{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:21:33Z","timestamp":1750220493326,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":48,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,3,18]],"date-time":"2022-03-18T00:00:00Z","timestamp":1647561600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["DGE 1841052"],"award-info":[{"award-number":["DGE 1841052"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,3,19]]},"DOI":"10.1145\/3497776.3517767","type":"proceedings-article","created":{"date-parts":[[2022,3,18]],"date-time":"2022-03-18T17:28:13Z","timestamp":1647624493000},"page":"205-217","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Loner: utilizing the CPU vector datapath to process scalar integer data"],"prefix":"10.1145","author":[{"given":"Armand","family":"Behroozi","sequence":"first","affiliation":[{"name":"University of Michigan, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sunghyun","family":"Park","sequence":"additional","affiliation":[{"name":"University of Michigan, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Scott","family":"Mahlke","sequence":"additional","affiliation":[{"name":"University of Michigan, USA \/ NVIDIA Research, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,3,18]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/29873.29875"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/2838735"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/381694.378854"},{"key":"e_1_3_2_1_4_1","unstructured":"ARM. 2013. Arm Architecture Reference Manual Armv8 for Armv8-A architecture profile. https:\/\/developer.arm.com\/documentation\/ddi0487\/ga  ARM. 2013. Arm Architecture Reference Manual Armv8 for Armv8-A architecture profile. https:\/\/developer.arm.com\/documentation\/ddi0487\/ga"},{"key":"e_1_3_2_1_5_1","unstructured":"ARM. 2013. Neon Programmer\u2019s Guide. https:\/\/developer.arm.com\/documentation\/den0018\/latest  ARM. 2013. Neon Programmer\u2019s Guide. https:\/\/developer.arm.com\/documentation\/den0018\/latest"},{"key":"e_1_3_2_1_6_1","unstructured":"ARM. 2019. Arm\u00ae Cortex\u00ae-A76 Software Optimization Guide. https:\/\/developer.arm.com\/documentation\/swog307215\/a  ARM. 2019. Arm\u00ae Cortex\u00ae-A76 Software Optimization Guide. https:\/\/developer.arm.com\/documentation\/swog307215\/a"},{"key":"e_1_3_2_1_7_1","unstructured":"ARM. 2019. Arm\u00ae Cortex\u00ae-A77 Software Optimization Guide. https:\/\/developer.arm.com\/documentation\/swog011050\/c  ARM. 2019. Arm\u00ae Cortex\u00ae-A77 Software Optimization Guide. https:\/\/developer.arm.com\/documentation\/swog011050\/c"},{"key":"e_1_3_2_1_8_1","unstructured":"ARM. 2019. Arm\u00ae Cortex\u00ae-A78 Software Optimization Guide. https:\/\/developer.arm.com\/documentation\/102160\/latest  ARM. 2019. Arm\u00ae Cortex\u00ae-A78 Software Optimization Guide. https:\/\/developer.arm.com\/documentation\/102160\/latest"},{"key":"e_1_3_2_1_9_1","unstructured":"ARM. 2021. Arm\u00ae Cortex\u00ae-A710 Software Optimization Guide. https:\/\/developer.arm.com\/documentation\/PJDOC-466751330-14951\/latest\/  ARM. 2021. Arm\u00ae Cortex\u00ae-A710 Software Optimization Guide. https:\/\/developer.arm.com\/documentation\/PJDOC-466751330-14951\/latest\/"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3307650.3322234"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/2908080.2908111"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-37051-9_2"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/177492.177575"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3185768.3185771"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/800230.806984"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3445814.3446692"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/88616.88621"},{"volume-title":"AMD, and VIA CPUs","author":"Fog Agner","key":"e_1_3_2_1_18_1","unstructured":"Agner Fog . 2021. Instruction tables: Lists of instruction latencies, throughputs and micro-operation breakdowns for Intel , AMD, and VIA CPUs . Technical University of Denmark . Agner Fog. 2021. Instruction tables: Lists of instruction latencies, throughputs and micro-operation breakdowns for Intel, AMD, and VIA CPUs. Technical University of Denmark."},{"volume-title":"AMD, and VIA CPUs: An optimization guide for assembly programmers and compiler makers","author":"Fog Agner","key":"e_1_3_2_1_19_1","unstructured":"Agner Fog . 2021. The microarchitecture of Intel , AMD, and VIA CPUs: An optimization guide for assembly programmers and compiler makers . Technical University of Denmark . Agner Fog. 2021. The microarchitecture of Intel, AMD, and VIA CPUs: An optimization guide for assembly programmers and compiler makers. Technical University of Denmark."},{"volume-title":"Test programs for measuring clock cycles and performance monitoring","author":"Fog Agner","key":"e_1_3_2_1_20_1","unstructured":"Agner Fog . 2021. Test programs for measuring clock cycles and performance monitoring . Technical University of Denmark , https:\/\/github.com\/tpn\/agner\/tree\/master\/testp Agner Fog. 2021. Test programs for measuring clock cycles and performance monitoring. Technical University of Denmark, https:\/\/github.com\/tpn\/agner\/tree\/master\/testp"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2002.1015494"},{"volume-title":"Commercially Representative Embedded Benchmark Suite. In Proceedings of the Workload Characterization, 2001. WWC-4. 2001 IEEE International Workshop (WWC \u201901)","author":"Guthaus M. R.","key":"e_1_3_2_1_22_1","unstructured":"M. R. Guthaus , J. S. Ringenberg , D. Ernst , T. M. Austin , T. Mudge , and R. B. Brown . 2001. MiBench: A Free , Commercially Representative Embedded Benchmark Suite. In Proceedings of the Workload Characterization, 2001. WWC-4. 2001 IEEE International Workshop (WWC \u201901) . M. R. Guthaus, J. S. Ringenberg, D. Ernst, T. M. Austin, T. Mudge, and R. B. Brown. 2001. MiBench: A Free, Commercially Representative Embedded Benchmark Suite. In Proceedings of the Workload Characterization, 2001. WWC-4. 2001 IEEE International Workshop (WWC \u201901)."},{"key":"e_1_3_2_1_23_1","volume-title":"SPEC CPU2000: Measuring CPU Performance in the New Millennium. Computer, July.","author":"Henning J. L.","year":"2000","unstructured":"J. L. Henning . 2000 . SPEC CPU2000: Measuring CPU Performance in the New Millennium. Computer, July. J. L. Henning. 2000. SPEC CPU2000: Measuring CPU Performance in the New Millennium. Computer, July."},{"key":"e_1_3_2_1_24_1","volume-title":"SPEC CPU2006 Benchmark Descriptions. SIGARCH Comput. Archit. News, Sept..","author":"Henning John L.","year":"2006","unstructured":"John L. Henning . 2006 . SPEC CPU2006 Benchmark Descriptions. SIGARCH Comput. Archit. News, Sept.. John L. Henning. 2006. SPEC CPU2006 Benchmark Descriptions. SIGARCH Comput. Archit. News, Sept.."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2018.2789903"},{"key":"e_1_3_2_1_26_1","unstructured":"Intel. 2021. Intel\u00ae 64 and IA-32 Architectures Optimization Reference Manual.  Intel. 2021. Intel\u00ae 64 and IA-32 Architectures Optimization Reference Manual."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/349299.349320"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2004.1281665"},{"key":"e_1_3_2_1_29_1","volume-title":"Expression Rematerialization for VLIW DSP Processors with Distributed Register File. In 14th Workshop on compilers for parallel computing.","author":"Wu Lee Chung-Ju","year":"2009","unstructured":"Chung-Ju Wu Lee , Chia-Han Lu , and Jenq-Kuen. 2009 . Expression Rematerialization for VLIW DSP Processors with Distributed Register File. In 14th Workshop on compilers for parallel computing. Chung-Ju Wu Lee, Chia-Han Lu, and Jenq-Kuen. 2009. Expression Rematerialization for VLIW DSP Processors with Distributed Register File. In 14th Workshop on compilers for parallel computing."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3332373"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-014-1181-2"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/1375527.1375574"},{"volume-title":"Pin: Building Customized Program Analysis Tools with Dynamic Instrumentation. In Proceedings of the 2005 ACM SIGPLAN Conference on Programming Language Design and Implementation.","author":"Luk Chi-Keung","key":"e_1_3_2_1_33_1","unstructured":"Chi-Keung Luk , Robert Cohn , Robert Muth , Harish Patil , Artur Klauser , Geoff Lowney , Steven Wallace , Vijay Janapa Reddi , and Kim Hazelwood . [n. d.]. Pin: Building Customized Program Analysis Tools with Dynamic Instrumentation. In Proceedings of the 2005 ACM SIGPLAN Conference on Programming Language Design and Implementation. Chi-Keung Luk, Robert Cohn, Robert Muth, Harish Patil, Artur Klauser, Geoff Lowney, Steven Wallace, Vijay Janapa Reddi, and Kim Hazelwood. [n. d.]. Pin: Building Customized Program Analysis Tools with Dynamic Instrumentation. In Proceedings of the 2005 ACM SIGPLAN Conference on Programming Language Design and Implementation."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2006.28"},{"key":"e_1_3_2_1_35_1","unstructured":"Michael Matz Jan Hubicka Andreas Jaeger and Mark Mitchell. 2014. System V Application Binary Interface AMD64 Architecture Processor Supplement Draft Version 0.99.7. https:\/\/www.uclibc.org\/docs\/psABI-x86_64.pdf  Michael Matz Jan Hubicka Andreas Jaeger and Mark Mitchell. 2014. System V Application Binary Interface AMD64 Architecture Processor Supplement Draft Version 0.99.7. https:\/\/www.uclibc.org\/docs\/psABI-x86_64.pdf"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/1995896.1995938"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3243176.3243189"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2004.840306"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2018.00049"},{"key":"e_1_3_2_1_40_1","unstructured":"Colin Robertson Nick Schonning and Feng Xu. 2021. x64 calling convention. https:\/\/docs.microsoft.com\/en-us\/cpp\/build\/x64-calling-convention?view=msvc-160##callercallee-saved-registers  Colin Robertson Nick Schonning and Feng Xu. 2021. x64 calling convention. https:\/\/docs.microsoft.com\/en-us\/cpp\/build\/x64-calling-convention?view=msvc-160##callercallee-saved-registers"},{"key":"e_1_3_2_1_41_1","unstructured":"Ira Rosen D. Nuzman and A. Zaks. 2007. Loop-aware SLP in GCC. 01 131\u2013142.  Ira Rosen D. Nuzman and A. Zaks. 2007. Loop-aware SLP in GCC. 01 131\u2013142."},{"key":"e_1_3_2_1_42_1","unstructured":"David Patterson Scott Beamer Krste Asanovi\u0107. 2015. The GAP Benchmark Suite. In arXiv:1508.03619 [cs.DC].  David Patterson Scott Beamer Krste Asanovi\u0107. 2015. The GAP Benchmark Suite. In arXiv:1508.03619 [cs.DC]."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/2512432"},{"key":"e_1_3_2_1_44_1","unstructured":"Sam Siewert. 2016. Using Intel\u00ae Streaming SIMD Extensions and Intel\u00ae Integrated Performance Primitives to Accelerate Algorithms.  Sam Siewert. 2016. Using Intel\u00ae Streaming SIMD Extensions and Intel\u00ae Integrated Performance Primitives to Accelerate Algorithms."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/PACT.2013.6618831"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00026"},{"volume-title":"High Performance Compilers for Parallel Computing","author":"Wolfe Michael Joseph","key":"e_1_3_2_1_47_1","unstructured":"Michael Joseph Wolfe , Carter Shanklin , and Leda Ortega . 1995. High Performance Compilers for Parallel Computing . Addison-Wesley Longman Publishing Co., Inc. , USA. isbn:0805327304 Michael Joseph Wolfe, Carter Shanklin, and Leda Ortega. 1995. High Performance Compilers for Parallel Computing. Addison-Wesley Longman Publishing Co., Inc., USA. isbn:0805327304"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/2886101"}],"event":{"name":"CC '22: 31st ACM SIGPLAN International Conference on Compiler Construction","sponsor":["SIGPLAN ACM Special Interest Group on Programming Languages"],"location":"Seoul South Korea","acronym":"CC '22"},"container-title":["Proceedings of the 31st ACM SIGPLAN International Conference on Compiler Construction"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3497776.3517767","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3497776.3517767","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3497776.3517767","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:49:26Z","timestamp":1750193366000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3497776.3517767"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,3,18]]},"references-count":48,"alternative-id":["10.1145\/3497776.3517767","10.1145\/3497776"],"URL":"https:\/\/doi.org\/10.1145\/3497776.3517767","relation":{},"subject":[],"published":{"date-parts":[[2022,3,18]]},"assertion":[{"value":"2022-03-18","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}