HPC-
Venkata Sai Karthikeya
Created on March 14, 2023
Over 30 million people build interactive content in Genially.
Check out what others have designed:
ESSENTIAL OILS PRESENTATION
Presentation
ANCIENT EGYPT FOR KIDS PRESENTATION
Presentation
CIRQUE DU SOLEIL
Presentation
YURI GAGARIN IN DENMARK
Presentation
EIDIKO JEWELRY
Presentation
PRODUCT MANAGEMENT IN MOVIES & TV SHOWS
Presentation
A GLIMPSE INTO CAPE TOWN’S PAST
Presentation
Transcript
Presented by
Topics Distributed Computing
Vamsi Krishna Raju (030709040)Venkata Sai Karthikeya (030690801)Yamini (030239558)Vinay Kumar Reddy (030738290)
high performance computing systems-analysis on aws ec2
To put it into perspective, a laptop or desktop with a 3 GHz processor can perform around 3 billion calculations per second. While that is much faster than any human can achieve, it pales in comparison to HPC solutions that can perform quadrillions of calculations per second.
High performance computing (HPC) is the ability to process data and perform complex calculations at high speeds.
High Performance Computing
- It is through data that groundbreaking scientific discoveries are made, game-changing innovations are fueled, and quality of life is improved for billions of people around the globe. HPC is the foundation for scientific, industrial, and societal advancements.
- As technologies like the Internet of Things (IoT), artificial intelligence (AI), and 3-D imaging evolve, the size and amount of data that organizations have to work with is growing exponentially. For many purposes, such as streaming a live sporting event, tracking a developing storm, testing new products, or analyzing stock trends, the ability to process data in real time is crucial.
- To keep a step ahead of the competition, organizations need lightning-fast, highly reliable IT infrastructure to process, store, and analyze massive amounts of data.
Importance of HPC
- Academic research: HPC is widely used in academic research, particularly in fields such as physics, chemistry, biology, and engineering. HPC systems are used to run simulations, model complex systems, and analyze large datasets.
- Aerospace and defense: HPC is used extensively in the aerospace and defense industries for tasks such as simulating flight conditions, designing aircraft and missiles, and analyzing sensor data.
- Automotive: HPC is used in the automotive industry for tasks such as simulating crash tests, optimizing engine designs, and analyzing aerodynamics.
Applications of HPC
- Energy: HPC is used in the energy industry for tasks such as modeling weather patterns, simulating fluid dynamics in oil and gas reservoirs, and optimizing wind turbine designs.
- Financial services: HPC is used in the financial services industry for tasks such as risk analysis, high-frequency trading, and fraud detection.
- Healthcare: HPC is used in healthcare for tasks such as analyzing medical images, simulating the effects of drugs on the body, and developing personalized treatment plans.
- Manufacturing: HPC is used in manufacturing for tasks such as simulating manufacturing processes, optimizing supply chain logistics, and designing and testing new products.
Applications of HPC (Contd)
- Compute
- Network
- Storage
HPC Architecture:
Top HPC Vendors
- Amazon EC2
- Elastic Fabric Adapter
- AWS ParallelCluster
- AWS Batch
- Amazon FSx for Lustre
- Amazon FSx for OpenZFS
- NICE DCV
AWS High Performance Computing Services
- EC2 is one of the most popular of AWS’ offering
- EC2 = Elastic Compute Cloud = Infrastructure as a Service
- It mainly consists in the capability of :
- Renting virtual machines (EC2)
- Storing data on virtual drives (EBS)
- Distributing load across machines (ELB)
- Scaling the services using an auto-scaling group (ASG)
- Scaling the services using an auto-scaling group (ASG)
Amazon EC2
- Operating System (OS): Linux, Windows or Mac OS
- How much compute power & cores (CPU)
- How much random-access memory (RAM)
- How much storage space:Network-attached (EBS & EFS)
- hardware (EC2 Instance Store)Network card: speed of the card, Public IP address
- Firewall rules: security group Bootstrap script (configure at first launch): EC2 User Data
- Bulleted list
- Bulleted list
- Bulleted list
- Bulleted list
EC2 Sizing And Configuration
- Bulleted list
- Bulleted list
- Bulleted list
- Bulleted list
ARM BASED PROCESSOR
Advanced RISC Machines or ARM architecture has wide adoption on the compute filed since last one decade. Due to ARM’s architectural built-in capabilities, first time adoptions were more in mobile phones, tablets, setup boxes, smart TVs, electronic wearable’s and Special hardware devices such as IOT devices as their Micro Controllers or minicomputer. The low power consumption and reduced heat generation made a great fitment later in the compute field as well.
How are ARM different from X86?
- The existing X86_64, widely adopted in desktops, laptops, Servers and other general-purpose compute infrastrcture are evolved from traditional Microprocessors 8085 and 8086
- The basic difference between X86 (Intel) and ARM is, x86 is CISC (Complex Instruction Set Computing) and ARM is Arm is RISC (Reduced Instruction Set Computing) based
CISC ARCHITECTURE(X86)
RISC ARCHITECTURE
- AWS is one of the early adopters of ARM architecture in their compute offering stream (AWS EC2). AWS has developed own processor family Gravition, based on ARM architecture.
- AWS Graviton processors are designed to deliver the best price performance. AWS made further enhancement by introducing Graviton-2 with 40% performance improvement in contrast to X86 processor family.
- Graviton2 processors are custom built by AWS using 64-bit Arm Neoverse cores. All Graviton processors include dedicated cores & caches for each vCPU, along with additional security features courtesy of AWS Nitro System; the Graviton2 processors add support for always-on memory encryption
ARM ON AWS
- Graviton-3 based instance family (g7) are in preview mode which is expected to give 25% performance improvement of their Gravition (g6) family.
- The performance improvement will be varied based on the workload characters, higher improvements are expected in Machine Learning (ML) and cryptographic workload due to the larger floating point.
- DDR5 memory in Graviton-3 will compliment the performance improvement
Latest ARM based technology in AWS
ARM options in AWS EC2
AWS added Gravition processor based “g” series in their AWS EC2 family to extend the choice of instance models by Year 2019. This had given flexibility for many customers to explore the ARM capabilities and benchmark performance improvement. Graviton instances are available in most of the common set of instance families such as “tg” for burstable general purpose, “mg” for general purpose workloads, “cg” for compute-intensive workloads, “rg” for memory-intensive workloads, “ig” for storage-intensive workloads.
- AWS offers a range of HPC services that can be used to run high-performance computing workloads on ARM-based processors. These services include:
- Amazon EC2: Amazon Elastic Compute Cloud (EC2) provides resizable compute capacity in the cloud. Users can choose from a range of instance types optimized for different workloads, including ARM-based Graviton and Graviton2 processors. EC2 provides high-performance computing resources, with support for high core counts, large amounts of memory, and high-speed networking.
- Amazon EKS: Amazon Elastic Kubernetes Service (EKS) is a fully managed Kubernetes service that makes it easy to deploy, manage, and scale containerized applications. EKS supports ARM-based processors, providing a scalable and efficient platform for running HPC workloads in containers.
- Amazon FSx: Amazon FSx provides fully managed, scalable file storage for compute-intensive workloads. FSx supports Lustre and BeeGFS file systems, both of which are optimized for high-performance computing workloads. FSx can be used with ARM-based EC2 instances to provide fast, scalable storage for HPC workloads.
Various HPC services offered by AWS
- As most of the Linux distributions have ARM available, container platform has greater flexibility on ARM adoption. As captured , the serverless model of AWS container services, Fargate uses ARM based EC2 instances behind the scene to spin up compute resources for your tasks.
- In both AWS Managed Container Services (ECS and EKS), you can use Graviton-2 based instances on your container cluster
Container platform in ARM
- HPC workloads can be run on AWS ARM-based processors using a variety of different tools and frameworks.
- One of the most popular options for running HPC workloads on AWS is using Amazon Elastic Compute Cloud (EC2) instances that are powered by ARM-based Graviton and Graviton2 processors.
- These instances provide the performance and scalability needed for high-performance computing workloads while also offering energy efficiency and cost savings.
- AWS provides a range of EC2 instance types optimized for HPC workloads, including the C6g and M6g instance families that are powered by the Graviton2 processor. These instance families offer high core counts, large amounts of memory, and high-speed networking to support compute-intensive workloads.
- Users can also leverage AWS HPC tools such as AWS ParallelCluster and AWS Batch to run HPC workloads on ARM-based processors. These tools provide simplified cluster management and job scheduling, making it easy to run and manage large-scale HPC workloads on AWS.
How HPC workloads can be run on AWS arm processors ?
Customizable design
ARM-based processors can be customized to meet the unique requirements of different workloads. This allows users to optimize their systems for specific applications and achieve higher performance and efficiency
Improved energy efficiency
ARM-based processors are designed for energy efficiency, which means they can deliver high performance with lower power consumption compared to traditional x86-based processors. This results in reduced operating costs and a smaller environmental footprint.
Large amounts of memory
: AWS ARM-based processors also offer large amounts of memory, which is essential for processing large data sets and running memory-intensive applications
High core counts
: AWS ARM-based processors, such as the Graviton2, offer high core counts that allow for parallel processing of compute-intensive workloads. This can lead to significant performance improvements for HPC workloads.
Performance Benefits of AWS Arm-based processors for HPC Workloads
- Use Spot Instances: Spot Instances are unused EC2 instances that are available at a discounted price. By using Spot Instances for HPC workloads, organizations can significantly reduce their compute costs. However, since the price of Spot Instances fluctuates based on supply and demand, organizations should be prepared for the possibility of instances being terminated due to higher demand.
- Use Autoscaling: Autoscaling enables organizations to automatically increase or decrease the number of EC2 instances based on workload demands. This means that organizations can scale up their compute resources when needed and scale down when the resources are not needed, reducing the overall compute costs.
- Leverage AWS Cost Management Tools: AWS provides several cost management tools, such as AWS Cost Explorer and AWS Budgets, which enable organizations to monitor and optimize their AWS costs. These tools provide cost reports, usage reports, and alerts, enabling organizations to identify areas of cost optimization and take appropriate action.
Strategies of optimising the costs when using AWS for HPC workloads
- Evaluate your compute and storage requirements: Determine the types of workloads you need to run and the storage requirements for your data. This will help you choose the right compute instances and storage options on AWS.
- Leverage AWS management tools: Use management tools like AWS Batch and AWS ParallelCluster to automate the deployment and management of your HPC workloads on AWS.
- Optimize costs: Use spot instances for compute workloads that are flexible and can tolerate interruptions. Also, leverage AWS cost management tools to monitor and optimize your AWS spending.
- Test and optimize your workloads: Test your HPC workloads on AWS and optimize them for performance and scalability.
Recommendations for organizations looking to use AWS for HPC Workload
- There are several examples of use cases where HPC workloads have been successfully run on AWS ARM-based processors. For example, researchers at the University of Bristol used AWS Graviton2 instances to run simulations of the human heart, which required large amounts of compute power and memory. By using Graviton2 instances, the researchers were able to achieve faster simulation times and reduced costs compared to traditional x86-based instances.
- In another example, researchers at the University of Manchester used AWS Graviton instances to run simulations of the Large Hadron Collider, which required large amounts of memory and compute resources. By using Graviton instances, the researchers were able to achieve faster simulation times and reduce their costs by 30-40% compared to traditional x86-based instances.
- Overall, AWS ARM-based processors offer a powerful and cost-effective option for running HPC workloads in the cloud. By leveraging the power and scalability of ARM-based processors, users can achieve high performance and cost savings for their compute-intensive workloads.
Example Where HPC Workloads have been successfully run on arm-based processors
- Maxar Technologies: Maxar Technologies, a leading provider of satellite imaging and geospatial solutions, used AWS Graviton2 processors to run HPC workloads for satellite imagery processing. The company faced challenges with optimizing their workflows for ARM-based processors, but with the help of AWS, they were able to recompile their code and achieve a 20% reduction in costs while maintaining performance.
- Genialis: Genialis, a bioinformatics company, used AWS Graviton2 processors to run HPC workloads for their genomic analysis platform. The company faced challenges with ensuring their software was compatible with ARM-based processors, but with the help of AWS, they were able to optimize their code and achieve a 25% reduction in costs while maintaining performance.
- SnapEDA: SnapEDA, a provider of digital models for electronic components, used AWS Graviton2 processors to run HPC workloads for their AI-powered component search engine. The company faced challenges with optimizing their algorithms for ARM-based processors, but with the help of AWS, they were able to achieve a 30% improvement in search times while reducing costs.
Case Studies of companies that have successfully run HPC workloads on AWS Arm-based processors
- In conclusion, AWS ARM-based processors, such as the Graviton and Graviton2, offer a range of benefits for running HPC workloads in the cloud.
- These processors provide high performance, reduced costs, and increased scalability, making them an attractive option for companies looking to run compute-intensive workloads.
- AWS offers a range of HPC services, such as Amazon EC2, Amazon EKS, and Amazon FSx, that can be used with ARM-based processors to run HPC workloads.
- Case studies have shown that companies can achieve significant cost savings and performance improvements by leveraging these services.
- Overall, AWS provides a powerful platform for organizations to run HPC workloads, with a range of services and tools to support their needs. By following these recommendations, organizations can successfully leverage AWS for their HPC workloads and achieve their desired outcomes.
CONCLUSION
Thanks for your attention
Any question?