基于GPU的关联函数X-engine在CHIME Pathfinder上的实现
A GPU-based Correlator X-engine Implemented on the CHIME Pathfinder
摘要：
我们提出了一个自定义的基于GPU的计算集群，提供相关的CHIME探路者射电望远镜的X引擎的设计和实现。它是最大的此类系统之一，在400 MHz的无线电带宽上关联32，896个基线（256个输入）。该系统大量使用消费级部件和定制软件堆栈，开发成本仅为同类安装成本的一小部分。与现有的GPU后端不同，该系统是围绕在消费级AMD GPU上运行的OpenCL内核构建的，利用低成本硬件并利用打包整数运算将算法效率提高一倍。该系统在10 kW的功率范围内实现了所需的105 TOPS，使其成为当今使用的最节能的X发动机之一。
英文摘要：
We present the design and implementation of a custom GPU-based compute cluster that provides the correlation X-engine of the CHIME Pathfinder radio telescope. It is among the largest such systems in operation, correlating 32,896 baselines (256 inputs) over 400MHz of radio bandwidth. Making heavy use of consumer-grade parts and a custom software stack, the system was developed at a small fraction of the cost of comparable installations. Unlike existing GPU backends, this system is built around OpenCL kernels running on consumer-level AMD GPUs, taking advantage of low-cost hardware and leveraging packed integer operations to double algorithmic efficiency. The system achieves the required 105TOPS in a 10kW power envelope, making it among the most power-efficient X-engines in use today.
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。
