{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T05:09:39Z","timestamp":1768280979114,"version":"3.49.0"},"reference-count":16,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Comput. Arch. Lett."],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1109\/lca.2025.3646622","type":"journal-article","created":{"date-parts":[[2025,12,22]],"date-time":"2025-12-22T18:40:38Z","timestamp":1766428838000},"page":"21-24","source":"Crossref","is-referenced-by-count":0,"title":["Enabling Cost-Efficient LLM Inference on Mid-Tier GPUs With NMP DIMMs"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6748-2890","authenticated-orcid":false,"given":"Heewoo","family":"Kim","sequence":"first","affiliation":[{"name":"University of Colorado Boulder, Boulder, CO, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1697-1632","authenticated-orcid":false,"given":"Alan","family":"La","sequence":"additional","affiliation":[{"name":"University of Colorado Boulder, Boulder, CO, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1267-5024","authenticated-orcid":false,"given":"Joseph","family":"Izraelevitz","sequence":"additional","affiliation":[{"name":"University of Colorado Boulder, Boulder, CO, USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA61900.2025.00129"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00082"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3676641.3716267"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00019"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA61900.2025.00102"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3676641.3716009"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640422"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3695053.3731056"},{"key":"ref9","article-title":"NVIDIA A100 tensor core GPU","year":"2022"},{"key":"ref10","article-title":"NVIDIA A10 GPU accelerator","year":"2022"},{"key":"ref11","article-title":"NVIDIA A10","year":"2021"},{"key":"ref12","article-title":"NVIDIA ampere GA102 GPU architecture","year":"2021"},{"key":"ref13","article-title":"NVIDIA Tesla A100 80 G deep learning GPU","year":"2025"},{"key":"ref14","article-title":"NVIDIA A10 24 GB","year":"2025"},{"key":"ref15","article-title":"Flash communication: Reducing tensor parallelization bottleneck for fast large language model inference","author":"Li","year":"2024"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO61859.2024.00105"}],"container-title":["IEEE Computer Architecture Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10208\/11321093\/11309767.pdf?arnumber=11309767","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T21:59:19Z","timestamp":1768255159000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11309767\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":16,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/lca.2025.3646622","relation":{},"ISSN":["1556-6056","1556-6064","2473-2575"],"issn-type":[{"value":"1556-6056","type":"print"},{"value":"1556-6064","type":"electronic"},{"value":"2473-2575","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]}}}