Compare Amazon EC2 Auto Scaling vs. Amazon Elastic Inference

You must select at least 2 products to compare!
Quotes From Members

We asked business professionals to review the solutions they use. Here are some excerpts of what they said:

Pricing and Cost Advice
"Pricing could be a little bit more competitive.""The pricing is not fixed and it is based on usage.""The price of this product could be a little bit lower."

More Amazon EC2 Auto Scaling Pricing and Cost Advice »

Information Not Available
Use our free recommendation engine to learn which Compute Service solutions are best for your needs.
475,208 professionals have used our research since 2012.
Questions from the Community
Top Answer: The most valuable features are that it is stable, flexible, and reliable.
Top Answer: The price of this product could be a little bit lower.
Top Answer: The technical support needs to be improved. From a usage perspective, it runs well, although there may be a use case where it will break that I have not yet come across.
Ask a question

Earn 20 points

out of 13 in Compute Service
Average Words per Review
out of 13 in Compute Service
Average Words per Review
Popular Comparisons
Also Known As
Learn More

Amazon EC2 Auto Scaling helps you maintain application availability and allows you to automatically add or remove EC2 instances according to conditions you define. ... Dynamic scaling responds to changing demand and predictive scaling automatically schedules the right number of EC2 instances based on predicted demand.

Amazon Elastic Inference allows you to attach low-cost GPU-powered acceleration to Amazon EC2 and Amazon SageMaker instances or Amazon ECS tasks to reduce the cost of running deep learning inference by up to 75%. Amazon Elastic Inference supports TensorFlow, Apache MXNet, and ONNX models, with more frameworks coming soon.
In most deep learning applications, making predictions using a trained model—a process called inference—can drive as much as 90% of the compute costs of the application due to two factors. First, standalone GPU instances are designed for model training and are typically oversized for inference. While training jobs batch process hundreds of data samples in parallel, most inference happens on a single input in real time that consumes only a small amount of GPU compute. Even at peak load, a GPU's compute capacity may not be fully utilized, which is wasteful and costly. Second, different models need different amounts of GPU, CPU, and memory resources. Selecting a GPU instance type that is big enough to satisfy the requirements of the most demanding resource often results in under-utilization of the other resources and high costs.
Amazon Elastic Inference solves these problems by allowing you to attach just the right amount of GPU-powered inference acceleration to any EC2 or SageMaker instance type or ECS task with no code changes. With Amazon Elastic Inference, you can now choose the instance type that is best suited to the overall CPU and memory needs of your application, and then separately configure the amount of inference acceleration that you need to use resources efficiently and to reduce the cost of running inference.

Learn more about Amazon EC2 Auto Scaling
Learn more about Amazon Elastic Inference
Sample Customers
Expedia, Intuit, Royal Dutch Shell, Brooks Brothers
Expedia, Intuit, Royal Dutch Shell, Brooks Brothers
Top Industries
Media Company27%
Computer Software Company23%
Comms Service Provider16%
Media Company32%
Comms Service Provider24%
Computer Software Company21%
Financial Services Firm7%
Find out what your peers are saying about Apache, Amazon, StackStorm and others in Compute Service. Updated: April 2021.
475,208 professionals have used our research since 2012.

Amazon EC2 Auto Scaling is ranked 5th in Compute Service with 3 reviews while Amazon Elastic Inference is ranked 11th in Compute Service. Amazon EC2 Auto Scaling is rated 8.0, while Amazon Elastic Inference is rated 0.0. The top reviewer of Amazon EC2 Auto Scaling writes "Stable, flexible, reliable, and scales up or down automatically according to your requirements". On the other hand, Amazon EC2 Auto Scaling is most compared with AWS Fargate, Apache NiFi and Oracle Compute Cloud Service, whereas Amazon Elastic Inference is most compared with AWS Fargate, AWS Lambda and AWS Batch.

See our list of best Compute Service vendors.

We monitor all Compute Service reviews to prevent fraudulent reviews and keep review quality high. We do not post reviews by company employees or direct competitors. We validate each review for authenticity via cross-reference with LinkedIn, and personal follow-up with the reviewer when necessary.