DALIAN, China, April 28, 2019 — On April 25, the ASC19 Student Supercomputer Challenge (ASC19) finals came to a close at Dalian University of Technology. Taiwan Tsing Hua University claimed Champion for the first time, Tsinghua University won Silver, Sun Yat-sen University won e Prize, Beihang University won the Highest LINPACK, while the group made up of teams from Sun Yat-sen University, Taiyuan University of Technology, the Chinese University of Hong Kong and Friedrich-Alexander-Universität Erlangen-Nürnberg became the winner of the first-ever Group Competition.
ASC19 was jointly organized by Asia Supercomputer Community, Inspur Group and Dalian University of Technology. More than 300 teams from colleges all over the world signed up and 20 of them entered the finals.
In the finals, the teams were asked to design their own supercomputer system within 3000W power consumption and run cutting-edge science and engineering applications such as HPL&HPCG benchmarks, Face Super Resolution, Community Earth System Model (CESM), wtdbg, a gene sequencing assembly software, and ShengBTE, a phonon calculation software. The top 20 teams formed 5 groups through an on-site draw and tackle the Fluidity challenge. It is the first-ever Group Competition in ASC, aiming to promote cross-team cooperation and communication.
The battle for Champion was extremely fierce as the top teams are very close. In the end, the Taiwan Tsing Hua University team played perfectly in multiple tasks including HPCG, CESM and ShengBTE, and won their first ASC champion with profound understanding of supercomputing system and applications as well as excellent performance optimization. The Tsinghua University team also delivered stunning performance, achieved good results in various tasks and won the Silver Prize, showing their strength as a “Dream Team”. Interestingly, this is the second time in the ASC final that Taiwan Tsing Hua University and Tsinghua University won Champion and Silver Prize respectively. The difference is that in ASC13, Tsinghua University claimed Champion while Taiwan Tsing Hua University won Silver Prize.
The Sun Yat-sen University team performed best in CESM, the task for e Prize, by designing a multithreading method and greatly optimizing process communication, memory access and vectorization, thus won the prize. The Beihang University team ran the HPL benchmark test within 3000W power consumption and achieved consistent floating-point performance of 50.21 TFLOPS and won the Highest LINPACK. Meanwhile, the Beihang University team also achieved the best results in the artificial intelligence (AI) task Face Super Resolution. Compared with original high-definition images, the high-definition images generated by computer showed a very high identity similarity, demonstrating the team members' abilities of rapid learning, understanding and innovation in the field of AI.
The group consisting of teams from Sun Yat-sen University, Taiyuan University of Technology, the Chinese University of Hong Kong and Friedrich-Alexander-Universitat Erlangen-Nurnberg became the first Group Competition winner ASC for their outstanding cross-team work on optimizing Fluidity, a fluid mechanics software.
“I am very happy to see the new Group Competition,” said Jack Dongarra, Member of National Academy of Engineering, and Distinguished Professor at the Oak Ridge National Laboratory and the University of Tennessee. “One of the objectives of the ASC competition is to encourage students to work together and find the best strategies to accomplish the tasks through communication and discussion. Group Competition will help students understand the meaning and value of cooperation. Meanwhile, many old team members participating in ASC before now coach new team members, which is a legacy of ASC.”
According to Wang Endong, the initiator of the ASC challenge and Academician of the Chinese Academy of Engineering, noted that the rise of AI has created a new and important application area for HPC, and how to achieve better integration of supercomputing and AI will become an important research topic of future computing technology. Through scientific computing and AI computing tasks, ASC inspires new ideas and innovation of college students and promotes supercomputing talents training in the era of AI.
“Currently, more and more key issues in scientific research and major engineering cannot be solved by relying solely on theoretical and experimental research methods. Large-scale, high-performance computation and simulation are providing new research approaches,” said Guo Dongming, Academician of the Chinese Academy of Engineering and President of Dalian University of Technology. “The ASC competition is of great value for the application and promotion of high-performance computing. The competition has enabled college students to have hands-on experience in high-performance computing, stimulated their interest and passion for supercomputers, and effectively promoted the cultivation and communication of young supercomputing talents. “
The ASC Student Supercomputer Challenge is the world's largest student supercomputer competition, sponsored and organized by China and supported by Asian, European, and American experts and institutions. The main objectives of ASC are to encourage exchange and training of young supercomputing talent from different countries, improve supercomputing applications and R&D capacity, boost the development of supercomputing, and promote technical and industrial innovation. The annual ASC Supercomputer Challenge was first held in 2012 and has since attracted over 7,000 undergraduates from all over the world. Learn more about ASC at https://www.asc-events.org/
The winners of ASC19 finals are:
Taiwan Tsing Hua University
Tsing Hua University
Group Competition Award:
Sun Yat-sen University, Taiyuan University of Technology, the Chinese University of Hong Kong and Friedrich-Alexander-Universitat Erlangen-Nurnberg
Sun Yat-sen University
Universidad EAFIT, Jinan University, Southern University of Science and Technology
Most Popular Team:
Southern University of Science and Technology, Universidad EAFIT
Sun Yat-sen University, Beihang University, Jinan University, Fuzhou University, Southern University of Science and Technology, The Chinese University of Hong Kong, Huazhong University of Science and Technology, Universidad EAFIT, Peking University, Shanxi University, Shanghai Jiao Tong University, Friedrich-Alexander-Universitat Erlangen-Nurnberg, University of Electronic Science and Technology of China, Taiyuan University of Technology, Dalian University of Technology, University of Warsaw / Warsaw University of Technology, Sungkyunkwan University, University of Tartu
SOURCE Inspur Electronic Information Industry Co., Ltd
Powered by WPeMatico