This IBM® Redbooks® publication is a guide about the IBM PowerAI Deep Learning solution. This book provides an introduction to artificial intelligence (AI) and deep learning (DL), IBM PowerAI, and components of IBM PowerAI, deploying IBM PowerAI, guidelines for working with data and creating models, an introduction to IBM Spectrum™ Conductor Deep Learning Impact (DLI), and case scenarios.

IBM PowerAI started as a package of software distributions of many of the major DL software frameworks for model training, such as TensorFlow, Caffe, Torch, Theano, and the associated libraries, such as CUDA Deep Neural Network (cuDNN). The IBM PowerAI software is optimized for performance by using the IBM Power Systems™ servers that are integrated with NVLink. The AI stack foundation starts with servers with accelerators. graphical processing unit (GPU) accelerators are well-suited for the compute-intensive nature of DL training, and servers with the highest CPU to GPU bandwidth, such as IBM Power Systems servers, enable the high-performance data transfer that is required for larger and more complex DL models.

This publication targets technical readers, including developers, IT specialists, systems architects, brand specialist, sales team, and anyone looking for a guide about how to understand the IBM PowerAI Deep Learning architecture, framework configuration, application and workload configuration, and user infrastructure.

This book was produced by a team of specialists from around the world working at the International Technical Support Organization, Poughkeepsie Center.

Dino Quintero is a Solutions Enablement Project Leader and an IBM Level 3 Certified Senior IT Specialist with IBM Redbooks in Poughkeepsie, New York. Dino shares his technical computing passion and expertise by leading teams developing content in the areas of enterprise continuous availability, enterprise systems management, high-performance computing (HPC), cloud computing, and Analytics Solutions. He also is an Open Group Distinguished Technical Specialist. Dino holds a Master of Computing Information Systems degree and a Bachelor of Science degree in Computer Science from Marist College.

Bing He is a Consultant IT Specialist at IBM China. He joined IBM in 2007. He holds a degree in Computer Science from BeiJing JiaoTong University. His areas of expertise include IBM AIX®, performance tuning, IBM PowerVM®, IBM PowerHA®, IBM Geographically Dispersed Resiliency for IBM Power Systems, SAP HANA on Power, and Linux on Power.

Bruno C. Faria is a Data Engineer at IBM Brazil. He has 9 years of experience in the Data and machine learning (ML) fields. He has worked at IBM for 9 years, and dedicated the last 3 years to big data and how to scale and manage large amounts of data and real-time data, and how to apply ML techniques to those systems. His areas of expertise include several SQL and No-SQL databases, ETL, DL, and others.

Alfonso Jara joined IBM Spain in 2001. He has 15+ years of experience designing and deploying highly available and highly virtualized solutions for AIX and IBM pSeries customers. He holds a degree in Physics from Universidad Complutense de Madrid. Today, he is a Certified IT Architect at IBM Global Services, mainly helping to migrate workloads to IBM Cloud, and designing the underlaying infrastructure for some Infrastructure as a Service (IaaS) solutions.

Chris Parsons is a Machine Learning Engineer working at IBM Lab Services in the UK. He has 3 years of experience in the AI field. Chris gained a First-class honors BSc degree in Computer Science at the University of Swansea. He has several areas of expertise, including Mobile Application Development, Web Development, and DevOps. His current focus is DL and TensorFlow applications on IBM Power Systems.

Shota Tsukamoto is in High Performance Data Analytics (HPDA) technical sales at IBM Japan. Since he joined IBM in 2015, he has been in charge of HPDA for Power Systems, and is one of the founding members of the DL team at IBM Japan. He holds a BS degree from Central Washington University. His areas of expertise include IBM Power Systems, Linux (Ubuntu and Red Hat Enterprise Linux), DL frameworks, and genomics applications running on IBM POWER® processor-based servers that are integrated with GPU technology.

Richard Wale is a Senior IT Specialist working at the IBM Hursley Lab, UK. He holds a B.Sc. (Hons) degree in Computer Science from Portsmouth University, England. He has been supporting production IBM AIX systems since 1998. His areas of expertise include IBM Power Systems, PowerVM, AIX, and IBM i.

Thanks to the following people for their contributions to this project:

Wade Wallace
International Technical Support Organization, Austin Center

Minsik Cho, Jason M Furmanek, Cesar Maciel, Scott Soutter
IBM US

De Gao DG Chu, Lin BJ Dong, Zhi Wen Fu, Qing AG Li, Yu Y Song, Kai Yuan KY Wu, Ze Ming ZM Zhao
IBM China

Junfeng JF Liu, Kelvin Lui, Helena H Krolak, Raymond Zhao
IBM Canada

Here’s an opportunity to spotlight your skills, grow your career, and become a published author—all at the same time! Join an ITSO residency project and help write a book in your area of expertise, while honing your experience using leading-edge technologies. Your efforts will help to increase product acceptance and customer satisfaction, as you expand your network of technical contacts and relationships. Residencies run from two to six weeks in length, and you can participate either in person or as a remote resident working from your home base.

Find out more about the residency program, browse the residency index, and apply online at:

Your comments are important to us!

We want our books to be as helpful as possible. Send us your comments about this book or other IBM Redbooks publications in one of the following ways:

IBM Corporation, International Technical Support Organization
Dept. HYTD Mail Station P099
2455 South Road
Poughkeepsie, NY 12601-5400