云中的GROMACS：一台全球超级计算机，可加速炼金术药物设计
GROMACS in the cloud: A global supercomputer to speed up alchemical drug design
摘要：
我们评估了最先进的高性能云计算与传统本地计算集群相比的成本和效率。我们的用例是使用GROMACS分子动力学（MD）工具包进行的原子模拟，重点是炼金术蛋白质-配体结合自由能计算。我们在Amazon Web Services（AWS）云中设置了一个计算集群，该集群将各种不同的实例与英特尔、AMD和ARM CPU结合在一起，其中一些实例具有GPU加速功能。使用代表性的生物分子模拟系统，我们基准测试GROMACS如何在单个实例和多个实例上执行。因此，我们评估哪些实例提供最高的性能，哪些是我们用例中最具成本效益的实例。我们发现，就包括硬件、人员、空间、能源和冷却在内的总成本而言，如果选择了最佳的云实例，在云中生成MD轨迹可以与本地集群一样具有成本效益。此外，我们发现，通过使用全球云资源，可以显着加快蛋白质-配体结合亲和力估计的高通量配体筛选。对于由19，872个独立模拟组成的配体筛选研究，我们使用了研究时云中可用的所有硬件。计算规模不断扩大，在全球范围内同时使用超过4，000个实例、140，000个核心和3，000个GPU达到峰值性能。我们的模拟集合在云中大约两天内完成，而在由数百个节点组成的典型本地集群上完成任务则需要数周时间。我们证明，这样的和类似的研究的成本可以大大降低与检查点重新启动协议，允许使用便宜的现货定价，并通过使用实例类型具有最佳的成本效益。
英文摘要：
We assess costs and efficiency of state-of-the-art high performance cloud computing compared to a traditional on-premises compute cluster. Our use case are atomistic simulations carried out with the GROMACS molecular dynamics (MD) toolkit with a focus on alchemical protein-ligand binding free energy calculations. We set up a compute cluster in the Amazon Web Services (AWS) cloud that incorporates various different instances with Intel, AMD, and ARM CPUs, some with GPU acceleration. Using representative biomolecular simulation systems we benchmark how GROMACS performs on individual instances and across multiple instances. Thereby we assess which instances deliver the highest performance and which are the most cost-efficient ones for our use case. We find that, in terms of total costs including hardware, personnel, room, energy and cooling, producing MD trajectories in the cloud can be as cost-efficient as an on-premises cluster given that optimal cloud instances are chosen. Further, we find that high-throughput ligand-screening for protein-ligand binding affinity estimation can be accelerated dramatically by using global cloud resources. For a ligand screening study consisting of 19,872 independent simulations, we used all hardware that was available in the cloud at the time of the study. The computations scaled-up to reach peak performances using more than 4,000 instances, 140,000 cores, and 3,000 GPUs simultaneously around the globe. Our simulation ensemble finished in about two days in the cloud, while weeks would be required to complete the task on a typical on-premises cluster consisting of several hundred nodes. We demonstrate that the costs of such and similar studies can be drastically reduced with a checkpoint-restart protocol that allows to use cheap Spot pricing and by using instance types with optimal cost-efficiency.
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。
