{"id":"https://openalex.org/W7204643456","doi":"https://doi.org/10.5281/zenodo.22164007","title":"qgemv-roofline: a quantized GEMV kernel ladder measured against its own bandwidth roof","display_name":"qgemv-roofline: a quantized GEMV kernel ladder measured against its own bandwidth roof","publication_year":2026,"publication_date":"2026-08-29","ids":{"openalex":"https://openalex.org/W7204643456","doi":"https://doi.org/10.5281/zenodo.22164007"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.22164007","doi":"https://doi.org/10.5281/zenodo.22164007","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22164007","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"Software"},"volume":null,"type":"software","is_traditional":false,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.22164007","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5146049571","display_name":"Manu Nicholas Jacob","orcid":"https://orcid.org/0009-0007-6589-6572","observed_orcids":["https://orcid.org/0009-0007-6589-6572"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jacob, Manu Nicholas","raw_affiliation_strings":["Independent Researcher"],"raw_orcid":"https://orcid.org/0009-0007-6589-6572","affiliations":[{"raw_affiliation_string":"Independent Researcher","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5146049571"],"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9976000189781189,"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":0.9976000189781189,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.0003000000142492354,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11697","display_name":"Numerical Methods and Algorithms","score":0.0003000000142492354,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/cuda-kernels","display_name":"CUDA kernels","score":0.7049999833106995},{"id":"https://openalex.org/keywords/triton","display_name":"Triton","score":0.9150000214576721},{"id":"https://openalex.org/keywords/nvidia-gpus","display_name":"NVIDIA GPUs","score":0.8309999704360962}],"concepts":[{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.6535000205039978},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.515500009059906},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.47620001435279846},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.3935000002384186},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.3874000012874603},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3718000054359436},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.3521000146865845},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.32190001010894775},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.30239999294281006},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.27950000762939453},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.27489998936653137},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.2718000113964081},{"id":"https://openalex.org/C165005293","wikidata":"https://www.wikidata.org/wiki/Q1074500","display_name":"Chip","level":2,"score":0.26460000872612},{"id":"https://openalex.org/C557945733","wikidata":"https://www.wikidata.org/wiki/Q389772","display_name":"Data transmission","level":2,"score":0.26190000772476196},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.2565000057220459},{"id":"https://openalex.org/C200157131","wikidata":"https://www.wikidata.org/wiki/Q4854763","display_name":"Bandwidth allocation","level":3,"score":0.25429999828338623}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.5281/zenodo.22164007","doi":"https://doi.org/10.5281/zenodo.22164007","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22164007","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"Software"},{"id":"doi:10.5281/zenodo.22164008","doi":"https://doi.org/10.5281/zenodo.22164008","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22164008","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"Software"},{"id":"doi:10.5281/zenodo.23341234","doi":"https://doi.org/10.5281/zenodo.23341234","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23341234","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"Software"}],"best_oa_location":{"id":"doi:10.5281/zenodo.22164007","doi":"https://doi.org/10.5281/zenodo.22164007","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22164007","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"Software"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7197045844","https://openalex.org/W7202029923","https://openalex.org/W7155213767","https://openalex.org/W7159651904","https://openalex.org/W4417473264","https://openalex.org/W7165142542","https://openalex.org/W4407557142","https://openalex.org/W7203651398","https://openalex.org/W4391901161","https://openalex.org/W7201871197"],"abstract_inverted_index":{"Twelve":[0],"CUDA":[1],"kernels":[2],"and":[3,16],"a":[4,29],"Triton":[5],"implementation":[6],"of":[7],"the":[8,32],"batch-1":[9],"LLM":[10],"decode":[11],"GEMV":[12],"over":[13],"ggml":[14],"q8_0":[15],"q4_0":[17],"weights,":[18],"measured":[19],"on":[20],"five":[21],"NVIDIA":[22],"GPUs":[23],"spanning":[24],"sm_60":[25],"to":[26],"sm_89":[27],"against":[28],"bandwidth":[30],"ceiling":[31],"harness":[33],"measures":[34],"for":[35],"itself.":[36]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-30T00:00:00"}