AWS Intel HPC and Big Data Solutions April
AWS & Intel HPC and Big Data Solutions April 2016
AWS & Intel® = Better Together • 10+ year partnership • Shared passion for delivering innovation and customer value • Joint development of custom silicon optimized for cloud and AWS • Deliver customers consistently high performance and low costs • World class supply chain to meet increasing customer demands
Gartner Cloud Infrastructure Magic Quadrant
Intel® Processor Technologies • Intel® AVX – Dramatically increases performance for highly parallel HPC workloads such as life science engineering, data mining, financial analysis, media processing • Intel® AES-NI – Enhances security with new encryption instructions that reduce the performance penalty associated with encrypting/decrypting data • Intel® Turbo Boost Technology – Increases computing power with performance that adapts to spikes in workloads • Intel Transactional Synchronization (TSX) Extensions – Enables execution of transactions that are independent to accelerate throughput • P state & C state control – provides granular performance tuning for cores and sleep states to improve overall application performance
AWS EC 2 Instances with Intel® Technologies AWS Instance Type High Memory X 1 Compute Optimized C 4 Storage Optimized D 2 Intel Processor Intel Xeon E 78880 v 3 Custom Intel Xeon E 5 -2666 v 3 Intel AVX 2. 0 Intel AES-NI Yes Intel Turbo Boost Yes Intel TSX SSD Storage General Purpose M 4 Memory Optimized R 3 IO Optimized I 2 Graphics Burstable Optimized Performance G 2 T 2 Intel Xeon E 5 -2670 v 2 Intel Xeon E 5 -2670 Intel Xeon Family AVX 2. 0 Yes Yes Yes Yes No No No EBS Optimized by default Yes Yes EBS only Custom Intel Xeon E 5 -2676 v 3
New X 1 Instance - Tons of Memory • Designed for running large-scale, memory intensive applications in the cloud • Ideal for in-memory databases like SAP HANA and big data processing apps like Spark and Presto • First public cloud use of Intel® Xeon® E 7 v 3 Haswell processors • Features up to 2 TB of memory and up to 128 v. CPUs per instance • > 4 X the memory offered by any public cloud instance • Available Summer 2016
Cost Benefits of HPC and Big Data in the Cloud Resources scaled to demand Actual Demand Actual demand Predicted Demand Waste Customer Dissatisfaction Rigid On-Premises Resources Elastic Cloud-Based Resources Capital Expense Model Pay As You Go Model High upfront capital cost Use only what you need High cost of ongoing support Multiple pricing models
HPC Solutions
Unlimited infrastructure Low cost with flexible pricing Latest Intel® Xeon® processers Why AWS & Intel for HPC? Faster time to results Increased speed of research Concurrent clusters on-demand
Popular HPC workloads on AWS Genome Processing Modeling and Simulation Government and Educational Research Monte Carlo Simulations Transcoding and Encoding Computational Chemistry
HPC Spotlight: Genomics • Leverage the Intel Cloud Edition for Lustre on AWS • Quickly and securely build genomics pipelines • Build population analysis infrastructure with Amazon Redshift or Apache Spark • Use built-in tooling to analyze data sets
Sample of AWS HPC Customers
HPC Customer Spotlight “ “ The key advantage that AWS has over running this workflow on Unilever’s existing cluster is the ability to scale up to a much larger number of parallel compute nodes on demand. Pete Keeley Unilever Researchs e. Science IT Lead for Cloud Solutions The combination of our approach to biomedical computing and AWS allowed us to focus our time and energy on simulation development, rather than technology, to get results quickly. Without the benefits of AWS, we certainly would not be as far along as we are. Dr. Peter Tonellato, LPM, Center for Biomedical Informatics, Harvard Medical School ” ”
Big Data Solutions
Unlimited infrastructure Low cost with flexible pricing Latest Intel® Xeon® processers Why AWS & Intel for Big Data? On-demand analytics Interactive query & analysis Real-time clickstream analysis
Popular Big Data workloads on AWS Big Data Analytics Clickstream Analysis Event-Driven ETL Smart Applications Data Warehousing Business Intelligence
Big Data Spotlight: Analytics • Build an entire analytics application to power your business • Scale Hadoop cluster to thousands of instances in minutes • Leverage powerful AWS compute instances using Intel technology
Sample of AWS Big Data Customers
Big Data Customer Spotlight “ “ We were running out of hard drive space and capacity on our Hadoop cluster. With AWS, our developers can now do things they couldn’t before. Our systems team can focus their energies on other challenges. Dave Marin Search & Data Mining Engineer The speed and agility that using AWS gives us lets us develop and deliver business services much more quickly than before, so that we can keep one step ahead of the market. Our staff can deploy instances 90 percent faster than with our previous on-premises solution. Stover Mc. Ilwain Senior Director of IT Infrastructure Engineering ” ”
Getting Started with HPC and Big Data on AWS Learn more at aws. amazon. com/intel and www. cloudinsights. com Get training at aws. amazon. com/training Create free account at aws. amazon. com/register
Thank You
- Slides: 21