Amazon Elastic Inference – GPU Acceleration for Faster Inferencing

“Add GPU acceleration to any Amazon EC2 instance for faster inference at much lower cost (up to 75% savings)”

So you’ve just kicked off the training phase of your multilayered deep neural network. The training phase is leveraging Amazon EC2 P3 instances to keep the training time to a minimum, but it’s still going to take a while. With time in hand, you begin to contemplate what infrastructure you’ll use to run your inferences.

You’re already familiar with the merits of using GPUs for the training phase. GPUs have the ability to parallelize massive amounts of simple math computations, which makes them perfect for training neural networks. GPUs are more expensive to run than CPUs, but because they can parallelize the number crunching, you don’t need to run them as long as you would the equivalent training performed on CPUs. In fact, training on GPUs can be orders-of-magnitude quicker. So it may cost you more per hour to run a GPU, but you won’t need to run it anywhere nearly as long when on a CPU. Besides factoring in cost, training your models faster allows you to get them into production quicker to perform inferences. So in terms of the training phase, it makes complete sense to go with GPUs.

So your contemplation now focuses on whether to use GPU or CPU infrastructure to perform inferencing once the training completes and your model is ready. We know that GPUs cost more per hour to run. Performing inferences through a trained neural network are far less taxing in terms of required computation and data volume that needs to be ingested and processed. Therefore, CPUs seem to be the way to go. However, you know from past experiences that over time, your CPU hosted inferencing tends to bottleneck due to overwhelming demand and this makes you reconsider running the inferencing on GPUs, but you now need to budget in the extra cost as a project consideration. This dilemma of whether to use GPUs versus CPUs for inferencing, with respect to both cost and performance is all too familiar for many organizations. The choice of using a GPU or CPU was a fairly mutually exclusive upfront decision made when using EC2. As of today, this is no longer the case.

Amazon Elastic Inference

Amazon Elastic Inference is a new service from AWS which allows you to complement your EC2 CPU instances with GPU acceleration, which is perfect for hosting your inferencing models. You can now select the appropriate CPU sized EC2 instance and boost its number crunching ability with GPU processing. Like with many other AWS services, you only pay for the actual accelerator hours you use. What this means is that you can get full GPU processing power but being up to 75% cheaper than running an equivalent GPU sized EC2 instance.

See: https://aws.amazon.com/machine-learning/elastic-inference/
(You might also want to read up on this year’s announcements from re:Invent, particularly our blog post on how Amazon FSx for Lustre Makes High Performance Computing More Accessible.)

For starters, Amazon Elastic Inference is launching with 3 types of Teraflop mixed precision powered accelerators: eia1.medium, eia1.large, and the eia1.xlarge

Elastic Inferencing GPU Types

Amazon Elastic Inference has been seamlessly integrated into both the AWS EC2 console and the AWS CLI. In the following EC2 console screenshot, attaching GPU acceleration, is as simple as enabling the “Add an Elastic Inference accelerator” option:

AWS EC2 Console - Elastic Inferencing

The equivalent AWS CLI command looks like the following, noting that the existing API has been extended with a new optional elastic-inference-accelerator parameter:

aws ec2 run-instances \ 
--image-id ami-00ffbd996ef2211e3 \
--key-name DNN_Key
--security-group-ids sg-12345678 \
--subnet-id subnet-12345678 \ 
--instance-type c5.xlarge \
--elastic-inference-accelerator Type=eia1.large
--iam-instance-profile Name="InferenceAcceleratorProfile"

The following list itemizes several prerequisites that need to be in place to leverage Amazon Elastic Inference:

  • A Private Link endpoint configured for Elastic Inference must be present
  • An IAM role with the necessary policies to connect to the Elastic Inference accelerator
  • Build your models using TensorFlow, Apache MXNet, and/or ONNX
  • Use the latest AWS Deep learning AMIs, which have been updated with Amazon Elastic Inference support baked directly into the TensorFlow, Apache MXNet deep learning frameworks
Deep Learning AMIs - Elastic Inferencing Enabled

As you can see with a few extra configuration options in place you can have the best of both worlds, CPU hosted inferencing with GPU acceleration. You no longer need to spend time contemplating CPUs over GPUs – take both!!

Another game changer in the machine learning space from AWS – give it a try and check out our Lab on Analyzing CPU vs GPU Performance for AWS Machine Learning.

Avatar

Written by

Jeremy Cook

Jeremy is currently employed as a Cloud Researcher and Trainer - and operates within CloudAcademy's content provider team authoring technical training documentation for both AWS and GCP cloud platforms. Jeremy has achieved AWS Certified Solutions Architect - Professional Level, and GCP Qualified Systems Operations Professional certifications.

Related Posts

Avatar
Michael Sheehy
— August 19, 2019

What Exactly Is a Cloud Architect and How Do You Become One?

One of the buzzwords surrounding the cloud that I'm sure you've heard is "Cloud Architect." In this article, I will outline my understanding of what a cloud architect does and I'll analyze the skills and certifications necessary to become one. I will also list some of the types of jobs ...

Read more
  • AWS
  • Cloud Computing
Avatar
Andrew Larkin
— August 13, 2019

Content Roadmap: AZ-500, ITIL 4, MS-100, Google Cloud Associate Engineer, and More

Last month, Cloud Academy joined forces with QA, the UK’s largest B2B skills provider, and it put us in an excellent position to solve a massive skills gap problem. As a result of this collaboration, you will see our training library grow with additions from QA’s massive catalog of 500+...

Read more
  • AWS
  • Azure
  • content roadmap
  • Google Cloud Platform
Avatar
Adam Hawkins
— August 9, 2019

DevSecOps: How to Secure DevOps Environments

Security has been a friction point when discussing DevOps. This stems from the assumption that DevOps teams move too fast to handle security concerns. This makes sense if Information Security (InfoSec) is separate from the DevOps value stream, or if development velocity exceeds the band...

Read more
  • AWS
  • cloud security
  • DevOps
  • DevSecOps
  • Security
Avatar
Stefano Giacone
— August 8, 2019

Test Your Cloud Knowledge on AWS, Azure, or Google Cloud Platform

Cloud skills are in demand | In today's digital era, employers are constantly seeking skilled professionals with working knowledge of AWS, Azure, and Google Cloud Platform. According to the 2019 Trends in Cloud Transformation report by 451 Research: Business and IT transformations re...

Read more
  • AWS
  • Cloud skills
  • Google Cloud
  • Microsoft Azure
Avatar
Andrew Larkin
— August 7, 2019

Disadvantages of Cloud Computing

If you want to deliver digital services of any kind, you’ll need to estimate all types of resources, not the least of which are CPU, memory, storage, and network connectivity. Which resources you choose for your delivery —  cloud-based or local — is up to you. But you’ll definitely want...

Read more
  • AWS
  • Azure
  • Cloud Computing
  • Google Cloud Platform
Joe Nemer
Joe Nemer
— August 6, 2019

Google Cloud vs AWS: A Comparison (or can they be compared?)

The "Google Cloud vs AWS" argument used to be a common discussion among our members, but is this still really a thing? You may already know that there are three major players in the public cloud platforms arena: Amazon Web Services (AWS), Microsoft Azure, and Google Cloud Platform (GCP)...

Read more
  • AWS
  • Google Cloud Platform
  • Kubernetes
Avatar
Stuart Scott
— July 29, 2019

Deployment Orchestration with AWS Elastic Beanstalk

If you're responsible for the development and deployment of web applications within your AWS environment for your organization, then it's likely you've heard of AWS Elastic Beanstalk. If you are new to this service, or simply need to know a bit more about the service and the benefits th...

Read more
  • AWS
  • elastic beanstalk
Avatar
Stuart Scott
— July 26, 2019

How to Use & Install the AWS CLI

What is the AWS CLI? | The AWS Command Line Interface (CLI) is for managing your AWS services from a terminal session on your own client, allowing you to control and configure multiple AWS services and implement a level of automation. If you’ve been using AWS for some time and feel...

Read more
  • AWS
  • AWS CLI
  • Command line interface
Alisha Reyes
Alisha Reyes
— July 22, 2019

Cloud Academy’s Blog Digest: July 2019

July has been a very exciting month for us at Cloud Academy. On July 10, we officially joined forces with QA, the UK’s largest B2B skills provider (read the announcement). Over the coming weeks, you will see additions from QA’s massive catalog of 500+ certification courses and 1500+ ins...

Read more
  • AWS
  • Azure
  • Cloud Academy
  • Cybersecurity
  • DevOps
  • Kubernetes
Avatar
Stuart Scott
— July 18, 2019

AWS Fundamentals: Understanding Compute, Storage, Database, Networking & Security

If you are just starting out on your journey toward mastering AWS cloud computing, then your first stop should be to understand the AWS fundamentals. This will enable you to get a solid foundation to then expand your knowledge across the entire AWS service catalog.   It can be both d...

Read more
  • AWS
  • Compute
  • Database
  • fundamentals
  • networking
  • Security
  • Storage
Avatar
Adam Hawkins
— July 17, 2019

How to Become a DevOps Engineer

The DevOps Handbook introduces DevOps as a framework for improving the process for converting a business hypothesis into a technology-enabled service that delivers value to the customer. This process is called the value stream. Accelerate finds that applying DevOps principles of flow, f...

Read more
  • AWS
  • AWS Certifications
  • DevOps
  • DevOps Foundation Certification
  • Engineer
  • Kubernetes
Avatar
Vineet Badola
— July 15, 2019

AWS AMI Virtualization Types: HVM vs PV (Paravirtual VS Hardware VM)

Amazon Machine Images (AWS AMI) offers two types of virtualization: Paravirtual (PV) and Hardware Virtual Machine (HVM). Each solution offers its own advantages. When we’re using AWS, it’s easy for someone — almost without thinking —  to choose which AMI flavor seems best when spinning...

Read more
  • AWS
  • Hardware Virtual Machine
  • Paravirtual
  • Virtualization