A company is designing a tightly coupled high-performance computing (HPC) environment in AWS and needs to optimize networking and storage for HPC. Which two solutions together meet these requirements? (Choose two.)
Choose an answer
Tap an option to check your answer.
Correct answer: Create an Amazon FSx for Lustre file system. Configure the file system with scratch storage., Launch Amazon EC2 instances and attach an Elastic Fabric Adapter (EFA) to the instances..
Why this is the answer
For tightly coupled HPC workloads, low-latency networking and high-throughput storage are critical. Elastic Fabric Adapter (EFA) is a network interface for Amazon EC2 instances that enables high-performance computing (HPC) and machine learning applications to achieve lower and more consistent latency and higher throughput than traditional TCP networking. Amazon FSx for Lustre is a high-performance file system optimized for HPC workloads, providing sub-millisecond latencies and high throughput. Configuring it with scratch storage is suitable for temporary, high-performance data processing. AWS Global Accelerator is for improving global application availability and performance by routing traffic through the AWS global network, not for optimizing intra-region HPC networking. Amazon CloudFront is a content delivery network (CDN) for caching web content, irrelevant for HPC internal networking. AWS Elastic Beanstalk is an orchestration service for deploying and managing web applications, not a core component for HPC infrastructure optimization.
Pass your exam — without the endless answer hunt
Get every verified question and explanation for this exam in one place, and save hours of prep. 1,000+ certifications · 20+ languages · free to start.
Pass your exam faster → No card needed