{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T03:40:11Z","timestamp":1742960411746,"version":"3.40.3"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031695766"},{"type":"electronic","value":"9783031695773"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024]]},"DOI":"10.1007\/978-3-031-69577-3_3","type":"book-chapter","created":{"date-parts":[[2024,8,25]],"date-time":"2024-08-25T19:02:05Z","timestamp":1724612525000},"page":"33-46","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["ESIMD GPU Implementations of\u00a0Deep Learning Sparse Matrix Kernels"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5449-1779","authenticated-orcid":false,"given":"Mohammad","family":"Zubair","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0096-2321","authenticated-orcid":false,"given":"Christoph","family":"Bauinger","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,8,26]]},"reference":[{"key":"3_CR1","unstructured":"ESIMD Implementation of Deep Learning Sparse Matrix Kernels. https:\/\/github.com\/zubair23517\/dlspm-esimd. Accessed 20 Mar 2024"},{"key":"3_CR2","unstructured":"Anderson, E., et al.: LAPACK Users\u2019 Guide. Society for Industrial and Applied Mathematics, Philadelphia, 3rd edn (1999)"},{"key":"3_CR3","doi-asserted-by":"publisher","unstructured":"Bharadwaj, V., Buluc, A., Demmel, J.: Distributed-memory sparse kernels for machine learning. In: 2022 IEEE IPDPS, pp. 47\u201358. IEEE Computer Society, Los Alamitos (2022). https:\/\/doi.org\/10.1109\/IPDPS53621.2022.00014","DOI":"10.1109\/IPDPS53621.2022.00014"},{"key":"3_CR4","unstructured":"Gale, T., Elsen, E., Hooker, S.: The state of sparsity in deep neural networks. arXiv preprint arXiv:1902.09574 (2019)"},{"key":"3_CR5","unstructured":"Gale, T., Narayanan, D., Young, C., Zaharia, M.: Megablocks: efficient sparse training with mixture-of-experts (2022)"},{"key":"3_CR6","unstructured":"Gale, T., Zaharia, M., Young, C., Elsen, E.: RN50 Data Set (2020). https:\/\/storage.googleapis.com\/sgk-sc2020\/dlmc.tar.gz. Accessed 22 Nov 2023"},{"key":"3_CR7","doi-asserted-by":"crossref","unstructured":"Gale, T., Zaharia, M., Young, C., Elsen, E.: Sparse GPU Kernels for deep learning. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis (SC 2020). IEEE Press (2020)","DOI":"10.1109\/SC41405.2020.00021"},{"key":"3_CR8","doi-asserted-by":"publisher","unstructured":"Hong, C., Sukumaran-Rajam, A., Nisa, I., Singh, K., Sadayappan, P.: Adaptive sparse tiling for sparse matrix multiplication. In: Proceedings of the 24th Symposium on Principles and Practice of Parallel Programming (PPoPP 2019), pp. 300\u2013314. Association for Computing Machinery, New York (2019). https:\/\/doi.org\/10.1145\/3293883.3295712","DOI":"10.1145\/3293883.3295712"},{"key":"3_CR9","doi-asserted-by":"crossref","unstructured":"Hu, Y., et al.: Featgraph: a flexible and efficient backend for graph neural network systems. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis (SC 2020). IEEE Press (2020)","DOI":"10.1109\/SC41405.2020.00075"},{"key":"3_CR10","unstructured":"Intel Corporation: Intel Advisor GPU Roofline. https:\/\/www.intel.com\/content\/www\/us\/en\/docs\/advisor\/user-guide\/2023-2\/analyze-gpu-roofline.html. Accessed 30 Oct 2023"},{"key":"3_CR11","unstructured":"Intel Corporation: Intel oneAPI. https:\/\/www.intel.com\/content\/www\/us\/en\/developer\/tools\/oneapi\/toolkits.html. Accessed 22 Nov 2023"},{"key":"3_CR12","unstructured":"Intel Corporation: Intel Thread Mapping. https:\/\/www.intel.com\/content\/www\/us\/en\/docs\/oneapi\/optimization-guide-gpu\/2023-2\/thread-mapping-and-gpu-occupancy.html. Accessed 30 Oct 2023"},{"key":"3_CR13","unstructured":"Intel Corporation: DPC++ Explicit SIMD API (2023). https:\/\/intel.github.io\/llvm-docs\/doxygen\/index.html. Accessed 25 May 2023"},{"key":"3_CR14","unstructured":"Intel Corporation: Explicit SIMD SYCL Extension (2023). https:\/\/www.intel.com\/content\/www\/us\/en\/docs\/dpcpp-cpp-compiler\/developer-guide-reference\/2023-1\/explicit-simd-sycl-extension.html. Accessed 25 May 2023"},{"key":"3_CR15","unstructured":"Intel Corporation: Intel Data Center GPU Max 1550 (2023). https:\/\/www.intel.com\/content\/www\/us\/en\/products\/sku\/232873\/intel-data-center-gpu-max-1550\/specifications.html. Accessed 14 July 2023"},{"key":"3_CR16","unstructured":"Intel Corporation: Intel Xe GPU Architecture (2023). https:\/\/www.intel.com\/content\/www\/us\/en\/docs\/oneapi\/optimization-guide-gpu\/2023-1\/intel-xe-gpu-architecture.html. Accessed 17 July 2023"},{"key":"3_CR17","unstructured":"Intel Corporation: oneMKL blas::gemm (2023). https:\/\/www.intel.com\/content\/www\/us\/en\/docs\/onemkl\/developer-reference-dpcpp\/2024-0\/gemm.html. Accessed 22 Nov 2023"},{"key":"3_CR18","unstructured":"Intel Corporation: oneMKL sparse::gemm (2023). https:\/\/www.intel.com\/content\/www\/us\/en\/docs\/onemkl\/developer-reference-dpcpp\/2024-0\/oneapi-mkl-sparse-gemm.html. Accessed 22 Nov 2023"},{"key":"3_CR19","unstructured":"Intel Corporation: Tensorflow on GPUs (2023). https:\/\/github.com\/intel\/intel-extension-for-tensorflow. Accessed 27 Oct 2023"},{"key":"3_CR20","unstructured":"Khronos Group: SYCL (2020). https:\/\/www.khronos.org\/sycl\/. Accessed 24 Aug 2020"},{"key":"3_CR21","unstructured":"NVIDIA Corporation: CUDA C Programming Guide. http:\/\/docs.nvidia.com\/cuda\/cuda-c-programming-guide\/#axzz4Hicq83a9. Accessed 14 July 2023"},{"key":"3_CR22","unstructured":"NVIDIA Corporation: cuSPARSE. https:\/\/developer.nvidia.com\/cusparse. Accessed 24 Aug 2020"},{"key":"3_CR23","unstructured":"NVIDIA Corporation: Tensor Cores (2023). https:\/\/www.nvidia.com\/en-us\/data-center\/tensor-cores\/. Accessed 23 Nov 2023"},{"key":"3_CR24","unstructured":"PyTorch Project a Series of LF Projects, LLC: PyTorch on GPUs (2023). https:\/\/pytorch.org\/docs\/stable\/notes\/cuda.html. Accessed 27 Oct 2023"},{"key":"3_CR25","doi-asserted-by":"publisher","unstructured":"Rahman, M.K., Sujon, M.H., Azad, A.: Fusedmm: a unified sddmm-spmm kernel for graph embedding and graph neural networks. In: 2021 IEEE IPDPS, pp. 256\u2013266 (2021). https:\/\/doi.org\/10.1109\/IPDPS49936.2021.00034","DOI":"10.1109\/IPDPS49936.2021.00034"},{"key":"3_CR26","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898718003","volume-title":"Iterative Methods for Sparse Linear Systems","author":"Y Saad","year":"2003","unstructured":"Saad, Y.: Iterative Methods for Sparse Linear Systems, 2nd edn. Society for Industrial and Applied Mathematics, Philadelphia (2003)","edition":"2"},{"key":"3_CR27","unstructured":"Volkov, V.: Understanding Latency Hiding on GPUs. Ph.D. thesis, EECS Department, University of California, Berkeley (2016). http:\/\/www2.eecs.berkeley.edu\/Pubs\/TechRpts\/2016\/EECS-2016-143.html"},{"key":"3_CR28","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"672","DOI":"10.1007\/978-3-319-96983-1_48","volume-title":"Euro-Par 2018: Parallel Processing","author":"C Yang","year":"2018","unstructured":"Yang, C., Bulu\u00e7, A., Owens, J.D.: Design principles for sparse matrix multiplication on the GPU. In: Aldinucci, M., Padovani, L., Torquati, M. (eds.) Euro-Par 2018. LNCS, vol. 11014, pp. 672\u2013687. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-319-96983-1_48"}],"container-title":["Lecture Notes in Computer Science","Euro-Par 2024: Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-69577-3_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,25]],"date-time":"2024-08-25T19:05:39Z","timestamp":1724612739000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-69577-3_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031695766","9783031695773"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-69577-3_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"26 August 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"Euro-Par","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Parallel Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Madrid","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Spain","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 August 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 August 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"europar2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2024.euro-par.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}