{"_id":"uZqP46ceis5EcpMwj","bibbaseid":"barve-neema-kang-sun-gokhale-roth-exppoexecutionperformanceprofilingandoptimizationforcpscosimulationasaservice","author_short":["Barve, Y. D","Neema, H.","Kang, Z.","Sun, H.","Gokhale, A.","Roth, T."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"propositions":[],"lastnames":["Barve"],"firstnames":["Yogesh","D"],"suffixes":[]},{"propositions":[],"lastnames":["Neema"],"firstnames":["Himanshu"],"suffixes":[]},{"propositions":[],"lastnames":["Kang"],"firstnames":["Zhuangwei"],"suffixes":[]},{"propositions":[],"lastnames":["Sun"],"firstnames":["Hongyang"],"suffixes":[]},{"propositions":[],"lastnames":["Gokhale"],"firstnames":["Aniruddha"],"suffixes":[]},{"propositions":[],"lastnames":["Roth"],"firstnames":["Thomas"],"suffixes":[]}],"booktitle":"2020 IEEE 23rd International Symposium on Real-Time Distributed Computing (ISORC)","date":"2020","title":"EXPPO: EXecution Performance Profiling and Optimization for CPS Co-simulation-as-a-Service","organization":"IEEE","pages":"184–191","comment":"* context: co-simulation * problem: assign resources (e.g., CPU) to simulations, so that all run at roughly the same pace * specifically: how to place simulations of a distributed simulation on available execution hosts * presents the Execution Performance Profiling and Optimization (EXPPO) methodology * contribute * identification of problem * slower simulations slow down the whole co-simulation (surprise?) * approach for modifying source of simulations for (distributed) tracing * Opentracing, model-driven engineering, domain-specific languages * # leave unanswered how/what exactly * resource recommendation engine * i.e., determine how to split resources among simulations for maximum progress * i.e., minimize time where simulations wait for other simulations * different schedulers: first-fit, best-fit, custom * special scheduling problem, since tasks must run at the same time (i.e., \"bag of tasks scheduling\" or \"gang scheduling\") * measure quality by efficiency (execution time and resource costs) * case study * best-fit performs best * EXXPO finds best tradeoff between execution time and resource * according to their metric :) * co-simulation as a service middleware * front end * Docker swarm","file":":barve20exppo - EXPPO_ EXecution Performance Profiling and Optimization for CPS Co-simulation-as-a-Service.pdf:PDF","groups":"simulation","timestamp":"2021-02-13","bibtex":"@InProceedings{barve20exppo,\n author = {Barve, Yogesh D and Neema, Himanshu and Kang, Zhuangwei and Sun, Hongyang and Gokhale, Aniruddha and Roth, Thomas},\n booktitle = {2020 IEEE 23rd International Symposium on Real-Time Distributed Computing (ISORC)},\n date = {2020},\n title = {EXPPO: EXecution Performance Profiling and Optimization for CPS Co-simulation-as-a-Service},\n organization = {IEEE},\n pages = {184--191},\n comment = {* context: co-simulation\n* problem: assign resources (e.g., CPU) to simulations, so that all run\n at roughly the same pace\n\n * specifically: how to place simulations of a distributed simulation\n on available execution hosts\n\n* presents the Execution Performance Profiling and Optimization (EXPPO)\n methodology\n* contribute\n\n * identification of problem\n\n * slower simulations slow down the whole co-simulation (surprise?)\n\n * approach for modifying source of simulations for (distributed) tracing\n\n * Opentracing, model-driven engineering, domain-specific languages\n * \\# leave unanswered how/what exactly\n\n * resource recommendation engine\n\n * i.e., determine how to split resources among simulations for\n maximum progress\n\n * i.e., minimize time where simulations wait for other simulations\n\n * different schedulers: first-fit, best-fit, custom\n\n * special scheduling problem, since tasks must run at the same\n time (i.e., \"bag of tasks scheduling\" or \"gang scheduling\")\n\n * measure quality by efficiency (execution time and resource costs)\n\n * case study\n\n * best-fit performs best\n * EXXPO finds best tradeoff between execution time and resource\n\n * according to their metric :)\n\n* co-simulation as a service middleware\n\n * front end\n * Docker swarm},\n file = {:barve20exppo - EXPPO_ EXecution Performance Profiling and Optimization for CPS Co-simulation-as-a-Service.pdf:PDF},\n groups = {simulation},\n timestamp = {2021-02-13},\n}\n\n","author_short":["Barve, Y. D","Neema, H.","Kang, Z.","Sun, H.","Gokhale, A.","Roth, T."],"key":"barve20exppo","id":"barve20exppo","bibbaseid":"barve-neema-kang-sun-gokhale-roth-exppoexecutionperformanceprofilingandoptimizationforcpscosimulationasaservice","role":"author","urls":{},"metadata":{"authorlinks":{}},"downloads":0,"html":""},"bibtype":"inproceedings","biburl":"https://bibbase.org/network/files/AsPiHTmHHGjgy6xSQ","dataSources":["wjZw5s4JL49uLwn3p"],"keywords":[],"search_terms":["exppo","execution","performance","profiling","optimization","cps","simulation","service","barve","neema","kang","sun","gokhale","roth"],"title":"EXPPO: EXecution Performance Profiling and Optimization for CPS Co-simulation-as-a-Service","year":null}