paper-with-me

Papers

CREW: Computation Reuse and Efficient Weight Storage for Hardware-accelerated MLPs and RNNs

2021-07-20 · Marc Riera, Jose-Maria Arnau, Antonio Gonzalez

Deep Neural Networks (DNNs) have achieved tremendous success for cognitive applications. The core operation in a DNN is the dot product between quantized inputs and weights. Prior works exploit the weight/input repetition that arises due to quantization to avoid redundant computations in Convolutional Neural Networks (CNNs). However, in this paper we show that their effectiveness is severely limited when applied to Fully-Connected (FC) layers, which are commonly used in state-of-the-art DNNs, as it is the case of modern Recurrent Neural Networks (RNNs) and Transformer models. To improve energy-efficiency of FC computation we present CREW, a hardware accelerator that implements Computation Reuse and an Efficient Weight Storage mechanism to exploit the large number of repeated weights in FC layers. CREW first performs the multiplications of the unique weights by their respective inputs and stores the results in an on-chip buffer. The storage requirements are modest due to the small number of unique weights and the relatively small size of the input compared to convolutional layers. Next, CREW computes each output by fetching and adding its required products. To this end, each weight is replaced offline by an index in the buffer of unique products. Indices are typically smaller than the quantized weights, since the number of unique weights for each input tends to be much lower than the range of quantized weights, which reduces storage and memory bandwidth requirements. Overall, CREW greatly reduces the number of multiplications and provides significant savings in model memory footprint and memory bandwidth usage. We evaluate CREW on a diverse set of modern DNNs. On average, CREW provides 2.61x speedup and 2.42x energy savings over a TPU-like accelerator. Compared to UCNN, a state-of-art computation reuse technique, CREW achieves 2.10x speedup and 2.08x energy savings on average.

📄 PDF Abstract BibTeX arXiv:2107.09408

Code (0)

등록된 구현이 없습니다.

Tasks

Quantization

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Residual Connection 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

Similar Papers 제목 키워드 기반

LUT Tensor Core: A Software-Hardware Co-Design for LUT-Based Low-Bit LLM Inference

2024-08-12 · Zhiwen Mo, Lei Wang, Jianyu Wei, Zhichen Zeng 외

As large language model (LLM) inference continues to demand increasing computational resources, there is a rapidly growing trend toward using low-bit weights to reduce memory footprint and improve inference efficiency. H…

Code GenerationLanguage ModellingLarge Language Model

SortScrews: A Dataset and Baseline for Real-time Screw Classification

2026-03-13 · Tianhao Fu, Bingxuan Yang, Juncheng Guo, Shrena Sribalan 외 arxiv

Automatic identification of screw types is important for industrial automation, robotics, and inventory management. However, publicly available datasets for screw classification are scarce, particularly for controlled si…

Transfer Learning

Deep Neural Networks Based Weight Approximation and Computation Reuse for 2-D Image Classification

2021-04-28 · Mohammed F. Tolba, Huruy Tekle Tesfai, Hani Saleh, Baker Mohammad 외

Deep Neural Networks (DNNs) are computationally and memory intensive, which makes their hardware implementation a challenging task especially for resource constrained devices such as IoT nodes. To address this challenge,…

image-classificationImage Classification

SmartDeal: Re-Modeling Deep Network Weights for Efficient Inference and Training

2021-01-04 · Xiaohan Chen, Yang Zhao, Yue Wang, Pengfei Xu 외

The record-breaking performance of deep neural networks (DNNs) comes with heavy parameterization, leading to external dynamic random-access memory (DRAM) for storage. The prohibitive energy of DRAM accesses makes it non-…

The Evolution of Raw Data Archiving and the Growth of Its Importance in Crystallography

2024-02-23 · John R. Helliwell, James R. Hester, Loes Kroon-Batenburg, Brian McMahon 외

The hardware for data archiving has expanded capacities for digital storage enormously in the past decade or more. This article charts the efforts of IUCr to facilitate discussions and plans relating to raw data archivin…