QIAD: A quadratic interpolation approximate divider

抄録

The balance between computational performance and power consumption is a key constraint in computing systems, with integrated circuit technology posing a bottleneck. Approximate computation can trade off accuracy for performance or power improvement in error-tolerant scenarios. Division, with high computational demands and latency, is a bottleneck for computational efficiency. We propose a quadratic interpolation approximate divider (QIAD) based on multiplicative division, which has superior statistical performance. The design is simulated and synthesized at TSMC 65nm process and tested on image color quantization, showing the best quantization effect using evaluation indicators such as PSNR, MSE, and SSIM.