Skip to content
FireSimFireSimFireSim

First-time AWS User Setup

If you’ve never used AWS before and don’t have an account, follow the instructions below to get started.

Creating an AWS Account

Section titled “Creating an AWS Account”

First, you’ll need an AWS account. Create one by going to aws.amazon.com and clicking “Sign Up.” You’ll want to create a personal account. You will have to give it a credit card number.

Requesting Limit Increases

Section titled “Requesting Limit Increases”

AWS limits access to particular instance types for new/infrequently used accounts to protect their infrastructure. You can learn more about how these limits/quotas work here.

Select one of the following regions, which has F2 support, according to your location:

  • US East (N. Virginia) [us-east-1]

  • US West (Oregon) [us-west-2]

  • EU (London) [eu-west-2]

You should make sure that your account has the ability to launch a sufficient number of instances to follow this guide by looking at the “Service Quotas” page in the AWS Console, which you can access here. Be sure that the correct region is selected once you open this page.

The values listed on this page represent the maximum number vCPUs of any of these instances that you can run at once, which will limit the size of simulations (e.g., number of parallel FPGAs) that you can run. If you need to increase your limits, follow the instructions below.

Note

Note that requests will take a few business days to process by Amazon AWS (prepare for a worst case time of 1 week if cases need to be escalated).

We recommend the following limits:

  • Running On-Demand F instances: 1024 vCPUs.

    • This is sufficient for 42 parallel FPGAs. Each 24 vCPUs = one FPGA.

  • Running On-Demand Standard (A, C, D, H, I, M, R, T, Z) instances: 1024 vCPUs.

    • We will use c5.4xlarge for our FireSim manager instance and z1d.2xlarge for our build farm instances.

    • Each c5.4xlarge requires 10 vCPUs

    • Each z1d.2xlarge requires 8 vCPUs

    • Your 1024 vCPU capacity is shared across the A, C, D, H, I, M, R, T, Z instances you launch.

At a minimum, you need to have the following limits:

  • Running On-Demand F instances: 192 vCPUs.

    • This is sufficient for 8 parallel FPGAs. Each 24 vCPUs = one FPGA.

  • Running On-Demand Standard (A, C, D, H, I, M, R, T, Z) instances: 24 vCPUs.

    • This is sufficient for one c5.4xlarge manager instance and one z1d.2xlarge build farm instance.

If you have insufficient limits, request a limit increase by following these steps:

Visit: https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/ec2-resource-limits.html#request-increase

In your request, enter the vCPU limits for the two instance classes shown above.

At this point, you should wait for the response to this request.

If your request gets rejected, you will need to go through the escalation process. Gather the following details from your request:

  • Your Support Case ID for your rejected request (or both if both requests were rejected). You can find your case ID from the AWS Support page, under Support cases.

  • Your Service quota string that you requested a quota increase on. Ex: Running On-Demand F instances.

  • The number of vCPUs you requested a quota increase to.

  • Requested region. Ex: US West (Oregon).

You will then need to send an email to Amazon AWS for escalation. We’ve been informed by AWS that if you are not able to be granted a quota increase through their normal quota increase process, you will need to reach out to AWS Support or your site/institution’s AWS Sales Support Representative (if applicable) with the case details specified above. They will handle case-by-case escalations to increase your quota. AWS has given us the following 2 links to start from:

Hit Next below to continue.