使用图形处理单元的每秒万亿次引力透镜射线拍摄
Teraflop per second gravitational lensing ray-shooting using graphics processing units
摘要：
使用直接逆射线拍摄方法的引力透镜计算是确定放大率图、焦散图案和光变曲线（例如，作为源轮廓和大小的函数）的计算上昂贵的方式。然而，作为一种易于并行化的计算，引力射线拍摄可以使用可编程图形处理单元（GPU）加速。我们提出了我们的实施逆向射线拍摄的NVIDIA G80一代图形处理器使用NVIDIA计算统一设备架构（CUDA）软件开发工具包。我们还将代码扩展到多GPU系统，包括4 GPU NVIDIA S1070 Tesla单元。我们在单个GPU上实现了182 Gflop/s的持续处理性能，并且使用特斯拉单元实现了1.28 Tflop/s的持续处理性能。我们证明，十亿透镜微透镜模拟可以运行在一台计算机上的特斯拉单位的时间尺度，为了一天，而不使用分层树代码。
英文摘要：
Gravitational lensing calculation using a direct inverse ray-shooting approach is a computationally expensive way to determine magnification maps, caustic patterns, and light-curves (e.g. as a function of source profile and size). However, as an easily parallelisable calculation, gravitational ray-shooting can be accelerated using programmable graphics processing units (GPUs). We present our implementation of inverse ray-shooting for the NVIDIA G80 generation of graphics processors using the NVIDIA Compute Unified Device Architecture (CUDA) software development kit. We also extend our code to multiple-GPU systems, including a 4-GPU NVIDIA S1070 Tesla unit. We achieve sustained processing performance of 182 Gflop/s on a single GPU, and 1.28 Tflop/s using the Tesla unit. We demonstrate that billion-lens microlensing simulations can be run on a single computer with a Tesla unit in timescales of order a day without the use of a hierarchical tree code.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
