{"id":"https://openalex.org/W7154133303","doi":"https://doi.org/10.48550/arxiv.2604.09240","title":"DiffHLS: Differential Learning for High-Level Synthesis QoR Prediction with GNNs and LLM Code Embeddings","display_name":"DiffHLS: Differential Learning for High-Level Synthesis QoR Prediction with GNNs and LLM Code Embeddings","publication_year":2026,"publication_date":"2026-04-10","ids":{"openalex":"https://openalex.org/W7154133303","doi":"https://doi.org/10.48550/arxiv.2604.09240"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.09240","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.09240","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.09240","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133539435","display_name":"Zedong Peng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peng, Zedong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133550912","display_name":"Zeju Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Zeju","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133498075","display_name":"Qiang Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Qiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5133539365","display_name":"Jieru Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Jieru","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10904","display_name":"Embedded Systems Design Techniques","score":0.40700000524520874,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.40700000524520874,"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/T10260","display_name":"Software Engineering Research","score":0.14239999651908875,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11948","display_name":"Machine Learning in Materials Science","score":0.08709999918937683,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.6736999750137329},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5763999819755554},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5430999994277954},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.47940000891685486},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4433000087738037},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4059999883174896},{"id":"https://openalex.org/keywords/differential","display_name":"Differential (mechanical device)","score":0.3882000148296356}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7717000246047974},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6736999750137329},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5805000066757202},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5763999819755554},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5605999827384949},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5430999994277954},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.47940000891685486},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4433000087738037},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4059999883174896},{"id":"https://openalex.org/C93226319","wikidata":"https://www.wikidata.org/wiki/Q193137","display_name":"Differential (mechanical device)","level":2,"score":0.3882000148296356},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.38260000944137573},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.34880000352859497},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.3334999978542328},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3224000036716461},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3107999861240387},{"id":"https://openalex.org/C122280245","wikidata":"https://www.wikidata.org/wiki/Q620622","display_name":"Kernel method","level":3,"score":0.29089999198913574},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.274399995803833},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27379998564720154},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2635999917984009},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.2606000006198883},{"id":"https://openalex.org/C100595998","wikidata":"https://www.wikidata.org/wiki/Q11731931","display_name":"Graph kernel","level":5,"score":0.25270000100135803}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.09240","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.09240","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.09240","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.09240","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"High-Level":[0],"Synthesis":[1],"(HLS)":[2],"compiles":[3],"C/C++":[4],"into":[5],"RTL,":[6],"but":[7],"exploring":[8],"pragma-driven":[9],"optimization":[10],"choices":[11],"remains":[12],"expensive":[13],"because":[14],"each":[15],"design":[16,44,49,97],"point":[17],"requires":[18],"time-consuming":[19],"synthesis.":[20],"We":[21,122],"propose":[22],"\\textbf{\\DiffHLS},":[23],"a":[24,38,42,68,119],"differential":[25],"learning":[26],"framework":[27],"for":[28],"HLS":[29],"Quality-of-Result":[30],"(QoR)":[31],"prediction":[32],"that":[33],"learns":[34],"from":[35,67],"kernel--design":[36],"pairs:":[37],"kernel":[39,47,85],"baseline":[40,86],"and":[41,48,59,87,91,112],"pragma-inserted":[43],"variant.":[45],"\\DiffHLS~encodes":[46],"intermediate-representation":[50],"graphs":[51],"with":[52,64],"dedicated":[53],"graph":[54],"neural":[55],"network":[56],"(GNN)":[57],"branches,":[58],"augments":[60],"the":[61,84,88,96,127],"delta":[62],"pathway":[63],"code":[65,70,114],"embeddings":[66,115],"pretrained":[69],"large":[71],"language":[72],"model":[73],"(LLM).":[74],"Instead":[75],"of":[76],"regressing":[77],"absolute":[78],"targets":[79],"directly,":[80],"we":[81],"jointly":[82],"predict":[83],"design-induced":[89],"delta,":[90],"compose":[92],"them":[93],"to":[94],"obtain":[95],"prediction.":[98],"On":[99],"PolyBench,":[100],"\\DiffHLS~attains":[101],"lower":[102],"average":[103],"MAPE":[104],"than":[105],"GNN":[106,110],"baselines":[107],"under":[108],"four":[109],"backbones,":[111],"LLM":[113],"consistently":[116],"improve":[117],"over":[118],"GNN-only":[120],"ablation.":[121],"further":[123],"validate":[124],"scalability":[125],"on":[126],"ForgeHLS":[128],"dataset.":[129]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-04-14T00:00:00"}