当前位置: X-MOL 学术IEEE Trans. Circuit Syst. II Express Briefs › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
AxBMs: Approximate Radix-8 Booth Multipliers for High-Performance FPGA-Based Accelerators
IEEE Transactions on Circuits and Systems II: Express Briefs ( IF 4.0 ) Pub Date : 2021-03-11 , DOI: 10.1109/tcsii.2021.3065333
Haroon Waris , Chenghua Wang , Weiqiang Liu , Fabrizio Lombardi

The focus of existing designs on approximate radix-8 Booth multipliers has been on ASIC-based platforms. These multipliers are based on an approximation as defined for ASIC-based systems, so they cannot achieve comparable performance gains when used for FPGA-based hardware accelerators. This is due to the inherited architectural differences between FPGAs and ASICs. This brief bridges this gap by proposing high-performance approximate radix-8 Booth multipliers whose designs target FPGA-based systems. Hence, two approximate radix-8 Booth multipliers (referred to as AxBM1 and AxBM2) are proposed. Approximation is implemented such that the 6-input lookup table (LUT) and the associated carry chains of the FPGAs are fully utilized. AxBM2 exhibits 49% improvement in delay compared to the previous best FPGA-targeted design (Booth-Approx). AxBM2 has the advantage of complementing errors; this feature has been combined with truncation to achieve up to 60% in energy savings. Moreover, the resolution of the previous state-of-the-art error-energy Pareto front is improved, such that better energy gains can be achieved for a given error constraint. As a case study, the proposed multipliers are applied to the application of Sobel edge detection, AxBM2 detected 98.45% edges with energy savings of 26.41%.

中文翻译:

AxBM:用于高性能基于FPGA的加速器的近似Radix-8展台乘法器

现有设计对基数为8的近似Booth乘法器的关注点一直在基于ASIC的平台上。这些乘法器基于为基于ASIC的系统定义的近似值,因此当用于基于FPGA的硬件加速器时,它们无法实现可比的性能提升。这是由于FPGA和ASIC之间继承的体系结构差异。通过提供高性能的基数为8的Booth乘法器,本文简要介绍了这种差距,该乘法器的设计针对基于FPGA的系统。因此,提出了两个近似的基数为8的Booth乘数(称为AxBM1和AxBM2)。实现逼近,以便充分利用6输入查找表(LUT)和FPGA的相关进位链。与以前的最佳FPGA定位设计(Booth-Approx)相比,AxBM2的延迟提高了49%。AxBM2具有弥补错误的优势;此功能与截断功能相结合,可节省多达60%的能源。此外,改进了先前的最新的误差能量帕累托前沿的分辨率,从而对于给定的误差约束可以实现更好的能量增益。作为案例研究,所提出的乘法器被应用于Sobel边缘检测的应用中,AxBM2检测到98.45%的边缘,节能26.41%。
更新日期:2021-05-04
down
wechat
bug