{"id":"https://openalex.org/W4408029485","doi":"https://doi.org/10.1145/3710848.3710886","title":"Jigsaw: Toward Conflict-free Vectorized Stencil Computation by Tessellating Swizzled Registers","display_name":"Jigsaw: Toward Conflict-free Vectorized Stencil Computation by Tessellating Swizzled Registers","publication_year":2025,"publication_date":"2025-02-28","ids":{"openalex":"https://openalex.org/W4408029485","doi":"https://doi.org/10.1145/3710848.3710886"},"language":"en","primary_location":{"id":"doi:10.1145/3710848.3710886","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3710848.3710886","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3710848.3710886","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3710848.3710886","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080114640","display_name":"Yiwei Zhang","orcid":"https://orcid.org/0000-0003-2050-572X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yiwei Zhang","raw_affiliation_strings":["Chinese Academy of Sciences, Beijing, China","University of Chinese Academy of Sciences, Microsoft Research, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2050-572X","affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Microsoft Research, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100377529","display_name":"Kun Li","orcid":"https://orcid.org/0000-0002-1013-1325"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kun Li","raw_affiliation_strings":["Microsoft Research, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1013-1325","affiliations":[{"raw_affiliation_string":"Microsoft Research, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072946868","display_name":"Liang Yuan","orcid":"https://orcid.org/0000-0003-3406-2907"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Yuan","raw_affiliation_strings":["Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3406-2907","affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102695664","display_name":"Haozhi Han","orcid":"https://orcid.org/0009-0004-3075-3385"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haozhi Han","raw_affiliation_strings":["Peking University, Microsoft Research, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-3075-3385","affiliations":[{"raw_affiliation_string":"Peking University, Microsoft Research, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016255357","display_name":"Yunquan Zhang","orcid":"https://orcid.org/0000-0001-7520-9640"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunquan Zhang","raw_affiliation_strings":["Chinese Academy of Sciences, Beijing, China","University of Chinese Academy of Sciences, Microsoft Research, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7520-9640","affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Microsoft Research, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101534161","display_name":"Ting Cao","orcid":"https://orcid.org/0000-0002-9107-013X"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ting Cao","raw_affiliation_strings":["Microsoft Research, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9107-013X","affiliations":[{"raw_affiliation_string":"Microsoft Research, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100438310","display_name":"Mao Yang","orcid":"https://orcid.org/0009-0009-6455-3898"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mao Yang","raw_affiliation_strings":["Microsoft Research, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-6455-3898","affiliations":[{"raw_affiliation_string":"Microsoft Research, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5080114640"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02683805,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"481","last_page":"495"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9950000047683716,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.989799976348877,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/jigsaw","display_name":"Jigsaw","score":0.9237706065177917},{"id":"https://openalex.org/keywords/stencil","display_name":"Stencil","score":0.7435001134872437},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6886285543441772},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6459414958953857},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6048669815063477},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.38883692026138306},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1783064901828766},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14961495995521545},{"id":"https://openalex.org/keywords/mathematics-education","display_name":"Mathematics education","score":0.09261327981948853}],"concepts":[{"id":"https://openalex.org/C2779405079","wikidata":"https://www.wikidata.org/wiki/Q356040","display_name":"Jigsaw","level":2,"score":0.9237706065177917},{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.7435001134872437},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6886285543441772},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6459414958953857},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6048669815063477},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.38883692026138306},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1783064901828766},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14961495995521545},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.09261327981948853}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3710848.3710886","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3710848.3710886","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3710848.3710886","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3710848.3710886","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3710848.3710886","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3710848.3710886","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4408029485.pdf"},"referenced_works_count":63,"referenced_works":["https://openalex.org/W174757544","https://openalex.org/W1492882524","https://openalex.org/W1559264847","https://openalex.org/W1561247983","https://openalex.org/W1968013322","https://openalex.org/W1968347730","https://openalex.org/W1973271197","https://openalex.org/W1973532523","https://openalex.org/W1979457157","https://openalex.org/W1991009705","https://openalex.org/W1997375049","https://openalex.org/W2003798513","https://openalex.org/W2008005532","https://openalex.org/W2013156670","https://openalex.org/W2016618963","https://openalex.org/W2034761517","https://openalex.org/W2039378765","https://openalex.org/W2039417226","https://openalex.org/W2049510645","https://openalex.org/W2063249715","https://openalex.org/W2068993993","https://openalex.org/W2076780324","https://openalex.org/W2079834329","https://openalex.org/W2098220211","https://openalex.org/W2099404643","https://openalex.org/W2104512032","https://openalex.org/W2107725926","https://openalex.org/W2108730477","https://openalex.org/W2111394443","https://openalex.org/W2118031182","https://openalex.org/W2119609467","https://openalex.org/W2135682468","https://openalex.org/W2135736783","https://openalex.org/W2147423491","https://openalex.org/W2151764765","https://openalex.org/W2162323496","https://openalex.org/W2167713801","https://openalex.org/W2198872802","https://openalex.org/W2296218291","https://openalex.org/W2333659671","https://openalex.org/W2902566644","https://openalex.org/W2903775786","https://openalex.org/W2913533776","https://openalex.org/W2962946415","https://openalex.org/W2983655274","https://openalex.org/W2984920043","https://openalex.org/W2996929894","https://openalex.org/W3099814709","https://openalex.org/W3132763358","https://openalex.org/W3175788003","https://openalex.org/W3205077974","https://openalex.org/W3205799311","https://openalex.org/W4232301837","https://openalex.org/W4242539338","https://openalex.org/W4244894488","https://openalex.org/W4249968602","https://openalex.org/W4255560897","https://openalex.org/W4283641593","https://openalex.org/W4321636661","https://openalex.org/W4367684987","https://openalex.org/W4376632753","https://openalex.org/W4391987273","https://openalex.org/W4405756205"],"related_works":["https://openalex.org/W2039378765","https://openalex.org/W2003798513","https://openalex.org/W2151764765","https://openalex.org/W2890431355","https://openalex.org/W4376875029","https://openalex.org/W3149084271","https://openalex.org/W4247008888","https://openalex.org/W2150319905","https://openalex.org/W2962978274","https://openalex.org/W1429949169"],"abstract_inverted_index":{"Stencil":[0],"computation":[1],"plays":[2],"a":[3,45,95],"pivotal":[4],"role":[5],"in":[6,38],"numerous":[7],"scientific":[8],"and":[9,71,82],"engineering":[10],"applications.":[11],"Previous":[12],"studies":[13],"have":[14],"extensively":[15],"investigated":[16],"vectorization":[17,47],"techniques":[18],"to":[19,49,99],"enhance":[20],"in-core":[21],"parallelism;":[22],"however,":[23],"the":[24,100],"performance":[25],"bottleneck":[26],"caused":[27],"by":[28,55],"data":[29],"alignment":[30],"conflicts":[31],"(DAC)":[32],"has":[33],"not":[34],"been":[35],"effectively":[36,77],"resolved":[37],"all":[39,53],"dimensions.":[40,84],"This":[41],"paper":[42],"proposes":[43],"Jigsaw,":[44],"conflict-free":[46],"method":[48],"reduce":[50],"DAC":[51,79],"across":[52,80],"dimensions":[54],"tessellating":[56],"swizzled":[57],"finest-grained":[58],"lanes.":[59],"Jigsaw":[60,92],"comprises":[61],"three":[62],"key":[63],"components:":[64],"Lane-based":[65],"Butterfly":[66],"Vectorization,":[67],"SVD-based":[68],"Dimension":[69],"Flattening,":[70],"Iteration-based":[72],"Temporal":[73],"Merging.":[74],"These":[75],"components":[76],"address":[78],"spatial":[81],"temporal":[83],"Experimental":[85],"results":[86],"on":[87,109],"different":[88],"machines":[89],"demonstrate":[90],"that":[91],"could":[93],"achieve":[94],"significant":[96],"improvement":[97],"compared":[98],"state-of-the-art":[101],"techniques,":[102],"with":[103],"an":[104],"average":[105],"speedup":[106],"of":[107],"2.31x":[108],"various":[110],"stencil":[111],"kernels.":[112]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}