{"52439":{"#nid":"52439","#data":{"type":"event","title":"CSE Seminar: Hyesoon Kim","body":[{"value":"\u003Cp class=\u0022MsoPlainText\u0022\u003EHyesoon Kim\u003C\/p\u003E\n\u003Cp class=\u0022MsoPlainText\u0022\u003EAssistant Professor, School of Computer Science, Georgia Tech\u003C\/p\u003E\n\u003Cp class=\u0022MsoPlainText\u0022\u003EFor more information please contact Dr. Rich Vuduc at \u003Ca href=\u0022mailto:richie@cc.gatech.edu\u0022\u003Erichie@cc.gatech.edu\u003C\/a\u003E\u003C\/p\u003E\n\u003Cp class=\u0022MsoPlainText\u0022\u003E~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\u003C\/p\u003E\n\u003Cp class=\u0022MsoPlainText\u0022\u003E\u003C\/p\u003E\n\u003Cp class=\u0022MsoPlainText\u0022\u003E\u003C\/p\u003E\n\u003Cp class=\u0022MsoPlainText\u0022\u003E\u0022An analytical GPU performance model and a dynamic compilation system for CPU\/GPU systems\u0022\u003C\/p\u003E\n\u003Cp class=\u0022MsoPlainText\u0022\u003EAbstract: \u003C\/p\u003E\n\u003Cp class=\u0022MsoPlainText\u0022\u003EHeterogeneous multiprocessors are increasingly important in the multi-core era due to their potential for high performance and energy efficiency. To increase efficiency, it is very critical to find optimal resources for different computations. In this talk, I\u2019ll present two our on-going work about building an efficient heterogeneous computing system.\u003C\/p\u003E\n\u003Cp class=\u0022MsoPlainText\u0022\u003EFirst, I\u2019ll present a static time GPU performance analytical model. The GPU analytical model provides insights into the performance bottlenecks of parallel applications on GPU architectures. The key component of the model is estimating the number of parallel memory requests by considering the number of running threads and memory bandwidth. Through this analytical model, we can predict the execution time of a set of important GPGPU applications on average less than a 13% error.\u003C\/p\u003E\n\u003Cp class=\u0022MsoPlainText\u0022\u003ESecondly, I\u2019ll present an automatic technique to map computations to processing elements on a CPU+GPU machine, which we call Qilin. Qilin dynamically compiles code and distributes the computation between the CPU and GPU automatically. This automatic adaptive mapping achieves a 25% reduction in execution time and a 20% reduction in energy consumption than static mappings for a set of important GPGPU applications.\u003C\/p\u003E\n\u003Cp class=\u0022MsoPlainText\u0022\u003E\u003C\/p\u003E\n\u003Cp class=\u0022MsoPlainText\u0022\u003EBio: \u003C\/p\u003E\n\u003Cp class=\u0022MsoPlainText\u0022\u003EHyesoon Kim is an Assistant professor in the School of Computer Science at the Georgia Institute of Technology. Her research interests include high-performance energy-efficient heterogeneous architectures, programmer-compiler-microarchitecture interaction especially for CPU\/GPU systems. She received a BA in mechanical engineering from Korea Advanced Institute of Science and Technology (KAIST), an MS in mechanical engineering from Seoul National University, and an MS and a Ph.D in computer engineering at The University of Texas at Austin.\u003C\/p\u003E\n\u003Cp\u003E\u00a0~~~~~~~~~~~\u003C\/p\u003E\n\u003Cp\u003EYou are cordially invited to attend a reception between 1:30 - 2:00; before the seminar to chat informally with faculty and students.\u003C\/p\u003E\n\u003Cp\u003ERefreshments will be provided\u003C\/p\u003E\n\u003Cp\u003ETo receive future announcements, please sign up to the cse-seminar email list:\u003C\/p\u003E\n\u003Cp\u003E\u003Ca href=\u0022https:\/\/mailman.cc.gatech.edu\/mailman\/listinfo\/cse-seminar\u0022\u003Ehttps:\/\/mailman.cc.gatech.edu\/mailman\/listinfo\/cse-seminar\u003C\/a\u003E\u003C\/p\u003E\n\u003Cp\u003E\u003C\/p\u003E\n\u003Cp\u003E\u003C\/p\u003E","summary":null,"format":"limited_html"}],"field_subtitle":"","field_summary":"","field_summary_sentence":"","uid":"27154","created_gmt":"2010-02-11 15:51:41","changed_gmt":"2016-10-08 01:49:43","author":"Louise Russo","boilerplate_text":"","field_publication":"","field_article_url":"","field_event_time":{"event_time_start":"2009-09-11T15:00:00-04:00","event_time_end":"2009-09-11T16:00:00-04:00","event_time_end_last":"2009-09-11T16:00:00-04:00","gmt_time_start":"2009-09-11 19:00:00","gmt_time_end":"2009-09-11 20:00:00","gmt_time_end_last":"2009-09-11 20:00:00","rrule":null,"timezone":"America\/New_York"},"extras":[],"groups":[{"id":"47223","name":"College of Computing"}],"categories":[],"keywords":[],"core_research_areas":[],"news_room_topics":[],"event_categories":[],"invited_audience":[],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[{"value":"Lometa Mitchell","format":"limited_html"}],"email":[],"slides":[],"orientation":[],"userdata":""}}}