oneAPI DevSummit Southeast Asia 2022

September 15, 2022 | 9:00 am to 6.00 pm IST

Join us at the oneAPI DevSummit Southeast Asia focused on oneAPI, SYCL, and AI for accelerated computing across xPU architectures (CPU, GPU, FPGA, and other accelerators). In this LIVE virtual conference, you will learn from leading industry and academia speakers who are working on innovative cross-platform, multi-vendor architecture oneAPI solutions. – Collaborate with fellow developers and connect with other innovators. – Dive into a hands-on session where you will learn and apply optimizations in order to fully exploit device capabilities on CPU’s and GPU’s. – Join a vibrant community supporting each other using oneAPI, SYCL, and AI.

Why attend?

  • Join us for a day of discovery with renowned industry & academia experts who demystify the latest technologies, tools, trends, and techniques
  • Opportunities to attend tech talks and Lightning talks with experts from IIT Dharwad, Durham University, L&T Technology Services, CodeplaySoftware & BittWare.
  • Learn Intel AI tools for end-to-end development—data preparation, training, inference, deployment, and scaling
  • Get best practices for accelerating application performance across CPUs, GPUs, and FPGAs
  • Expand your skills with a hands-on workshop focused on “GPU porting of an HPC application using Intel® oneAPI” & an oneAPI AI Analytics workshop on “Intel optimizations for deep learning frameworks”

Are you an C++ and GPU Programmer, AI Developer, Researcher, or Data Scientist who develops applications in HPC and AI? Interested in accelerating workflows and delivering high-performance applications across one or multiple architectures? Then this event is for you.


September 15th

September 15th

9:00 - 9:10am

Welcome & Introduction

Welcoming the developer community to the oneAPI DevSummit Southeast Asia and introduction to the DevSummit, agenda, topics, speakers. We will introduce the platform and brief the participants on the upcoming contest! Stay tuned for more details, participate and win excisting prizes!
Kavita Aroor

9:10 - 9:20am Opening Note

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 towards fulfilling user needs with an open, accelerated computing ecosystem.
Greg Lavender

9:20 - 9:55am Tech Talk 1

oneAPI Based GPU Porting and Optimization of a Lattice Boltzmann Flow Solver

CFD solvers are computationally expensive as they require higher grid resolutions to capture flow physics accurately and parallelization is necessary to reduce simulation time. In this work, the performance of a Lattice Boltzmann flow solver was optimized on an Intel® Xeon® CPU resulting in a 6X performance gain. Analysis tools like Intel® Advisor and Intel® VTune™ Profiler were used to guide the optimizations. Further, the…
Dr. Dhiraj V. Patil

9:55 - 10:15am Lightning Talk 1

LTTS’s Chest-rAi™ AI Solution for Radiologist/Healthcare

LTTS Chest-rAi™ is an AI-based chest X-Ray Radiology Solution for symptom detection, localization, and reporting intelligence. It automatically detects 10 (will be scaled up to 34) prominent symptoms related to various pulmonary and other thoracic diseases, using chest X-ray images and covering more than 85% of diagnosis encountered at a medical institution. The solution improves symptom detection accuracy to over 92% and saves radiologists time and effort.
Aniket Joshi

10:15 - 10:35am Lightning Talk 2

Accelerating Django Based Performance Monitoring System with Intel Distribution of Python

Server Monitoring Software is an essential tool for system administrators, as it allows for automated reporting, scheduled checks and pre-emptive warnings about the health of your many servers within our operating environment, the tool is used to monitor key resources such as CPU Usage, Memory Consumption, Network, Disk Usage, Process etc. The current tool helps in Monitoring server performance like resource utilization, User usage, &…
Krishna Mouli

10:35 - 10:55am Lightning Talk 3

A Tool for Analyzing High Dimension Data Using oneAPI AI Analytics Toolkits

The topic is about implementation of oneAPI analytics toolkit in Medical Science.We will be exploring single cell data (eg:- scRNA sequence). We will be porting Clustergrammer2 to AI analytics toolkit. Clustergrammer2  produces highly interactive visualizations that enable intuitive exploration of high-dimensional data and has several optional biology-specific features (e.g. enrichment analysis; see Biology-Specific Features) to facilitate the exploration of gene-level biological data. It is a…
Abhishek Nandy

10:55 - 11:15am Lightning Talk 4

oneAPI: Quant Finance Made Easy

In quantitative finance Monte Carlo method is a popular approach when using GPUs. It is implemented using CUDA or OpenCL. The acceleration device use for other areas of the quantitative finance is slowed down due to the high cost of implementation and low rate of speed up.  Thanks to oneAPI a complex pricing using sophisticated models and methods can be easily implemented. Here we demonstrate…
Dr. Suiunbek Ibraev

11:15 - 11:30am Break

11:30 - 11:50am Lightning Talk 5

Playing with Different Devices Through SYCL with oneAPI

toyBrot is a personal project that draws a fractal using raymarching. As a study tool, I reimplement it in different languages/models to explore parallelisation. In this talk, I go over my experiences with using Intel’s oneAPI toolkit to build and run my SYCL implementation of toyBrotfor different types of devices, going over the changes and challenges of expanding from previously using only hipSYCL
Jehferson Mello

11:50am - 12:05pm

Intel® oneAPI Toolkits – Priority Support, Technology Partners & Certified Instructors

Availability of commercial versions with expert worldwide support for the oneAPI Base Toolkit and the HPC, IoT &  Rendering toolkits. Transitioning prior tool suites like Intel Parallel Studio XE and Intel System Studio – where all their components are now available in our oneAPI products extended to Intel XPUs – these will no longer be available to new customers by the end of the year.
Ritesh R. Kulkarni

12:05 - 12:40pm Tech Talk 2

ExaHyPE's SYCL Kernels Within a Multitasked Simulation Environment

Classic task parallelism is not a direct fit to SYCL (or GPUs in general), as tasks are often chosen to be tiny without further nested parallelism. If we deploy a task to a GPU, we however expect it to exploit the accelerator’s hardware concurrency and to be reasonably large. Within the ExaHyPE project, we work with tiny tasks. However, we do not deploy all tasks…
Tobias Weinzierl

12:40 - 1:15pm Tech Talk 3

Free your code from CUDA with Open Standard SYCL

During the past decade or so software developers have been bound to CUDA to write highly parallel software for GPUs. The challenge with this approach is that CUDA is a proprietary programming interface and can only be used with Nvidia GPUs. The landscape for processors is changing rapidly with vendors, including Intel, and new specialized processors such as those harnessing the RISC-V ISA bringing increasing…
Rod Burns

1:15 - 1:45pm Lunch

1:45 - 2:00pm

Jeopardy Game

Kavita Aroor

2:00 - 2:20pm Lightning Talk 6

Using HBM2-enabled FPGAs for 2D FFT Acceleration

FPGAs combine HBM2 memory and reconfigurable pipeline logic to efficiently perform memory access patterns that other parallel architectures might struggle with. This is demonstrated here using a 2D FFT which requires a matrix transpose. We can overlap the transpose operation with computation, with minimal buffering, making it almost free from a throughput perspective. Heavily optimized FPGA FFTs can significantly benefit from reduced precision, but for…
Richard Chamberlain

2:20 - 4:00pm oneAPI Workshop 1

GPU Porting of an HPC Application Using Intel® oneAPI

oneAPI is a cross-industry, open, standards-based unified programming model that delivers a common developer experience across accelerator architectures for faster application performance, more productivity, and greater innovation. Intel® oneAPI Toolkits include implementations of the oneAPI specification along with complementary tools to develop and deploy applications and solutions across Intel® CPU and XPU architectures. This training shall demonstrate the use of Intel® oneAPI tools in the…
Dr. Amarpal S Kapoor

4:00 - 4:10pm Break

4:10 - 5:45pm oneAPI AI Analytics Workshop 2

Intel Optimizations for Deep Learning Frameworks

Overview: This session helps users to learn Intel’s optimizations to TensorFlow and PyTorch. The introduction involves methodologies of Intel optimizations, installation guide, how to use Intel optimizations via exercises. In this session, we will deep dive into Intel’s optimization methodologies, like operator optimization, operator fusion, parallelism, vectorization, on most widely used deep learning frameworks TensorFlow and PyTorch. Meanwhile, we will also briefly introduce oneDNN, a…

5:45 - 6:00pm

Prizes & Closing

Sachin Kelkar