“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 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.
(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
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:
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
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.
New Content: Featuring CKAD Labs in Consumable Sizes
New Content in the Training Library In May, our team of expert certification specialists released seven new or updated learning paths, 18 courses, 28 hands-on labs, and two lab challenges! Three very large CKAD hands-on labs (average duration over two hours each) have been refactore...
New Content: AWS VPC & CloudFormation Playgrounds, Alibaba Lab Challenges and more
New Content in the Training Library In April, our Content Team released three new or updated learning paths, 15 courses, 18 hands-on labs, and six lab challenges! You can always find the latest content additions, as well as insight into what content we’re working on next, on our Conte...
New Content: Platforms, Programming, and DevOps – Something for Everyone
This month our team of expert certification specialists released three new or updated learning paths, 16 courses, 13 hands-on labs, and four lab challenges! New content on Cloud Academy You can always visit our Content Roadmap to see what’s just released as well as what’s coming soon....
Mastering AWS Organizations Service Control Policies
Service Control Policies (SCPs) are IAM-like policies to manage permissions in AWS Organizations. SCPs restrict the actions allowed for accounts within the organization making each one of them compliant with your guidelines. SCPs are not meant to grant permissions; you should consider ...
New Content: Focus on DevOps and Programming Content this Month
This month our team of expert certification specialists released 12 new or updated learning paths, 15 courses, 25 hands-on labs, and four lab challenges! New content on Cloud Academy You can always visit our Content Roadmap to see what’s just released as well as what’s coming soon. Ja...
New Content: Get Ready for the CISM Cert Exam & Learn About Alibaba, Plus All the AWS, GCP, and Azure Courses You Know You Can Count On
This month our team of intrepid certification specialists released five learning paths, seven courses, 19 hands-on labs, and three lab challenges! One particularly interesting new learning path is Certified Information Security Manager (CISM) Foundations. After completing this learn...
Which Certifications Should I Get?
The old AWS slogan, “Cloud is the new normal” is indeed a reality today. Really, cloud has been the new normal for a while now and getting credentials has become an increasingly effective way to quickly showcase your abilities to recruiters and companies. With all that in mind, the s...
The 12 AWS Certifications: Which is Right for You and Your Team?
As companies increasingly shift workloads to the public cloud, cloud computing has moved from a nice-to-have to a core competency in the enterprise. This shift requires a new set of skills to design, deploy, and manage applications in cloud computing. As the market leader and most ma...
AWS Certified Solutions Architect Associate: A Study Guide
Want to take a really impactful step in your technical career? Explore the AWS Solutions Architect Associate certificate. Its new version (SAA-C02) was released on March 23, 2020. The AWS Solutions Architect - Associate Certification (or Sol Arch Associate for short) offers some ...
New Content: AWS Terraform, Java Programming Lab Challenges, Azure DP-900 & DP-300 Certification Exam Prep, Plus Plenty More Amazon, Google, Microsoft, and Big Data Courses
This month our Content Team continues building the catalog of courses for everyone learning about AWS, GCP, and Microsoft Azure. In addition, this month’s updates include several Java programming lab challenges and a couple of courses on big data. In total, we released five new learning...
Where Should You Be Focusing Your AWS Security Efforts?
Another day, another re:Invent session! This time I listened to Stephen Schmidt’s session, “AWS Security: Where we've been, where we're going.” Amongst covering the highlights of AWS security during 2020, a number of newly added AWS features/services were discussed, including: AWS Audit...
AWS re:Invent: 2020 Keynote Top Highlights and More
We’ve gotten through the first five days of the special all-virtual 2020 edition of AWS re:Invent. It’s always a really exciting time for practitioners in the field to see what features and services AWS has cooked up for the year ahead. This year’s conference is a marathon and not a...