GPU-Accelerated Applications for HPC Industries| NVIDIA

Total Page:16

File Type:pdf, Size:1020Kb

GPU-Accelerated Applications for HPC Industries| NVIDIA ПРИЛОЖЕНИЯ С GPU УСКОРЕНИЕМ ПРИЛОЖЕНИЯ С GPU Экономические и финансовые вычисления Приложение Описание Поддерживаемая Поддержка Multi-GPU функциональность УСКОРЕНИЕМ Aon Benfield Pathwise ™ Specialized platform for real-time Spreadsheet-like modeling Yes hedging, valuation, pricing and risk interfaces, Python-based scripting СОДЕРЖАНИЕ management environment and Grid middleware Altimesh’s Hybridizer C# Multi-target C# framework for data C# with translation to GPU or Yes 01 Экономические и финансовые вычисления parallel computing. Multi-Core Xeon 02 Моделирование климата, погоды и океана Elsen Accelerated Computing Secure, accessible, and accelerated Web-like API with Native bindings Yes 02 Анализ данных Engine (TM) back-testing, scenario analysis, for Python, R, Scala, C. Custom risk analytics and real-time trading models and data streams are easy 03 Оборона и разведка designed for easy integration and to add rapid development. 05 Машинное обучение и глубокое обучение 07 Вычислительные решения для промышленности ВЫЧИСЛИТЕЛЬНАЯ ГИДРОДИНАМИКА Global Valuation Esther In-memory risk analytics system High quality models not admitting Yes НАУЧНО-ИССЛЕДОВАТЕЛЬСКИЕ И ОПЫТНО-КОНСТРУКТОРСКИЕ РАБОТЫ В ОБЛАСТИ for OTC portfolios with a particular closed form solutions, efficient focus on XVA metrics and balance solvers based on full matrix linear ВЫЧИСЛИТЕЛЬНОЙ ГИДРОДИНАМИКИ sheet simulations. algebra powered by GPUs and МЕХАНИКА ТВЕРДОГО ТЕЛА, ПРОЧНОСТНЫЕ РАСЧЕТЫ Monte Carlo algorithms. Hanweck Associates Real-time options analytical engine Real-time options analytics engine Yes ДИЗАЙН И ВИЗУАЛИЗАЦИЯ (Volera) АВТОМАТИЗАЦИЯ ПРОЕКТИРОВАНИЯ ЭЛЕКТРОННЫХ УСТРОЙСТВ (EDA) MiAccLib 2.0.1 Accelerated libraries which Text Processing : Exact Match, Yes 12 Индустрия масс-медиа и развлечений encompasses high speed multi- Approximate\Similarity Text, algorithm search engines, Wild Card, MultiKeyword and АНИМАЦИЯ, МОДЕЛИРОВАНИЕ, РЕНДЕРИНГ data security engine and also MultiColumnMultiKeyword, etc video analytics engines for text Data Security: Accelerated ЦВЕТОКОРРЕКЦИЯ, ШУМОПОДАВЛЕНИЕ processing, encryption/decryption Encryption/Description for AES- СПЕЦЭФФЕКТЫ, КОМПОЗИТИНГ and video surveillance respectively. 128 Vide Analytics: Accelerated РЕДАКТИРОВАНИЕ ВИДЕО И ИЗОБРАЖЕНИЙ Intrusion Detection Algorithm ПЕРЕКОДИРОВАНИЕ ВИДЕОТРАНСЛЯЦИЯ В ПРЯМОМ ЭФИРЕ МОНТАЖ И ЭФФЕКТЫ В ПРЯМОМ ЭФИРЕ MISYS Global Risk Regulatory compliance and Risk analytics Yes ВИЗУАЛИЗАЦИЯ МЕТЕОРОЛОГИЧЕСКИХ ДАННЫХ enterprise wide risk transparency package 16 Визуализация медицинских данных Murex MACS Analytics Library Analytics library for modeling Market standard models for all Yes 16 Вычисления в нефтегазовой отрасли valuation and risk for derivatives asset classes paired with the across multiple asset classes most efficient resolution methods 17 Исследовательские задачи в научно-образовательной сфере (Monte Carlo simulations and Partial Differential Equations) ВЫЧИСЛИТЕЛЬНАЯ ХИМИЯ И БИОЛОГИЯ Numerical Algorithms Group Random number generators, Monte Carlo and PDE solvers Single only ЧИСЛЕННЫЙ АНАЛИЗ (NAG) Brownian bridges, and PDE solvers ФИЗИКА QuantAlea’s Alea.cuBase F# F# package enabling a growing set F# for GPU accelerators Yes of F# capability to run on a GPU ВИЗУАЛИЗАЦИЯ НАУЧНЫХ ВЫЧИСЛЕНИЙ RMS Catastrophic risk modeling for Risk analytics Yes 27 Безопасность FSI (earthquakes, hurricanes, terrorism, infectuous diseases) SciComp, Inc Derivative pricing (SciFinance) Monte Carlo and PDE pricing Single only models Экономические и финансовые вычисления Приложение Описание Поддерживаемая Поддержка Multi-GPU функциональность Aon Benfield Pathwise ™ Specialized platform for real-time Spreadsheet-like modeling Yes hedging, valuation, pricing and risk interfaces, Python-based scripting management environment and Grid middleware Altimesh’s Hybridizer C# Multi-target C# framework for data C# with translation to GPU or Yes parallel computing. Multi-Core Xeon Elsen Accelerated Computing Secure, accessible, and accelerated Web-like API with Native bindings Yes Engine (TM) back-testing, scenario analysis, for Python, R, Scala, C. Custom risk analytics and real-time trading models and data streams are easy designed for easy integration and to add rapid development. Global Valuation Esther In-memory risk analytics system High quality models not admitting Yes for OTC portfolios with a particular closed form solutions, efficient focus on XVA metrics and balance solvers based on full matrix linear sheet simulations. algebra powered by GPUs and Monte Carlo algorithms. Hanweck Associates Real-time options analytical engine Real-time options analytics engine Yes (Volera) MiAccLib 2.0.1 Accelerated libraries which Text Processing : Exact Match, Yes encompasses high speed multi- Approximate\Similarity Text, algorithm search engines, Wild Card, MultiKeyword and data security engine and also MultiColumnMultiKeyword, etc video analytics engines for text Data Security: Accelerated processing, encryption/decryption Encryption/Description for AES- and video surveillance respectively. 128 Vide Analytics: Accelerated Intrusion Detection Algorithm MISYS Global Risk Regulatory compliance and Risk analytics Yes enterprise wide risk transparency package Murex MACS Analytics Library Analytics library for modeling Market standard models for all Yes valuation and risk for derivatives asset classes paired with the across multiple asset classes most efficient resolution methods (Monte Carlo simulations and Partial Differential Equations) Numerical Algorithms Group Random number generators, Monte Carlo and PDE solvers Single only (NAG) Brownian bridges, and PDE solvers QuantAlea’s Alea.cuBase F# F# package enabling a growing set F# for GPU accelerators Yes of F# capability to run on a GPU RMS Catastrophic risk modeling for Risk analytics Yes FSI (earthquakes, hurricanes, terrorism, infectuous diseases) SciComp, Inc Derivative pricing (SciFinance) Monte Carlo and PDE pricing Single only models POPULAR GPU‑ACCELERATED APPLICATIONS CATALOG | NOV14 | 01 SunGard- Adaptiv Analytics A flexible and extensible engine for Existing models code in C# Yes Blazegraph DASL It marries the power and speed of Scala-based graph analytic and Yes fast calculations of a wide variety supported transparently, with CUDA. It delivers graph analytics at machine learning application of pricing and risk measures on a minimal code changes, Supports over 32 billion traversed edges per language, Ease of integration broad range of asset classes and multiple backends including second and easily integrates with into Spark and Hadoop data derivatives. CUDA and OpenCL, Switches Spark and other data management ecosystems, Support for GPU transparently between multiple platforms. cluster deployment. GPUs and CPUS depending on the GPUdb A distributed database for many Query against Big Data in real Yes deal support and load factors. core devices. time. GPUdb is a scalable, distributed No pre-indexing allows for database with SQL-style query complex, ad-hoc query chains. capability for Big Data. Interactively explore large, Synerscope- Synerscope Data Visual big data exploration and Graphical exploration of large Single only Full suite of geospatial calculation streaming data sets. Visualization insight tools network datasets including geo- capability. spatial and temporal components. *Gunrock Gunrock is a library for graph Direction-optimizing BFS, Yes Tanay ZX Lib (Fuzzy Logic) Financial analytics and data mining Monte Carlo simulations, pricing Yes processing on the GPU. Gunrock SSSP, PageRank, Connected library of vanilla and exotic options, fixed achieves a balance between Components, Betweenness- income analytics, data mining. performance and expressiveness centrality by coupling high performance GPU Xcelerit SDK Software Development Kit (SDK) to C++ programming language, Yes implementations with a high-level boost the performance of Financial cross-platform (back-end programming model, that requires applications (e.g. Monte-Carlo, generates CUDA and optimized minimal GPU programming Finite-difference) with minimum CPU code), supports Windows and knowledge. changes to existing code. Linux operating systems. Jedox Helps with portfolio analysis, This database holds all relevant Yes management consolidation, data in GPU memory and is thus liquidity controlling, cash an ideal application to utilize flow statements, profit center the Tesla K40’s 12 GB on-board Моделирование климата, погоды и океана accounting, treasury management, RAM. Scale that up with multiple customer value analysis and many GPUs and keep close to 100 GB of Приложение Описание Поддерживаемая Поддержка Multi-GPU more applications, all accessible compressed data in GPU memory функциональность in a powerful web and mobile on a single server system for fast application or Excel environment. analysis, reporting and planning. *ACME-Atmosphere Global atmospheric model Dynamics only Yes MapD MapD is GPU-powered big data MapD uses GPUs to execute Yes *COSMO Regional numerical weather Radiation only Yes analytics and visualization platform SQL queries on multi-billion row prediction and climate model that is hundreds of times faster datasets and optionally render the than CPU in-memory systems. results, all in milliseconds. Анализ данных *Sqream DB GPU accelerated SQL database Up to 100TB of raw data can be Yes Приложение Описание Поддерживаемая Поддержка Multi-GPU engine for big data analytics. stored and queried in a standard функциональность Sqream speeds SQL analytics by 2U server. Inserts
Recommended publications
  • Cognitive Computing Featuring the IBM Power System AC922
    Front cover Cognitive Computing Featuring the IBM Power System AC922 Ivaylo Bozhinov Boran Lee Gustavo Santos Redpaper IBM Redbooks Cognitive Computing Featuring the IBM Power System AC922 October 2019 REDP-5555-00 Note: Before using this information and the product it supports, read the information in “Notices” on page v. First Edition (October 2019) This edition applies to IBM Power System AC922 models GTH and GTX for Cognitive Solutions. © Copyright International Business Machines Corporation 2019. All rights reserved. Note to U.S. Government Users Restricted Rights -- Use, duplication or disclosure restricted by GSA ADP Schedule Contract with IBM Corp. Contents Notices . .v Trademarks . vi Preface . vii Authors. vii Now you can become a published author, too . viii Comments welcome. viii Stay connected to IBM Redbooks . ix Chapter 1. Introduction to cognitive computing . 1 1.1 Definition of cognitive computing . 2 1.2 What is IBM cognitive computing . 3 1.3 IBM cognitive solutions . 3 1.3.1 Watson Machine Learning . 4 1.3.2 IBM PowerAI Vision . 5 1.4 Third party cognitive solutions. 6 1.5 Power AC922 end-to-end . 6 Chapter 2. IBM Power System AC922 for cognitive computing . 9 2.1 Key hardware components . 10 2.2 Software supported on the Power AC922. 11 2.3 Outstanding features. 12 Chapter 3. Cognitive solutions . 15 3.1 Cognitive solutions from IBM . 16 3.1.1 IBM Watson Machine Learning Accelerator . 16 3.2 Third-party cognitive solutions . 30 3.2.1 H2O Driverless AI and Power AC922 . 30 3.2.2 SQream DB and Power AC922. 31 3.2.3 Kinetica and Power AC922 .
    [Show full text]
  • Gpu-Accelerated Applications Gpu‑Accelerated Applications
    GPU-ACCELERATED APPLICATIONS GPU-ACCELERATED APPLICATIONS Accelerated computing has revolutionized a broad range of industries with over five hundred applications optimized for GPUs to help you accelerate your work. CONTENTS 1 Computational Finance 2 Climate, Weather and Ocean Modeling 2 Data Science & Analytics 4 Deep Learning and Machine Learning 8 Defense and Intelligence 9 Manufacturing/AEC: CAD and CAE COMPUTATIONAL FLUID DYNAMICS COMPUTATIONAL STRUCTURAL MECHANICS DESIGN AND VISUALIZATION ELECTRONIC DESIGN AUTOMATION 17 Media & Entertainment ANIMATION, MODELING AND RENDERING COLOR CORRECTION AND GRAIN MANAGEMENT COMPOSITING, FINISHING AND EFFECTS EDITING ENCODING AND DIGITAL DISTRIBUTION ON-AIR GRAPHICS ON-SET, REVIEW AND STEREO TOOLS WEATHER GRAPHICS 24 Medical Imaging 27 Oil and Gas 28 Research: Higher Education and Supercomputing COMPUTATIONAL CHEMISTRY AND BIOLOGY NUMERICAL ANALYTICS PHYSICS SCIENTIFIC VISUALIZATION 39 Safety and Security 42 Tools and Management Computational Finance APPLICATION NAME COMPANY/DEVELOPER PRODUCT DESCRIPTION SUPPORTED FEATURES GPU SCALING Accelerated Elsen Secure, accessible, and accelerated back- • Web-like API with Native bindings for Multi-GPU Computing Engine testing, scenario analysis, risk analytics Python, R, Scala, C Single Node and real-time trading designed for easy • Custom models and data streams are integration and rapid development. easy to add Adaptiv Analytics SunGard A flexible and extensible engine for fast • Existing models code in C# supported Multi-GPU calculations of a wide variety of pricing transparently, with minimal code Single Node and risk measures on a broad range of changes asset classes and derivatives. • Supports multiple backends including CUDA and OpenCL • Switches transparently between multiple GPUs and CPUS depending on the deal support and load factors.
    [Show full text]
  • Gpu-Accelerated Applications Gpu‑Accelerated Applications
    GPU-ACCELERATED APPLICATIONS GPU-ACCELERATED APPLICATIONS Accelerated computing has revolutionized a broad range of industries with over five hundred applications optimized for GPUs to help you accelerate your work. CONTENTS 1 Computational Finance 2 Climate, Weather and Ocean Modeling 2 Data Science and Analytics 4 Artificial Intelligence DEEP LEARNING AND MACHINE LEARNING 8 Federal, Defense and Intelligence 10 Design for Manufacturing/Construction: CAD/CAE/CAM COMPUTATIONAL FLUID DYNAMICS COMPUTATIONAL STRUCTURAL MECHANICS DESIGN AND VISUALIZATION ELECTRONIC DESIGN AUTOMATION INDUSTRIAL INSPECTION 19 Media & Entertainment ANIMATION, MODELING AND RENDERING COLOR CORRECTION AND GRAIN MANAGEMENT Test Drive the COMPOSITING, FINISHING AND EFFECTS World’s Fastest EDITING ENCODING AND DIGITAL DISTRIBUTION Accelerator – Free! ON-AIR GRAPHICS ON-SET, REVIEW AND STEREO TOOLS Take the GPU Test Drive, a free and WEATHER GRAPHICS easy way to experience accelerated computing on GPUs. You can run 29 Medical Imaging your own application or try one of the preloaded ones, all running on a 30 Oil and Gas remote cluster. Try it today. 31 Research: Higher Education and Supercomputing www.nvidia.com/gputestdrive COMPUTATIONAL CHEMISTRY AND BIOLOGY NUMERICAL ANALYTICS PHYSICS SCIENTIFIC VISUALIZATION 47 Safety and Security 49 Tools and Management Computational Finance APPLICATION NAME COMPANY/DEVELOPER PRODUCT DESCRIPTION SUPPORTED FEATURES GPU SCALING Accelerated Elsen Secure, accessible, and accelerated back- • Web-like API with Native bindings for Multi-GPU Computing Engine testing, scenario analysis, risk analytics Python, R, Scala, C Single Node and real-time trading designed for easy • Custom models and data streams are integration and rapid development. easy to add Adaptiv Analytics SunGard A flexible and extensible engine for fast • Existing models code in C# supported Multi-GPU calculations of a wide variety of pricing transparently, with minimal code Single Node and risk measures on a broad range of changes asset classes and derivatives.
    [Show full text]
  • Sqream DB Technical Whitepaper
    SQream DB Technical Whitepaper A database designed for exponentially growing data July 2017 SQream DB Whitepaper THE SHORT VERSION SQream DB uses GPU technology to improve the performance of columnar queries by at least 20x on large data sets, while reducing the hardware required to perform the query. Typically, a single 2U server equipped with a GPU is equivalent to a 42U rack full of servers. SQream DB is exceptionally well suited for data science, due to its flexibility. Fast discovery of data science models through reducing query latency allows data scientists to be productive and place models into production quickly. SQream DB can query large and complex data up to 100x faster than other relational databases. INTRODUCTION SQream provides a GPU powered big data analytics solution for data scientists, business intelligence professionals and developers to execute complex SQL queries to derive tactical and strategic insights from 10s of TB to 100s of TB to 1 PB or more of raw data using the tools they use today. SQream’s value proposition is increased productivity, 20x-100x in query performance improvement with a reduced hardware footprint, lower software license fees and simplified administration resulting in more data provided for more insights at better service levels at significantly less cost for complex use cases when compared to currently utilized solutions. SQream DB enables high velocity querying of large analytical workloads on a single database installation powered by a one or more GPU cards, deployed on-premise or in the cloud. THE NEED FOR A NEW APPROACH It is well established that data volumes grow exponentially each year.
    [Show full text]
  • Download Extract
    Full text available at: http://dx.doi.org/10.1561/1900000076 Database Systems on GPUs Full text available at: http://dx.doi.org/10.1561/1900000076 Other titles in Foundations and Trends® in Databases Machine Knowledge: Creation and Curation of Comprehensive Knowl- edge Bases Gerhard Weikum, Xin Luna Dong, Simon Razniewski and Fabian Suchanek ISBN: 978-1-68083-836-7 Cloud Data Services: Workloads, Architectures and Multi-Tenancy Vivek Narasayya and Surajit Chaudhuri ISBN: 978-1-68083-774-2 Data Provenance Boris Glavic ISBN: 978-1-68083-828-2 FPGA-Accelerated Analytics: From Single Nodes to Clusters Zsolt István, Kaan Kara and David Sidler ISBN: 978-1-68083-734-6 Distributed Learning Systems with First-Order Methods Ji Liu and Ce Zhango ISBN: 978-1-68083-700-1 Full text available at: http://dx.doi.org/10.1561/1900000076 Database Systems on GPUs Johns Paul National University of Singapore Shengliang Lu National University of Singapore Bingsheng He National University of Singapore [email protected] Boston — Delft Full text available at: http://dx.doi.org/10.1561/1900000076 Foundations and Trends® in Databases Published, sold and distributed by: now Publishers Inc. PO Box 1024 Hanover, MA 02339 United States Tel. +1-781-985-4510 www.nowpublishers.com [email protected] Outside North America: now Publishers Inc. PO Box 179 2600 AD Delft The Netherlands Tel. +31-6-51115274 The preferred citation for this publication is J. Paul, S. Lu and B. He. Database Systems on GPUs. Foundations and Trends® in Databases, vol. 11, no. 1, pp. 1–108, 2021.
    [Show full text]
  • GPU-Accelerated Database Systems Group
    Advanced database systems The Survey of GPU-Accelerated Database Systems Group 133 Abhinav Sharma, 1009225 [email protected] Rohit Kumar Gupta, 1023418 [email protected] Shun-Cheng Tsai, 965062 [email protected] Hyesoo Kim, 881330 [email protected] Abstract GPUs can perform batch processing of considerable chunks in parallel, providing extreme performance over traditional CPU based system. Their usage has shifted dras- tically from exclusive video processing to generic parallel processing. In the past decade, the need for better processors and computing power has increased due to technological advancements achieved by the computing industry. GPUs work as a coprocessor of CPUs and the integration of their architectures has raised many bottlenecks. Multiple GPUs solutions have been developed by industry to tackle these bottle- necks. In this paper, we have explored the current state of GPU-accelerated database industry. We have surveyed eight such databases in the industry and compared them on eight most prominent parameters such as performance, portability, query optimization, and storage models. We have also discussed some of the significant challenges in the industry and the solutions that have been devised to manage these bottleneck. Contents 1 Introduction 1 2 Background Considerations 2 3 The design-space of GPU-accelerated DBMS 3 4 A survey of GPU-accelerated database systems 4 4.1 CoGaDB . .4 4.2 GPUDB . .6 4.3 OmniSci/MapD . .8 4.4 Brytlyt . 10 4.5 SQream . 13 4.6 PGstrom . 15 4.7 OmniDB . 17 4.8 Virginian . 19 5 GPU-accelerated Database Systems Comparison 21 5.1 Functional Properties .
    [Show full text]
  • A Novel GPU Algorithm for Indexing Columnar Databases with Column Imprints
    A Novel GPU Algorithm for Indexing Columnar Databases with Column Imprints A THESIS SUBMITTED TO THE FACULTY OF THE GRADUATE SCHOOL OF THE UNIVERSITY OF MINNESOTA BY Manaswi Mannem IN PARTIAL FULFILLMENT OF THE REQUIREMENTS FOR THE DEGREE OF MASTER OF SCIENCE Eleazar Leal July 2020 c Manaswi Mannem 2020 Acknowledgements I would like to thank my advisor, Dr. Eleazar Leal, who gave me the opportunity to work on this research. He has guided and supported me throughout my degree program, including this research. I have really learnt a lot from him. Additionally, I would like to thank Dr. Arshia Khan and Dr. Desineni Subbaram Naidu for being on my defense committee and for taking the time to go over this research work with me. Finally, many thanks to all the Masters of Computer Science students from the graduating classes of 2018, 2019 and 2020 for being an integral part of my growth here at UMD. i Dedication I dedicate this thesis to my parents, Syam Prasanna and Kamala Mannem, and my brother, Manasseh for being the most remarkable role models to me throughout my life. Their constant support and guidance has always pushed me to pursue my dreams and to excel at them. I would also like to dedicate this thesis to the incredible faculty of the Department of Computer Science at UMD. Working and interacting with each one of them as a student, a researcher and a teaching assistant has been the most rewarding learning experience of my graduate school tenure. ii Abstract Columnar database management systems (CDBMS) are specialized database sys- tems that store data in column-major order, i.e.
    [Show full text]
  • NVIDIA Introduces RAPIDS Open-Source GPU-Acceleration Platform for Large-Scale Data Analytics and Machine Learning
    NVIDIA Introduces RAPIDS Open-Source GPU-Acceleration Platform for Large-Scale Data Analytics and Machine Learning HPE, IBM, Oracle, Open-Source Community, Startups Integrate RAPIDS, Giving Giant Performance Boost to End-to-End Predictive Data Analytics GTC Europe--NVIDIA today announced a GPU-acceleration platform for data science and machine learning, with broad adoption from industry leaders, that enables even the largest companies to analyze massive amounts of data and make accurate business predictions at unprecedented speed. RAPIDS™ open-source software gives data scientists a giant performance boost as they address highly complex business challenges, such as predicting credit card fraud, forecasting retail inventory and understanding customer buying behavior. Reflecting the growing consensus about the GPU's importance in data analytics, an array of companies is supporting RAPIDS -- from pioneers in the open-source community, such as Databricks and Anaconda, to tech leaders like Hewlett Packard Enterprise, IBM and Oracle. Analysts estimate the server market for data science and machine learning at $20 billion annually, which -- together with scientific analysis and deep learning -- pushes up the value of the high performance computing market to approximately $36 billion. “Data analytics and machine learning are the largest segments of the high performance computing market that have not been accelerated -- until now,'' said Jensen Huang, founder and CEO of NVIDIA, who revealed RAPIDS in his keynote address at the GPU Technology Conference. “The world's largest industries run algorithms written by machine learning on a sea of servers to sense complex patterns in their market and environment, and make fast, accurate predictions that directly impact their bottom line.
    [Show full text]
  • Gpu-Accelerated Applications
    GPU-ACCELERATED APPLICATIONS Test Drive the World’s Fastest Accelerator – Free! Take the GPU Test Drive, a free and easy way to experience accelerated computing on GPUs. You can run your own application or try one of the preloaded ones, all running on a remote cluster. Try it today. www.nvidia.com/gputestdrive GPU-ACCELERATED APPLICATIONS Accelerated computing has revolutionized a broad range of industries with over five hundred applications optimized for GPUs to help you accelerate your work. CONTENTS 1 Computational Finance 2 Climate, Weather and Ocean Modeling 2 Data Science and Analytics 5 Artificial Intelligence DEEP LEARNING AND MACHINE LEARNING 9 Federal, Defense and Intelligence 10 Design for Manufacturing/Construction: CAD/CAE/CAM COMPUTATIONAL FLUID DYNAMICS COMPUTATIONAL STRUCTURAL MECHANICS DESIGN AND VISUALIZATION ELECTRONIC DESIGN AUTOMATION INDUSTRIAL INSPECTION 19 Media & Entertainment ANIMATION, MODELING AND RENDERING COLOR CORRECTION AND GRAIN MANAGEMENT COMPOSITING, FINISHING AND EFFECTS EDITING ENCODING AND DIGITAL DISTRIBUTION ON-AIR GRAPHICS ON-SET, REVIEW AND STEREO TOOLS WEATHER GRAPHICS 26 Medical Imaging 29 Oil and Gas 30 Research: Higher Education and Supercomputing COMPUTATIONAL CHEMISTRY AND BIOLOGY NUMERICAL ANALYTICS PHYSICS SCIENTIFIC VISUALIZATION 41 Safety and Security 44 Tools and Management Computational Finance APPLICATION NAME COMPANY/DEVELOPER PRODUCT DESCRIPTION SUPPORTED FEATURES GPU SCALING Accelerated Elsen Secure, accessible, and accelerated back- • Web-like API with Native bindings for Multi-GPU Computing Engine testing, scenario analysis, risk analytics Python, R, Scala, C Single Node and real-time trading designed for easy • Custom models and data streams are integration and rapid development. easy to add Adaptiv Analytics SunGard A flexible and extensible engine for fast • Existing models code in C# supported Multi-GPU calculations of a wide variety of pricing transparently, with minimal code Single Node and risk measures on a broad range of changes asset classes and derivatives.
    [Show full text]
  • International Journal for Scientific Research & Development
    IJSRD - International Journal for Scientific Research & Development| Vol. 5, Issue 04, 2017 | ISSN (online): 2321-0613 Parallel Data Mining on Graphics Processing Unit with CUDA Vandana Purohit1 Piyush Raut2 Sharda Reddy3 Rishikesh Yadav4 Prof. Yashwant Dongre5 1,2,3,4Student 5Assistant Professor 1,2,3,4,5Department of Computer Engineering 1,2,3,4,5VIIT, PUNE India Abstract— The traditional data mining algorithms work in sequential manner which increases their time of execution. II. NVIDIA CUDA ARCHITECTURE[5] These algorithms should use the parallel processing CUDA is an Application Program Interface (API) created by capabilities of the modern GPUs to execute parallel programs NVIDIA which provides a platform for parallel computing. It efficiently. Therefore a parallel data mining algorithm should allows general purpose computing on Graphics Processing be implemented that can utilize the processing power of Unit (GPU). CUDA gives access to parallel computational GPUs to speed up the execution. elements and the virtual instruction set. It also has a unified Key words: CUDA, Graphics Processing Unit virtual memory. CUDA can work with programming languages like C, C++ and Fortran. CUDA is compatible with I. INTRODUCTION all standard operating systems. The traditional data mining algorithms work in sequential GPU is a specialized processor which works on high manner which increases their time of execution. With serial resolution tasks like 3D graphics. GPU allows manipulation processing in multicore systems, only one core does pro- of large block of data faster than CPU as GPU is evolution of cessing while other cores remain idle. A sequential data parallel multicore systems. GPU architecture hides latency mining algorithm handling large data sets would potentially from computation.
    [Show full text]
  • Reference Architecture for 50-100 CONCURRENT Users
    reference architecture for 50-100 CONCURRENT users SQream DB Reference Architectures v1.2 © SQream Technologies 2019 sqream.com SQream DB Reference Architecture Executive Summary This document describes the necessary hardware and software considerations for a 50-100 user installation of SQream DB GPU accelerated data warehouse. Document Purpose The purpose of this document is to describe the SQream DB reference architecture, emphasizing the benefits to the technical audience, while providing guidance for end-users on selecting the right configuration for a SQream DB installation. This document was written in January 2019. Target Audience This document is intended for influencers and decision makers, IT and system architects, system administrators, and experienced users who are interested in a comprehensive reference for a SQream DB installation. Servers SQream recommends rackmount servers by server manufacturers Dell, HP, Cisco, Supermicro, IBM, and others. A typical SQream DB node includes: • Two-socket enterprise processors, like the Intel® Xeon® Gold processor family or an IBM® Power9 processor, providing the high performance required for compute-bound database workloads. See the appendix for other suggested processors. • NVIDIA Tesla GPU accelerators, with up to 5,120 CUDA and Tensor cores, running on PCIe or fast NVLINK busses, delivering high core count, and high-throughput performance on massive datasets • High density chassis design, offering between 2 and 4 GPUs in a 1U, 2U, or 3U package, for best-in- class performance per cm2 Storage SQream DB relies on OS-mountable file systems. A standalone node may use mountable filesystems on simple spinning disk redundant arrays, all the way up to 24 internal SSD or NVMe drives, providing up to 40GB/s per node, or up to 10GB/s per GPU.
    [Show full text]
  • The Infoworld Review of Kinetica
    Review: Kinetica analyzes billions of rows in real time GPU database is not only hugely scalable, but integrates graph analysis, location intelligence, and machine learning with standard SQL In 2009, the future founders of Kinetica​ ​ came up empty when trying to find an existing database that could give the United States Army Intelligence and Security Command (INSCOM) at Fort Belvoir (Virginia) the ability to track millions of different signals in real time to evaluate national security threats. So they built a new database from the ground up, centered on massive parallelization combining the power of the GPU and CPU to explore and visualize data in space and time. By 2014 they were attracting other customers, and in 2016 they incorporated as Kinetica. The current version of this database is the heart of Kinetica 7, now expanded in scope to be the Kinetica Active Analytics Platform. The platform combines historical and streaming data analytics, location intelligence, and machine learning in a high-performance, cloud-ready package. As reference customers, Kinetica has, among others, Ovo, GSK, SoftBank, Telkomsel, Scotiabank, and Caesars. Ovo uses Kinetica for retail personalization. Telkomsel, the Indonesian wireless carrier, uses Kinetica for network and subscriber insights. Anadarko, recently acquired by Chevron, uses Kinetica to speed up oil basin analysis to the point where the company doesn’t need to downsample its 90-billion-row survey data sets for 3D visualization and analysis. Kinetica is often compared to other GPU databases, such as OmniSci​ ​, Brytlyt, SQream DB, and BlazingDB. According to the company, however, they usually compete with a much wider range of solutions, from bespoke SMACK (Spark, Mesos, Akka, Cassandra, and Kafka) stack solutions to the more traditional distributed data processing and data warehousing platforms.
    [Show full text]