{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T17:04:21Z","timestamp":1774631061754,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":26,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819615414","type":"print"},{"value":"9789819615421","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-981-96-1542-1_16","type":"book-chapter","created":{"date-parts":[[2025,2,14]],"date-time":"2025-02-14T17:17:03Z","timestamp":1739553423000},"page":"263-282","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["MSA2: An Efficient Sparsity-Aware Accelerator for\u00a0Matrix Multiplication with\u00a0Multi-core Systolic Arrays"],"prefix":"10.1007","author":[{"given":"Minjin","family":"Tang","sequence":"first","affiliation":[]},{"given":"Mei","family":"Wen","sequence":"additional","affiliation":[]},{"given":"Junzhong","family":"Shen","sequence":"additional","affiliation":[]},{"given":"Jingkui","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Zeyu","family":"Xue","sequence":"additional","affiliation":[]},{"given":"Zili","family":"Shao","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,2,15]]},"reference":[{"key":"16_CR1","unstructured":"Powering the edge: Driving optimal performance with the ethos-N77 NPU (2019)"},{"key":"16_CR2","unstructured":"Intel architecture instruction set extensions programming reference (2020)"},{"key":"16_CR3","unstructured":"Intel\u00ae 64 and IA-32 architectures software developer manuals (2020)"},{"key":"16_CR4","unstructured":"NVIDIA H100 tensor core GPU architecture (2022). https:\/\/resources.nvidia.com\/en-us-tensor-core"},{"key":"16_CR5","doi-asserted-by":"crossref","unstructured":"Asgari, B., Hadidi, R., Kim, H.: MEISSA: multiplying matrices efficiently in a scalable systolic architecture. In: ICCD. IEEE (2020)","DOI":"10.1109\/ICCD50377.2020.00036"},{"key":"16_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Z., Qu, Z., Liu, L., Ding, Y., Xie, Y.: Efficient tensor core-based GPU kernels for structured sparsity under reduced precision. In: SC, p.\u00a078. ACM (2021)","DOI":"10.1145\/3458817.3476182"},{"key":"16_CR7","doi-asserted-by":"crossref","unstructured":"Davis, T.A., Hu, Y.: The university of Florida sparse matrix collection. ACM Trans. Math. Softw. 38(1), 1:1\u20131:25 (2011)","DOI":"10.1145\/2049662.2049663"},{"key":"16_CR8","doi-asserted-by":"crossref","unstructured":"Gale, T., Zaharia, M., Young, C., Elsen, E.: Sparse GPU kernels for deep learning. In: SC, p.\u00a017. IEEE\/ACM (2020)","DOI":"10.1109\/SC41405.2020.00021"},{"key":"16_CR9","unstructured":"Google Research: Deep Learning Matrix Collection (n.d.). https:\/\/github.com\/google-research\/google-research\/tree\/master\/sgk"},{"key":"16_CR10","doi-asserted-by":"crossref","unstructured":"Guo, C., et al.: Balancing efficiency and flexibility for DNN acceleration via temporal GPU-systolic array integration. In: DAC, pp.\u00a01\u20136. IEEE (2020)","DOI":"10.1109\/DAC18072.2020.9218732"},{"key":"16_CR11","doi-asserted-by":"crossref","unstructured":"Jeong, G., et al.: VEGETA: vertically-integrated extensions for sparse\/dense GEMM tile acceleration on CPUs, pp. 259\u2013272 (2023)","DOI":"10.1109\/HPCA56546.2023.10071058"},{"key":"16_CR12","doi-asserted-by":"crossref","unstructured":"Jeong, G., et al.: RASA: efficient register-aware systolic array matrix engine for CPU, pp. 253\u2013258 (2021)","DOI":"10.1109\/DAC18074.2021.9586257"},{"key":"16_CR13","unstructured":"Jouppi, N.P., Young, C., et\u00a0al.: In-datacenter performance analysis of a tensor processing unit. In: Proceedings of the 44th ISCA, ACM (2017)"},{"key":"16_CR14","doi-asserted-by":"crossref","unstructured":"Kabir, H., Booth, J.D., Raghavan, P.: A multilevel compressed sparse row format for efficient sparse computations on multicore processors. In: 2014 21st International Conference on High Performance Computing (HiPC), pp. 1\u201310. IEEE (2014)","DOI":"10.1109\/HiPC.2014.7116882"},{"issue":"1","key":"16_CR15","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1177\/1094342015597082","volume":"31","author":"S Kirmani","year":"2017","unstructured":"Kirmani, S., Park, J., Raghavan, P.: An embedded sectioning scheme for multiprocessor topology-aware mapping of irregular applications. Int. J. High Perform. Comput. Appl. 31(1), 91\u2013103 (2017)","journal-title":"Int. J. High Perform. Comput. Appl."},{"key":"16_CR16","doi-asserted-by":"crossref","unstructured":"Kirmani, S., Raghavan, P.: Scalable parallel graph partitioning. In: Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis, pp. 1\u201310 (2013)","DOI":"10.1145\/2503210.2503280"},{"key":"16_CR17","doi-asserted-by":"crossref","unstructured":"Kung, H.T., McDanel, B., Zhang, S.Q.: Packing sparse convolutional neural networks for efficient systolic array implementations: column combining under joint optimization. In: ASPLOS. ACM (2019)","DOI":"10.1145\/3297858.3304028"},{"key":"16_CR18","doi-asserted-by":"crossref","unstructured":"Kung, H.T., McDanel, B., Zhang, S.Q., Dong, X., Chen, C.: Maestro: a memory-on-logic architecture for coordinated parallel use of many systolic arrays, pp. 42\u201350 (2019)","DOI":"10.1109\/ASAP.2019.00-31"},{"key":"16_CR19","doi-asserted-by":"crossref","unstructured":"Mishra, A., Kirmani, S., Madduri, K.: Fast spectral graph layout on multicore platforms. In: Proceedings of the 49th International Conference on Parallel Processing, pp. 1\u201311 (2020)","DOI":"10.1145\/3404397.3404471"},{"key":"16_CR20","doi-asserted-by":"crossref","unstructured":"Parashar, A., et al.: SCNN: an accelerator for compressed-sparse convolutional neural networks. In: ISCA, pp. 27\u201340. ACM (2017)","DOI":"10.1145\/3140659.3080254"},{"key":"16_CR21","doi-asserted-by":"crossref","unstructured":"Peltekis, C., Filippas, D., Dimitrakopoulos, G., Nicopoulos, C., Pnevmatikatos, D.N.: ArrayFlex: a systolic array architecture with configurable transparent pipelining. In: DATE. IEEE (2023)","DOI":"10.23919\/DATE56975.2023.10136913"},{"key":"16_CR22","doi-asserted-by":"crossref","unstructured":"Qin, E., et al.: SIGMA: a sparse and irregular GEMM accelerator with flexible interconnects for DNN training. In: HPCA, pp. 58\u201370. IEEE (2020)","DOI":"10.1109\/HPCA47549.2020.00015"},{"key":"16_CR23","doi-asserted-by":"crossref","unstructured":"Starke, W.J., Thompto, B.W., Stuecheli, J.A., Moreira, J.E.: IBM\u2019s power10 processor. IEEE Micro (2021)","DOI":"10.1109\/MM.2021.3058632"},{"key":"16_CR24","doi-asserted-by":"crossref","unstructured":"Sui, B., Shen, J., Sun, C., Wang, J., Zheng, Z., Guo, W.: MACO: exploring GEMM acceleration on a loosely-coupled multi-core processor. In: Design, Automation and Test in Europe Conference (DATE) (2024)","DOI":"10.23919\/DATE58400.2024.10546765"},{"key":"16_CR25","doi-asserted-by":"crossref","unstructured":"Tang, M., et al.: Mentha: Enabling sparse-packing computation on systolic arrays, pp. 18:1\u201318:11 (2022)","DOI":"10.1145\/3545008.3545053"},{"key":"16_CR26","doi-asserted-by":"crossref","unstructured":"Y\u00fcz\u00fcg\u00fcler, A.C., S\u00f6nmez, C., Drumond, M., Oh, Y., Falsafi, B., Frossard, P.: Scale-out systolic arrays. ACM Trans. Archit. Code Optim. 20(2), 27:1\u201327:25 (2023)","DOI":"10.1145\/3572917"}],"container-title":["Lecture Notes in Computer Science","Algorithms and Architectures for Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-1542-1_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,14]],"date-time":"2025-02-14T17:17:16Z","timestamp":1739553436000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-1542-1_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819615414","9789819615421"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-1542-1_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"15 February 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICA3PP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Algorithms and Architectures for Parallel Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Macau","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"30 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 November 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ica3pp2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ica3pp2024.scimeeting.cn\/en\/web\/index\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}