[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-83868-en":3,"doc-seo-83868-105":30,"detail-sidebar-cat-0-en-105":83},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},83868,8796095462418,"Noah","https://ap-avatar.wpscdn.com/avatar/80000253c1241d02b47?x-image-process=image/resize,m_fixed,w_180,h_180&k=1778826106357471780",8,"Research & Report","TARE Tail Aware Evaluation of HPC Job Runtime Prediction","Runtime estimates shape reservation quality, backfilling opportunities, and queue delays in HPC schedulers. Under heavy-tailed workloads, job-level averaging can hide the prediction errors that matter most because a small subset of jobs dominates resource usage. The paper proposes a tail-focused evaluation methodology using GeoAccuracy weighted by resource usage, supported by decile and split analyses, to compare XGBoost and Last2 against UserReq on production traces from NREL Eagle and ALCF Mira/Intrepid. Tail evaluation changes conclusions by separating methods more clearly and revealing UserReq’s upper-tail strength.","TARE: Tail Aware Evaluation of HPC Job Runtime Prediction  \nHaili Xiao∗ CNIC, CAS  \nChina [haili@sccas.cn](haili@sccas.cn)  \nXiaoning Wang CNIC, CAS  \nChina [wxn@sccas.cn](wxn@sccas.cn)  \nCan Wu∗ CNIC, CAS  \nChina [wucan@sccas.cn](wucan@sccas.cn)  \nYining Zhao  \nCNIC, CAS  \nChina [zhaoyn@sccas.cn](zhaoyn@sccas.cn)  \nShasha Lu CNIC, CAS  \nChina [lusha721@sccas.cn](lusha721@sccas.cn)  \nRong He CNIC, CAS  \nChina [herong@sccas.cn](herong@sccas.cn)  \narXiv :2607 .04935v 1 [ cs .DC] 6 Jul 2026  \nAbstract  \nRuntime estimates affect reservation quality, backfilling opportunities, and queue delay in HPC schedulers. Under heavy tailed workloads, however, averaging over jobs can misrepresent scheduling impact because a small fraction of jobs dominates resource usage. This paper presents an empirical evaluation methodology for HPC job runtime prediction that focuses on the tail, combining GeoAccuracy weighted by resource usage with decile and split analyses. Using production traces from NREL Eagle and ALCF Mira/Intrepid, we compare XGBoost and Last2 against the user provided walltime estimate at submission (UserReq) . Across all three datasets, evaluation focused on the tail changes the offline conclusion: MeanAccuracy keeps the methods relatively close, whereas GeoAccuracy reveals clearer separation and makes UserReq’s strength in the upper tail visible. In the top decile, UserReq achieves the highest GeoAccuracy and lowest underestimation rate on all three datasets, and this pattern remains stable across rolling splits. We then translate this signal into a simple hybrid scheduling policy that keeps XGBoost for most jobs and routes the top decile by proxy_cost at submission to UserReq. Online replay on four production queues reduces mean wait time by up to 8% and increases backfilled jobs by 50%–115%. These results show that offline evaluation focused on the tail better characterizes prediction quality relevant to scheduling and informs scheduling policy design.  \nCCS Concepts  \n• Computer systems organization → Parallel architectures; Resource management; • Computing methodologies → Machine learning.  \nKeywords  \nHPC runtime prediction, performance evaluation, performance metrics, heavy tail workloads, online simulation  \n∗ Both authors contributed equally to this work as co-first authors.  \nPermission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission [and/or a fee. Request permissions from permissions@acm.org](and/or a fee. Request permissions from permissions@acm.org).  \nICPP’26, Singapore  \n© 2026 Copyright held by the owner/author(s) . Publication rights licensed to ACM. ACM ISBN 978-x-xxxx-xxxx-x/YYYY/MM [https://doi.org/10.1145/nnnnnnn.nnnnnnn](https://doi.org/10.1145/nnnnnnn.nnnnnnn)  \nACM Reference Format:  \nHaili Xiao, Can Wu, Shasha Lu, Xiaoning Wang, Yining Zhao, and Rong He.  \n2026. TARE: Tail Aware Evaluation of HPC Job Runtime Prediction. In The 55th International Conference on Parallel Processing (ICPP’26), September 28–October 1, 2026, Singapore. ACM, New York, NY, USA, 10 pages. [https:](https:)//[doi.org/10.1145/nnnnnnn.nnnnnnn](doi.org/10.1145/nnnnnnn.nnnnnnn)  \n1 Introduction  \nIn batch scheduled HPC systems, users submit jobs with requested resources such as node counts and walltime limits, and those jobs wait in queue until the scheduler selects them for execution. Under FCFS with EASY backfilling, the scheduler uses a runtime estimate to reserve resources for the job at the head of the queue and to determine whether later jobs can start early without delayin","cbCaifAmSctRS1ni","https://ap.wps.com/l/cbCaifAmSctRS1ni","pdf",717021,4,1,10,"English","en",105,"# Introduction\n## Problem motivation and evaluation gap\n# Methodology\n## Tail-focused metrics and analysis\n# Experimental evaluation\n## Datasets and predictor comparisons\n# Scheduling policy impact\n## Hybrid policy and online replay","[{\"question\":\"How is the tail evaluation result used to design a scheduling policy?\",\"answer\":\"A hybrid scheduling policy keeps XGBoost for most jobs and routes the top decile, selected via a proxy_cost at submission, to UserReq. Online replay across four production queues reduces mean wait time up to 8% and increases backfilled jobs by about 50%–115%. \"}]",1784191092,25,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":78,"head_meta":80,"extra_data":82,"updated_unix":28},"tare-tail-aware-evaluation-of-hpc-job-runtime-prediction","",{"@graph":36,"@context":77},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":20},"https://docshare.wps.com/document/tare-tail-aware-evaluation-of-hpc-job-runtime-prediction/83868/",{"url":52,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-25","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71],{"name":72,"@type":73,"acceptedAnswer":74},"How is the tail evaluation result used to design a scheduling policy?","Question",{"text":75,"@type":76},"A hybrid scheduling policy keeps XGBoost for most jobs and routes the top decile, selected via a proxy_cost at submission, to UserReq. Online replay across four production queues reduces mean wait time up to 8% and increases backfilled jobs by about 50%–115%.","Answer","https://schema.org",{"og:url":52,"og:type":79,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":81,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":84},[85,89,93,97,102,107,112,115,120,123,126],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":86,"show_sort_weight":87,"slug":88},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":90,"show_sort_weight":91,"slug":92},"Literature",80,"literature",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Exam",70,"exam",{"id":98,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},5,"Comic",60,"comic",{"id":103,"doc_module":4,"doc_module_name":46,"category_name":104,"show_sort_weight":105,"slug":106},6,"Technology",50,"technology",{"id":108,"doc_module":4,"doc_module_name":46,"category_name":109,"show_sort_weight":110,"slug":111},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":113,"slug":114},30,"research-report",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},9,"Religion & Spirituality",20,"religion-spirituality",{"id":118,"doc_module":4,"doc_module_name":46,"category_name":121,"show_sort_weight":118,"slug":122},"World Cup","world-cup",{"id":22,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":22,"slug":125},"Lifestyle","lifestyle",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":98,"slug":129},19,"General","general"]