arxiv_org_abs_2509_10627
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ReCross: Efficient Embedding Reduction Scheme for In-Memory Computing using ReRAM-Based Crossbar
Lai, Yu-Hong
Tsai, Chieh-Lin
Lim, Wen Sheng
Hu, Han-Wen
Kuo, Tei-Wei
Chang, Yuan-Hao
Hardware Architecture
Emerging Technologies
Deep learning-based recommendation models (DLRMs) are widely deployed in commercial applications to enhance user experience. However, the large and sparse embedding layers in these models impose substantial memory bandwidth bottlenecks due to high memory access costs and irregular access patterns, leading to increased inference time and energy consumption. While resistive random access memory (ReRAM) based crossbars offer a fast and energy-efficient solution through in-memory embedding reduction operations, naively mapping embeddings onto crossbar arrays leads to poor crossbar utilization and thus degrades performance. We present ReCross, an efficient ReRAM-based in-memory computing (IMC) scheme designed to minimize execution time and enhance energy efficiency in DLRM embedding reduction. ReCross co-optimizes embedding access patterns and ReRAM crossbar characteristics by intelligently grouping and mapping co-occurring embeddings, replicating frequently accessed embeddings across crossbars, and dynamically selecting in-memory processing operations using a newly designed dynamic switch ADC circuit that considers runtime energy trade-offs. Experimental results demonstrate that ReCross achieves a 3.97x reduction in execution time and a 6.1x improvement in energy efficiency compared to state-of-the-art IMC approaches.
title ReCross: Efficient Embedding Reduction Scheme for In-Memory Computing using ReRAM-Based Crossbar
topic Hardware Architecture
Emerging Technologies
url https://arxiv.org/abs/2509.10627