oneAPI DevSummit for AI, South Korea 2022

October 26, 2022 | 2:00 - 5:00 pm KST

The oneAPI DevSummit for AI is coming.

Join us for the oneAPI Developer Summit, focused on AI, oneAPI and SYCL for accelerated computing across xPU architectures. In this virtual conference, you will learn from leading industry and academia speakers innovating new oneAPI solutions for cross-platform, multi-vendor architecture.

 

Why attend?

  • Hear about advancements in high-performance computing and AI
  • Get opportunities to attend keynotes, customer voice, and lightning talks hosted by experts from Samsung Healthcare, Moasys, Quanta Cloud Technology, Codeplay Software, JLK, Deeping Source, KMCP and DEEPNOID, as well as hands-on tutorials from Intel (blue)
  • Attend a workshop on the oneAPI AI Analytics Toolkit, oneAPI and SYCL
  • Learn how to migrate CUDA to SYCL using SYCLomatic and how to execute a program written in SYCL on NVIDIA

Agenda

October 26th

October 26th

2:00 - 2:05 KST

Opening Note & Welcome

Welcoming message with Intel’s investment for oneAPI and Intel AI technologies and overall introduction of the event.
LEARN MORE
Presenting
MS Kwon - Vice President, Sales and Marketing Group, The President of Intel Korea
×

MS Kwon - Vice President, Sales and Marketing Group, The President of Intel Korea

Myung-sook (MS) Kwon is vice president of Sales, Marketing, and Communications and President of Intel Korea. She is responsible for sales, marketing and all of Intel’s operations in Korea.

2:05 - 2:10 KST Keynote

The Evolving Ecosystem for Open Accelerated Computing

Intel is putting software first and software developers are the heart of its transformation across the global software ecosystem. From high-performance, data-driven, connected workloads have driven diverse accelerated infrastructures, developers and users demand greater ease of deployment and choice in their solutions. This talk will frame opportunities and progress fowards fulfilling user needs with an open, accelerated computing ecosystem.
LEARN MORE
Presenting
Greg Lavender - Senior Vice President, Chief Technology Officer (CTO), and General Manager of the Software & Advanced Technology Group, Intel
×

Greg Lavender - Senior Vice President, Chief Technology Officer (CTO), and General Manager of the Software & Advanced Technology Group, Intel

Greg Lavender is Senior Vice President, Chief Technology Officer (CTO) and General Manager of the Software and  Advanced Technology Group at Intel Corporation. As CTO, he is responsible for driving Intel’s future technical innovation and research programs. He is also responsible for defining a singular artificial intelligence software stack to support Intel’s range of business and hardware offerings.

Lavender has more than 35 years of experience in software and hardware product engineering & advanced R&D, he joined Intel in June 2021 from VMware, where he served as senior vice president and CTO. Lavender holds a Bachelor of Science in computer science from the University of Georgia, and a Master of Science and Ph.D. in computer science from Virginia Tech.

2:10 - 2:20 KST Lightning Talk

Towards performance portability of DNN Models using SYCL

The wide adoption of Deep Neural Networks (DNN) has served as an incentive to design and manufacture powerful and specialized hardware technologies, targeting systems from Edge devices to Cloud and supercomputers. From the software point of view, there are several AI frameworks (such as TensorFlow, Pytorch, ONNXRuntime, MXNet, etc) and libraries provided to efficiently match the close to metal performance of such devices. From the…
LEARN MORE
Presenting
Mehdi Goli - VP of R&D, Codeplay Software Ltd
×

Mehdi Goli - VP of R&D, Codeplay Software Ltd

Mehdi is VP of R&D, responsible for leading impactful, influential, and innovative research and development projects, ensuring Codeplay remains a leading independent provider of AI and HPC enablement. He joined Codeplay in 2017 as a Senior Software Engineer in AI Parallelisation and he was the Team Lead of Eigen, SYCL-BLAS, and Nvidia backend for Intel oneMKL and oneDNN.

Mr. Goli is also a member of the Technical Advisory Board for Intel oneMKL and Intel oneAPI AI. He has completed his PhD in Parallel Computing at Robert Gordon University, Aberdeen (2015), during which he was a Research Assistant in Parallel Computing at IDEAS Research Institute, working on the ParaPhrase project.

2:20 - 2:35 KST Customer Voice

QCT oneAPI DevCloud

The need for a standard and unified language that can run across various heterogeneous compute platforms is growing with the booming of XPU devices. Intel oneAPI toolkits offers a common language based on SYCL and a set of library APIs, allowing the same code to run on various XPUs. To enable our partners and customers with the latest Intel hardware platform and cutting-edge development tools,…
LEARN MORE
Presenting
Grover Hwang - Solution Architect HPC/AI at QCT
×

Grover Hwang - Solution Architect HPC/AI at QCT

Grover Hwang is the solution architect HPC/AI at QCT. He leads a team to optimize HPC/AI workloads over various platforms. Before joining QCT, he was the administrator of multiple HPC systems for more than fifteen years, including several mission-critical ones. He focuses on introducing cutting-edge software and hardware technologies to accelerate HPC/AI workloads and fulfill customers’ ever-growing computation and storage demands.

“Intel oneAPI offers a common language based on SYCL allowing the same code to run across heterogeneous compute platforms​” – Grover Hwang

2:35 - 2:50 KST Customer Voice

oneAPI for FPGA

Whole genome sequencing is key in the field of genomics, but since it takes a long time to execute calculations, parallelization and offloading using GPU are applied to accelerate it. The most widely used Genome Analysis Toolkit (GATK) is written in Java, so it is impossible to directly apply oneAPI to port it to FPGA, but the previous step, aligning/mapping, is written in C/C++, BWA-MEM…
LEARN MORE
Presenting
Jinwoo Jung - oneAPI Certified Instructor, Moasys
×

Jinwoo Jung - oneAPI Certified Instructor, Moasys

I have 20 years of experience in the HPC field, including code optimization/parallelization, user tech support, and user training.I am currently working as an Intel oneAPI instructor, and I am researching the application of HPC and AI using the tool.

“Ported the open source DRAGMAP program implemented in C/C++ to FPGA (Arria PAC) using the DPC++ compiler implementing oneAPI ” – Jinwoo Jung

2:50 - 3:00 KST Customer Voice

Samsung Healthcare and Intel’s Collaboration on Healthcare Ecosystem

How Samsung Healthcare and Intel collaborated on the projects a. SWBF In order to have flexibilities on choosing architectures and reducing the HW cost, we migrated existing CUDA to SYCL using DPC++ Compatibility Tool. We became to utilize Intel GPUs and CPU altogether. b. Shearwave To optimize our Shearwave feature, we used Intel VTune Profiler. It helped analyze and optimize hotspots and bottlenecks. We have…
LEARN MORE
Presenting
Sungshik Baik - Principle Engineer, Samsung Healthcare
×

Sungshik Baik - Principle Engineer, Samsung Healthcare

Principal Engineer at Samsung Healthcare since 2013, researching Computer Engineering especially in Ultrasound Medical Imaging equipment. He had been developing Laptops for 17 years and joined Samsung Healthcare in 2013. He has Masters in Electrical Engineering from University of Southern California.

3:00 - 3:10 KST Break

3:10 - 3:25 KST Kahoot Game

Quiz on oneAPI, SYCL, FPGA & AI

At an online event that can be boring, quizzes are used to arouse interest while learning oneAPI-related content, and 10 questions are given and prizes are awarded to the top 10 people.
LEARN MORE
Presenting
Ike Lee - Industry Technical Specialist
×

Ike Lee - Industry Technical Specialist

Ike Lee, Industry Technology Specialist, is in charge of technical support for Intel Korea Channel Scale & Partner Team, is developing Intel’s AI platform and trying to introduce and spread AI through education and competitions. In addition, by supporting oneAPI training through oneAPI technology partners, developers can use oneAPI to support parallelization programs on various devices to improve performance and provide HW compatibility.

3:25 - 4:40 KST Workshop- Intel® oneAPI , SYCL

Intel Strategy for Heterogeneous Programming with oneAPI

Intel believes that innovation thrives in an open ecosystem, enables choice, and is equally accessible to all. The oneAPI project and its components reflect this commitment to active ecosystem and featuring an open specification. In this belief, we advance its support for numerous diverse computing architectures. We introduce SYCLomatic and SYCL to support this large ecosystem. SYCLomatic assists developers in migrating their existing code written…
LEARN MORE
Presenting
Jon Kim - Technical Consulting Engineer, Intel
×

Jon Kim - Technical Consulting Engineer, Intel

Jon Kim is a Technical Consulting Engineer at Intel Korea, joined in 2014. He is responsible for Intel® oneAPI supports and consulting customers to enhance their development process as well as to optimize and improve their products’ quality. Acquired his Master’s in Robotics/AI from University of Pennsylvania.

Taehun Kim - Software Technical Consulting Engineer, Intel
×

Taehun Kim - Software Technical Consulting Engineer, Intel

Taehun Kim is a software technical consulting engineer at Intel Korea, joined in 2022. He had worked at Cray, KIAPS and Samsung SDS and has more than 20 years of experience in improving the SW performance of HPC. He holds a Ph.D in Environmental Atmospheric Science from Pukyong National University and Master’s in Marine science from Pusan National University, S.Korea.

4:40 - 5:00 KST

Q&A, Summary & Close

Join us at this session to know the key takeaways from the conference, we shall summarize the event and announce the winners for the Collaboration Hero Contest, Kahoot Game and Survey winners!!
LEARN MORE
Presenting
Ike Lee - Industry Technical Specialist
×

Ike Lee - Industry Technical Specialist

Ike Lee, Industry Technology Specialist, is in charge of technical support for Intel Korea Channel Scale & Partner Team, is developing Intel’s AI platform and trying to introduce and spread AI through education and competitions. In addition, by supporting oneAPI training through oneAPI technology partners, developers can use oneAPI to support parallelization programs on various devices to improve performance and provide HW compatibility.

×


Watch the oneAPI DevSummit hosted by UXL:

Watch Now