oneAPI DevSummit China 2022

October 19, 2022 | 9:00-18:00 CST

Are you a C++ and GPU Programmer, AI Developer, Researcher, or Data Scientist who develops applications in HPC and AI in China? Interested in accelerating workflows and delivering high-performance applications across one or multiple architectures?

Join us at the oneAPI DevSummit China 2022 hosted by Intel, focused on oneAPI, SYCL and AI for accelerated computing across xPU architectures (CPU, GPU, FPGA, and other accelerators) from multi-vendors.

In this one-day, live virtual conference, you will learn from leading industry and academia speakers who are working on innovative oneAPI solutions for cross-platform, multi-vendor architecture. Collaborate with fellow developers and connect with other innovators. Dive into a hands-on session where you will learn and be able to apply optimizations to unleash device capabilities on CPUs and GPUs.

 

Agenda

Oct. 19th

Oct. 19th

9:30 - 9:40 CST 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.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.
Presenting

9:40 - 10:25 CST Tech Talk

oneAPI and SYCL: Driving Open, Multivendor, Cross-Architecture for Accelerated Computing

Accelerated computing is here to stay, and the future will consist of more accelerators, from more vendors, with enormous innovation from around the world. Software can harness this diverse innovation only if it rests on open foundations. Proprietary software stacks for accelerators limit choices too much for our future. James will talk about the initiatives and projects of oneAPI and SYCL to provide essential open…
Presenting

10:25 - 10:40 CST Lightning Talk

A Community Forum for Open Accelerated Computing

The oneAPI initiative was announced around 3 years ago to facilitate the publishing of the oneAPI specification, a set of defined programming interfaces for writing software for accelerators such as GPUs. Multiple versions of this specification have been successfully released and regular technical discussions have been facilitated through a set of Technical Advisory Boards. This session will present the next steps for this effort, a…
Presenting

10:40 - 10:45 CST Happy Time

10:45 - 11:05 CST Tech Talk

E-HPC 3.0: Alibaba Cloud E-HPC Integrated Intel oneAPI Development Experience

An introduction to Alibaba Cloud’s high-performance product E-HPC, which integrates Alibaba Cloud ECS (bare metal), RoCE/eRDMA, CPFS, Wuying and other cloud products to form cloud-based HPC solutions for industrial manufacturing, climate meteorology, biological information, rendering, etc. This industry provides computing services. Now it is integrated with intel oneAPI to realize the whole process of parallel software development, debugging, job submission and performance analysis in the…
Presenting

11:05 - 11:25 CST Tech Talk

Lenovo Intelligent Supercomputing Platform LiCO's Deep Integration with Intel oneAPI

LiCO is Lenovo’s one-stop solution for HPC and AI. Through LiCO, HPC clusters can be quickly deployed, including scheduling, monitoring, billing, computing libraries, distributed file systems, high availability, etc. required for cluster operation and management. A friendly web interface is provided for administrators and users. Through the deep integration of Intel oneAPI, it not only provides users with a variety of HPC/AI job templates based…
Presenting

11:25 - 11:45 CST Tech Talk

Application of oneAPI in GeoEast, A Domestic Petroleum Exploration Software

As a petroleum exploration software with completely independent intellectual property rights, GeoEast has become a comprehensive geophysical exploration software family after 20 years of development, and has participated in almost all major oil and gas discoveries in China. With the popularization of high-density acquisition and pre-stack migration imaging technology, the amount of computation has increased by more than 1,000 times. As a GeoEast construction tool,…
Presenting

11:45 - 12:05 CST Tech Talk

Ultrasound Imaging Application Based on DPC++ Technology

At present, Hisense medical equipment company is independently developing a new generation of ultrasound platform, and will derive ultrasound desktop and portable devices based on this platform. The new platform will adopt a brand-new “GPU + CPU” heterogeneous computing architecture. In order to provide users with a more flexible use experience, the new platform places more post-processing functions on the CPU side for execution, which…
Presenting

12:05 - 13:00 CST Lunch

13:00 - 13:05 CST Happy Time

13:05 - 13:25 CST Tech Talk

AI Performance Acceleration Based on oneAPI

The superset information will bring AI Max, the self-developed artificial intelligence container cloud platform integrated with Intel® oneAPI AI Tookits, to realize the optimization and sharing of machine learning. During the period, Intel Extension for Scikit-learn practice sharing and visual defect detection based on Intel AI Reference Kits will be shared.
Presenting

13:25 - 13:45 CST Tech Talk

The Deployment of oneAPI Based on FPGA in Financial Field

This paper introduces the financial acceleration application of FPGA developed with high-level language OpenCL. It includes how to understand and practice the development of FPGA in high-level language from the perspective of software personnel, and some financial acceleration products and practices developed by Guotai Junan Securities using OpenCL in recent years, including Monte Carlo European option pricing, Shanghai and Shenzhen stock market decoding, hardware option…
Presenting

13:45 - 14:05 CST Tech Talk

oneAPI Use Case - Achieve Better Performance Tuning & Optimization for HPC Software

Shuai Liu will demo how to use oneAPI Base and oneAPI HPC toolkits to do performance tuning and optimization for HPC softwares, such as LAMMPS, WRF and VASP.
Presenting

14:05 - 14:10 CST Happy Time

14:10 - 14:30 CST Tech Talk

Integration of oneAPI and “C Programming Practice”

Mr Fang will Introduce the integration of oneAPI and “C Programming Skills Training”, including course overview, association of course modules, course design, integration of oneAPI into course teaching, examples of project proposals based on oneAPI, and further cooperation plans.
Presenting

14:30 - 14:50 CST Tech Talk

Extending SYCL support to multi-vendor GPU and Accelerator

This report mainly introduces how they extend the cross architecture programming language DPC++ to AMD GPU platform. The report first briefly analyzes the basic architecture and constituent modules of AMD GPU computing platforms ROCM and DPC++. Based on the above analysis, the report describes how they integrate AMD device compilation tool chain and DPC + + SYCL compilation tool chain, and realize the mapping from…
Presenting

14:50 - 15:10 CST Tech Talk

Research on High-Performance Financial Application Development for Real-Time Computing

In the highly uncertain market environment, the development of financial models depends on massive data and quantitative back test verification. In recent years, financial application development for in-depth market data has been highly valued by all trading parties. This report takes the application of financial deep market as an example to introduce the development scheme based on oneapi and the efficient solution technology of financial…
Presenting

15:10 - 15:15 CST Happy Time

15:15 - 15:50 CST Workshop

oneAPI Heterogeneous Computing Programming

An introduction to SYCL, a programming language supporting heterogeneous computing based on open standards, as well as the core components of the basic tool suite in Intel® oneAPI series products and the tool suite for HPC-specific workloads . Will also introduce the SYCL program structure, operation examples and code analysis of several sample codes, so that audiences can have a preliminary understanding of this single-source…
Presenting

15:50 - 16:15 CST Workshop

Introduction to Intel® DPC++ Compatibility Tool

The SYCL compatibility tool assists in migrating CUDA code to SYCL code that supports multiple platforms. Follow the guide to learn how to use this assistant tool for code migration, and learn about common problems and solutions encountered when migrating sample code to SYCL.
Presenting

16:15 - 17:30 CST Workshop

Accelerate TensorFlow* Model Inference on CPU with Intel ® AI Software and Hardware Technology

Accelerating AI inference on CPU is a common requirement when AI projects are implemented. Intel has developed a hardware technology to accelerate low precision inference on CPU: Intel ® Deep learning boost technology; At the same time, Intel also launched ® AI analytics toolkit. Through the combination of the two, it helps users to accelerate AI inference on the CPU simply and conveniently. This training…
Presenting

17:30 - 17:35 CST Lucky Draw

×


Learn about joining the UXL Foundation:

Join now