{"id":"https://openalex.org/W7213579446","doi":"https://doi.org/10.48550/arxiv.2609.19147","title":"Qupertino: Pure MLX Array Kernels versus Hand-Tuned Metal Shaders for Quantum Circuit Simulation on Apple Silicon","display_name":"Qupertino: Pure MLX Array Kernels versus Hand-Tuned Metal Shaders for Quantum Circuit Simulation on Apple Silicon","publication_year":2026,"publication_date":"2026-07-09","ids":{"openalex":"https://openalex.org/W7213579446","doi":"https://doi.org/10.48550/arxiv.2609.19147"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.19147","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.19147","pdf_url":"https://arxiv.org/pdf/2609.19147","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.19147","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047618440","display_name":"Shlomo Kashani","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kashani, Shlomo","raw_affiliation_strings":["Baltimore , MD , USA","Johns Hopkins University , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Baltimore , MD , USA","institution_ids":[]},{"raw_affiliation_string":"Johns Hopkins University , USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5047618440"],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T10682","display_name":"Quantum Computing Algorithms and Architecture","score":0.9937000274658203,"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"}},"topics":[{"id":"https://openalex.org/T10682","display_name":"Quantum Computing Algorithms and Architecture","score":0.9937000274658203,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.005799999926239252,"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/T11804","display_name":"Quantum many-body systems","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/3107","display_name":"Atomic and Molecular Physics, and Optics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/quantum-circuit-simulation","display_name":"quantum circuit simulation","score":0.9660000205039978},{"id":"https://openalex.org/keywords/apple-silicon","display_name":"Apple Silicon","score":0.7429999709129333},{"id":"https://openalex.org/keywords/gpu-acceleration","display_name":"GPU acceleration","score":0.4129999876022339},{"id":"https://openalex.org/keywords/quantum-fourier-transform","display_name":"quantum Fourier transform","score":0.5740000009536743},{"id":"https://openalex.org/keywords/variational-quantum-algorithms","display_name":"variational quantum algorithms","score":0.7260000109672546},{"id":"https://openalex.org/keywords/quantum-approximate-optimization-algorithm","display_name":"quantum approximate optimization algorithm","score":0.7649999856948853}],"concepts":[{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.8429999947547913},{"id":"https://openalex.org/C177681979","wikidata":"https://www.wikidata.org/wiki/Q633182","display_name":"Shader","level":3,"score":0.7264000177383423},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.636900007724762},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5169000029563904},{"id":"https://openalex.org/C124148022","wikidata":"https://www.wikidata.org/wiki/Q2122210","display_name":"Quantum circuit","level":5,"score":0.44909998774528503},{"id":"https://openalex.org/C58053490","wikidata":"https://www.wikidata.org/wiki/Q176555","display_name":"Quantum computer","level":3,"score":0.42910000681877136},{"id":"https://openalex.org/C203087015","wikidata":"https://www.wikidata.org/wiki/Q378201","display_name":"Qubit","level":3,"score":0.396699994802475},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.382099986076355},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.36039999127388},{"id":"https://openalex.org/C99821215","wikidata":"https://www.wikidata.org/wiki/Q1136583","display_name":"Swap (finance)","level":2,"score":0.358599990606308},{"id":"https://openalex.org/C3019562390","wikidata":"https://www.wikidata.org/wiki/Q4860306","display_name":"Bare metal","level":4,"score":0.3580999970436096},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3379000127315521},{"id":"https://openalex.org/C50831359","wikidata":"https://www.wikidata.org/wiki/Q165436","display_name":"Assembly language","level":3,"score":0.32519999146461487},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.32089999318122864},{"id":"https://openalex.org/C2908650547","wikidata":"https://www.wikidata.org/wiki/Q20999234","display_name":"Intrinsics","level":2,"score":0.30730000138282776},{"id":"https://openalex.org/C190902152","wikidata":"https://www.wikidata.org/wiki/Q1325106","display_name":"Optimizing compiler","level":3,"score":0.29420000314712524},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.2842000126838684},{"id":"https://openalex.org/C59500034","wikidata":"https://www.wikidata.org/wiki/Q1464944","display_name":"Quantum Fourier transform","level":5,"score":0.2766999900341034},{"id":"https://openalex.org/C182953411","wikidata":"https://www.wikidata.org/wiki/Q917713","display_name":"Controlled NOT gate","level":5,"score":0.273499995470047},{"id":"https://openalex.org/C131017901","wikidata":"https://www.wikidata.org/wiki/Q170451","display_name":"Logic gate","level":2,"score":0.26330000162124634},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.2612000107765198},{"id":"https://openalex.org/C58849907","wikidata":"https://www.wikidata.org/wiki/Q2118982","display_name":"Quantum gate","level":4,"score":0.26089999079704285},{"id":"https://openalex.org/C145108525","wikidata":"https://www.wikidata.org/wiki/Q656154","display_name":"Xeon","level":2,"score":0.25619998574256897}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.19147","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.19147","pdf_url":"https://arxiv.org/pdf/2609.19147","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.19147","doi":"https://doi.org/10.48550/arxiv.2609.19147","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.19147","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,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.19147","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.19147","pdf_url":"https://arxiv.org/pdf/2609.19147","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7213579446.pdf","grobid_xml":"https://content.openalex.org/works/W7213579446.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7160942121","https://openalex.org/W7203790637","https://openalex.org/W3194686376","https://openalex.org/W7164813674","https://openalex.org/W7168235763","https://openalex.org/W2901692656","https://openalex.org/W4416124907","https://openalex.org/W4389159513","https://openalex.org/W7168259244","https://openalex.org/W7151542675"],"abstract_inverted_index":{"We":[0],"present":[1],"Qupertino,":[2],"an":[3,67],"open-source":[4],"quantum":[5],"circuit":[6,128],"simulator":[7,19],"for":[8,31,90],"Apple":[9],"Silicon,":[10],"and":[11,28,64,111,114,168,189,199,235,260],"use":[12],"it":[13],"to":[14,47,78,124],"ask":[15],"how":[16],"far":[17],"a":[18,70,75,136,202,241,261],"written":[20],"purely":[21],"in":[22,95,158,177,193,271],"MLX":[23,49,212],"array":[24],"operations":[25],"can":[26],"go":[27],"what":[29],"remains":[30,269],"hand-tuned":[32],"Metal":[33,88],"shaders.":[34],"The":[35,41,82,223],"framework":[36,224],"ships":[37],"two":[38],"measured":[39,146],"tiers.":[40],"pure":[42,211],"tier":[43,85,152],"dispatches":[44],"structured":[45,92],"gates":[46,52,59],"specialized":[48],"kernels:":[50],"diagonal":[51],"run":[53],"as":[54,60,66],"broadcast":[55],"phase":[56],"multiplies,":[57],"controlled":[58],"masked":[61],"half-state":[62],"updates,":[63],"SWAP":[65],"axis":[68],"permutation;":[69],"paired":[71,208],"dense-path":[72],"ablation":[73],"attributes":[74],"25-33x":[76],"speedup":[77,209],"this":[79],"dispatch":[80],"alone.":[81],"opt-in":[83],"shader":[84,151,206],"adds":[86],"hand-written":[87],"kernels":[89],"every":[91],"layer":[93],"family":[94],"our":[96],"benchmarks,":[97],"including":[98],"phase-LUT":[99],"diagonals,":[100],"GF(2)":[101],"affine":[102],"permutation":[103],"gathers,":[104],"fused":[105],"tensor-product":[106],"single-qubit":[107],"layers,":[108],"radix-4":[109],"QFT":[110,175],"Walsh-Hadamard":[112],"butterflies,":[113],"basis-conjugated":[115],"XX/YY":[116],"Trotter":[117,191],"layers;":[118],"runtime":[119,157],"fusion":[120],"detectors":[121],"route":[122],"work":[123],"them":[125],"while":[126],"preserving":[127],"semantics":[129],"exactly,":[130],"confirmed":[131],"by":[132,155],"parity":[133],"tests.":[134],"In":[135],"four-way":[137],"interleaved":[138],"campaign":[139],"on":[140,248,253],"M1":[141],"Max":[142],"(two":[143],"warmups,":[144],"ten":[145],"repeats":[147],"per":[148],"cell),":[149],"the":[150,205],"is":[153],"fastest":[154],"mean":[156],"all":[159],"18":[160],"comparison":[161],"cells":[162],"against":[163,264],"same-machine":[164],"Qiskit":[165],"Aer":[166],"CPU":[167],"PennyLane":[169],"lightning.qubit.":[170],"At":[171],"25":[172,216],"qubits,":[173],"gate-stream":[174],"runs":[176],"0.0591":[178],"+/-":[179,195],"0.0029":[180],"s":[181,197],"(paired":[182],"47.2x":[183],"over":[184,187,210],"Aer,":[185],"95.3x":[186],"PennyLane)":[188],"TFIM":[190],"evolution":[192],"0.495":[194],"0.035":[196],"(36.2x":[198],"67.2x).":[200],"Across":[201],"29-workload":[203],"suite,":[204],"tier's":[207],"reaches":[213,245],"25x,":[214],"with":[215],"of":[217],"29":[218],"workloads":[219],"accelerating":[220],"above":[221],"parity.":[222],"also":[225],"supports":[226],"variational":[227],"ansatz":[228],"workloads,":[229],"QAOA,":[230],"QCBM,":[231],"Trotter-Suzuki":[232],"Hamiltonian":[233],"simulation,":[234],"OpenQASM":[236],"2.0":[237],"import":[238],"(unitary":[239],"subset);":[240],"preliminary":[242],"MPS":[243],"backend":[244],"150":[246],"qubits":[247],"limited-entanglement":[249],"workloads.":[250],"Correctness":[251],"rests":[252],"253":[254],"Python":[255],"tests,":[256],"independent":[257],"complex128":[258],"checks,":[259],"Trotter-error":[262],"curve":[263],"exact":[265],"diagonalization.":[266],"State-vector":[267],"memory":[268],"exponential":[270],"qubit":[272],"count.":[273]},"counts_by_year":[],"updated_date":"2026-11-06T12:05:46.655746","created_date":"2026-09-19T00:00:00"}
