Amazon EC2 F1 Instances

Enable faster FPGA accelerator development and deployment in the cloud

Why Amazon EC2 F1 Instances?

Amazon EC2 F1 instances use FPGAs to enable delivery of custom hardware accelerations. F1 instances are easy to program and come with everything you need to develop, simulate, debug, and compile your hardware acceleration code, including an FPGA Developer AMI and supporting hardware level development on the cloud. Using F1 instances to deploy hardware accelerations can be useful in many applications to solve complex science, engineering, and business problems that require high bandwidth, enhanced networking, and very high compute capabilities. Examples of target applications that can benefit from F1 instance acceleration are genomics, search/analytics, image and video processing, network security, electronic design automation (EDA), image and file compression and big data analytics.

F1 instances provide diverse development environments: from low-level hardware developers to software developers who are more comfortable with C/C++ and openCL environments (available on our GitHub). Once your FPGA design is complete, you can register it as an Amazon FPGA Image (AFI), and deploy it to your F1 instance in just a few clicks. You can reuse your AFIs as many times as you like, and across as many F1 instances as you like. There is no software charge for the development tools when using the FPGA developer AMI and you can program the FPGAs on your F1 instance as many times as you like with no additional fees.

Amazon EC2 F1 Instances with Customizable FPGAs for Hardware Acceleration

Benefits

Unlike on-premises systems, running high-performance computing on Amazon EC2 F1 instances offers virtually unlimited capacity to scale out your infrastructure and the flexibility to change resources easily and as often as your workload demands. You can configure your resources to meet the demands of your application, and launch as many FPGA instances needed, in minutes, and pay for only what you use.

Amazon EC2 F1 instances provide up to 100X acceleration compared to CPUs for a diverse set of compute-bound applications. Customers can discover, test and deploy custom accelerators directly from the AWS Marketplace to accelerate their compute pipelines with ease. There is no need to know how to program FPGAs, as F1 based products developed by F1 technology partners are packaged as any other EC2 instance software.

Developers can accelerate their FPGA development with advanced cloud-based tools and flows that allow them to focus on their value-add acceleration logic. Developers can get hands-on experience with self-paced online tutorials and learn from many GitHub examples. To ease the debugging process, AWS has developed virtual hardware debugging tools like virtual JTAG, providing a familiar development environment allowing for multiple developers to make progress without being dependent on limited on-premises resources.

Use cases

Amazon EC2 F1 instances are the ideal option to process massive amounts of genomics data, provide the fastest time to results, with best accuracy and low cost per genome. FPGAs can provide up to 30x Next-Generation Sequencing (NGS) compute acceleration compared to the latest CPU based instances on AWS.

Amazon EC2 F1 instances deliver the ability to efficiently compute networking packets at line rate using the virtual ethernet feature. With this capability, FPGAs on can be used for security applications like deep packet inspection or high-performance load-balancers or other networking applications that require real-time packet processing.

Live broadcast video transcoding applications using F1 instances deliver higher performance than applications using compute instances, F1 instances are an ideal solution to meet the requirements of these applications, reducing the compute costs without compromising quality.

The volume, variety, and velocity of data analysis and search requirements in many big data applications have risen to the point where customers are looking for hardware acceleration to keep up. For those applications, customers can leverage the increased performance of F1 instances to meet their big data analytics and search requirements.

Financial organizations can use F1 instances to get faster results of risk modeling and analysis, transaction analysis for security in addition to other workloads.

Features

FPGAs are reprogrammable hardware devices that can implement any logic function. This makes FPGAs similar to custom silicon (aka Application-Specific Integrated Circuits, or ASICs), allowing developers to create custom processors/accelerators that provide optimized compute tailored to accelerate a specific workload. This enables in specific cases a significant acceleration compared to fixed-function compute solutions like CPUs and GPUs.

Developers can get started on F1 instances by creating an AWS account and downloading the AWS FPGA Development Kit. The kit is avaliable on GitHub and includes all documentation on F1, internal FPGA interfaces, and compiler scripts for generating Amazon FPGA Images (AFIs). AWS FPGAs support multiple development environments to serve both hardware and software developers. The HDK provides fully custom hardware development, and the software-defined environment allows developing accelerations using C/C++/OpenCL code with no hardware knowledge needed. This allows for fast FPGA development for the EC2 F1 instances.

The FPGA Developer AMI includes Xilinx Vivado at no additional software charge as well as a prepackaged tool development environment with scripts and tools for simulating your FPGA design and building and registering your AFI. The FPGA Developer AMI also includes tools for debugging and compiling your code. You can deploy the FPGA Developer AMI on an Amazon EC2 instance and quickly provision the resources you need to write and test your FPGA design.

Customer and Partner testimonials

Here are some examples of how customers and partners have achieved their business goals with Amazon EC2 F1 instances.

  • Munich Leukemia Lab

    We have been able to use the FPGA-based F1 instances to greatly speed up the process of whole genome sequencing. As a result, what used to take us 20 hours of compute time can now be achieved in only 3 hours.

    Professor Dr. Torsten Haferlach Chief Executive Officer at Munich Leukemia Lab
  • Bigstream

    Bigstream is an automated acceleration technology for Apache Spark. It includes a compiler and runtime that routes execution of Spark application tasks onto Amazon F1 FPGA instances requiring zero user code change. Users experience up to a 10x improvement in performance. In addition to single node operation, Bigstream also supports clustering of F1 instances. Bigstream is available in public preview at no cost as an Amazon Machine Image (AMI) for Amazon Elastic Compute Cloud (EC2) F1 instances of all sizes.

  • Merlin™ Compiler

    Merlin™ Compiler brings the power of FPGA acceleration to application developers with a simple software programming model and no hardware knowledge required. It provides an automated compilation flow from C/C++ to highly-optimized FPGA accelerators. It enables significant gains in productivity while maintaining performance comparable to manual optimization.

  • Illumina

    The Illumina DRAGEN Bio-IT Platform provides accurate, ultra-rapid secondary genome analysis of sequencing data. It enables labs of all sizes and disciplines to do more with their genomic data. The DRAGEN Platform uses FPGA-based Amazon EC2 F1 instances to provide hardware-accelerated implementations of genomic analysis algorithms, such as BCL conversion, mapping, alignment, sorting, duplicate marking, and haplotype variant calling. Secondary analysis of a human genome with DRAGEN takes less than 20 minutes on Amazon EC2 F1 instances which is 30x faster than without acceleration. Dragen on AWS is available here or through Illumina BaseSpace sequencing hub.

  • InAccel

    InAccel FPGA-Accelerated ML (AML) Suite provides a set of accelerators that run on Amazon EC2 F1 instances for ML applications. Applications developed using popular frameworks such as Apache Spark, Scikit-learn, and Keras can be accelerated using InAccel FPGA-Accelerated ML Suite. It is shipped as a fully integrated AMI that can be used to accelerate deep learning and machine learning algorithms for classification and clustering. InAccel's novel "FPGA Resource Manager" Docker container handles all the available FPGA resources allowing developers to seamlessly scale their containerized workloads to multiple F1 instances.

  • rENIAC

    rENIAC is a fully managed, highly available Cassandra accelerator enabled by Amazon EC2 F1 instances that stores multiple TBs of hot data to deliver up to a 10x performance improvement, 10x density increase and 15x latency reduction over Cassandra alone. rENIAC leverages SSDs to cache data, tightly coupled with FPGA-based acceleration to access and serve TBs of data with in-memory-like performance. rENIAC is also compatible with DataStax clusters.

  • Socionext

    Socionext, a leading provider of video processing and distribution products, possesses decades of hardware-based solution expertise essential for the development of a powerful and innovative FPGA-based virtual server platform. By working together with AWS, Socionext offers a hardware-accelerated, cloud-based encoding solution on Amazon EC2 F1 instances that ensures consistent, high-quality video streams while significantly reducing processing time and delivery costs.

  • Trend Micro

    Trend Micro provides automated, flexible and all-in-one security for AWS customers via the Trend Micro Cloud One platform. Trend Micro, an advanced technology partner, leverages Amazon EC2 F1 instances to enable our joint customers to maximize compute efficiency and performance to inspect network traffic, allowing customers to quickly and efficiently deploy broad, scalable network layer security on AWS.

  • Valtix

    Using Amazon EC2 F1 instances, Valtix can provide high performance and low latency SSL encryption/decryption and deep packet inspection (DPI) for threat detection. This gives Valtix an edge as the industry's first cloud-native advanced network security service that protects against attacks, prevents exfiltration and stops lateral movement of threats. Customers can quickly discover their cloud apps, deploy auto scaling security, and defend their applications.

    Vijay Chander, CTO and co-founder at Valtix

Product Details

Name FPGAs
vCPUs Instance Memory (GiB) SSD Storage (GB) Enhanced Networking EBS Optimized On-Demand Price/hr* 1-yr Reserved Instance Effective Hourly* 3-yr Reserved Instance Effective Hourly*
f1.2xlarge 1
8 122 470
Yes Yes $1.65 $1.06 $0.76
f1.4xlarge 2 16 244
940
Yes Yes $3.30 $2.12 $1.52
f1.16xlarge 8
64 976
4 x 940
Yes Yes $13.20 $8.50 $6.10

*Prices shown are for Linux/Unix in the US East (Northern Virginia) AWS Region and rounded to the nearest cent. Prices for 1-year and 3-year reserved instances are for "Partial Upfront" payment options. For full pricing details, see the Amazon EC2 pricing page.  

Tutorials

Developing on AWS F1 with SDAccel and RTL Kernels - Part 1 of 4 (30:43)
Developing on AWS F1 with SDAccel and RTL Kernels - Part 2 of 4 (9:21)
Developing on AWS F1 with SDAccel and RTL Kernels - Part 3 of 4 (41:36)
Developing on AWS F1 with SDAccel and RTL Kernels - Part 4 of 4 (31:09)

Partner Solutions

Edico Genome Cloud-Based Genomic Analysis with AWS F1 Instances: Powered by Xilinx (3:11)
rENIAC Data Store Acceleration-as-a-Service with Amazon EC2 F1 Instances: Powered by Xilinx (3:05)
Bigstream Demonstrates Seamless Hyper-Acceleration (3:48)
NGCodec Video Encoding in the Cloud with Amazon EC2 F1 Instances: Powered by Xilinx (3:20)

Additional resources

Deploy Illumina DRAGEN on the AWS Cloud with new Quick Start 

Introducing Amazon EC2 F1 Instances (0:59)
FPGA Accelerated Computing Using Amazon EC2 F1 Instances (49:29)