{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T15:00:17Z","timestamp":1743001217254,"version":"3.40.3"},"publisher-location":"Cham","reference-count":17,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319421070"},{"type":"electronic","value":"9783319421087"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016]]},"DOI":"10.1007\/978-3-319-42108-7_1","type":"book-chapter","created":{"date-parts":[[2016,7,1]],"date-time":"2016-07-01T03:25:04Z","timestamp":1467343504000},"page":"3-18","source":"Crossref","is-referenced-by-count":3,"title":["Parallel Sparse Matrix-Vector Multiplication Using Accelerators"],"prefix":"10.1007","author":[{"given":"Hiroshi","family":"Maeda","sequence":"first","affiliation":[]},{"given":"Daisuke","family":"Takahashi","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2016,7,12]]},"reference":[{"key":"1_CR1","unstructured":"MVAPICH Benchmarks. http:\/\/mvapich.cse.ohio-state.edu\/benchmarks\/"},{"key":"1_CR2","unstructured":"Davis, T.: University of Florida Sparse Matrix Collection: sparse matrices from a wide range of applications. http:\/\/www.cise.ufl.edu\/research\/sparse\/matrices\/"},{"key":"1_CR3","unstructured":"Alexandersen, J., Lazarov, B., Dammann, B.: Parallel Sparse Matrix - Vector Product: Pure MPI and hybrid MPI-OpenMP implementation. IMM-Technical report-2012 (2012)"},{"issue":"7","key":"1_CR4","doi-asserted-by":"crossref","first-page":"673","DOI":"10.1109\/71.780863","volume":"10","author":"U Catalyurek","year":"1999","unstructured":"Catalyurek, U., Aykanat, C.: Hypergraph-partitioning-based decomposition for parallel sparse-matrix vector multiplication. IEEE Trans. Parallel Distrib. Syst. 10(7), 673\u2013693 (1999)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"issue":"15","key":"1_CR5","first-page":"1","volume":"2009","author":"A Cevahir","year":"2009","unstructured":"Cevahir, A., Nukada, A., Matsuoka, S.: CG on GPU-enhanced clusters. IPSJ SIG Tech. Rep. 2009(15), 1\u20138 (2009)","journal-title":"IPSJ SIG Tech. Rep."},{"issue":"22","key":"1_CR6","first-page":"151","volume":"2002","author":"M Kudo","year":"2002","unstructured":"Kudo, M., Kuroda, H., Katagiri, T., Kanada, Y.: The effect of optimal algorithm selection of parallel sparse matrix-vector multiplication. IPSJ SIG Tech. Rep. 2002(22), 151\u2013156 (2002). (in Japanese)","journal-title":"IPSJ SIG Tech. Rep."},{"key":"1_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"97","DOI":"10.1007\/978-3-642-38750-0_8","volume-title":"Supercomputing","author":"M Lange","year":"2013","unstructured":"Lange, M., Gorman, G., Weiland, M., Mitchell, L., Southern, J.: Achieving efficient strong scaling with PETSc using hybrid MPI\/OpenMP optimisation. In: Kunkel, J.M., Ludwig, T., Meuer, H.W. (eds.) ISC 2013. LNCS, vol. 7905, pp. 97\u2013108. Springer, Heidelberg (2013)"},{"key":"1_CR8","unstructured":"Liu, W., Vinter, B.: bhSPARSEBenchmark SpMV using CSR5. https:\/\/github.com\/bhSPARSE\/Benchmark_SpMV_using_CSR5"},{"key":"1_CR9","doi-asserted-by":"crossref","unstructured":"Liu, W., Vinter, B.: CSR5: An Efficient Storage Format for Cross-Platform Sparse Matrix-Vector Multiplication. CoRR abs\/1503.05032 (2015)","DOI":"10.1145\/2751205.2751209"},{"key":"1_CR10","doi-asserted-by":"crossref","unstructured":"Liu, X., Smelyanskiy, M., Chow, E., Dubey, P.: Efficient sparse matrix-vector multiplication on x86-based many-core processors. In: Proceedings of the 27th International ACM Conference on International Conference on Supercomputing. ICS 2013, pp. 273\u2013282. ACM (2013)","DOI":"10.1145\/2464996.2465013"},{"key":"1_CR11","doi-asserted-by":"crossref","unstructured":"Maeda, H., Takahashi, D.: Performance evaluation of sparse matrix-vector multiplication using GPU\/MIC cluster. In: 2015 Third International Symposium on Computing and Networking (CANDAR 2015). 3rd International Workshop on Computer Systems and Architectures (CSA 2015), pp. 396\u2013399 (2015)","DOI":"10.1109\/CANDAR.2015.73"},{"key":"1_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1007\/978-3-642-11515-8_10","volume-title":"High Performance Embedded Architectures and Compilers","author":"A Monakov","year":"2010","unstructured":"Monakov, A., Lokhmotov, A., Avetisyan, A.: Automatically tuning sparse matrix-vector multiplication for GPU architectures. In: Patt, Y.N., Foglia, P., Duesterwald, E., Faraboschi, P., Martorell, X. (eds.) HiPEAC 2010. LNCS, vol. 5952, pp. 111\u2013125. Springer, Heidelberg (2010)"},{"key":"1_CR13","unstructured":"Ohshima, S., Sakurai, T., Katagiri, T., Nakajima, K., Kuroda, H., Naono, K., Igai, M., Itoh, S.: Optimized implementation of segmented scan method for CUDA. IPSJ Tech. Rep. 2010-HPC-126(1), 1\u20137 (2010). (in Japanese)"},{"key":"1_CR14","doi-asserted-by":"crossref","unstructured":"Pinar, A., Heath, M.T.: Improving performance of sparse matrix-vector multiplication. In: Proceedings of the 1999 ACM\/IEEE Conference on Supercomputing. SC 1999. ACM (1999)","DOI":"10.1145\/331532.331562"},{"key":"1_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"559","DOI":"10.1007\/978-3-642-55224-3_52","volume-title":"Parallel Processing and Applied Mathematics","author":"E Saule","year":"2014","unstructured":"Saule, E., Kaya, K.: Performance evaluation of sparse matrix multiplication kernels on intel Xeon Phi. In: Wyrzykowski, R., Dongarra, J., Karczewski, K., Wa\u015bniewski, J. (eds.) Parallel Processing and Applied Mathematics. LNCS, vol. 8384, pp. 559\u2013570. Springer, Heidelberg (2014)"},{"key":"1_CR16","doi-asserted-by":"crossref","unstructured":"Tang, W.T., Tan, W.J., Ray, R., Wong, Y.W., Chen, W., Kuo, S., Goh, R.S.M., Turner, S.J., Wong, W.: Accelerating sparse matrix-vector multiplication on GPUs using bit-representation-optimized schemes. In: Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis. SC 2013, pp. 26:1\u201326:12 (2013)","DOI":"10.1145\/2503210.2503234"},{"key":"1_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1007\/978-3-319-17353-5_4","volume-title":"High Performance Computing for Computational Science \u2013 VECPAR 2014","author":"F Ye","year":"2015","unstructured":"Ye, F., Calvin, C., Petiton, S.G.: A study of SpMV implementation using MPI and OpenMP on intel many-core architecture. In: Dayd\u00e9, M., Marques, O., Nakajima, K. (eds.) VECPAR 2014. LNCS, vol. 8969, pp. 43\u201356. Springer, Heidelberg (2015)"}],"container-title":["Lecture Notes in Computer Science","Computational Science and Its Applications \u2013 ICCSA 2016"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-42108-7_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,10]],"date-time":"2019-09-10T10:02:32Z","timestamp":1568109752000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-42108-7_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319421070","9783319421087"],"references-count":17,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-42108-7_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2016]]}}}