paper-with-me

홈 › Papers

Hardware Complexity Aware Design Strategy for a Fused Logarithmic and Anti-Logarithmic Converter

2020-11-12 · Botao Xiong, Yuanfeng Sui

The logarithmic and anti-logarithmic converters are realized with the piecewise linear approximation method, which is implemented by the shift-and-add architecture. This brief utilizes the similarities of Log and Antilog functions so that the adder tree block and multiplexer block can be shared by the Log and Antilog converters. As a result, the Antilog function can be implemented by the Log converter at the cost of additional 14% area and 6% latency. It implies the shift-and-add architecture can approximate multiple similar nonlinear functions with a slightly hardware cost. In addition, this brief proposes a set of formulas to predict the area and latency of shift-and-add architecture with different quantized coefficients that can facilitate the finding of a trade-off point in the Latency-Area-Precision space.

📄 PDF Abstract BibTeX arXiv:2011.06341

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

HEAT: Hardware-Efficient Automatic Tensor Decomposition for Transformer Compression

2022-11-30 · Jiaqi Gu, Ben Keller, Jean Kossaifi, Anima Anandkumar 외

Transformers have attained superior performance in natural language processing and computer vision. Their self-attention and feedforward layers are overparameterized, limiting inference speed and energy efficiency. Tenso…

Efficient ExplorationKnowledge DistillationTensor Decomposition

Accelerating ViT Inference on FPGA through Static and Dynamic Pruning

2024-03-21 · Dhruv Parikh, Shouyi Li, Bingyi Zhang, Rajgopal Kannan 외

Vision Transformers (ViTs) have achieved state-of-the-art accuracy on various computer vision tasks. However, their high computational complexity prevents them from being applied to many real-world applications. Weight a…

HALOC: Hardware-Aware Automatic Low-Rank Compression for Compact Neural Networks

2023-01-20 · Jinqi Xiao, Chengming Zhang, Yu Gong, Miao Yin 외

Low-rank compression is an important model compression strategy for obtaining compact neural network models. In general, because the rank values directly determine the model complexity and model accuracy, proper selectio…

GPULow-rank compressionModel Compression

Hardware-Aware Graph Neural Network Automated Design for Edge Computing Platforms

2023-03-20 · Ao Zhou, Jianlei Yang, Yingjie Qi, Yumeng Shi 외

Graph neural networks (GNNs) have emerged as a popular strategy for handling non-Euclidean data due to their state-of-the-art performance. However, most of the current GNN model designs mainly focus on task accuracy, lac…

Edge-computingGPUGraph Neural NetworkNeural Architecture Search

Fused Bayesian Flow Networks for Dual-Target Molecular Design

2026-08-02 · Jingyuan Zhou, Shikui Tu, Lei Xu arxiv

Dual-target drug design aims to generate 3D molecules that can simultaneously interact with two target proteins, offering a promising route for discovering polypharmacological compounds against complex diseases. While re…