HPC Pros 2020 Conference Schedule

The Association of High Performance Computing Professionals is excited to present the HPC Pros 2020 Conference lineup!  But first, we need to take a moment to thank our generous sponsors who have helped to make this conference a reality.  Thank you!

Register for the conference here!  You’ll need an HPC Pros Professional or Supplier account, which you can sign up for at the same time.  Just go to the signup page, select the appropriate membership level and conference level and fill out the new account information.  Or if you already have an existing account on the website, be sure to log in with that account and add the conference to your membership.

Important:  At the checkout page, you need to select “Checkout with PayPal” option in order to pay for the conference.  You do not need a PayPal account, you can pay as a guest using a credit card as a one-time transaction.

We have an exciting lineup for this year’s conference!  Please note that at this time the schedule is still tentative.  We’re working to firm things up as soon as we can, but as you can see we’ve got a great lineup of speakers and topics!

The below schedule is subject to change of times and speakers.  Be sure to check back in advance of each week.  We’ll do our best to keep changes to a minimum.

Compute Week

Tuesday, September 1, 2020

Time (Pacific Daylight Time)Company AffiliationSpeakerTopic
8:00 - 8:15HPC ProsDerek MagillWelcome and logistics
8:15 - 9:00AnsysJJ JonesAnsys in the Cloud: Product Strategy and Roadmap
9:00 - 10:00IBMLarry Adams for Bill McMillanCognitive Scheduling with LSF: From on premise to the Cloud
10:00 - 11:00AzurePrashant Varshney and Rob FutrickAzure compute solutions powering the HPC platform

Thursday, September 3, 2020

Time (Pacific Daylight Time)Company AffiliationSpeakerTopic
8:00 - 9:00Texas InstrumentsMitch RichlingA Tale of Two IT Universes: A case study in unifying HPC & enterprise workloads
9:00 - 10:00Amazon Web ServicesDavid PellerinAccelerating and Securing Semiconductor Design and Verification on AWS
10:00 - 11:00IntelShesha KrishnapuraInnovative HPC optimizations for Silicon Design
11:00 - 12:00N/AAll Compute Week Speakers InvitedPanel Session

Storage Week

Tuesday, September 15, 2020

Time (Pacific Daylight Time)Company AffiliationSpeakerTopic
8:00 - 9:00Vast DataJeff DenworthDesigning Silicon at Silicon Speed… Introducing the All-Flash Workflow Powered by VAST Data
9:00 - 10:00AzureAndy Chan and Giancarlo DiPasqualeDeep Dive on Azure HPC Storage solutions
10:00 - 11:00IBMStieg Klein, John Welch: Solution ArchitectsLeveraging IBM Spectrum Scale for EDA workloads

Thursday, September 17, 2020

Time (Pacific Daylight Time)Company AffiliationSpeakerTopic
8:00 - 9:00EllexusDr. Rosemary FrancisI/O profiling for efficiencies on-prem and in the cloud
9:00 - 10:00AWSAhmed ElzeftawiAWS Storage deep dive
10:00 - 11:00Panel Session

License Week

Tuesday, September 29, 2020

Time (Pacific Daylight Time)Company AffiliationSpeakerTopic
8:00 - 9:00FlexeraVijay MenonFNMEA Roadmap
9:00 - 10:00ReveneraPaul BlandFNP Roadmap
10:00 - 11:00AltairAlhad JoshiIntroduction to Software Asset Optimization (SAO)
11:00 - 12:00Electronic Design Systems AllianceSashi SubramanianESDA License Management and Anti Piracy Committee Update

Thursday, October 1, 2020

Time (Pacific Daylight Time)Company AffiliationSpeakerTopic
8:00 - 9:00IBMRenita Leung & Larry Adams: Solution ArchitectsLicense Management and Optimization in LSF environments
Key License Vendors
9:00 - 9:20AnsysSteve DelAnsys License Roadmap
9:20 - 9:40CadenceSashi SubramanianCadence License Roadmap
9:40 - 10:00MathworksEric RaffiMathworks License Roadmap
10:00 - 10:20Mentor Graphics, a Siemens CompanyBela KirchbergerMentor License Roadmap
10:20 - 10:40SynopsysRajendra KundapurSynopsys License Roadmap
10:40 - 11:00Key License VendorsAllQ&A
11:00 - 12:00Panel Session

Abstracts and Speaker Bios

Shesha Krishnapura, Intel

Shesha Krishnapura is an Intel Fellow and CTO in Intel’s Information Technology organization. He is responsible for advancing Intel’s data centers for energy- and rack space-efficiency, disaggregated server innovation and hardware designs, high-performance computing (HPC) for electronic design automation (EDA), and optimized platforms for enterprise computing.  He has led the introduction and optimization of Intel architecture compute platforms in the EDA industry since 2001, and his team has delivered five generations of HPC clusters and four supercomputers for Intel’s silicon design and device physics computation.
Shesha is a three-time recipient of the Intel Achievement Award.  He has received the InformationWeek Elite 100 award, the InfoWorld Green 15 award, and been recognized by the US Dept. of Energy for industry leadership in energy efficiency.  He holds several patents and has published over 75 technical articles.  Shesha has a Bachelors in electronics and communications engineering, and a Masters in Computer Science from Oregon State University.  He is the founding chair of the EDA computing board of advisers that influences computer platform standards among EDA application vendors, and has also represented Intel as a voting member of the Open Compute Project since its inception.
Shesha Krishnapura is an Intel Fellow and CTO in Intel’s Information Technology organization.
Title: Innovative HPC optimizations for Silicon Design
Abstract: In the last 13 years, Intel chip design computing has grown 6000% to meet ever-growing compute demands of silicon design complexities due to addition of several new features and the shrinking of process technology. Intensifying the trend, the business drivers such as shorter product development time, and the pressures for reduced headcount and lower cost raise the need for substantial increase in pre-silicon verification, high degree of design automation, and global multi-site design teams. These factors related to both technological and business issues astronomically increase demand for computing and storage, which in turn drives the need for product development to be engineered in optimal HPC environment. Intel IT has brought disruptive technological innovations in datacenter infrastructure and meeting Intel silicon design computing need through more than 293,000+ servers (2.2+ million Xeon high clock cores), 356+ peta bytes of storage, and 588,000+ network ports served out of 63 MW data centers capacity. This presentation will cover the Intel IT HPC innovations journey towards silicon design..

Paul Bland, Revenera

Paul has a background of webapp, API and embedded software development for networked storage. His career has taken him from hands-on engineering, to Agile Product Ownership and Technical Product Management. He has been a Product Manager with Revenera for two and a half years, where he is engaging with customers and engineering teams involved with Revenera’s Software Monetization products. Paul’s qualifications include Finance, Education, Software Development and Advanced Scrum Product Ownership.

Paul is a Senior Technical Product Manager at Revenera

Title: FlexNet Publisher Roadmap 

Abstract:

Mitch Richling, Texas Instruments

Mitch is an IT solution architect focusing on HPC at Texas Instruments for the past 20 years.

Mitch is a Member, Group Technical Staff at Texas Instruments

Title:  A Tale of Two IT Universes: A case study in unifying HPC & enterprise workloads

Abstract:

This talk discusses the methodology, challenges, and results of TI’s first steps in unifying HPC and enterprise workloads on the same hardware.

Ahmed Elzeftawi, Amazon Web Services

Ahmed Elzeftawi is a Semiconductor and EDA Partner Solutions Architect at Amazon Web Services. Prior to joining AWS, he was a Cloud Product Management Director at Cadence Design Systems where he architected and deployed multiple compute clusters for Cadence EDA workloads on AWS. He has 18+ years of experience in Electronic Design Automation, chip design, and High Performance Compute clusters. Ahmed holds a Bachelor of Science in electrical and communications engineering from Cairo University and an MBA from Santa Clara University.

Ahmed Elzeftawi is a Semiconductor and EDA Partner Solutions Architect at Amazon Web Services

Topic: AWS Storage Deep Dive – Accelerating Semiconductor Design Innovation

Abstract: In this session, we’ll do a deep dive into AWS storage services and provide architecture recommendations to build HPC clusters. We’ll provide best practices for the key storage services involved and how to use them to efficiently support HPC and EDA workloads.

Bela Kirchberger, Mentor Graphics, a Siemens Company

Bela Kirchberger is the engineering Technical Lead for Licensing Software.  The License Software team provides licensing technology used by Mentor and Siemens Digital Industries Software products and business systems. Bela’s background includes System Administration, Release Management, Installation, and Licensing software development. He joined Mentor Graphics in 1982 and has been the Licensing Technical Lead since 2002.

Bela is the Technical Lead, Licensing Software at Mentor Graphics, a Siemens Company.

Title: Mentor Product Licensing Roadmap

Abstract:

Mentor’s product licensing roadmap and key information.

Jeff Denworth, VAST Data

Jeff Denworth is the VP of Products and Marketing and a co-founder of VAST Data. Jeff has over a decade of experience with big data and cloud storage technologies. Prior to VAST, Jeff managed marketing at companies such as CTERA Networks, DataDirect Networks (DDN) and Cluster File Systerms where he oversaw marketing, business and corporate development during times of rapid sales growth.

Jeff Denworth is VP, Products at VAST Data

Topic:  Designing Silicon at Silicon Speed… Introducing the All-Flash Workflow Powered by VAST Data

Abstract:

Storage for design automation has been complicated for the past 30 years.  Customers have always struggled to manage capacity and performance because these have been on divergent ends of the storage spectrum, a byproduct of the limitations of mechanical media and limited architecture thinking.  Fast forward to 2020, the need to liberate data from slow and archival storage has never been greater as businesses look to apply new machine learning approaches to their pipelines data to gain insights and advantage.  The modern application agenda has rendered the storage pyramid obsolete – and new solutions are required to modernize infrastructure and data to take businesses into the AI era.

Vijay Menon, Flexera

Vijay has a varied background in managing enterprise products across IT Asset Management, Governance Risk and Compliance, Cloud Services Brokerage and B2C order fulfilment and customer support platforms. He has been a Product Manager with Flexera for three years where he works with passionate and driven teams to address challenges around IT asset lifecycle management, software compliance and optimization.

Vijay Menon is a Product Manager at Flexera

Topic: Roadmap for FlexNet Manager for Engineering Applications

Abstract:

Managing infrastructure and licensing for engineering applications has always been a bit of a dark art. The inherent complexity, performance sensitivity and cost implications of this arena makes the case for a product like FlexNet Manager for Engineering Applications. Our goal is to provide visibility and manageability for this complexity, performance and cost so that license administrators, asset managers and engineering organizations at large can focus on their business and go-to-market objectives. This roadmap session will be focusing on the key areas that engineering companies typically face problems in and how our product is geared to solve those problems.

Eric Raffi, the MathWorks

Eric Raffi is a Principal Engineer at the MathWorks.  Eric has been working at the MathWorks for 25 years, with over 20 years in the Installation and Licensing area.

Eric Raffi

Principal Engineer at the MathWorks

Topic: Mathworks Platform Roadmap

Abstract:

Mathworks platform roadmap.

Bill McMillan, IBM

Bill is the Global Offering Leader for IBM Spectrum LSF within IBM Cloud and Cognitive Software.   With over 25 years experience in High Performance Computing in wide range of industries, Bill is responsible for the offering management, strategic direction and OEM relationships for the LSF family of products.  His interests include the use of GPU’s, Containers and Cloud for high performance and high throughput computing.

He joined IBM in 2012 as part of IBM’s acquisition of Platform Computing.  At Platform, he undertook various roles including Product Architect, Solution Architect, Consultant, Technical Marketing, Systems Engineer as well as Product Management.   Prior to Platform, he worked in varied roles in Aerospace Engineering and Marine Engineering.

Bill holds a BEng(Hons) in Naval Architecture and Offshore Engineering from the University of Strathclyde, and a Diploma in Management from The Open University.

Bill is the Global Offering Leader for IBM Spectrum LSF within IBM Cloud and Cognitive Software.

Topic: Cognitive Scheduling with LSF: From on premise to the Cloud

When I started as an LSF user many moons ago, clusters were in the 10’s of nodes and 10’s of cores. Today it is many thousands of nodes and hundreds of thousands of cores.  Over that time we have added thousands of client driven features as workloads have evolved.  But despite that evolution three things have remained constant: an ever-increasing desire for more compute power, productivity is less than desires due to inefficient workflows, and very limited administrative time. This session will examine new capabilities in the LSF family to help alleviate these challenges.

David Pellerin, Amazon Web Services

David Pellerin serves as Head of Worldwide Business Development for Infotech/Semiconductor at Amazon Web Services. Prior to joining AWS, Mr. Pellerin had a career in electronic design automation and hardware-accelerated reconfigurable computing. He has experience with digital logic simulation and optimization, high-level synthesis, grid and cluster computing, FPGA design, and embedded systems. He has published five Prentice Hall technical books including “Practical Design Using Programmable Logic”, “VHDL Made Easy”, and “Practical FPGA Programming in C”.

David is the Head of Worldwide Business Development for Infotech/Semiconductor at Amazon Web Services

Topic:  Accelerating and Securing Semiconductor Design and Verification on AWS

Abstract:

In this session, we provide an overview of how AWS Cloud improves the performance, throughput, and security of advanced node silicon design. We cover best-practice architectures for compute, storage, and secure supply chain collaboration, along with real-world examples of uses cases including front-end design, physical verification, library characterization, OPC, and other critical workloads. We also provide insights into Amazon’s own use of AWS Cloud for design and verification.

Steve Del, Ansys

Steve Del is Director of Research and Development at Ansys, leading licensing direction and strategy. He has been involved in software licensing for the last 20 years, delivering modern license solutions that align technical and business objectives. More recently, Steve brought to market the industry-changing Ansys Elastic Licensing as a Service solution that bridges the gap between traditional licensing and HPC/Cloud. Steve’s experience includes various roles of increasing responsibility, including testing, development, DevOps, and HPC.
Steve Del is Director of Research and Development at Ansys.
Topic
Ansys Licensing: Improving Customer Success
Abstract
Licensing is critical to the relationship between customers and vendors. Learn what Ansys is doing to improve and simplify licensing experience.

Dr. Rosemary Francis, Ellexus

Dr. Rosemary Francis is the CEO and technical founder of Ellexus, the I/O profiling company. She has a PhD in computer architecture and EDA. Ellexus have recently published a white paper with AWS on migrating EDA workloads for the cloud, focusing on discovery of legacy workloads on-prem as well as cost efficiency through right sizing in the cloud.
Dr. Rosemary Francis is the CEO and technical founder of Ellexus

Topic:  I/O profiling for efficiencies on-prem and in the cloud

Abstract:

Rosemary will be presenting solutions for monitoring I/O, profiling storage, and detecting dependencies for optimizing and migrating EDA workloads. Rosemary will be calling on case studies from customers across the semiconductor industry to show what can be achieved with the right tools and actionable telemetry. The talk will look at how to get more from the on-prem environment as well as how to tackle a burst-cloud model with a particular focus on I/O and storage.

Prashant Varshney, Microsoft Azure

Prashant is a customer-focused product leader with over 20 years of Product Management, Design and development experience in Cloud computing, Semiconductor and EDA industries. Currently, Prashant leads Product Management for Microsoft Azure’s Silicon Vertical with a mission to make Azure the platform of choice for Silicon design. Prashant is responsible for developing, optimizing, and evangelizing the Azure’s cloud solution for chip design. With an industry focused approach, Prashant is also responsible for developing the market, ensuring customer success through production deployments, and developing deep engineering partnerships with IP and EDA vendors.

Rob Futrick, Microsoft Azure

Rob Futrick is the principal program manager lead for the Azure Compute HPC Software + Services team, including Azure Batch, Azure CycleCloud, and HPC Pack. Prior to joining Microsoft, Rob was a co-founder and CTO of Cycle Computing, acquired by Microsoft in 2017. He was responsible for driving the company’s technology and product vision, with a particular focus on enabling highly scalable cloud and hybrid HPC solutions for customers. As a cloud user since 2007, he brings a unique perspective to the challenges that large scale cloud computation presents.
Prashant is a Sr. Director, Product Management, Azure Engineering – Silicon Design & EDA
Rob Futrick is the principal program manager lead for the Azure Compute HPC Software + Services team

Topic: Azure compute solutions powering the HPC platform

Andy Chan, Microsoft Azure

Andy Chan is an innovative, customer focused, and award-winning member of the electronic design automation/ semiconductor industry within Microsoft Azure.  As Azure’s Semiconductor Global Solution Manager, he is part of the technical and business efforts for the “Azure for Silicon initiative”.

Andy has an MBA from Marylhurst University and 15+ years semiconductor industry experience in engineering, operations and architecture from Lockheed Martin, Credence Systems, and Mentor Graphics.

Andy has published and co-authored whitepapers and studies on the semiconductor industry.  In his spare time, Andy likes to read and write even more technical papers.

Giancarlo DiPasquale, Microsoft Azure

Giancarlo DiPasquale is 20+ years data storage veteran with experience helping enterprises solve their most demanding data storage, replication and migration challenges with best of breed solutions across the FinServ, Life Sciences, Education and Enterprise verticals.  He joins the Microsoft HPC team and has spent the last 18 months focused on enabling EDA customers to develop and adapt their silicon design processes to run on Azure.  Giancarlo is based in the Philadelphia area.
Andy is an Azure Global Solutions Principal, Semiconductor & EDA at Microsoft
Giancarlo is a Technical Solutions Professional at Microsoft

Topic: Deep Dive on Azure HPC Storage solutions

Abstract:

Sharing insights on Microsoft’s consideration matrix on optimizing Cloud storage solutions for HPC workloads.  The EDA vertical will be used as a case-in-point in high lighting Azure’s considerations in this presentation

JJ Jones, Ansys

JJ Jones is the Cloud Sales Manager at Ansys, leading direct engagements for the Ansys Cloud product in the Americas and APAC.  He has been working directly with CAE simulation in the cloud for the past 5+ years and recently joined Ansys to help guide the cloud strategy and lead the go-to-market for the resulting products.  JJ has an extensive business partnership background and has worked with many of the major IaaS providers to integrate and deliver solutions to the marketplace.

JJ Jones is the Cloud Sales Manager, Ansys Inc.

Topic: Ansys in the Cloud: Product Strategy and Roadmap

Abstract:

The cloud migration for Ansys customers was well underway prior to the Covid-19 pandemic and has certainly accelerated since.  In this presentation we will cover the paths to the cloud for Ansys customers with particular emphasis on the Ansys Cloud solution we introduced last year and our strategy for that product.  We will also explore the roadmap for further migration to the cloud as well as hybrid cloud and on-premises support.

Stieg Klein, IBM

Stieg Klein is an IBM Subject Matter Expert within the Software Defined Infrastructure team supporting IBM Spectrum Scale/ESS and IBM Spectrum LSF.

He has over 30 years of based experience in High Performance Computing, in Technical Sales, and Development Engineering.  Areas of concentration include Spectrum Scale, a parallel scale out file system, Spectrum LSF and enterprise class workload management.  Prior areas of focus included data communication.

Stieg has a Bachelor of Arts Computer Science degree from University of California Berkeley.  Avid Herper.

John Welch, IBM

John Welch is an LSF Technical Specialist at the IBM Washington Systems Center.  He has over 30 years of experience in IT and software development and has worked on numerous HPC cluster implementation over the last 20 years in both a technical advisor and a consulting role.  John has developed technical labs on AI  and OpenFOAM for IBM Technical University and the IBM Client Experience Centers Cloud.  He has published blogs and demonstrations on Containers, AI, Cloud, and MPI while also co-authoring IBM Spectrum LSF Suite Installation Best Practices Guide and Using IBM Spectrum LSF with NVIDIA DGX systems.

John has a Bachelor of Science degree in Computer Science from Virginia Tech (Go Hokies!) and has an IBM Software Application Implementation Certification.  He is based in San Francisco Bay Area with his family of five and is an avid cyclist and occasionally climbs Mountain Diablo on his bike.

Stieg Klein is an IBM Subject Matter Expert supporting IBM Spectrum Scale and Spectrum LSF.
John Welch is an LSF Technical Specialist at IBM.

Topic: Leveraging IBM Spectrum Scale for EDA workloads

Speakers: Stieg Klein & John Welch, IBM

HPC clusters have four key components –the servers, the storage, the interconnect and the workload manager that ensures the right work is run in the right place at the right time.  Not all schedulers are created equal, and how the scheduler leverages the other components varies.  This session will provide an overview of the IBM Spectrum Storage software portfolio and highlight key capabilities in IBM Spectrum Scale.  It will then examine the interaction between Spectrum LSF Family and Spectrum Scale and how the combination can deliver unique capabilities

Renita Leung, IBM

Renita Leung, P. Eng., is a IBM Global Solutions Architect focusing on HPC, Big Data Analytics, Machine Learning, Deep Learning and AI for Financial Services, Electronics, Aerospace, Automotive, and Life Sciences.  Renita partners with sales, other architects and clients to analyze requirements and design complex technical environments.   Embarking on her 20th year at IBM (10+ years tenure at Platform Computing), she enjoys partaking in consulting, SME work, solution creation, enablement delivery and technical marketing across the globe.  She is also a contributor to IBM Redbooks, authored an HPC related best practices guide as well as technical whitepaper which was later cited in patent applications.

In her spare time, Renita enjoys boxing, gastronomic travel and helping organizations make a positive social impact.

Larry Adams, IBM

Larry Adams is an avid sales focused Global Solutions Architect, Consultant and Open Source Developer who believes that to “do it” means you understand it, and therefore can sell it.

He has over 30 years of broad based experience in High Performance Computing, Manufacturing Engineering, Quality Assurance, Facilities, IT and Network Operations, Software Sales, Consulting and Product Development.  He is Vice President and founding member of the Cacti Group, Inc.  He created IBM Spectrum LSF RTM product based upon Open Source Cacti, and focuses his energy in positioning and selling the LSF Family of Products, including RTM, to IBM customers worldwide.

Larry has a Bachelors of Electrical Engineering (BEE) from the Georgia Institute of Technology in Atlanta Georgia.  He, with his wife and two children hail from Oakland Township Michigan.  He enjoys engaging people in both social and political discussions, has a libertarian approach to all things “life”, he believes in personal privacy, the US Constitution and our oath as citizens to uphold it, and of course exploring information technology, Cacti, billiards and bicycling from time to time

Renita Leung, P. Eng., is a IBM Global Solutions Architect focusing on HPC, Big Data Analytics, Machine Learning, Deep Learning and AI.
Larry Adams is an avid sales focused Global Solutions Architect, Consultant and Open Source Developer at IBM.

Topic: License Management and Optimization in LSF environments

Speakers: Renita Leung & Larry Adams, IBM

 For LSF customers who have the daunting challenge of managing the most scarce resource in the world of HPC, the commercial software license, LSF License Scheduler is indispensable.  In this talk Renita Leung and Larry Adams will explain the challenges that customers face surrounding capital cost savings, organizational consolidations, management and allocation to critical projects, and how those goals can be achieved through the use of LSF License Scheduler combined with insightful reports from LSF RTM.

dmagill

Derek Magill has been in Engineering IT for over 20 years, starting out on the UNIX Help Desk at Texas Instruments. While at TI, he held several technical and leadership roles, mainly focused on the areas of license management and HPC. While at Qualcomm, he led the global EDA License Infrastructure team, the Grid Administration Team, and was the primary Engineering Cloud Architect. He currently is an HPC Solutions Architect at Flux7 Labs, a DevOps Cloud Consultancy. Derek has also served as the Chairman of CELUG since 2015 and is the Executive Director of the Association of High Performance Computing Professionals. He also is a member of the Executive Committee of the 2020 Design Automation Conference.

1

Leave a Reply

This site uses Akismet to reduce spam. Learn how your comment data is processed.