用于MVDR波束成形的单精度浮点脉动Givens-QRD三角求解器
A single-precision floating-point systolic Givens-QRD Triangular Solver for MVDR Beamforming
浏览论文内容
中文总结 AI 辅助
本文提出单精度浮点脉动Givens-QRD三角求解器的FPGA实现，用于MVDR波束成形，其功率归一化吞吐量优于24核Intel Xeon Gold处理器，且数值精度符合要求。
中文摘要 AI 辅助
最小方差无失真响应（MVDR）处理中自适应波束成形权重的计算是一项对延迟要求极高的操作，给实时硬件实现带来了重大挑战。本文针对模拟32阵元超声换能器阵列的MVDR波束成形，提出了一种基于单精度浮点运算的脉动Givens旋转QR分解流水线的FPGA实现方案。该设计部署在Zynq UltraScale+ FPGA上，工作频率为100 MHz，包含3个并行内核实例同时运行，相对于单实例实测速率，并行效率达90.9%，实测吞吐量为31123个权重向量/秒。在可编程逻辑功耗约2.451 W、包含处理系统总功耗5.286 W的情况下，分别对应12698和5888个权重向量/秒/瓦。在匹配的三路调度下，24核Intel Xeon Gold 5220R处理器（2.20 GHz）实测吞吐量为465699个权重向量/秒，封装功耗83.08 W，对应5606个权重向量/秒/瓦。因此，FPGA在可编程逻辑基础上的功率归一化吞吐量是该处理器的2.3倍，在总片上基础上为1.05倍；而在此工作点下，处理器的原始吞吐量优势约为15倍。数值精度通过与Field II囊肿体模仿真的MATLAB float32参考输出进行验证，通过率达100%，均方根误差为5.10×10^-7，确认其无系统偏差，呈现接近理论的有限精度行为。
英文摘要
Computation of adaptive beamforming weights in Minimum Variance Distortionless Response (MVDR) processing is a latency-critical operation that poses significant challenges for real-time hardware implementation. This paper presents an FPGA implementation of a systolic Givens-rotation QR decomposition pipeline for MVDR beamforming on a simulated 32-element ultrasound transducer array, using single-precision floating-point arithmetic. The design is deployed on a Zynq UltraScale+ FPGA at 100 MHz with three parallel kernel instances operating concurrently, achieving a measured throughput of 31,123 weight vectors/s at 90.9% parallel efficiency relative to the measured single-instance rate. At an estimated 2.451 W of programmable-logic power, and 5.286 W including the processing system, this corresponds to 12,698 and 5,888 weight vectors/s/W, respectively. Under a matched three-way dispatch, a 24-core Intel Xeon Gold 5220R at 2.20 GHz achieves 465,699 weight vectors/s at a measured 83.08 W package power, corresponding to 5,606 weight vectors/s/W. The FPGA therefore attains 2.3x the power-normalised throughput of the processor on a programmable-logic basis and 1.05x on a total on-chip basis. In contrast, the processor retains a raw throughput advantage of approximately 15x at this operating point. Numerical precision is validated against MATLAB float32 reference outputs from a Field II cyst phantom simulation, achieving a 100% pass rate with a root mean square error of 5.10x10^-7, confirming near-theoretical finite-precision behaviour without systematic bias.
发表机构
- NIELIT Calicut（NIELIT 卡利卡特）
机构由 AI 辅助整理，请以论文原文为准。
