# Low Precision Floating-point Arithmetic for High Performance FPGA-based CNN Acceleration

arXiv: https://arxiv.org/abs/2003.03852 · HTML: https://mlsanity.com/paper/2003.03852/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Feb 2020.

## Built on by (most cited first, 5 of 5)

- [Ultralytics YOLO Evolution: An Overview of YOLO27, YOLO26, YOLO11, YOLOv8, and YOLOv5 Object Detectors for Computer Vision and Pattern Recognition](https://mlsanity.com/paper/2510.09653/) (2025)
- [Neural Network Quantization for Microcontrollers: A Comprehensive Survey of Methods, Platforms, and Applications](https://mlsanity.com/paper/2508.15008/) (2025)
- [Number Systems for Deep Neural Network Architectures: A Survey](https://mlsanity.com/paper/2307.05035/) (2023)
- [CORDIC Is All You Need](https://mlsanity.com/paper/2503.11685/) (2025)
- [Resource-Efficient Automatic Software Vulnerability Assessment via Knowledge Distillation and Particle Swarm Optimization](https://mlsanity.com/paper/2508.02840/) (2025)

## Abstract (arXiv)

Low precision data representation is important to reduce storage size and memory access for convolutional neural networks (CNNs). Yet, existing methods have two major limitations: (1) requiring re-training to maintain accuracy for deep CNNs, and (2) needing 16-bit floating-point or 8-bit fixed-point for a good accuracy. In this paper, we propose a low precision (8-bit) floating-point (LPFP) quantization method for FPGA-based acceleration to overcome the above limitations. Without any re-training, LPFP finds an optimal 8-bit data representation with negligible top-1/top-5 accuracy loss (within 0.5%/0.3% in our experiments, respectively, and significantly better than existing methods for deep CNNs). Furthermore, we implement one 8-bit LPFP multiplication by one 4-bit multiply-adder (MAC) and one 3-bit adder, and therefore implement four 8-bit LPFP multiplications using one DSP slice of Xilinx Kintex 7 family (KC705 in this paper) while one DSP can implement only two 8-bit fixed-point multiplications. Experiments on six typical CNNs for inference show that on average, we improve throughput by 64.5x over Intel i9 CPU and by 1.5x over existing FPGA accelerators. Particularly for VGG16 and YOLO, compared to six recent FPGA accelerators, we improve average throughput by 3.5x and 27.5x and improve average throughput per DSP by 4.1x and 5x, respectively. To the best of our knowledge, this is the first in-depth study to simplify one multiplication for CNN inference to one 4-bit MAC and implement four multiplications within one DSP while maintaining comparable accuracy without any re-training.