Exploration of Unary Arithmetic-Based Matrix Multiply Units for Low Precision DL Accelerators
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917239001710592 |
|---|---|
| author | Vellaisamy, Prabhu Nair, Harideep Wu, Di Blanton, Shawn Shen, John Paul |
| author_facet | Vellaisamy, Prabhu Nair, Harideep Wu, Di Blanton, Shawn Shen, John Paul |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_00838 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Exploration of Unary Arithmetic-Based Matrix Multiply Units for Low Precision DL Accelerators Vellaisamy, Prabhu Nair, Harideep Wu, Di Blanton, Shawn Shen, John Paul Hardware Architecture Artificial Intelligence 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. |
| title | Exploration of Unary Arithmetic-Based Matrix Multiply Units for Low Precision DL Accelerators |
| topic | Hardware Architecture Artificial Intelligence |
| url | https://arxiv.org/abs/2602.00838 |