{"628061":{"#nid":"628061","#data":{"type":"news","title":"HPC Framework Blocks May Instigate a New Era of Accessibility for Software Engineers","body":[{"value":"\u003Cp\u003EResearchers are beginning a three-year cross-institute project that aims to lower the barrier to entry for software engineers developing new high-performance applications on large scale parallel systems.\u003C\/p\u003E\r\n\r\n\u003Cp\u003EThe new\u0026nbsp;\u003Ca href=\u0022https:\/\/www.nsf.gov\/awardsearch\/showAward?AWD_ID=1919021\u0022\u003E$1.26 million National Science Foundation (NSF) project\u003C\/a\u003E\u0026nbsp;seeks to develop compiler tools and runtime systems to create a framework, named\u0026nbsp;\u003Cem\u003EParallel Algorithms by Blocks (PAbB\u003C\/em\u003E), built specifically to facilitate simpler programming of scalable parallel systems in high-performance computing (HPC) and exascale machines.\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026ldquo;Current supercomputers and exascale machines are getting harder to program because of how technology is evolving,\u0026rdquo; said School of Computational Science and Engineering (CSE) Professor\u0026nbsp;\u003Ca href=\u0022https:\/\/www.cc.gatech.edu\/people\/umit-v-catalyurek\u0022\u003E\u003Cstrong\u003E\u0026Uuml;mit \u0026Ccedil;ataly\u0026uuml;rek\u003C\/strong\u003E\u003C\/a\u003E\u003Cstrong\u003E.\u003C\/strong\u003E\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026Ccedil;ataly\u0026uuml;rek is Georgia Tech\u0026rsquo;s principal investigator (PI) for the project and joins the project\u0026rsquo;s lead PI, University of Utah Professor\u0026nbsp;\u003Cstrong\u003EPonnuswamy Sadayappan,\u0026nbsp;\u003C\/strong\u003Eand co-PIs,\u0026nbsp;\u003Cstrong\u003EAnanth Kalyanaraman\u003C\/strong\u003E,\u0026nbsp;\u003Cstrong\u003EAravind Sukumaran\u0026nbsp;\u003C\/strong\u003E\u003Cstrong\u003ERajam\u003C\/strong\u003E, and\u0026nbsp;\u003Cstrong\u003ESriram\u0026nbsp;\u003C\/strong\u003E\u003Cstrong\u003EKrishnamoorthy\u0026nbsp;\u003C\/strong\u003Eof Washington State University. The team of researchers plan to combine user insights, new compiler optimizations, and advanced runtime support to create the PAbB framework which will ultimately create building blocks of parallel code for heterogeneous environments to use across a number of applications from computational science and data science.\u003C\/p\u003E\r\n\r\n\u003Cp\u003EFrom caches to networks, architectures are written so that a system inherently wants to transfer multiple items at once. And, according to \u0026Ccedil;ataly\u0026uuml;rek, when looking at algorithms and problems, and thinking of them in terms of blocks \u0026ndash; or packages of data \u0026ndash; they are able to take advantage of hardware transfer and have better scheduling of communication and computation in these heterogeneous systems.\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026ldquo;We cannot make the single core in a computer much faster anymore, which is why sequential programs are not gettingfaster, and why we have to do everything in parallel computing,\u0026rdquo; he said.\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026ldquo;If you look at today\u0026rsquo;s supercomputers you will see that all of the architectures are becoming more and more heterogenous. So, writing parallel code by itself without heterogeneity is difficult, but, when combined, it becomes a barrier for many engineers.\u0026rdquo;\u003C\/p\u003E\r\n\r\n\u003Cp\u003EHeterogenous systems are made up of hardware and software components that necessitate the use of different languages, run on different operations, and usually incorporate specialized processing capabilities to handle particular tasks.\u0026nbsp;\u003C\/p\u003E\r\n\r\n\u003Cp\u003EResearchers, particularly those in the HPC and exascale spaces, need a way to ensure they write their data and computation to work in these heterogenous environments, on multiple nodes, and are still able to communicate effectively with the rest of a program while producing the results fast. PAbB aims to become the first framework that achieves both high productivity and high performance in such environments by creating a framework that utilizes block programming.\u0026nbsp;\u003C\/p\u003E\r\n","summary":null,"format":"limited_html"}],"field_subtitle":"","field_summary":"","field_summary_sentence":[{"value":"CSE Professor \u00dcmit \u00c7ataly\u00fcrek receives NSF grant to develop a framework that facilitates simpler programming of scalable parallel systems in high-performance computing (HPC) and exascale machines. "}],"uid":"34540","created_gmt":"2019-10-24 19:36:41","changed_gmt":"2019-10-27 23:38:41","author":"Kristen Perez","boilerplate_text":"","field_publication":"","field_article_url":"","dateline":{"date":"2019-10-24T00:00:00-04:00","iso_date":"2019-10-24T00:00:00-04:00","tz":"America\/New_York"},"extras":[],"hg_media":{"628064":{"id":"628064","type":"image","title":"HPC Resource - data stack","body":null,"created":"1571946376","gmt_created":"2019-10-24 19:46:16","changed":"1571946376","gmt_changed":"2019-10-24 19:46:16","alt":"The image of a computer in a data stack with yellow and orange tabs","file":{"fid":"239161","name":"Data Center_MG_9964.jpg","image_path":"\/sites\/default\/files\/images\/Data%20Center_MG_9964.jpg","image_full_path":"http:\/\/hg.gatech.edu\/\/sites\/default\/files\/images\/Data%20Center_MG_9964.jpg","mime":"image\/jpeg","size":369349,"path_740":"http:\/\/hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/images\/Data%20Center_MG_9964.jpg?itok=dHQYGpbl"}}},"media_ids":["628064"],"groups":[{"id":"50877","name":"School of Computational Science and Engineering"},{"id":"624060","name":"Center for High Performance Computing (CHiPC)"},{"id":"47223","name":"College of Computing"}],"categories":[],"keywords":[{"id":"702","name":"hpc"},{"id":"181217","name":"cse-hpc"},{"id":"3427","name":"High performance computing"},{"id":"4305","name":"cse"},{"id":"170627","name":"Umit Catalyurek"}],"core_research_areas":[],"news_room_topics":[],"event_categories":[],"invited_audience":[],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[{"value":"\u003Cp\u003EKristen Perez\u003C\/p\u003E\r\n\r\n\u003Cp\u003ECommunications Officer\u003C\/p\u003E\r\n","format":"limited_html"}],"email":["kristen.perez@cc.gatech.edu"],"slides":[],"orientation":[],"userdata":""}}}