.png){kind=icon}
返回
Efficient Approximate Posit Multipliers for Deep Learning Computation
.png){kind=icon}
PRE
AI
DOI：10.1109/JETCAS.2022.3231642.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Posit numeric format is getting more and more attention in recent years. Its tapered precision makes it especially suitable in many applications including deep learning computation. However, due to its dynamic component bit-width, the cost of implementing posit arithmetic in hardware is more expensive than its floating-point counterpart. To solve this cost problem, in this paper, posit multipliers with approximate computing features are proposed. The core idea of the proposed design is to truncate the fraction multiplier according to the estimated fraction bit-width of the product. So that the resource consumption of the fraction multiplier and thus the fraction adder can be significantly reduced. The proposed method is applied in both linear domain and logarithm domain posit multipliers. The 8/16/32-bit version of the proposed approximate posit multipliers are implemented and analyzed. For the commonly used 16-bit posit format in deep learning computation, the proposed approximate posit multiplier can consume 16% less power compared to the conventional posit multiplier design. The proposed 16-bit approximate logarithm multiplier can achieve a 15% improvement in terms of power consumption compared to the state-of-the-art posit approximate logarithm multiplier. The proposed 16-bit approximate posit multipliers are applied in the computation of several deep neural network models and significant improvements on energy efficiency can be achieved with negligible accuracy degradation.
Keyword:
Deep learning
Arithmetic
Standards
Hardware
Computational efficiency
Circuits and systems
Approximate computing
Posit multiplier
deep learning computation
approximate computing
Booth multiplier
logarithm multiplier
期刊
IF:
3.8
论文数:
1.4K
被引数:
2.8K
机构
引用论文
.png){kind=icon}
Do Perceptions of Competence Mediate The Relationship Between Fundamental Motor Skill Proficiency and Physical Activity Levels of Children in Kindergarten?能力的感知是否可以介导幼儿园儿童的基本运动技能熟练程度与身体活动水平之间的关系？
PREAI
分享收藏分享收藏The power of obfuscation techniques in malicious JavaScript code: A measurement study恶意JavaScript代码中混淆技术的功能: 一项测量研究
OAAI
OAAI分享收藏Carbon Foam with In Situ Fe-Catalyzed Dense CNT@Graphite Core-Shell Fiber on Skeletons for High-Performance Radar-Infrared Stealth具有原位Fe催化致密CNT@石墨核壳纤维骨架的碳泡沫，用于高性能雷达-红外隐身
PREAI
分享收藏
查看更多内容