GPC2022

ABSTRACT: Serverless computing has been widely used to run fine grained functions in the cloud native era. However, large scale applications with complex dependencies between the functions are not able to benefit from serverless computing. This is mainly because the design logic of serverless computing did not consider: 1) the impact of the communication overheads between the functions, 2) the overhead of the cold container startup. To this end, this talk introduces the key challenges in serverless computing to handle complex applications, the communication-aware function scheduling, and a technique that alleviates the container cold startup through inter-function container sharing.

BIO: Dr. Quan Chen is a professor at the department of computer science and engineering, Shanghai Jiao Tong University. His main research interest lies in computer systems, computer architectures and cloud computing. He has published over 100 peer-reviewed papers in leading venues related to these areas, including ASPLOS, ATC, ISCA, SC, ICS, TPDS, TC, et, al. He is the recipient of the NSFC career award, and IEEE TCSC Award for Excellence (Early career researcher). He is awarded the 2019 Alibaba DAMO Academy Young Fellow. He is on the editorial board of Parallel Computing, JCST, and FCS.

ABSTRACT: The healthcare industry has been at the cutting edge of technology since time immemorial. Hardware, software, medication, surgical procedures; the quality of care available to patients in 2022 has never been better. And yet, the administration and data management underpinning that care is severely lagging behind. In this talk, we will examine how Blockchain Technology may be a game changer for the Medical profession. The technology most commonly associated with Bitcoin could actually transform how we manage electronic medical records (EMR). Deploying EMR using blockchain has the potential to fundamentally disrupt the healthcare industry for good. During this tutorial, we will look at the pros as well as the cons of such implementations. We will dive into current research that is ongoing in this growing field and try to predict future directions this research may take.

BIO: Dr. Gautam Srivastava (Senior Member, IEEE) has extensive Editorial Experience including IEEE Trans on Fuzzy Systems, IEEE Trans on Industrial Informatics, IEEE Transactions on Intelligent Transportations Systems, ACM Transactions on Internet Technology, and ACM Transactions on Low-Resource Asian Languages. Dr. Gautam Srivastava was awarded a B.Sc. from Briar Cliff University in Sioux City, Iowa, the U.S.A. in 2004, followed by an M.Sc. and Ph.D. from the University of Victoria in Victoria, British Columbia, Canada, in the years 2006 and 2012, respectively. He then worked for 3 years at the University of Victoria in the Department of Computer Science (Faculty of Engineering), where he was regarded as one of the top Undergraduate professors in Computer Science Course Instruction at the University. From there in 2014 he started a tenure-track position at Brandon University in Brandon, Manitoba, Canada, where he currently is an Assistant Professor. Dr. G (as he is popularly known) is active in research in the fields of Data Mining and Big Data. During his 8-year academic career, he has published a total of 400 papers in high-impact conferences and journals. He has over 7000 citations in his career and has been recognized with additional adjunct positions in Canada, Taiwan, India, and China. He has given keynote addresses at many well known conferences. Dr. Srivastava currently hold a federal grants through NSERC, MITACS, and CIRA. He also sits on many internal funding agencies as an external reviewer and is currently a Section Chair for the NSERC Discovery Grant Evaluation Group for Computer Science. Google Scholar: https://scholar.google.ca/citations?user=qk9hEQoAAAAJ&hl=en

ABSTRACT: Currently, the heterogenous hardware has been widely adopted in cloud datacenter to provide a wide variety of performance accelerations, TCO reduction and security enhancements. However, practical deployment of such heterogenous system relies on deep system software (such as FS or KMS) codesign with the miscellaneous hardware. Data compression that can not only provide space efficiency with lower Total Cost of Ownership (TCO) but also enhance I/O performance to address the storage wall because of the reduced read/write operations. However, lossless compression algorithms with high compression ratio (e.g. gzip) inevitably incur high CPU resource consumption. This talk will introduce an ASIC-accelerated compression in file system to transparently benefit all applications running on it and provide high-performance and cost-efficient data storage. In addition, this talk will also introduce the high-critical data protection, such as the private key, in public cloud infrastructure.

BIO: Jian Li received the PhD degree in computer science from the “Institut National Polytechnique de Lorraine (INPL)”- Nancy, France, in 2007. He is currently a professor in School of Software, Shanghai Jiao Tong University. He is an ACM member, IEEE senior Member and CCF member. His research interests include virtualization, networking system and cloud computing. He has fruitful publications in the related scope, and the representative publications include PPoPP, ATC, SoCC, VEE, INFOCOM, ICPP, DATE, TPDS, JSAC, TDSC, TCC, JSA, etc.