Exploration of Unary Arithmetic-Based Matrix Multiply Units for Low Precision DL Accelerators

• URL: http://arxiv.org/abs/2602.00838v1
• Date: Sat, 31 Jan 2026 18:10:55 GMT
• Title: Exploration of Unary Arithmetic-Based Matrix Multiply Units for Low Precision DL Accelerators
• Abstract summary: General matrix multiplication (GEMM) is a fundamental operation in deep learning (DL)<n>Recent works have proposed novel unary GEMM designs as an alternative to conventional binary GEMM hardware.<n>We demonstrate how unary GEMM can be effectively used for energy-efficient compute in future edge AI accelerators.
• Score: 3.1197830253827026
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: General matrix multiplication (GEMM) is a fundamental operation in deep learning (DL). With DL moving increasingly toward low precision, recent works have proposed novel unary GEMM designs as an alternative to conventional binary GEMM hardware. A rigorous evaluation of recent unary and binary GEMM designs is needed to assess the potential of unary hardware for future DL compute. This paper focuses on unary GEMM designs for integer-based DL inference and performs a detailed evaluation of three latest unary design proposals, namely, uGEMM, tuGEMM and tubGEMM, by comparing them to a conventional binary GEMM. Rigorous post-synthesis evaluations beyond prior works are performed across varying bit-widths and matrix sizes to assess the designs' tradeoffs and determine optimal sweetspots. Further, we perform weight sparsity analysis across eight pretrained convolutional neural networks (CNNs) and the LLaMA2 large language model (LLM). In this work, we demonstrate how unary GEMM can be effectively used for energy-efficient compute in future edge AI accelerators.

Related papers

• MoEMB: Scaling Universal Multimodal Embeddings with Efficient Mixture-of-Experts Models [55.732137666068446]
  Universal multimodal embedding (UME) increasingly demands encoder's capacity for handling a broad range of tasks and modalities.<n>MoEMB scales UME along the expert axis through mixture-of-experts (MoE)<n>MoEMB surpasses TTE-based methods with >4x active parameters, using significantly less computes.
  arXiv  Detail & Related papers  (2026-09-08T12:29:50Z)
• 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)
• Nemotron-Flash: Towards Latency-Optimal Hybrid Small Language Models [97.55009021098554]
  This work aims to identify the key determinants of SLMs' real-device latency and offer generalizable principles and methodologies for SLM design and training.<n>We introduce a new family of hybrid SLMs, called Nemotron-Flash, which significantly advances the accuracy-efficiency frontier of state-of-the-art SLMs.
  arXiv  Detail & Related papers  (2025-11-24T08:46:36Z)
• Precoder Design in Multi-User FDD Systems with VQ-VAE and GNN [20.38676347543672]
  We build on previous work that successfully designed site-specific precoders based on a combination of Gaussian mixture models (GMMs) and graph neural networks (GNNs)<n>In this paper, by utilizing a vector quantized-variational autoencoder (VQ-VAE), we circumvent one of the key drawbacks of GMMs, i.e., the number of GMM components scales exponentially to the feedback bits.<n>In addition, the deep learning architecture of the VQ-VAE allows us to jointly train the GNN together with VQ-VAE along with pilot optimization forming an end
  arXiv  Detail & Related papers  (2025-10-10T15:55:18Z)
• Does Generative Retrieval Overcome the Limitations of Dense Retrieval? [117.49076770892583]
  Generative retrieval (GR) has emerged as a new paradigm in neural information retrieval.<n>We investigate how GR fundamentally diverges from dense retrieval (DR) in both learning objectives and representational capacity.
  arXiv  Detail & Related papers  (2025-09-26T09:38:01Z)
• Effective Clustering for Large Multi-Relational Graphs [14.055388501740326]
  Multi-relational graphs (MRGs) are an expressive data structure for modeling diverse interactions/relations among real objects (i.e., nodes)<n>In this paper, we present DEMM and DEMM+, two effective MRGC approaches to address the limitations above.
  arXiv  Detail & Related papers  (2025-08-24T14:51:38Z)
• Diagonally-Weighted Generalized Method of Moments Estimation for Gaussian Mixture Modeling [7.266474956854856]
  The diagonally-weighted GMM (DGMM) achieves a balance among statistical efficiency, computational complexity, and numerical stability.<n>We apply DGMM to study the parameter estimation problem for weakly separated heteroscedastic low-rank Gaussian mixtures.<n>In numerical studies, DGMM attains smaller estimation errors while requiring substantially shorter runtimes than MM and GMM.
  arXiv  Detail & Related papers  (2025-07-28T01:24:55Z)
• Panacea: Novel DNN Accelerator using Accuracy-Preserving Asymmetric Quantization and Energy-Saving Bit-Slice Sparsity [2.78181759570722]
  Low bit-precisions and their bit-slice sparsity have been studied to accelerate general matrix-multiplications (GEMM) during large-scale deep neural network (DNN) inferences.<n>Recent studies have actively utilized asymmetric quantization for activations without requiring additional operations.<n>This paper proposes an Asymmetrically-Quantized bit-Slice GEMM for the first time.
  arXiv  Detail & Related papers  (2024-12-13T11:44:09Z)
• SMPLer: Taming Transformers for Monocular 3D Human Shape and Pose Estimation [74.07836010698801]
  We propose an SMPL-based Transformer framework (SMPLer) to address this issue. SMPLer incorporates two key ingredients: a decoupled attention operation and an SMPL-based target representation. Extensive experiments demonstrate the effectiveness of SMPLer against existing 3D human shape and pose estimation methods.
  arXiv  Detail & Related papers  (2024-04-23T17:59:59Z)
• Understanding the Performance Horizon of the Latest ML Workloads with NonGEMM Workloads [1.4107658666233678]
  We conduct a performance analysis of 17 widely adopted ML models in Hugging Face and Torchvision.<n>Non-GEMM performance bottleneck accounts for 11.3% to 73.6% of total latency, on average.<n>We demystify the most dominant non-GEMM operators for each model and deployment software.
  arXiv  Detail & Related papers  (2024-04-17T22:44:22Z)
• Lighter, Better, Faster Multi-Source Domain Adaptation with Gaussian Mixture Models and Optimal Transport [5.492296610282042]
  We tackle Multi-Source Domain Adaptation (MSDA), a task in transfer learning where one adapts multiple heterogeneous, labeled source probability measures towards a different, unlabeled target measure. We propose a novel framework for MSDA, based on Optimal Transport (OT) and Gaussian Mixture Models (GMMs) We empirically evaluate our proposed methods on four benchmarks in image classification and fault diagnosis, showing that we improve over the prior art while being faster and involving fewer parameters.
  arXiv  Detail & Related papers  (2024-04-16T03:31:28Z)
• Large Multi-Modal Models (LMMs) as Universal Foundation Models for AI-Native Wireless Systems [57.41621687431203]
  Large language models (LLMs) and foundation models have been recently touted as a game-changer for 6G systems. This paper presents a comprehensive vision on how to design universal foundation models tailored towards the deployment of artificial intelligence (AI)-native networks.
  arXiv  Detail & Related papers  (2024-01-30T00:21:41Z)
• Adaptive Stochastic ADMM for Decentralized Reinforcement Learning in Edge Industrial IoT [106.83952081124195]
  Reinforcement learning (RL) has been widely investigated and shown to be a promising solution for decision-making and optimal control processes. We propose an adaptive ADMM (asI-ADMM) algorithm and apply it to decentralized RL with edge-computing-empowered IIoT networks. Experiment results show that our proposed algorithms outperform the state of the art in terms of communication costs and scalability, and can well adapt to complex IoT environments.
  arXiv  Detail & Related papers  (2021-06-30T16:49:07Z)
• Cauchy-Schwarz Regularized Autoencoder [68.80569889599434]
  Variational autoencoders (VAE) are a powerful and widely-used class of generative models. We introduce a new constrained objective based on the Cauchy-Schwarz divergence, which can be computed analytically for GMMs. Our objective improves upon variational auto-encoding models in density estimation, unsupervised clustering, semi-supervised learning, and face analysis.
  arXiv  Detail & Related papers  (2021-01-06T17:36:26Z)
• GAT-GMM: Generative Adversarial Training for Gaussian Mixture Models [29.42264360774606]
  Generative adversarial networks (GANs) learn the distribution of observed samples through a zero-sum game. We propose Gene Adversarial Gaussian Models (GAT-GMM), a minimax GANMs. We show that GAT-GMM can perform as well as the expectation-maximization algorithm in learning mixtures of two Gaussians.
  arXiv  Detail & Related papers  (2020-06-18T06:11:28Z)

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.