Turbocharge Your Applications

2y ago
24 Views
2 Downloads
1.60 MB
18 Pages
Last View : Today
Last Download : 2m ago
Upload by : Asher Boatman
Transcription

Turbocharge Your ApplicationsNVIDIA Tesla GPUs in Dell EMC PowerEdge serversINTRODUCTION:CHAPTER 1:Benefits of GPU-Accelerated WorkloadsCHAPTER 2:CHAPTER 3:Dell EMC and NVIDIAMachine LearningCHAPTER 4:CHAPTER 5:Deep Learning / Neural NetworksHigh-Performance ComputingCHAPTER 6:CHAPTER 7:Data AnalyticsVirtual Desktop InfrastructureNEXT STEPS1

IntroductionFor three decades, the microprocessor industry reflected Moore’s Law, with the numberof transistors on a chip doubling about every two years. This rate brought tremendousgrowth, but it couldn’t last forever. The glory days of 50% growth per year are behindus. Today, CPU performance advances at about an average of 10% each year.Fortunately, another game-changing technology is positioned to kickstart the industry.GPU computing has given the industry another huge push forward. NVIDIA , for example,is on track to deliver a 1,000X performance increase over CPUs alone by 2025.1 It’s anexciting time, and the potential benefits are mind-boggling. 100x increaseA GPU is a graphics processing unit designed to accelerate compute performance.Early GPUs were primarily used to quickly render high-resolution images and videosfor PCs and game consoles. Because they can perform parallel processing, GPUs arenow commonly adopted for many uses, including MRI scans, seismic processing, dataanalysis and visualization, and modeling and simulation. Today, GPUs play a leadingrole in high-performance computing (HPC), artificial intelligence (AI), and virtualdesktop infrastructure (VDI).High-PerformanceArtificialVirtual DesktopComputing (HPC)Intelligence (AI)Infrastructure (VDI)2

They also continue to evolve to facilitate machine learning (ML) and deep learning (DL),both for training and inference. GPUs today can accelerate more than 600 applicationswith additional ones coming available monthly. GPUs are used inside everything fromdesktops to supercomputers, including seven of the TOP500’s ten fastest supercomputers.When it comes to server design, Dell EMC’s strong partnership with NVIDIA provides asignificant advantage. The Dell EMC PowerEdge portfolio includes servers specificallydesigned for optimal GPU performance, providing ultimate performance for acceleratoroptimized workloads.This eBook provides an overview of GPU-accelerated computing, then dives into specificaccelerator-optimized workloads. We’ll discuss the most important requirementsand use cases for each workload and provide recommendations for specific Dell EMCPowerEdge servers, highlighting these options in a simple “good, better, best” format.Armed with this information, you’ll be able to customize your data center to meet yourobjectives—today and into the future.3

CHAPTER 1:Benefits of GPU-AcceleratedWorkloadsThe main difference between GPUs and CPUs is in how they process tasks. However,GPUs offload tasks from the CPU—they do not replace them. GPUs have a massivelyparallel architecture consisting of thousands of smaller cores designed for handlingmultiple tasks simultaneously. As a result, GPUs can deliver dramatic performanceimprovements—anywhere from one teraFLOP (TFLOP) to over 100. Even the mostsophisticated CPUs available offer only one teraFLOP, and most offer much less.The Difference between a CPU and GPUCPUGPUAdditionally, GPUs have a different architecture and processing paradigm than CPUs.This allows for more than 50% growth in performance each year, which gives GPUs anadvantage in keeping up with today’s big data demands. The growth of GPU speed isexceeding the rate of data growth, which is why GPUs hold promise to deliver nextgeneration platforms for accelerating analytics at scale.GPU-accelerated computing is the use of a GPU together with a CPU, in order to accelerateprocessing-intensive workloads such as AI, ML, DL, business analytics, and engineeringapplications. It enables a divide-and-conquer approach that offloads compute-intensiveportions of an application to the GPU while the remainder of the code runs on the CPU,as well as freeing the CPU to handle disk and network I/O.4

GPU AccelerationApplication CodeCompute intensive operations-10% of codeSequential CPU codeGPUMulti-core CPUGPU-accelerated computing deployment is growing in popularity due to the large varietyof potential applications, including AI, robots, drones, and self-driving cars. With GPUaccelerated servers, you can easily handle large and extremely fast data streams fromsources such as the Internet of Things (IoT), clickstreams, and business transactions.They can run repetitive and complex queries in milliseconds. Traditional analyticalsolutions just can’t keep up.The benefits of GPU-acceleration include:A light IT footprint:Thousands of GPU processing cores and high-bandwidth memorycan fit on a single card.Innovation velocity:GPUs are twice as efficient as CPUs.Analytic efficiency:GPUs enable real-time data processing.IT managers all face the same challenge: how to meet the demand for computingresources that often exceed available cycles in the system. GPUs can dramaticallyboost the throughput of your data center with fewer nodes, completing more jobs andimproving data center efficiency.5

CHAPTER 2:Dell EMC and NVIDIAOne of the biggest challenges facing businesses today is determining how to dealwith massive amounts of data. Data is often considered an organization’s most importantasset, but handling and processing that data is not easy. Today’s data-intensive workloads require lightning-fast calculations and processing, and they need the fastesthardware including GPU power to get the job done.NVIDIA launched the modern-day GPU in 1999, which was used in the Microsoft Xboxconsole released in 2001. Over the next ten years, NVIDIA GPU technology expandedinto broader computing purposes across all industries. Ongoing performance innovationshave now brought NVIDIA GPUs into the forefront of high-performance computing and beyond.Dell EMC works closely with NVIDIA to develop solutions for today’s acceleratoroptimized workloads. Based on your organization’s workloads and specific needs,Dell EMC PowerEdge servers can help you reach your business objectives.Dell EMC PowerEdge NVIDIA Tesla V100NVIDIA Tesla V100 is the most advanced data center GPU ever built, offering theperformance of up to 100 CPUs in a single GPU. Equipped with 640 Tensor Cores, eachTesla V100 delivers up to 125 teraFLOPS of deep learning performance. Dell EMCPowerEdge servers, including the R740xd, R7425, and R940xa, can be boosted withup to four NVIDIA Tesla V100 GPU accelerators. The PowerEdge C4140 delivers thatacceleration interconnected with NVIDIA NVLink fabric for up to 300GB/s to unleashextreme application performance on a single server.6

Dell EMC PowerEdge NVIDIA T4The new NVIDIA T4 Tensor Core GPU is an accelerated computing platform for diverseworkloads, from the data center to the edge, across training, inferencing, virtualization,and machine learning. The small-form-factor, 70-watt design makes the NVIDIA T4 idealfor enterprise mainstream servers, providing 240x more energy efficiency than CPUs.NVIDIA Turing Tensor Core technology delivers up to 16x higher performance than CPUson training of neural networks, and up to 59x higher performance on inference. The NVIDIAT4 is now available in Dell EMC PowerEdge R740, R740xd, T640, and R7425 servers.27

CHAPTER 3:Machine LearningGPU acceleration can speed the processing of large data sets in machine learningenvironments such as Kinetica, MapD, BlazingDB, Brytlyt, OmniSci, and SQream,analyzing massive amounts of information and returning results in milliseconds. Whenit comes to GPU acceleration for ML, memory and storage are top priorities, and it’simportant to have a well-matched CPU-to-GPU ratio. Based on these requirements,Dell EMC recommends the following PowerEdge servers:GoodPowerEdge R7425PowerEdge R7425 is a 2U, AMD two-socket rack server that delivers outstandingTCO for data analytics, hybrid cloud, and scale-up software-defined deployments.The system can be easily expanded with extreme memory and storage capacityfor low latency, data-intensive workloads. With up to 64 cores, 128 PCIe lanes, andup to 32 DIMMs, the R7425 provides the right balance of compute to I/O thatgives you the freedom to take on challenging, data-intensive projects.BetterPowerEdge R740The PowerEdge R740 server has the perfect balance of accelerator cards, storage,and compute resources in a 2U, two-socket platform. The R740 offers up to 16x2.5” drives or 8x 3.5” drives and iDRAC9, so you can scale to meet demands andsimplify the entire IT lifecycle.8

BestPowerEdge R940xaThe PowerEdge R940xa accelerates applications to deliver real-time decisions.It combines four CPUs with four GPUs in a powerful 1:1 ratio to drive databaseacceleration. With up to 6TB of memory and four-socket performance, the R940xadelivers consistent and fast response times.The Dell EMC DSS 8440: Purpose-Built for Machine LearningThe DSS 8440 is a new 4U, two-socket server optimized for expansion. With awall of fans at the front of the chassis, it supports up to 10 GPUs. In the center, itincludes the latest 2nd Gen Intel Xeon Scalable Processors with Intel Optane DCPMM support. At the rear of the chassis is an array of ten drives, eitherNVMe or SAS/SATA. And there are four 2.4kW power supplies as well as amassive array of PCIe slots for fabric and other devices.Read MoreSee the Video9

CHAPTER 4:Deep Learning / Neural NetworksDeveloping AI applications starts with the training of deep neural networks with largedatasets. GPU-accelerated deep learning platforms like BrightML, Bitfusion, and NVIDIANGC offer the flexibility to design and train custom deep neural networks and provideinterfaces to commonly-used programming languages.Top priorities to consider with deep learning/neural network workloads include GPUdensity, high network bandwidth I/O (IB/OPA/100Gb or above), and peer-to-peer GPUconnectivity. Based on these requirements, Dell EMC recommends the followingPowerEdge servers:GoodPowerEdge T640The PowerEdge T640 is a versatile, powerhousetwo-socket server ideal for mid-sized offices, remotesites, and data centers. The T640 combines powerfulperformance and massive internal storage capacity in arack or tower platform. Winner of the 2018 IT Pro BestTower Server award, the T640 delivers fast insightswith up to 8 NVMe drives and 2x 10GbE connections.310

BetterPowerEdge R7425 or R740PowerEdge R7425 is a 2U, AMD two-socket rack server that delivers outstandingTCO for data analytics, hybrid cloud, and scale-up software-defined deployments.Easily add extreme memory and storage capacity for low latency, data-intensiveworkloads. With up to 64 cores, 128 PCIe lanes, and up to 32 DIMMs, the R7425provides the balance of compute to I/O that gives you the freedom to take onchallenging, data-intensive projects.The PowerEdge R740 server has the perfect balance of accelerator cards, storage,and compute resources in a 2U, Intel two-socket platform. The R740 offers up to16x 2.5” drives or 8x 3.5” drives and iDRAC9, so you can scale to meet demandsand simplify the entire IT lifecycle.BestPowerEdge C4140Give challenging cognitive computing workloads what they need with this high-density,accelerator-optimized server. The PowerEdge C4140 provides maximum densityand outstanding thermal efficiency for scale-out performance. Speed up yourapplications with four NVLink-interconnected GPUs in a 1U, two-socket formfactor, and harness the full potential of complex datasets.“Increasingly, deep learning is a strategic imperative for every major technology company,permeating every aspect of work. Specifically, artificial intelligence is being driven byleaps in GPU computing power that defy the slowdown in Moore’s law. The work we aredoing to advance GPU computing alongside Dell EMC will empower AI developers asthey race to build new frameworks to tackle some of the greatest challenges of our time.”–Ian Buck, NVIDIA411

CHAPTER 5:High-Performance ComputingGPU computing is the most accessible and energy-efficient path to high-performancecomputing (HPC) in the data center. The NVIDIA CUDA programming model for generalcomputing on GPUs offers a language-based solution for programmers who want tofine-tune their applications for the best possible performance. CUDA supports morethan 600 GPU-accelerated applications, including the top 15 HPC applications.When it comes to HPC, be sure to consider high GPU density, high network bandwidthI/O (IB/OPA/100Gb or above), and peer-to-peer transfers between GPUs. Based onthese requirements, Dell EMC recommends the following PowerEdge servers:GoodPowerEdge R7425PowerEdge R7425 is a 2U, AMD two-socket rack server that delivers outstandingTCO for data analytics, hybrid cloud, and scale-up software-defined deployments.Easily add extreme memory and storage capacity for low latency, data-intensiveworkloads. With up to 64 cores, 128 PCIe lanes, and up to 32 DIMMs, the R7425provides the balance of compute to I/O that gives you the freedom to take onchallenging, data-intensive projects.12

BetterPowerEdge R940xaWith the convergence of AI and HPC, the PowerEdge R940xa accelerates applicationsto power real-time decisions. It combines four CPUs with four GPUs in a powerful1:1 ratio to drive database acceleration. With up to 6TB of memory and four-socketperformance, the R940xa delivers consistent and fast response times.BestPowerEdge C4140Give challenging cognitive computing workloads what they need with this high-density,accelerator-optimized server. The PowerEdge C4140 provides maximum densityand outstanding thermal efficiency for scale-out performance. Speed up yourapplications with four interconnected GPUs in a 1U, two-socket form factor.The PowerEdge C4140 delivers that acceleration with NVIDIA NVLink fabricfor up to 300GB/s.13

CHAPTER 6:Data AnalyticsData analytics technologies help companies examine data, draw conclusions, andmake decisions. Data analytics workloads have a wide variety of business uses acrossindustries—for example, fraud detection in financial services, biomedical analysis inhealthcare, customer insights in retail, and demand forecasting in manufacturing.Analytics may involve structured or unstructured data—or both.The top considerations for data analytics include memory bandwidth, high I/O storage(NVMe/SSDs), and CPU sizing for an accelerated solution. Based on these requirements,Dell EMC recommends the following PowerEdge servers:GoodPowerEdge T640The PowerEdge T640 is a versatile, powerhousetwo-socket server ideal for mid-sized offices, remotesites, and data centers. The T640 combines powerfulperformance and massive internal storage capacity in arack or tower platform. Winner of the 2018 IT Pro BestTower Server award, the T640 delivers fast insightswith up to 8 NVMe drives and 2x 10GbE connections.314

BetterPowerEdge R7425 or R740PowerEdge R7425 is a 2U, AMD two-socket rack server that delivers outstandingTCO for data analytics, hybrid cloud, and scale-up software-defined deployments.Easily add extreme memory and storage capacity for low latency, data-intensiveworkloads. With up to 64 cores, 128 PCIe lanes, and up to 32 DIMMs, the R7425provides the balance of compute to I/O that gives you the freedom to take onchallenging, data-intensive projects.The PowerEdge R740 server has the perfect balance of accelerator cards, storage,and compute resources in a 2U, Intel two-socket platform. The R740 offers up to16x 2.5” drives or 8x 3.5” drives and iDRAC9, so you can scale to meet demandsand simplify the entire IT lifecycle.BestPowerEdge R940xaThe PowerEdge R940xa accelerates applications to deliver real-time decisions.It combines four CPUs with four GPUs in a powerful 1:1 ratio to drive databaseacceleration. With up to 6TB of memory and four-socket performance, the R940xadelivers consistent and fast response times.15

CHAPTER 7:Virtual Desktop InfrastructureWith virtual desktop infrastructure (VDI), a user desktop runs inside a virtual machinethat lives on a server in the data center. VDI gives end-users the mobility and freedomto access virtual desktops anytime, anywhere, from any device. VDI can also helporganizations streamline their processes and lower costs by consolidating and centralizingmanagement. NVIDIA has the industry’s highest user-density solution with support forup to 32 virtual desktops per GPU.When it comes to VDI, the most important factors are CPU-to-GPU ratio, storage capacity,and memory. Based on these requirements, Dell EMC recommends the followingPowerEdge servers:GoodPowerEdge T640The PowerEdge T640 is a versatile, powerhousetwo-socket server ideal for mid-sized offices, remotesites, and data centers. The T640 combines powerfulperformance and massive internal storage capacity in arack or tower platform. Winner of the 2018 IT Pro BestTower Server award, the T640 delivers fast insightswith up to 8 NVMe drives and 2x 10GbE connections.3BetterPowerEdge R7425PowerEdge R7425 is a 2U, AMD two-socket rack server that delivers outstandingTCO for data analytics, hybrid cloud, and scale-up software-defined deployments.Easily add extreme memory and storage capacity for low latency, data-intensiveworkloads. With up to 64 cores, 128 PCIe lanes, and up to 32 DIMMs, the R7425provides the balance of compute to I/O that gives you the freedom to take onchallenging, data-intensive projects.16

BestDell EMC VxRail Hyperconverged InfrastructureDell EMC VxRail Hyperconverged Infrastructure appliances, the standard inhyperconverged infrastructure (HCI) jointly developed by Dell EMC and VMware,are ideal for a range of VDI environments, including those that start small andgrow, or require GPU acceleration. HCI solutions benefit VDI customers by providingpredictable scaling for organization growth and simplifying infrastructuremanagement via VxRail Manager.Using NVIDIA GRID Quadro Virtual Data Center Workstation licenses in the VxRailV Series with up to 6 NVIDIA Tesla T4 GPUs, you can create the creative designerworkstation experience to meet your team’s needs. Powered by Dell EMC PowerEdgeservers, VxRail appliances simplify deployment of your software-defined data center,enhance the VDI user experience, and reduce the cost of managing hardware.Dell EMC VDI Complete: Virtual Desktop Infrastructure, EvolvedDell EMC VDI Complete offers a superior solution stack for simple end-to-enddesktop and application virtualization at an exceptional total cost of ownership.Dell EMC VDI Complete combines the power of industry-leading Dell EMC VxRailappliances and vSAN Ready Nodes with VMware Horizon virtualization software.With Optional NVIDIA GPU technology and purpose-built end-user devices, DellEMC VDI Complete provides everything you need for a powerful VDI environment inone fully validated bundle.Learn MoreWatch the Video17

Next StepsReady to learn more? Take a test drive in one of our worldwide DellEMC Customer Solution Centers, or visit Dell EMC to learn moreabout accelerator technology.Explore the Customer Solution Centers »Visit Dell EMCSources:1“Supercharged computing,” NVIDIA. ting2Kharya, Paresh, “Intel Highlighted Why NVIDIA Tensor Core GPUs Are Great for Inference,” NVIDIA, May 21, 2019. erence-nvidia-gpus/3“The IT Pro Product of the Year Awards 2018,” IT Pro, December 27, 2018. product-of-the-yearawards-20184“Dell EMC Demonstrates Significant Momentum in Advancing the High Performance Computing Community at ISC 2017,” Dell EMC, June 20, -nvidia18

T4 is now available in Dell EMC PowerEdge R740, R740xd, T640, and R7425 servers.2 Dell EMC PowerEdge NVIDIA T4. 8 Machine Learning CHAPTER 3: GPU acceleration can speed the processing of large data sets in machine learning environments such as Kinetica, MapD, BlazingDB, Brytlyt, OmniSci, and SQream,

Related Documents:

Sentence Correction Study Guide iii About the Turbocharge your GMAT Series The highly acclaimed Turbocharge Your GMAT series is the result of the arduous ef-fort of Manhattan Review to offer the most comprehensive and clear treatment of the concepts tests in the GMAT. The Manhattan Review Turbocharge Your GMAT prepara-

Microsoft MCSA, MCSE or MCTS on Windows Server 2008 certified and/or experience installing and administering Windows Server and Linux Note: the IT Academy program is currently only available in North America and Europe. Pilots are underway in other regions. Please contact us for general availability plans for your country. Goals

1 Bernard Marr, Forbes, 3 Important Ways Artificial Intelligence Will Transform Your Business And Turbocharge . The global standard ISO Prolog6 is a modern standard approach to logic programming. ISO Prolog is a

‐ The Ultimate Sales Machine is all about working smarter, not harder. ‐ It’s for everyone who plays a role in operating, marketing, selling, and running a company or department. ‐ The Ultimate Sales Machine mind‐set is the culmination of my experiences in the trenches. I've run

BIOS tuning allows you to match performance to your workload for ultimate efficiency. PowerEdge Rack Servers Specifications R940 R940xa R840 Powerful performance: In-memory databases Extreme acceleration: Turbocharge data analytics: GPU database acceleration and machine learning Data-intensive workloads, HFT and dense virtualization Processor

12.1.0.1 Standard Edition unable to enable Unified Auditing Patch 17466854 12.1.0.x Poor performance Patch 28186466, see MOS ID 2212196.1 12.1.0.2 AUDIT Commands Executed With CONTAINER ALL Inside The CDB Are Not Synchronized Into PDB See MOS ID 2312141.1 12.1.0.1 Audit ACTIONS ALL does not audit all actions Fixed in 12.1.0.2, See MOS ID .

Le ad the turbocharge. The 2020 CR-V doesn’t hold back on performance. The 1.5-litre, 16-valve, Direct Injection, DOHC, turbocharged 4-cylinder engine provides the CR-V with 190 horsepower1 and 179 lb.-ft of torque, while the continuously variable transmission (CVT) keeps it all working smoothly. It harnesses that power

Take-off Tests Answer key 2 Answer key 1 Fill in the gaps 1 open 6 switch 2 turn 7 clean 3 pull 8 remove 4 start 9 rotate 5 press 10 hold 2 Complete the sentences 1 must 2 must not 3 must 4 cannot/must 5 must not 6 must not 7 must not 8 can 9 must 3 Make full sentences 1 Electric tools are heavier than air tools. 2 Air tools are easier to handle than electric tools. 3 Air tools are cheaper .