{"601044":{"#nid":"601044","#data":{"type":"news","title":"Professor Margaret Martonosi Delivers Mary Jean Harrold Memorial Distinguished Lecture   ","body":[{"value":"\u003Cp\u003EProfessor \u003Ca href=\u0022http:\/\/www.princeton.edu\/~mrm\/\u0022\u003E\u003Cstrong\u003EMargaret Martonosi\u003C\/strong\u003E\u003C\/a\u003E gave the Mary Jean Harrold Memorial Distinguished Lecture on Friday, Jan. 12. It was standing room only for the Princeton computer science professor\u0026rsquo;s talk, \u003Cem\u003EA \u0026ldquo;Post-ISA\u0026rdquo; Era in Computer Systems: Challenges and Opportunities\u003C\/em\u003E.\u003C\/p\u003E\r\n\r\n\u003Cp\u003EThe lecture is named after former School of Computer Science Professor \u003Ca href=\u0022https:\/\/www.cc.gatech.edu\/features\/college-computing-remembers-mary-jean-harrold\u0022\u003E\u003Cstrong\u003EMary Jean Harrold\u003C\/strong\u003E\u003C\/a\u003E, who was a leading software engineer. Martonosi worked with Harrold at the \u003Ca href=\u0022https:\/\/cra.org\/cra-w\/\u0022\u003EComputing Research Association\u0026ndash;Women\u003C\/a\u003E, a division of the CRA that focuses on bringing more women to computing research. \u0026ldquo;Mary Jean was simultaneously very tough but very nice,\u0026rdquo; Martonosi said. \u0026ldquo;Balancing that is a life-long challenge for most of us, but she did it masterfully.\u0026rdquo;\u003C\/p\u003E\r\n\r\n\u003Cp\u003EThe renowned computer architect discussed the future of computing in this post-Moore\u0026rsquo;s law era. In 1965, businessman \u003Cstrong\u003EGordon Moore\u003C\/strong\u003E posited that the number of transistors on an integrated circuit doubles almost every two years. Computer trends have been dictated by this ever since, yet as transistors shrink so does their efficiency. Almost a decade later, electrical engineer \u003Cstrong\u003ERobert Dennard\u003C\/strong\u003E introduced Dennard scaling, or the idea that even as transistors get smaller, their power density remains consistent.\u003C\/p\u003E\r\n\r\n\u003Cp\u003EYet today we can only drop supply voltage so much. The future of hardware is devoted to figuring out what comes after Moore and Dennard are obsolete, and computer architects are some of the chief researchers trying to discover the next phase.\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026ldquo;Computer architects mediate between application trends from one side and technology trends from the other,\u0026rdquo; Martonosi said. \u0026ldquo;Some technology trends are challenges like the end of Moore\u0026rsquo;s law and Dennard scaling, and some are opportunities like technologies that might be emerging. Application trends are also guiding much of what architecture does, so coming up with accelerators and ways of better supporting big data and machine learning.\u0026rdquo;\u003C\/p\u003E\r\n\r\n\u003Cp\u003EThese opportunities were the focus of Martonosi\u0026rsquo;s talk. She detailed the history of attempts to solve this dilemma, such as per module approaches (not powering what a programmer isn\u0026rsquo;t using) or on-chip parallelism (spreading out operations through multiple processors). Yet these fixes could only go so far. Now the field is focused on heterogeneity and specialization, such as using accelerators or putting central processing units and graphics processing units on the same chip.\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026ldquo;What\u0026rsquo;s interesting about this is not just the degree of resourcefulness employed to keep scaling performance at manageable power,\u0026rdquo; Martonosi said. \u0026ldquo;The interesting thing \u0026mdash;and perhaps the scary thing about it \u0026mdash; is that over time more and more of this became exposed to software. Whether you\u0026rsquo;re architects or if you sit higher in the food chain, we\u0026rsquo;re all in this together.\u0026rdquo;\u003C\/p\u003E\r\n\r\n\u003Cp\u003EThere may be more complexity now, but with that comes more bugs and more security risks. \u0026ldquo;This is a fundamentally disruptive moment, not just for architects but for computer systems overall because the hardware-software interface is undergoing a seismic change,\u0026rdquo; Martonosi said.\u003C\/p\u003E\r\n\r\n\u003Cp\u003EShe outlined the challenges in this new era:\u003C\/p\u003E\r\n\r\n\u003Cul\u003E\r\n\t\u003Cli\u003EHow to program these heterogeneous systems in a way that\u0026rsquo;s correct\u003C\/li\u003E\r\n\t\u003Cli\u003EHow to verify that correctness\u003C\/li\u003E\r\n\t\u003Cli\u003EHow long will this method be sustainable\u003C\/li\u003E\r\n\u003C\/ul\u003E\r\n\r\n\u003Cp\u003EUltimately, Martonosi argued, we need new software abstractions to mitigate the problem in the short and long term. For the short term, Martonosi\u0026rsquo;s research is focusing on memory consistency models and how to verify them. These models guarantee that memory will be consistent if the programmer follows a systems\u0026rsquo; rules. Her team \u003Ca href=\u0022http:\/\/check.cs.princeton.edu\/\u0022\u003Ehas created\u003C\/a\u003E several verification tools that have found bugs. One such tool, known as \u003Ca href=\u0022https:\/\/github.com\/ctrippel\/TriCheck\u0022\u003ETriCheck\u003C\/a\u003E, is a full stack memory consistency model verification tool that can analyze everything from high-level languages to microarchitectures.\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026ldquo;Architects can have a lot of leverage if they verify things earlier,\u0026rdquo; Martonosi said.\u003C\/p\u003E\r\n\r\n\u003Cp\u003EYet Martonosi believes the long-term solution could be quantum computing. It may be too specialized to take over completely for Moore\u0026rsquo;s law, but it is the new paradigm. As researchers find faster quantum algorithms that need fewer qubits, the basic unit of quantum information, and improve reliability, this could translate to scaling improvements.\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u0026ldquo;I \u0026shy;see this as the golden age of computer systems design,\u0026rdquo; Martonosi said. \u0026ldquo;The rules are ready to be broken.\u0026rdquo;\u003C\/p\u003E\r\n","summary":null,"format":"limited_html"}],"field_subtitle":"","field_summary":"","field_summary_sentence":[{"value":"Professor Margaret Martonosi gave the Mary Jean Harrold Memorial Distinguished Lecture on the future of post-Moore computing."}],"uid":"34541","created_gmt":"2018-01-19 14:48:21","changed_gmt":"2018-01-19 14:54:02","author":"Tess Malone","boilerplate_text":"","field_publication":"","field_article_url":"","dateline":{"date":"2018-01-19T00:00:00-05:00","iso_date":"2018-01-19T00:00:00-05:00","tz":"America\/New_York"},"extras":[],"hg_media":{"601045":{"id":"601045","type":"image","title":"Martonosi","body":null,"created":"1516373584","gmt_created":"2018-01-19 14:53:04","changed":"1516373584","gmt_changed":"2018-01-19 14:53:04","alt":"Margaret Martonosi delivers lecture.","file":{"fid":"229090","name":"IMG_2306.JPG","image_path":"\/sites\/default\/files\/images\/IMG_2306.JPG","image_full_path":"http:\/\/www.tlwarc.hg.gatech.edu\/\/sites\/default\/files\/images\/IMG_2306.JPG","mime":"image\/jpeg","size":368370,"path_740":"http:\/\/www.tlwarc.hg.gatech.edu\/sites\/default\/files\/styles\/740xx_scale\/public\/images\/IMG_2306.JPG?itok=yR4gBEGl"}}},"media_ids":["601045"],"groups":[{"id":"47223","name":"College of Computing"},{"id":"50875","name":"School of Computer Science"}],"categories":[],"keywords":[],"core_research_areas":[],"news_room_topics":[],"event_categories":[],"invited_audience":[],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[{"value":"\u003Cp\u003ETess Malone, Communications Officer\u003C\/p\u003E\r\n\r\n\u003Cp\u003E\u003Ca href=\u0022mailto:tess.malone@cc.gatech.edu\u0022\u003Etess.malone@cc.gatech.edu\u003C\/a\u003E\u003C\/p\u003E\r\n","format":"limited_html"}],"email":["tess.malone@cc.gatech.edu"],"slides":[],"orientation":[],"userdata":""}}}