{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T15:50:19Z","timestamp":1774540219408,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":32,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,6,22]],"date-time":"2019-06-22T00:00:00Z","timestamp":1561161600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,6,22]]},"DOI":"10.1145\/3307650.3322234","type":"proceedings-article","created":{"date-parts":[[2019,6,14]],"date-time":"2019-06-14T12:42:33Z","timestamp":1560516153000},"page":"462-473","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":65,"title":["AsmDB"],"prefix":"10.1145","author":[{"given":"Grant","family":"Ayers","sequence":"first","affiliation":[{"name":"Stanford University"}]},{"given":"Nayana Prasad","family":"Nagendra","sequence":"additional","affiliation":[{"name":"Princeton University"}]},{"given":"David I.","family":"August","sequence":"additional","affiliation":[{"name":"Princeton University"}]},{"given":"Hyoun Kyu","family":"Cho","sequence":"additional","affiliation":[{"name":"Google"}]},{"given":"Svilen","family":"Kanev","sequence":"additional","affiliation":[{"name":"Google"}]},{"given":"Christos","family":"Kozyrakis","sequence":"additional","affiliation":[{"name":"Stanford University"}]},{"given":"Trivikram","family":"Krishnamurthy","sequence":"additional","affiliation":[{"name":"Nvidia"}]},{"given":"Heiner","family":"Litz","sequence":"additional","affiliation":[{"name":"UC Santa Cruz"}]},{"given":"Tipp","family":"Moseley","sequence":"additional","affiliation":[{"name":"Google"}]},{"given":"Parthasarathy","family":"Ranganathan","sequence":"additional","affiliation":[{"name":"Google"}]}],"member":"320","published-online":{"date-parts":[[2019,6,22]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Workshop on Profile and Feedback-Directed Compilation.","author":"Anderson Jennifer","year":"1998","unstructured":"Jennifer Anderson, Lance Berc, George Chrysos, Jeffrey Dean, Sanjay Ghemawat, Jamey Hicks, Shun-Tak Leung, Mitch Lichtenberg, Mark Vandevoorde, Carl A Waldspurger, et al. 1998. Transparent, low-overhead profiling on modern processors. In Workshop on Profile and Feedback-Directed Compilation."},{"key":"e_1_3_2_1_2_1","volume-title":"Christos Kozyrakis, and Parthasarathy Ranganathan.","author":"Ayers Grant","year":"2018","unstructured":"Grant Ayers, Jung Ho Ahn, Christos Kozyrakis, and Parthasarathy Ranganathan. 2018. Memory hierarchy for web search. In High Performance Computer Architecture (HPCA)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.5555\/3306658"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/2854038.2854044"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","unstructured":"Robert Cohn and P Geoffrey Lowney. 1996. Hot cold optimization of large Windows\/NT applications. In Microarchitecture (MICRO).","DOI":"10.5555\/243846.243861"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","unstructured":"Jeffrey Dean and Sanjay Ghemawat. 2004. MapReduce: simplified data processing on large clusters. In Operating Systems Design and Implementation (OSDI).","DOI":"10.5555\/1251254.1251264"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/1353522.1353531"},{"key":"e_1_3_2_1_9_1","volume-title":"Adrian Daniel Popescu, and Anastasia Ailamaki","author":"Ferdman Michael","year":"2012","unstructured":"Michael Ferdman, Babak Falsafi, Almutaz Adileh, Onur Kocberber, Stavros Volos, Mohammad Alisafaee, Djordje Jevdjic, Cansu Kaynak, Adrian Daniel Popescu, and Anastasia Ailamaki. 2012. Clearing the clouds. In Architectural Support for Programming Languages and Operating Systems (ASPLOS)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","unstructured":"Michael Ferdman Cansu Kaynak and Babak Falsafi. 2011. Proactive instruction fetch. In Microarchitecture (MICRO). 10.1145\/2155620.2155638","DOI":"10.1145\/2155620.2155638"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","unstructured":"Michael Ferdman Thomas F Wenisch Anastasia Ailamaki Babak Falsafi and Andreas Moshovos. 2008. Temporal instruction fetch streaming. In Microarchitecture (MICRO). 10.1109\/MICRO.2008.4771774","DOI":"10.1109\/MICRO.2008.4771774"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/262004.262005"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","unstructured":"John L Hennessy and David A Patterson. 2012. Computer architecture: a quantitative approach.","DOI":"10.5555\/1999263"},{"key":"e_1_3_2_1_14_1","volume-title":"Loop recognition in C++\/Java\/Go\/Scala. Scala Days","author":"Hundt Robert","year":"2011","unstructured":"Robert Hundt. 2011. Loop recognition in C++\/Java\/Go\/Scala. Scala Days (2011)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"crossref","unstructured":"Zhen Jia Lei Wang Jianfeng Zhan Lixin Zhang and Chunjie Luo. 2013. Characterizing data analysis workloads in data centers. In Workload Characterization (IISWC).","DOI":"10.1109\/IISWC.2013.6704671"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750392"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"crossref","unstructured":"Harshad Kasture and Daniel Sanchez. 2016. TailBench: A benchmark suite and evaluation methodology for latency-critical applications. In Workload Characterization (IISWC).","DOI":"10.1109\/IISWC.2016.7581261"},{"key":"e_1_3_2_1_18_1","volume-title":"Shift: Shared history instruction fetch for lean-core server processors. In Microarchitecture (MICRO).","author":"Kaynak Cansu","year":"2013","unstructured":"Cansu Kaynak, Boris Grot, and Babak Falsafi. 2013. Shift: Shared history instruction fetch for lean-core server processors. In Microarchitecture (MICRO)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/2830772.2830785"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/2540708.2540731"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","unstructured":"Rakesh Kumar Boris Grot and Vijay Nagarajan. 2018. Blasting through the front-end bottleneck with shotgun. In Architectural Support for Programming Languages and Operating Systems (ASPLOS). 10.1145\/3173162.3173178","DOI":"10.1145\/3173162.3173178"},{"key":"e_1_3_2_1_22_1","volume-title":"Boomerang: A metadata-free architecture for control flow delivery. In High Performance Computer Architecture (HPCA).","author":"Kumar Rakesh","year":"2017","unstructured":"Rakesh Kumar, Cheng-Chieh Huang, Boris Grot, and Vijay Nagarajan. 2017. Boomerang: A metadata-free architecture for control flow delivery. In High Performance Computer Architecture (HPCA)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/1064978.1065034"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","unstructured":"Chi-Keung Luk and Todd C Mowry. 1998. Cooperative prefetching: Compiler and hardware support for effective instruction prefetching in modern processors. In Microarchitecture (MICRO).","DOI":"10.5555\/290940.290979"},{"key":"e_1_3_2_1_25_1","volume-title":"BOLT: A Practical Binary Optimizer for Data Centers and Beyond. In Code Generation and Optimization (CGO).","author":"Panchenko Maksim","year":"2019","unstructured":"Maksim Panchenko, Rafael Auler, Bill Nell, and Guilherme Ottoni. 2019. BOLT: A Practical Binary Optimizer for Data Centers and Beyond. In Code Generation and Optimization (CGO)."},{"key":"e_1_3_2_1_26_1","volume-title":"The data center is the computer. Commun. ACM","author":"Patterson David A","year":"2008","unstructured":"David A Patterson. 2008. The data center is the computer. Commun. ACM (2008)."},{"key":"e_1_3_2_1_27_1","volume-title":"Performance characterization of spec cpu2006 benchmarks on intel core 2 duo processor. ISAST Transactions on Computer Software Engineering","author":"Prakash Tribuvan Kumar","year":"2008","unstructured":"Tribuvan Kumar Prakash and Lu Peng. 2008. Performance characterization of spec cpu2006 benchmarks on intel core 2 duo processor. ISAST Transactions on Computer Software Engineering (2008)."},{"key":"e_1_3_2_1_28_1","volume-title":"Software-Controlled Instruction Prefetch Buffering for Low-End Processors. Journal of Circuits, Systems and Computers","author":"Qadri Muhammad Yasir","year":"2015","unstructured":"Muhammad Yasir Qadri, Nadia N Qadri, Martin Fleury, and Klaus D McDonald-Maier. 2015. Software-Controlled Instruction Prefetch Buffering for Low-End Processors. Journal of Circuits, Systems and Computers (2015)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","unstructured":"Glenn Reinman Brad Calder and Todd Austin. 1999. Fetch directed instruction prefetching. In Microarchitecture (MICRO).","DOI":"10.5555\/320080.320085"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2010.68"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","unstructured":"Daniel Sanchez and Christos Kozyrakis. 2013. ZSim: fast and accurate microarchi-tectural simulation of thousand-core systems. In Computer Architecture (ISCA). 10.1145\/2485922.2485963","DOI":"10.1145\/2485922.2485963"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","unstructured":"Tom Way and Lori Pollock. 2002. Evaluation of a region-based partial inlining algorithm for an ILP optimizing compiler. In Parallel and Distributed Processing Techniques and Applications (PDPTA).","DOI":"10.5555\/646440.693854"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"crossref","unstructured":"Ahmad Yasin. 2014. A Top-Down method for performance analysis and counters architecture. (2014).","DOI":"10.1109\/ISPASS.2014.6844459"}],"event":{"name":"ISCA '19: The 46th Annual International Symposium on Computer Architecture","location":"Phoenix Arizona","acronym":"ISCA '19","sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture","IEEE-CS\\DATC IEEE Computer Society"]},"container-title":["Proceedings of the 46th International Symposium on Computer Architecture"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3307650.3322234","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3307650.3322234","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:54:05Z","timestamp":1750204445000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3307650.3322234"}},"subtitle":["understanding and mitigating front-end stalls in warehouse-scale computers"],"short-title":[],"issued":{"date-parts":[[2019,6,22]]},"references-count":32,"alternative-id":["10.1145\/3307650.3322234","10.1145\/3307650"],"URL":"https:\/\/doi.org\/10.1145\/3307650.3322234","relation":{},"subject":[],"published":{"date-parts":[[2019,6,22]]},"assertion":[{"value":"2019-06-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}