{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T08:57:11Z","timestamp":1781254631421,"version":"3.54.1"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T00:00:00Z","timestamp":1776729600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T00:00:00Z","timestamp":1776729600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100003816","name":"Huawei Technologies","doi-asserted-by":"publisher","award":["TC20240528049"],"award-info":[{"award-number":["TC20240528049"]}],"id":[{"id":"10.13039\/501100003816","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["CCF Trans. HPC"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1007\/s42514-026-00275-0","type":"journal-article","created":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T05:54:16Z","timestamp":1776750856000},"page":"294-313","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Exploiting intra-core heterogeneity for high-performance dense linear algebra on Huawei Ascend 910 NPUs"],"prefix":"10.1007","volume":"8","author":[{"given":"Shina","family":"Guo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weiguo","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinghui","family":"Tian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuan","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,4,21]]},"reference":[{"issue":"5","key":"275_CR1","doi-asserted-by":"publisher","first-page":"468","DOI":"10.1177\/10943420241261960","volume":"38","author":"A Abdelfattah","year":"2024","unstructured":"Abdelfattah, A., Beams, N., Carson, R., Ghysels, P., Kolev, T., Stitt, T., Vargas, A., Tomov, S., Dongarra, J.: Magma: enabling exascale performance with accelerated blas and lapack for diverse gpu architectures. Int. J. High Perform. Comput. Appl. 38(5), 468\u2013490 (2024). https:\/\/doi.org\/10.1177\/10943420241261960","journal-title":"Int. J. High Perform. Comput. Appl."},{"key":"275_CR2","volume":"180","author":"E Agullo","year":"2009","unstructured":"Agullo, E., Demmel, J., Dongarra, J., Hadri, B., Kurzak, J., Langou, J., Ltaief, H., Luszczek, P., Tomov, S.: Numerical linear algebra on emerging architectures: the PLASMA and MAGMA projects. J. Phys: Conf. Ser. 180, 012037 (2009)","journal-title":"J. Phys: Conf. Ser."},{"key":"275_CR3","doi-asserted-by":"crossref","unstructured":"Agullo, E., Augonnet, C., Dongarra, J., Faverge, M., Langou, J., Ltaief, H., Tomov, S.: Lu factorization for accelerator-based systems. In: 2011 9th IEEE\/ACS International Conference on Computer Systems and Applications (AICCSA), pp. 217\u2013224. IEEE (2011)","DOI":"10.1109\/AICCSA.2011.6126599"},{"key":"275_CR4","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898719604","volume-title":"LAPACK Users\u2019 Guide","author":"E Anderson","year":"1999","unstructured":"Anderson, E., Bai, Z., Bischof, C., Blackford, S., Demmel, J., Dongarra, J., Du Croz, J., Greenbaum, A., Hammarling, S., McKenney, A., Sorensen, D.: LAPACK Users\u2019 Guide, 3rd edn. SIAM, Philadelphia (1999)","edition":"3"},{"key":"275_CR5","doi-asserted-by":"crossref","unstructured":"Augonnet, C., Thibault, S., Namyst, R., Wacrenier, P.-A.: StarPU: A unified platform for task scheduling on heterogeneous multicore architectures. In: Proceedings of the 17th International European Conference on Parallel and Distributed Computing (Euro-Par \u201911), pp. 863\u2013874. Springer (2011)","DOI":"10.1007\/978-3-642-03869-3_80"},{"issue":"6","key":"275_CR6","doi-asserted-by":"publisher","first-page":"3495","DOI":"10.1137\/090760969","volume":"32","author":"G Ballard","year":"2010","unstructured":"Ballard, G., Demmel, J., Holtz, O., Schwartz, O.: Communication-optimal parallel and sequential cholesky decomposition. SIAM J. Sci. Comput. 32(6), 3495\u20133523 (2010). https:\/\/doi.org\/10.1137\/090760969","journal-title":"SIAM J. Sci. Comput."},{"issue":"3","key":"275_CR7","doi-asserted-by":"publisher","first-page":"866","DOI":"10.1137\/090769156","volume":"32","author":"G Ballard","year":"2011","unstructured":"Ballard, G., Demmel, J., Holtz, O., Schwartz, O.: Minimizing communication in numerical linear algebra. SIAM J. Matrix Analysis Appl. 32(3), 866\u2013901 (2011)","journal-title":"SIAM J. Matrix Analysis Appl."},{"key":"275_CR8","doi-asserted-by":"publisher","unstructured":"Ballard, G., Demmel, J., Lipshitz, B., Schwartz, O., Toledo, S.: Communication efficient gaussian elimination with partial pivoting using a shape morphing data layout. In: Blelloch, G.E., V\u00f6cking, B. (eds.) 25th ACM Symposium on Parallelism in Algorithms and Architectures, SPAA \u201913, Montreal - July 23\u201325, 2013, pp. 232\u2013240. ACM (2013). https:\/\/doi.org\/10.1145\/2486159.2486198","DOI":"10.1145\/2486159.2486198"},{"key":"275_CR9","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898719642","volume-title":"ScaLAPACK Users\u2019 Guide","author":"LS Blackford","year":"1997","unstructured":"Blackford, L.S., Choi, J., Cleary, A., D\u2019Azevedo, E., Demmel, J., Dhillon, I., Dongarra, J., Hammarling, S., Henry, G., Petitet, A., et al.: ScaLAPACK Users\u2019 Guide. SIAM, Philadelphia (1997)"},{"key":"275_CR10","unstructured":"Blelloch, G.E., Chowdhury, R.A., Gibbons, P.B., Ramachandran, V., Chen, S., Kozuch, M.: Provably good multicore cache performance for divide-and-conquer algorithms. In: Teng, S. (ed.) Proceedings of the Nineteenth Annual ACM-SIAM Symposium on Discrete Algorithms, SODA 2008, San Francisco, California, USA, January 20\u201322, 2008, pp. 501\u2013510. SIAM (2008). http:\/\/dl.acm.org\/citation.cfm?id=1347082.1347137"},{"key":"275_CR11","doi-asserted-by":"publisher","unstructured":"Blelloch, G.E., Fineman, J.T., Gibbons, P.B., Gu, Y., Shun, J.: Efficient algorithms with asymmetric read and write costs. In: Sankowski, P., Zaroliagis, C.D. (eds.) 24th Annual European Symposium on Algorithms, ESA 2016, August 22\u201324, 2016, Aarhus, Denmark. LIPIcs, vol. 57, pp. 14\u201311418. Schloss Dagstuhl - Leibniz-Zentrum f\u00fcr Informatik (2016). https:\/\/doi.org\/10.4230\/LIPICS.ESA.2016.14","DOI":"10.4230\/LIPICS.ESA.2016.14"},{"issue":"1","key":"275_CR12","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1016\/j.parco.2008.10.002","volume":"35","author":"A Buttari","year":"2009","unstructured":"Buttari, A., Langou, J., Luszczek, P., Dongarra, J.: A class of parallel tiled linear algebra algorithms for multicore architectures. Parallel Comput. 35(1), 38\u201353 (2009)","journal-title":"Parallel Comput."},{"key":"275_CR13","unstructured":"Chellapilla, K., Puri, S., Simard, P.: High performance convolutional neural networks for document processing. In: Tenth International Workshop on Frontiers in Handwriting Recognition (2006). Suvisoft"},{"issue":"7","key":"275_CR14","doi-asserted-by":"publisher","first-page":"911","DOI":"10.1016\/J.JPDC.2013.04.008","volume":"73","author":"RA Chowdhury","year":"2013","unstructured":"Chowdhury, R.A., Ramachandran, V., Silvestri, F., Blakeley, B.: Oblivious algorithms for multicores and networks of processors. J. Parallel Distrib. Comput. 73(7), 911\u2013925 (2013). https:\/\/doi.org\/10.1016\/J.JPDC.2013.04.008","journal-title":"J. Parallel Distrib. Comput."},{"key":"275_CR15","unstructured":"Demmel, J., Grigori, L., Xiang, H.: A communication optimal lu factorization algorithm. In: Technical Report, EECS Technical Report EECS-2010-29, UC Berkeley (2010)"},{"key":"275_CR16","unstructured":"Dhar, A., Thorens, C., Lazier, L.M., Cavigelli, L.: Ascend-cc: confidential computing on heterogeneous NPU for emerging generative AI workloads. CoRR arXiv:2407.11888 (2024) 10.48550\/ARXIV.2407.11888"},{"issue":"1","key":"275_CR17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/77626.79170","volume":"16","author":"JJ Dongarra","year":"1990","unstructured":"Dongarra, J.J., Du Croz, J., Hammarling, S., Duff, I.S.: A set of level 3 basic linear algebra subprograms. ACM Trans. Math. Softw. 16(1), 1\u201317 (1990). https:\/\/doi.org\/10.1145\/77626.79170","journal-title":"ACM Trans. Math. Softw."},{"key":"275_CR18","volume-title":"Computational Methods for Fluid Dynamics","author":"JH Ferziger","year":"2019","unstructured":"Ferziger, J.H., Peri\u0107, M., Street, R.L.: Computational Methods for Fluid Dynamics. Springer, New York (2019)"},{"issue":"1","key":"275_CR19","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1145\/2071379.2071383","volume":"8","author":"M Frigo","year":"2012","unstructured":"Frigo, M., Leiserson, C.E., Prokop, H., Ramachandran, S.: Cache-oblivious algorithms. ACM Trans. Algorithms (TALG) 8(1), 4\u20131422 (2012). https:\/\/doi.org\/10.1145\/2071379.2071383","journal-title":"ACM Trans. Algorithms (TALG)"},{"key":"275_CR20","volume-title":"Matrix Computations","author":"GH Golub","year":"2013","unstructured":"Golub, G.H., Van Loan, C.F.: Matrix Computations. JHU press, Baltimore (2013)"},{"key":"275_CR21","volume-title":"Deep Learning. Adaptive Computation and Machine Learning","author":"IJ Goodfellow","year":"2016","unstructured":"Goodfellow, I.J., Bengio, Y., Courville, A.C.: Deep Learning. Adaptive Computation and Machine Learning. MIT Press, Cambridge (2016)"},{"issue":"3","key":"275_CR22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1356052.1356053","volume":"34","author":"K Goto","year":"2008","unstructured":"Goto, K., Geijn, R.A.: Anatomy of a high-performance matrix multiplication. ACM Trans. Math. Softw. (TOMS) 34(3), 1\u201325 (2008). https:\/\/doi.org\/10.1145\/1356052.1356053","journal-title":"ACM Trans. Math. Softw. (TOMS)"},{"issue":"4","key":"275_CR23","doi-asserted-by":"publisher","first-page":"1317","DOI":"10.1137\/100788926","volume":"32","author":"L Grigori","year":"2011","unstructured":"Grigori, L., Demmel, J.W., Xiang, H.: CALU: a communication-optimal LU factorization algorithm. SIAM J. Matrix Anal. Appl. 32(4), 1317\u20131350 (2011)","journal-title":"SIAM J. Matrix Anal. Appl."},{"key":"275_CR24","doi-asserted-by":"publisher","unstructured":"Gu, Y.: Write-efficient algorithms. PhD thesis, Carnegie Mellon University, USA (2021). https:\/\/doi.org\/10.1184\/R1\/16826752.V1","DOI":"10.1184\/R1\/16826752.V1"},{"issue":"6","key":"275_CR25","doi-asserted-by":"publisher","first-page":"737","DOI":"10.1147\/RD.416.0737","volume":"41","author":"FG Gustavson","year":"1997","unstructured":"Gustavson, F.G.: Recursion leads to automatic variable blocking for dense linear-algebra algorithms. IBM J. Res. Dev. 41(6), 737\u2013756 (1997). https:\/\/doi.org\/10.1147\/RD.416.0737","journal-title":"IBM J. Res. Dev."},{"key":"275_CR26","doi-asserted-by":"crossref","unstructured":"Haidar, A., Tomov, S., Dongarra, J., Higham, N.J.: Harnessing gpu tensor cores for fast fp16 arithmetic to speed up mixed-precision iterative refinement solvers. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis (SC \u201918), pp. 1\u201312. IEEE (2018)","DOI":"10.1109\/SC.2018.00050"},{"issue":"9","key":"275_CR27","doi-asserted-by":"publisher","first-page":"1017","DOI":"10.1016\/j.jpdc.2004.03.021","volume":"64","author":"D Irony","year":"2004","unstructured":"Irony, D., Toledo, S., Tiskin, A.: Communication lower bounds for distributed-memory matrix multiplication. J. Parallel Distrib. Comput. 64(9), 1017\u20131026 (2004)","journal-title":"J. Parallel Distrib. Comput."},{"key":"275_CR28","unstructured":"Irony, D., Toledo, S.: Communication-efficient parallel dense LU using a3-dimnsional approach. In: Proceedings of the Tenth SIAM Conference on Parallel Processing for Scientific Computing, PP 2001, Portsmouth, Virginia, USA, March 12\u201314, 2001. SIAM (2001)"},{"key":"275_CR29","doi-asserted-by":"crossref","unstructured":"Jia-Wei, H., Kung, H.-T.: I\/o complexity: The red-blue pebble game. In: Proceedings of the Thirteenth Annual ACM Symposium on Theory of Computing, pp. 326\u2013333 (1981)","DOI":"10.1145\/800076.802486"},{"key":"275_CR30","doi-asserted-by":"crossref","unstructured":"Jouppi, N.P., Young, C., Patil, N., Patterson, D., Agrawal, G., Bajwa, R., Bates, S., Bhatia, S., Boden, N., Borchers, A., et al.: In-datacenter performance analysis of a tensor processing unit. In: Proceedings of the 44th Annual International Symposium on Computer Architecture, pp. 1\u201312 (2017)","DOI":"10.1145\/3079856.3080246"},{"issue":"1","key":"275_CR31","doi-asserted-by":"publisher","first-page":"405","DOI":"10.3390\/app14010405","volume":"14","author":"Q Li","year":"2024","unstructured":"Li, Q., Zuo, D., Feng, Y., Wen, D.: Research on high-performance Fourier transform algorithms based on the npu. Appl. Sci. 14(1), 405 (2024). https:\/\/doi.org\/10.3390\/app14010405","journal-title":"Appl. Sci."},{"key":"275_CR32","volume-title":"Ascend AI Processor Architecture and Programming: Principles and Applications of CANN","author":"X Liang","year":"2020","unstructured":"Liang, X.: Ascend AI Processor Architecture and Programming: Principles and Applications of CANN. Elsevier, Amsterdam (2020)"},{"key":"275_CR33","doi-asserted-by":"crossref","unstructured":"Liao, H., Tu, J., Xia, J., Liu, H., Zhou, X., Yuan, H., Hu, Y.: Ascend: a scalable and unified architecture for ubiquitous deep neural network computing: Industry track paper. In: 2021 IEEE International Symposium on High-Performance Computer Architecture (HPCA), pp. 789\u2013801. IEEE (2021)","DOI":"10.1109\/HPCA51647.2021.00071"},{"key":"275_CR34","volume-title":"Machine Learning: A Probabilistic Perspective","author":"KP Murphy","year":"2012","unstructured":"Murphy, K.P.: Machine Learning: A Probabilistic Perspective. MIT press, Cambridge (2012)"},{"key":"275_CR35","unstructured":"NVIDIA, T.: Nvidia tesla v100 gpu architecture. Santa Clara, CA, USA (2017)"},{"issue":"8","key":"275_CR36","doi-asserted-by":"publisher","first-page":"2319","DOI":"10.13328\/j.cnki.jos.006004","volume":"32","author":"C Shui","year":"2021","unstructured":"Shui, C., Yu, X., Wang, Y., Tan, G.: Optimization and analysis of HPL on domestic heterogeneous system. Ruan Jian Xue Bao \/ J. Softw. 32(8), 2319\u20132328 (2021). https:\/\/doi.org\/10.13328\/j.cnki.jos.006004","journal-title":"Ruan Jian Xue Bao \/ J. Softw."},{"issue":"8","key":"275_CR37","doi-asserted-by":"publisher","first-page":"2352","DOI":"10.13328\/j.cnki.jos.006007","volume":"32","author":"Q Sun","year":"2021","unstructured":"Sun, Q., Li, L., Zhao, H., Zhao, H., Wu, C.: Task parallel framework and its application in nested parallel algorithms on the SW26010 many-core platform. Ruan Jian Xue Bao \/ J. Softw. 32(8), 2352\u20132364 (2021). https:\/\/doi.org\/10.13328\/j.cnki.jos.006007","journal-title":"Ruan Jian Xue Bao \/ J. Softw."},{"issue":"4","key":"275_CR38","doi-asserted-by":"publisher","first-page":"1065","DOI":"10.1137\/S0895479896297744","volume":"18","author":"S Toledo","year":"1997","unstructured":"Toledo, S.: Locality of reference in lu decomposition with partial pivoting. SIAM J. Matrix Anal. Appl. 18(4), 1065\u20131081 (1997)","journal-title":"SIAM J. Matrix Anal. Appl."},{"key":"275_CR39","unstructured":"Tomov, S., Dongarra, J., Baboulin, M.: Magma: a new generation of dense linear algebra libraries for heterogeneous architectures. In: VECPAR\u201910: Proceedings of the 9th International Meeting on High Performance Computing for Computational Science, pp. 3\u201315 (2010)"},{"key":"275_CR40","unstructured":"Vasilache, N., Johnson, J., Mathieu, M., Chintala, S., Piantino, S., LeCun, Y.: Fast convolutional nets with fbfft: a gpu performance evaluation. Preprint at arXiv:1412.7580 (2014)"},{"issue":"3","key":"275_CR41","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/2764454","volume":"41","author":"FG Van Zee","year":"2015","unstructured":"Van Zee, F.G., Van De Geijn, R.A.: Blis: a framework for rapidly instantiating blas functionality. ACM Trans. Math. Softw. (TOMS) 41(3), 1\u201333 (2015)","journal-title":"ACM Trans. Math. Softw. (TOMS)"}],"container-title":["CCF Transactions on High Performance Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42514-026-00275-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s42514-026-00275-0","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42514-026-00275-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T08:14:19Z","timestamp":1781252059000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s42514-026-00275-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,21]]},"references-count":41,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,6]]}},"alternative-id":["275"],"URL":"https:\/\/doi.org\/10.1007\/s42514-026-00275-0","relation":{},"ISSN":["2524-4922","2524-4930"],"issn-type":[{"value":"2524-4922","type":"print"},{"value":"2524-4930","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,21]]},"assertion":[{"value":"2 September 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 January 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 April 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"On behalf of all authors, the corresponding author states that there is no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}