{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T07:18:39Z","timestamp":1775200719097,"version":"3.50.1"},"reference-count":5,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,17]],"date-time":"2025-12-17T00:00:00Z","timestamp":1765929600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,17]],"date-time":"2025-12-17T00:00:00Z","timestamp":1765929600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100006180","name":"Technology Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006180","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,17]]},"DOI":"10.1109\/hipcw66559.2025.00103","type":"proceedings-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T19:48:12Z","timestamp":1775159292000},"page":"297-298","source":"Crossref","is-referenced-by-count":0,"title":["Optimizing BLAS GEMM Kernel Performance: Scalable Multi-Core and Vectorized Design"],"prefix":"10.1109","author":[{"given":"Ragesh","family":"Hajela","sequence":"first","affiliation":[{"name":"Fujitsu Research of India,Bangalore,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Masato","family":"Nakagawa","sequence":"additional","affiliation":[{"name":"Fujitsu Limited,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Atsushi","family":"Nukariya","sequence":"additional","affiliation":[{"name":"Fujitsu Research of India,Bangalore,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kuninori","family":"Ishii","sequence":"additional","affiliation":[{"name":"Fujitsu Limited,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Masahiro","family":"Doteguchi","sequence":"additional","affiliation":[{"name":"Fujitsu Research of India,Bangalore,India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ikuo","family":"Miyoshi","sequence":"additional","affiliation":[{"name":"Fujitsu Limited,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Priyanka","family":"Sharma","sequence":"additional","affiliation":[{"name":"Fujitsu Research of India,Bangalore,India"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Improving Load Imbalance in Thread-Parallel GEMM","author":"Nakagawa"},{"key":"ref2","volume-title":"Multi-thread Performance Improvement of GEMM on NeoverseV1 with DIVIDE_RATE=1","author":"Nakagawa"},{"key":"ref3","volume-title":"Small gemm kernel improvements for AArch64","author":"Goplani"},{"key":"ref4","volume-title":"Small GEMM improvements for AArch64 with SVE","author":"Goplani"},{"key":"ref5","volume-title":"Small GEMM improvements for AArch64 with SVE","author":"Sidebottom"}],"event":{"name":"2025 IEEE 32nd International Conference on High Performance Computing, Data and Analytics Workshop (HiPCW)","location":"Hyderabad, India","start":{"date-parts":[[2025,12,17]]},"end":{"date-parts":[[2025,12,20]]}},"container-title":["2025 IEEE 32nd International Conference on High Performance Computing, Data and Analytics Workshop (HiPCW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11459184\/11459197\/11459331.pdf?arnumber=11459331","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T05:03:46Z","timestamp":1775192626000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11459331\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,17]]},"references-count":5,"URL":"https:\/\/doi.org\/10.1109\/hipcw66559.2025.00103","relation":{},"subject":[],"published":{"date-parts":[[2025,12,17]]}}}