Amazon Web Services (AWS) and Intel share a passion for delivering constant innovation. Together, they have developed a variety of resources and technologies for High Performance Computing, Big Data, Artificial Intelligence/Machine Learning and the Internet of Things
Welcome to the next generation of Amazon EC2 Compute-Optimized instances: C5.
Amazon EC2 C5 instances include the Intel® custom cloud solution based on next generation Intel® Xeon® Scalable processors (codenamed Skylake) with Intel AVX-512, offering up to 72 vCPUs—twice that of the previous generation compute-optimized instances—and 144 GiB of memory. C5 instances are ideal for compute-intensive scientific modeling, financial operations, machine learning (ML) inference, high performance computing (HPC) and distributed analytics that require high performance for floating point calculations.
For more information, see what Jeff Barr, Chief Evangelist at Amazon Web Services, says about it here.
NOW AVAILABLE – C5 INSTANCES: NEXT GENERATION OF AMAZON EC2 COMPUTE-OPTIMIZED INSTANCES
The new instances offer a 25% price/performance improvement over the C4 instances, with over 50% for some workloads. They also have additional memory per vCPU, and (for code that can make use of the new Intel AVX-512 instructions), twice the performance for vector and floating point workloads.
COLLABORATION OF AWS AND INTEL ON THE NEW AMAZON EC2 C5 INSTANCES
Watch Dr. Matt Wood, GM of Artificial Intelligence at Amazon Web Services, talk about the collaboration of AWS and Intel on the new Amazon EC2 instance.
“Together with Intel, we’ve optimized deep learning engines with the latest version of the Intel® Math Kernel Library, and the Intel® Xeon® Scalable processors available of the new Amazon EC2 C5 instance, to increase machine learning inference performance by over 100x.
Intel® Xeon® Scalable Processors
Intel® Xeon processor families are the foundation of new services being deployed by AWS. AWS instances based on Intel® processors are ready to serve unique and innovative new workloads that demand better data protection, faster processing of greater data volumes, and service flexibility without a hit to performance.
Intel® Advanced Vector Extension 512 (Intel® AVX-512) offers accelerated application performance 2x better than previous generation technologies, enabling significant improvements in workload speed and data application.
Intel® Trusted Execution Technology (Intel® TXT) remains Intel’s technology for establishing more secure platforms, and with Intel® One Touch Activation comes an added level of protection for geographic needs like regional and county-specific data sovereignty regulations.
Intel® Advanced Encryption Standard New Instructions allow you to enable encryption for enhanced data security without paying a performance penalty.
Intel® Advanced Vector Extensions 2 (Intel® AVX2) can double the floating-point performance for compute-intensive workloads over Intel® AVX, and it provides additional instructions useful for compression and encryption.
Intel® Transactional Synchronization Extensions (Intel® TSX) enabling faster application execution time, boosting the performance of in-memory transactional data processing.
Intel® Xeon® processor E5 family, based on the Haswell microarchitecture, has better branch prediction--making it efficient at prefetching instructions and data--along with other improvements that can boost existing applications’ performance by 30% or more.
P state and C state control provides the ability to individually tune each core’s performance and sleep states to improve application performance.
Intel® AVX2 can double the floating-point performance for compute-intensive workloads over Intel® AVX, and provides additional instructions useful for compression and encryption.
High Performance Computing
Deploying High Performance Computing (HPC) workloads on AWS allows customers to cost-effectively run and scale the most computationally intensive applications on-demand, discover new insights, and innovate faster.
SCHRODINGER CASE STUDY
Transforming pharmaceutical research with AWS
Personalized medicine and genomic research
HPC storage solutions with Cloud Edition Lustre* and AWS
AWS, using industry-leading Intel® Xeon® Scalable technologies for security and high performance, provides the broadest and deepest set of managed services. It offers the most proven Big Data and analytics platform, with over 170 unique customer references.
CLOUD COMPUTING AND PRECISION MEDICINE
From the lab to the clinic, precision medicine is increasingly becoming a reality. As the demand for precision medicine grows, cloud computing vendors like AWS and Intel are playing a role in delivering this important new approach to analyzing massive data sets to bring revolutionary treatment to patients.
In-Memory Processing in the Cloud with Amazon ElastiCache
Zappos Successfully Migrates to SAP HANA on AWS in Less Than 48 Hours
Power up your SAP environment with Amazon Web Services (AWS) super powers
Internet of Things
AWS and Intel® gateways provide a highly secure, scalable, edge-to-cloud solution for Internet of Things (IoT) applications. With AWS and Intel, you can deliver seamless connectivity and enhanced security from device to network to cloud, and then use AWS Big Data services to drive business insight.
IOT - DAY ONE
IoT is transforming the world we live in. Across industries, in both the public and private sector, IoT is connecting people and making technology accessible at an affordable cost.
The Michael J. Fox Foundation Accelerates Research to Cure Parkinson's with AWS and Intel
Securing Edge to Cloud IoT Solutions with Intel and AWS
IoT with Intel and AWS - use cases
Artificial Intelligence and Machine Learning
Today, business deploy more Machine Learning workloads on AWS than any other platform. The challenges associated with operating at scale have been removed in the cloud, and it’s never been easier or more cost-effective to collect data, store it, and build custom machine learning and deep-learning models. AWS C5 instance, with the computational power of the Intel® Xeon® Scalable processor, enables customer to create intelligent and innovative new products and experiences, powered by machine learning.
AWS DeepLens is a wireless video camera and API that can be used to learn the latest Artificial Intelligence (AI) tools and technologies, and enable the development of new computer vision applications. An Intel® Atom® Processor provides over 100 GFLOPS of compute power, enough to run tens of frames of incoming video through on-board deep learning models every second.
AWS DeepLens challenge
Jeff Barr blog - AWS DeepLens
DeepLens demo by Dr. Matt Wood at AWS re:Invent 2017
Amazon EC2 provides a wide selection of instance types optimized to fit different use cases. Instance types comprise varying combinations of CPU, memory, storage, and networking capacity and give you the flexibility to choose the appropriate mix of resources for your applications. Each instance type includes one or more instance sizes, allowing you to scale your resources to the requirements of your target workload.
|AWS Instance Type||High Memory instances (6 TB, 9 TB, 12 TB)
||Memory Optimized z1d||Compute Optimized C5||General Purpose M5
|GPU Compute P3||Memory Optimized X1e|
||Intel® Xeon® Platinum 8176M||Intel® Xeon® Scalable Processors||3.0 GHz Intel Xeon Platinum 8000||Intel® Xeon® Platinum 8175M series processors||Intel® Xeon® Platinum 8000 Series||Intel® Xeon® Scalable Processors||Intel E5-2686 v4 processor||Intel Xeon E5-2686 v4 processors||Intel Xeon E5-2686v4 processors||Intel® Xeon® E7 8880 processors|
|Intel® process technology
|14nm Skylake-SP||Yes||22nm Ivy Bridge||14nm Broadwell||14nm Broadwell||22nm Haswell|
|Intel® Turbo Boost
INTEL® CLOUD EDITION FOR LUSTRE
Online store to discover AWS cloud-based software
Maximize HPC storage performance with parallel file system
The easiest way to get started with BigDL is the BigDL AMI in the AWS Marketplace