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
Sudhi Seshachala
— October 9, 2019

Top 13 Amazon Virtual Private Cloud (VPC) Best Practices

Amazon Virtual Private Cloud (VPC) brings a host of advantages to the table, including static private IP addresses, Elastic Network Interfaces, secure bastion host setup, DHCP options, Advanced Network Access Control, predictable internal IP ranges, VPN connectivity, movement of interna...

Read more
  • AWS
  • best practices
  • VPC
Avatar
Stuart Scott
— October 2, 2019

Big Changes to the AWS Certification Exams

With AWS re:Invent 2019 just around the corner, we can expect some early announcements to trickle through with upcoming features and services. However, AWS has just announced some big changes to their certification exams. So what’s changing and what’s new? There is a brand NEW ...

Read more
  • AWS
  • Certifications
Alisha Reyes
Alisha Reyes
— October 1, 2019

New on Cloud Academy: ITIL® 4, Microsoft 365 Tenant, Jenkins, TOGAF® 9.1, and more

At Cloud Academy, we're always striving to make improvements to our training platform. Based on your feedback, we released some new features to help make it easier for you to continue studying. These new features allow you to: Remove content from “Continue Studying” section Disc...

Read more
  • AWS
  • Azure
  • Google Cloud Platform
  • ITIL® 4
  • Jenkins
  • Microsoft 365 Tenant
  • New content
  • Product Feature
  • Python programming
  • TOGAF® 9.1
Avatar
Stuart Scott
— September 27, 2019

AWS Security Groups: Instance Level Security

Instance security requires that you fully understand AWS security groups, along with patching responsibility, key pairs, and various tenancy options. As a precursor to this post, you should have a thorough understanding of the AWS Shared Responsibility Model before moving onto discussi...

Read more
  • AWS
  • instance security
  • Security
  • security groups
Avatar
Jeremy Cook
— September 17, 2019

Cloud Migration Risks & Benefits

If you’re like most businesses, you already have at least one workload running in the cloud. However, that doesn’t mean that cloud migration is right for everyone. While cloud environments are generally scalable, reliable, and highly available, those won’t be the only considerations dri...

Read more
  • AWS
  • Azure
  • Cloud Migration
Joe Nemer
Joe Nemer
— September 12, 2019

Real-Time Application Monitoring with Amazon Kinesis

Amazon Kinesis is a real-time data streaming service that makes it easy to collect, process, and analyze data so you can get quick insights and react as fast as possible to new information.  With Amazon Kinesis you can ingest real-time data such as application logs, website clickstre...

Read more
  • amazon kinesis
  • AWS
  • Stream Analytics
  • Streaming data
Joe Nemer
Joe Nemer
— September 6, 2019

Google Cloud Functions vs. AWS Lambda: The Fight for Serverless Cloud Domination

Serverless computing: What is it and why is it important? A quick background The general concept of serverless computing was introduced to the market by Amazon Web Services (AWS) around 2014 with the release of AWS Lambda. As we know, cloud computing has made it possible for users to ...

Read more
  • AWS
  • Azure
  • Google Cloud Platform
Joe Nemer
Joe Nemer
— September 3, 2019

Google Vision vs. Amazon Rekognition: A Vendor-Neutral Comparison

Google Cloud Vision and Amazon Rekognition offer a broad spectrum of solutions, some of which are comparable in terms of functional details, quality, performance, and costs. This post is a fact-based comparative analysis on Google Vision vs. Amazon Rekognition and will focus on the tech...

Read more
  • Amazon Rekognition
  • AWS
  • Google Cloud Platform
  • Google Vision
Alisha Reyes
Alisha Reyes
— August 30, 2019

New on Cloud Academy: CISSP, AWS, Azure, & DevOps Labs, Python for Beginners, and more…

As Hurricane Dorian intensifies, it looks like Floridians across the entire state might have to hunker down for another big one. If you've gone through a hurricane, you know that preparing for one is no joke. You'll need a survival kit with plenty of water, flashlights, batteries, and n...

Read more
  • AWS
  • Azure
  • Google Cloud Platform
  • New content
  • Product Feature
  • Python programming
Joe Nemer
Joe Nemer
— August 27, 2019

Amazon Route 53: Why You Should Consider DNS Migration

What Amazon Route 53 brings to the DNS table Amazon Route 53 is a highly available and scalable Domain Name System (DNS) service offered by AWS. It is named by the TCP or UDP port 53, which is where DNS server requests are addressed. Like any DNS service, Route 53 handles domain regist...

Read more
  • Amazon
  • AWS
  • Cloud Migration
  • DNS
  • Route 53
Alisha Reyes
Alisha Reyes
— August 22, 2019

How to Unlock Complimentary Access to Cloud Academy

Are you looking to get trained or certified on AWS, Azure, Google Cloud Platform, DevOps, Cloud Security, Python, Java, or another technical skill? Then you'll want to mark your calendars for August 23, 2019. Starting Friday at 12:00 a.m. PDT (3:00 a.m. EDT), Cloud Academy is offering c...

Read more
  • AWS
  • Azure
  • cloud academy content
  • complimentary access
  • GCP
  • on the house
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