Questions tagged with High Performance Compute

We are observing higher latency in US regions when compared to USW1. Using both redis-cli and nping we are seeing: USW1A: ~.1ms latency USW2D: ~.3ms latency For consistency-sake: - We are using the ...

I'm managing a high-read workload on Amazon RDS (MySQL) and I'm exploring ways to optimize performance. Right now, we're seeing occasional latency spikes during peak times. Any suggestion on best pra...

Hello, I'm working on running HPC workloads on AWS EC2 G4ad instances. For my setup, I need to enable Large BAR (Base Address Register) support to allow efficient memory transfers across nodes. Howev...

Hello, I’m trying to use Bedrock batch inference to process call transcripts at scale and have encountered an issue. In a small scale test with 100 records, each requiring a brief summary, the job s...

I am currently paying X for AWS services with around 3,000 monthly active users. If nothing changes in the infrastructure and suddently the number of users grows to 21,000, how can I estimate the appr...

I was looking to expedite some simulations using an EC2 console. The simulations are based on a C executable whose performance is dominated by CPU performance. I was using an Apple M1 processor with 8...

I set up spack in a new ParallelCluster instance following https://aws.amazon.com/blogs/hpc/install-optimized-software-with-spack-configs-for-aws-parallelcluster/ The installation takes many hours, bu...

Hi everyone, Apologies if this isn't the right forum to post about my issue. Please feel free to direct me to a more appropriate one if needed. Over the past few days, I’ve been analyzing the AWS E...

when I create a parallel cluster, I am given the option to load a custom image. But when I do it, I still must give also an OS (chosen among Amazon, Ubuntu, Centos, RHEL). See snapshot. Indeed, the re...

while starting an EC2 instance I chose Rocky 9 official distribution (x86_64 arch, free). However, it seems incompatible with any hpc7a*. (see snapshot). This seems very strange given that the archite...

Team, my customer would like to understand if ParallelCluster supports the use of static IPs within a VPC for the scale-out of the compute fleet via manipulating the NetworkConfiguration section in th...

Hello, I've set up an EC2 instance in the Chicago Local Zone where I'm expecting latency (by simple ping round trip test) to Interactive Brokers' Central servers to be sub-5 ms. Lately I'm getting 2...