{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T02:54:02Z","timestamp":1767840842717,"version":"3.49.0"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,11,1]],"date-time":"2021-11-01T00:00:00Z","timestamp":1635724800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,11,1]],"date-time":"2021-11-01T00:00:00Z","timestamp":1635724800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,11,1]],"date-time":"2021-11-01T00:00:00Z","timestamp":1635724800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,11]]},"DOI":"10.1109\/p3hpc54578.2021.00006","type":"proceedings-article","created":{"date-parts":[[2021,12,28]],"date-time":"2021-12-28T21:30:45Z","timestamp":1640727045000},"page":"22-32","source":"Crossref","is-referenced-by-count":18,"title":["oneAPI Open-Source Math Library Interface"],"prefix":"10.1109","author":[{"given":"Mariia","family":"Krainiuk","sequence":"first","affiliation":[]},{"given":"Mehdi","family":"Goli","sequence":"additional","affiliation":[]},{"given":"Vincent R.","family":"Pascuzzi","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref31","author":"alpay","year":"0","journal-title":"Sycl2020 in hipsycl dpc++ features on amd gpus nvidia gpus and cpus"},{"key":"ref30","year":"0","journal-title":"a gpu accelerated library for decompositions and linear system solutions for both dense and sparse matrices"},{"key":"ref10","author":"trott","year":"0","journal-title":"Kokkos c++ performance portability programming ecosystem Math kernels-provides blas sparse blas and graph kernels"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.2172\/1169830"},{"key":"ref12","year":"0","journal-title":"Arrayfire library"},{"key":"ref13","year":"0","journal-title":"MAGMA Project"},{"key":"ref14","year":"0","journal-title":"Intel oneapi math kernel library (onemkl)"},{"key":"ref15","year":"0","journal-title":"Basic linear algebra on nvidia gpus"},{"key":"ref16","year":"0","journal-title":"Nvidia curand Random number generation on nvidia gpus"},{"key":"ref17","year":"0","journal-title":"The ARM Computer Vision and Machine Learning library"},{"key":"ref18","year":"0","journal-title":"Amd hipblas Dense linear algebra on amd gpus"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/P3HPC51967.2020.00008"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/0010-4655(94)90217-8"},{"key":"ref4","year":"0","journal-title":"Netlib blas"},{"key":"ref27","first-page":"8003s","volume":"3","author":"aad","year":"2008","journal-title":"The ATLAS Experiment at the CERN Large Hadron Collider"},{"key":"ref3","year":"0","journal-title":"SYCL C++ single-source heterogeneous programming for OpenCL"},{"key":"ref6","first-page":"298","article-title":"Intel® threading building blocks","volume":"23","author":"pheatt","year":"2008","journal-title":"Journal of Computing Sciences in Colleges"},{"key":"ref29","first-page":"32","volume":"4","author":"dong","year":"2021","journal-title":"Porting hep parameterized calorimeter simulation code to gpus"},{"key":"ref5","year":"0","journal-title":"The FFTW Library"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MCSE.2010.69"},{"key":"ref7","year":"0","journal-title":"Nvidia cuda programming model"},{"key":"ref2","year":"0","journal-title":"Sycl™ specification version 1 2 1 revision date April 27 2020 khronos® sycl™ working group"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3388333.3388649"},{"key":"ref1","year":"0","journal-title":"oneapi specification 1 0 oneapi data parallel c++"},{"key":"ref20","year":"0","journal-title":"Performance brief “accelerate machine-learning workloads with intel® math kernel library”"},{"key":"ref22","year":"0","journal-title":"interop_task Improving sycl opencl interoperability"},{"key":"ref21","year":"0","journal-title":"oneapi for cuda overview codeplay solutions"},{"key":"ref24","year":"0","journal-title":"Convolutional layers user guide nvidia deep learning performance documentation"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.728"},{"key":"ref26","first-page":"42006","volume":"898","author":"s","year":"2017","journal-title":"The new ATLAS fast calorimeter simulation"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2017.08.007"}],"event":{"name":"2021 International Workshop on Performance, Portability and Productivity in HPC (P3HPC)","location":"St. Louis, MO, USA","start":{"date-parts":[[2021,11,14]]},"end":{"date-parts":[[2021,11,14]]}},"container-title":["2021 International Workshop on Performance, Portability and Productivity in HPC (P3HPC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9652829\/9652840\/09652858.pdf?arnumber=9652858","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T16:59:59Z","timestamp":1652201999000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9652858\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,11]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/p3hpc54578.2021.00006","relation":{},"subject":[],"published":{"date-parts":[[2021,11]]}}}