{"id":"https://openalex.org/W4360831799","doi":"https://doi.org/10.1109/hpca56546.2023.10071070","title":"CHOPPER: A Compiler Infrastructure for Programmable Bit-serial SIMD Processing Using Memory in DRAM","display_name":"CHOPPER: A Compiler Infrastructure for Programmable Bit-serial SIMD Processing Using Memory in DRAM","publication_year":2023,"publication_date":"2023-02-01","ids":{"openalex":"https://openalex.org/W4360831799","doi":"https://doi.org/10.1109/hpca56546.2023.10071070"},"language":"en","primary_location":{"id":"doi:10.1109/hpca56546.2023.10071070","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpca56546.2023.10071070","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Symposium on High-Performance Computer Architecture (HPCA)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016815186","display_name":"Xiangjun Peng","orcid":"https://orcid.org/0000-0002-4442-9744"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Xiangjun Peng","raw_affiliation_strings":["The Chinese University of Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101877535","display_name":"Yaohua Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaohua Wang","raw_affiliation_strings":["National University of Defense Technology"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102930563","display_name":"Ming-Chang Yang","orcid":"https://orcid.org/0000-0002-4029-757X"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Ming-Chang Yang","raw_affiliation_strings":["The Chinese University of Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5016815186"],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":4.3446,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.94950115,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1275","last_page":"1288"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10829","display_name":"Interconnection Networks and Systems","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.8610044717788696},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8566364645957947},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.6994158029556274},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6488025784492493},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.13668569922447205}],"concepts":[{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.8610044717788696},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8566364645957947},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.6994158029556274},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6488025784492493},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.13668569922447205}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpca56546.2023.10071070","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpca56546.2023.10071070","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Symposium on High-Performance Computer Architecture (HPCA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6200000047683716,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W131662869","https://openalex.org/W1515422725","https://openalex.org/W1547830536","https://openalex.org/W1548516269","https://openalex.org/W1784882828","https://openalex.org/W2005107218","https://openalex.org/W2034861439","https://openalex.org/W2085937320","https://openalex.org/W2112980698","https://openalex.org/W2129991978","https://openalex.org/W2134696992","https://openalex.org/W2140191557","https://openalex.org/W2147657366","https://openalex.org/W2164431468","https://openalex.org/W2170257519","https://openalex.org/W2332254524","https://openalex.org/W2396622873","https://openalex.org/W2402144811","https://openalex.org/W2765234579","https://openalex.org/W2766489088","https://openalex.org/W2785905327","https://openalex.org/W2791844663","https://openalex.org/W2801000640","https://openalex.org/W2955723980","https://openalex.org/W2963446712","https://openalex.org/W2979874885","https://openalex.org/W2980688670","https://openalex.org/W2981758446","https://openalex.org/W2981819390","https://openalex.org/W2982008795","https://openalex.org/W3005783121","https://openalex.org/W3016765354","https://openalex.org/W3016903199","https://openalex.org/W3100710793","https://openalex.org/W3101416431","https://openalex.org/W3155004489","https://openalex.org/W3205140122","https://openalex.org/W3206117777","https://openalex.org/W3207965708","https://openalex.org/W3209151516","https://openalex.org/W4232168013","https://openalex.org/W4237967454","https://openalex.org/W4246166885","https://openalex.org/W4252271806","https://openalex.org/W4295312788","https://openalex.org/W4301607055","https://openalex.org/W4308083597","https://openalex.org/W4308083751","https://openalex.org/W6605368212","https://openalex.org/W6633267553","https://openalex.org/W6679642144","https://openalex.org/W6683832327","https://openalex.org/W6749289006","https://openalex.org/W6766978945"],"related_works":["https://openalex.org/W2291920536","https://openalex.org/W2162270818","https://openalex.org/W2022397046","https://openalex.org/W2162726111","https://openalex.org/W1603583590","https://openalex.org/W338671845","https://openalex.org/W2063770303","https://openalex.org/W2018511057","https://openalex.org/W2286348849","https://openalex.org/W1587248296"],"abstract_inverted_index":{"Increasing":[0],"interests":[1],"in":[2,332,355],"Bit-serial":[3,31,86,137,167,189,202,236,250,316],"SIMD":[4,22,32,39,51,87,138,168,190,203,237,251,317],"Processing-Using-DRAM":[5],"(PUD)":[6],"architectures":[7,34],"amplify":[8],"the":[9,49,71,94,97,122,151,164,174,183,198,210,213,218,245,295,311],"needs":[10],"for":[11,159,222,249,315,339,351],"a":[12,66,80,128,326,341,356],"compiler":[13,82],"to":[14,19,47,74,84,105,118,135,161,292,294,367],"automate":[15],"code":[16,111],"generation,":[17,112],"credited":[18],"their":[20],"ultra-wide":[21,50],"width":[23,52],"and":[24,56,69,91,110,125,180,216,272,282,286,303,344,362,373],"reduction":[25,328],"of":[26,99,166,176,185,201,212,220,225,329,365],"data":[27,76,178,187,276,290],"movements.":[28],"The":[29],"state-of-the-art":[30,235,246,312],"PUD":[33,88,139,169,191,204,238,252,318],"(1)":[35,101,172,209],"only":[36],"provide":[37],"assembly":[38],"programming":[40],"interfaces,":[41],"which":[42,64,171],"heavily":[43],"saddles":[44],"with":[45,307,325],"programmers":[46],"exploit":[48,141,163],"on":[53,233,298],"these":[54],"architectures;":[55],"(2)":[57,126,181,217],"encapsulate":[58],"1-bit":[59],"operations":[60],"into":[61,121],"multi-bit":[62],"abstractions,":[63],"incurs":[65],"granularity":[67],"mismatch":[68],"restricts":[70],"optimization":[72],"space":[73],"minimize":[75,173],"movements.We":[77],"present":[78],"CHOPPER,":[79,366],"new":[81,129],"infrastructure":[83],"make":[85,136],"more":[89,148],"programmable":[90],"efficient.":[92],"For":[93,150],"better":[95,152,162,368],"programmability,":[96],"design":[98],"CHOPPER":[100,160,221,229,267,333],"exploits":[102],"bit-slicing":[103],"compilers":[104],"enable":[106],"automatic":[107],"memory":[108],"allocation":[109],"from":[113,262],"naturally-expressive":[114],"codes":[115,243,248,309],"(i.e.":[116,144,334],"similar":[117],"Parallel":[119],"Haskell)":[120],"\"SIMD-Within-A-Register\"-style":[123],"codes;":[124],"introduces":[127],"abstraction":[130],"called":[131],"\"Virtual":[132],"Code":[133],"Emitter\",":[134],"architecture":[140],"Memory-Level":[142],"Parallelism":[143],"Bank":[145],"or":[146],"Subarray)":[147],"effectively.":[149],"efficiency,":[153],"we":[154],"propose":[155],"three":[156,234],"novel":[157],"optimizations":[158,194],"potentials":[165,219],"architectures,":[170],"amount":[175],"intra-subarray":[177],"movements;":[179],"mitigate":[182],"overheads":[184],"spilling":[186],"outside":[188],"architectures.":[192,205,239,253,319],"These":[193,320],"can":[195,277],"greatly":[196],"improve":[197],"overall":[199],"efficiency":[200],"We":[206,240,254,358],"also":[207,323,359],"discuss":[208],"limitations":[211],"current":[214],"CHOPPER;":[215],"other":[223],"types":[224],"Processing-In-Memory":[226],"architectures.We":[227],"evaluate":[228],"by":[230,335],"hosting":[231],"it":[232],"compare":[241],"CHOPPER-generated":[242],"against":[244],"hands-tuned":[247,308],"highlight":[255],"that,":[256],"averaged":[257],"across":[258],"16":[259],"real-world":[260],"workloads":[261],"4":[263],"PUD-friendly":[264],"application":[265],"domains,":[266],"achieves":[268],"(A)":[269],"1.20X,":[270],"1.29X":[271],"1.26X":[273],"speedup":[274,288],"when":[275,289],"fit":[278],"within":[279],"DRAM":[280],"subarrays;":[281],"(B)":[283],"12.61X,":[284],"9.05X":[285],"9.81X":[287],"need":[291],"spill":[293],"secondary":[296],"storage,":[297],"Ambit":[299],"[50],":[300],"ELP2IM":[301],"[56]":[302],"SIMDRAM":[304],"[22],":[305],"compared":[306],"using":[310],"methodology":[313],"[22]":[314],"performance":[321],"benefits":[322,372],"accompany":[324],"great":[327],"Lines-of-Codes":[330],"(LoC)":[331],"4.3X":[336],"less":[337,350],"LoCs":[338],"hands-tuning":[340,352],"single":[342],"subarray,":[343],">10":[345],"<sup":[346],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[347],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">3</sup>":[348],"X":[349],"all":[353],"subarrays":[354],"rank).":[357],"perform":[360],"breakdown":[361],"sensitivity":[363],"studies":[364],"understand":[369],"its":[370,375],"source":[371],"examine":[374],"robustness":[376],"under":[377],"various":[378],"architectural":[379],"features.":[380]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-06T06:45:51.903784","created_date":"2025-10-10T00:00:00"}