Non-Uniform Random Number Generation Through Piecewise Linear Approximations
Non-Uniform Random Number Generation Through Piecewise Linear Approximations
复制标题
通过分段线性近似生成非均匀随机数
DOI：
10.1049/iet-cdt:20060188
复制
发表时间：
2006
期刊：
影响因子：
--
通讯作者：
W. Luk
中科院分区：
文献类型：
--
作者：
David B. Thomas;W. Luk
本文提出了一种用于非均匀随机数生成的硬件架构，该架构允许在运行时修改生成器的分布而无需重新配置。该架构基于分段线性近似，仅使用一次查表、一次比较和一次减法操作来从均匀源映射到任意非均匀分布，从而实现非常低的面积利用率和高速度。发行版的定制是全自动的，需要不到一秒的 CPU 时间来近似新的发行版，并且在运行时切换发行版需要大约 1000 个周期。与高斯特定生成器的比较表明，新架构使用了不到一半的资源，提供了更高的采样率，并保留了多达 500 亿个样本的统计质量，但也可以生成其他分布。
This paper presents a hardware architecture for non-uniform random number generation, which allows the generator's distribution to be modified at run-time without reconfiguration. The architecture is based on a piecewise linear approximation, using just one table lookup, one comparison and one subtract operation to map from a uniform source to an arbitrary non-uniform distribution, resulting in very low area utilisation and high speeds. Customisation of the distribution is fully automatic, requiring less than a second of CPU time to approximate a new distribution, and around 1000 cycles to switch distributions at run-time. Comparison with Gaussian specific generators show that the new architecture uses less than half the resources, provides a higher sample rate, and retains statistical quality for up to 50 billion samples, but can also generate other distributions.