{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T15:48:50Z","timestamp":1759333730302,"version":"build-2065373602"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783032067500"},{"type":"electronic","value":"9783032067517"}],"license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-06751-7_12","type":"book-chapter","created":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T04:29:04Z","timestamp":1759206544000},"page":"169-184","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A New Cross-Product Instruction for RISC-V CPUs"],"prefix":"10.1007","author":[{"given":"Valentin","family":"Volokitin","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Evgeny","family":"Kozinov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Valentin","family":"Petrov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Iosif","family":"Meyerov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,10,1]]},"reference":[{"issue":"2","key":"12_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2024716.2024718","volume":"39","author":"N Binkert","year":"2011","unstructured":"Binkert, N., et al.: The gem5 simulator. Sigarch Comput. Archit. News 39(2), 1\u20137 (2011). https:\/\/doi.org\/10.1145\/2024716.2024718","journal-title":"Sigarch Comput. Archit. News"},{"key":"12_CR2","doi-asserted-by":"publisher","unstructured":"Ram\u00edrez, C., et al.: A RISC-V simulator and benchmark suite for designing and evaluating vector architectures. ACM Trans. Archit. Code Optim. 17(4) (2020). https:\/\/doi.org\/10.1145\/3422667","DOI":"10.1145\/3422667"},{"key":"12_CR3","unstructured":"Chatzopoulos, O., et al.: Towards accurate performance modeling of RISC-V designs (2021). https:\/\/arxiv.org\/abs\/2106.09991"},{"issue":"4","key":"12_CR4","doi-asserted-by":"publisher","first-page":"807","DOI":"10.1007\/s11390-023-1266-6","volume":"38","author":"RS Li","year":"2023","unstructured":"Li, R.S., Peng, P., Shao, Z.Y., Jin, H., Zheng, R.: Evaluating RISC-V Vector Instruction Set Architecture Extension with Computer Vision Workloads. J. Comput. Sci. Technol. 38(4), 807\u2013820 (2023). https:\/\/doi.org\/10.1007\/s11390-023-1266-6","journal-title":"J. Comput. Sci. Technol."},{"key":"12_CR5","doi-asserted-by":"publisher","unstructured":"Sahaya Loui, M., et al.: Towards Deep Learning using TensorFlow Lite on RISC-V (2019). https:\/\/doi.org\/10.13140\/RG.2.2.30400.89606","DOI":"10.13140\/RG.2.2.30400.89606"},{"key":"12_CR6","unstructured":"Ta, T., Cheng, L., Batten, C.: Simulating Multi-Core RISC-V Systems in gem5: 2nd Workshop on Computer Architecture Research with RISC-V (CARRV-2) (2018)"},{"issue":"1","key":"12_CR7","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1007\/s11227-024-06530-x","volume":"81","author":"MS Yu","year":"2024","unstructured":"Yu, M.S., et al.: Optimizing computer vision algorithms with TVM on VLIW architecture based on RVV. J. Supercomput. 81(1), 172 (2024). https:\/\/doi.org\/10.1007\/s11227-024-06530-x","journal-title":"J. Supercomput."},{"key":"12_CR8","doi-asserted-by":"publisher","unstructured":"Nassyr, S., Pleiter, D.: Exploring Processor Micro-architectures Optimised for BLAS3 Micro-kernels. In: Carretero, J., et al. (eds.) Euro-Par 2024: Parallel Processing, pp. 47\u201361. Springer Nature Switzerland, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-69766-1_4","DOI":"10.1007\/978-3-031-69766-1_4"},{"issue":"5","key":"12_CR9","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1109\/MM.2022.3184867","volume":"42","author":"N Adit","year":"2022","unstructured":"Adit, N., Sampson, A.: Performance Left on the Table: An Evaluation of Compiler Autovectorization for RISC-V. IEEE Micro 42(5), 41\u201348 (2022). https:\/\/doi.org\/10.1109\/MM.2022.3184867","journal-title":"IEEE Micro"},{"key":"12_CR10","doi-asserted-by":"publisher","unstructured":"Zhao, Y., et al.: Enhancing RISC-V Vector Extension for Efficient Application of Post-Quantum Cryptography. In: IEEE 34th Int. Conf. on Application-Specific Systems, Architectures and Processors, pp. 10\u201317 (2023). https:\/\/doi.org\/10.1109\/ASAP57973.2023.00014","DOI":"10.1109\/ASAP57973.2023.00014"},{"key":"12_CR11","doi-asserted-by":"publisher","unstructured":"Kuang, H., Zhao, Y., Sun, Y., Han, J.: General Vector Instruction Extension for GF(2m) Polynomial Operation in Post-quantum Cryptography. In: IEEE 15th Int. Conf. on ASIC (ASICON), pp. 1\u20134 (2023). https:\/\/doi.org\/10.1109\/ASICON58565.2023.10396597","DOI":"10.1109\/ASICON58565.2023.10396597"},{"key":"12_CR12","doi-asserted-by":"publisher","unstructured":"Gupta, S.R., et al.: Co-Design of Convolutional Algorithms and Long Vector RISC-V Processors for Efficient CNN Model Serving. In: Proc. of the 53rd Int. Conf. on Parallel Processing, pp. 73\u201383. ACM, NY, USA (2024). https:\/\/doi.org\/10.1145\/3673038.3673121","DOI":"10.1145\/3673038.3673121"},{"key":"12_CR13","doi-asserted-by":"publisher","unstructured":"Wang, J., Wang, L., Wang, P.: Optimisation of x264 encoder acceleration based on RISC-V vector instructions. In: 3rd Int. Symp. on Computer Technology and Information Science, pp. 1128\u20131133 (2023). https:\/\/doi.org\/10.1109\/ISCTIS58954.2023.10213200","DOI":"10.1109\/ISCTIS58954.2023.10213200"},{"key":"12_CR14","doi-asserted-by":"publisher","unstructured":"Domingos, J.M., et al.: Unlimited Vector Extension with Data Streaming Support. In: 2021 ACM\/IEEE 48th Annual International Symposium on Computer Architecture (ISCA), pp. 209\u2013222 (2021). https:\/\/doi.org\/10.1109\/ISCA52012.2021.00025","DOI":"10.1109\/ISCA52012.2021.00025"},{"key":"12_CR15","unstructured":"Katebi, H., Asadi, N., Goudarzi, M.: FullPack: Full Vector Utilization for Sub-Byte Quantized Inference on General Purpose CPUs (2022). https:\/\/arxiv.org\/abs\/2211.06982"},{"key":"12_CR16","doi-asserted-by":"publisher","DOI":"10.1145\/3716873","author":"K Yang","year":"2025","unstructured":"Yang, K., Mart\u00ednez, J.F.: VersaTile: flexible tiled architectures via associative processors. ACM Trans. Archit. Code Optim. (2025). https:\/\/doi.org\/10.1145\/3716873","journal-title":"ACM Trans. Archit. Code Optim."},{"key":"12_CR17","doi-asserted-by":"publisher","unstructured":"Pu, Z., et al.: ChameSC: Virtualizing Superscalar Core of a SIMD Architecture for Vector Memory Access. In: 2024 IEEE 42nd International Conference on Computer Design (ICCD), pp. 52\u201359 (2024). https:\/\/doi.org\/10.1109\/ICCD63220.2024.00019","DOI":"10.1109\/ICCD63220.2024.00019"},{"key":"12_CR18","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysarc.2024.103236","volume":"154","author":"N Murthy","year":"2024","unstructured":"Murthy, N., Catthoor, F., Verhelst, M.: Optimization of block-scaled integer GeMMs for efficient DNN deployment on scalable in-order vector processors. J. Syst. Architect. 154, 103236 (2024). https:\/\/doi.org\/10.1016\/j.sysarc.2024.103236","journal-title":"J. Syst. Architect."},{"key":"12_CR19","doi-asserted-by":"publisher","unstructured":"Roelke, A., Stan, M.R.: Co-Optimizing CPUs and Accelerators in Constrained Systems. In: 2018 31st IEEE International System-on-Chip Conference (SOCC), pp. 254\u2013259 (2018). https:\/\/doi.org\/10.1109\/SOCC.2018.8618516","DOI":"10.1109\/SOCC.2018.8618516"},{"key":"12_CR20","doi-asserted-by":"publisher","unstructured":"Leiserson, C., et al.: There\u2019s plenty of room at the Top: What will drive computer performance after Moore\u2019s law? Science 368, eaam9744 (2020). https:\/\/doi.org\/10.1126\/science.aam9744","DOI":"10.1126\/science.aam9744"},{"key":"12_CR21","doi-asserted-by":"publisher","unstructured":"De Michell, G., Gupta, R.: Hardware\/software co-design. In: Proceedings of the IEEE 85(3), 30\u201344 (1997). https:\/\/doi.org\/10.1109\/5.558708","DOI":"10.1109\/5.558708"},{"issue":"7","key":"12_CR22","doi-asserted-by":"publisher","first-page":"2965","DOI":"10.1134\/S1995080224603680","volume":"45","author":"AS Antonov","year":"2024","unstructured":"Antonov, A.S., et al.: An Approach to Solving the Problem of Supercomputer Co-design. Lobachevskii Journal of Mathematics 45(7), 2965\u20132973 (2024). https:\/\/doi.org\/10.1134\/S1995080224603680","journal-title":"Lobachevskii Journal of Mathematics"},{"issue":"2","key":"12_CR23","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1109\/MM.2021.3136882","volume":"42","author":"M Sato","year":"2022","unstructured":"Sato, M., et al.: Co-Design and System for the Supercomputer \u201cFugaku.\u201d IEEE Micro 42(2), 26\u201334 (2022). https:\/\/doi.org\/10.1109\/MM.2021.3136882","journal-title":"IEEE Micro"},{"key":"12_CR24","doi-asserted-by":"publisher","unstructured":"Rodrigues, A., Sousa, L., Ilic, A.: A Performance Modelling-Driven Approach to Hardware Resource Scaling, pp. 143\u2013154. Springer-Verlag, Berlin, Heidelberg (2023). https:\/\/doi.org\/10.1007\/978-3-031-48803-0_15","DOI":"10.1007\/978-3-031-48803-0_15"},{"key":"12_CR25","doi-asserted-by":"crossref","unstructured":"Brown, N., Maurice, J.: Performance characterisation of the 64-core SG2042 RISC-V CPU for HPC. International Conference on HPC. Springer, Cham (2025)","DOI":"10.1007\/978-3-031-73716-9_25"},{"key":"12_CR26","unstructured":"Gem5 bootcamp 2022: Instruction execution and adding instructions: https:\/\/github.com\/gem5bootcamp\/gem5-bootcamp-env\/blob\/main\/assets\/slides\/develop-06-cpu-instructions.pdf. Last accessed 03 May 2025"},{"key":"12_CR27","unstructured":"RISC-V GNU Compiler Toolchain: https:\/\/github.com\/riscv-collab\/riscv-gnu-toolchain. Last accessed 03 May 2025"},{"key":"12_CR28","unstructured":"RVV Cross-Product extension: https:\/\/github.com\/UNN-ITMM-Software\/RVV-cross-ext"},{"key":"12_CR29","doi-asserted-by":"publisher","unstructured":"Somogyi, S., et al.: Spatial Memory Streaming. In: 33rd International Symposium on Computer Architecture (ISCA\u201906), pp. 252\u2013263 (2006). https:\/\/doi.org\/10.1109\/ISCA.2006.38","DOI":"10.1109\/ISCA.2006.38"},{"key":"12_CR30","unstructured":"Boris, J.P., Shanny, R., (eds.) Proceedings, Fourth Conference on Numerical Simulation of Plasmas. Naval Research Laboratory (1971)"},{"key":"12_CR31","unstructured":"Konata: https:\/\/github.com\/shioyadan\/Konata. Last accessed 03 May 2025"}],"container-title":["Lecture Notes in Computer Science","Parallel Computing Technologies"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-06751-7_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T04:29:07Z","timestamp":1759206547000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-06751-7_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,1]]},"ISBN":["9783032067500","9783032067517"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-06751-7_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025,10,1]]},"assertion":[{"value":"1 October 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PaCT","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Parallel Computing Technologies","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Almaty","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kazakhstan","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 October 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pact2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ssd.sscc.ru\/conference\/pact2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}