{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T16:53:16Z","timestamp":1783183996718,"version":"3.54.6"},"reference-count":20,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Computer"],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1109\/mc.2026.3652916","type":"journal-article","created":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T19:53:16Z","timestamp":1777665196000},"page":"55-64","source":"Crossref","is-referenced-by-count":3,"title":["Challenges and Research Directions for Large Language Model Inference Hardware"],"prefix":"10.1109","volume":"59","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-8066-6044","authenticated-orcid":false,"given":"Xiaoyu","family":"Ma","sequence":"first","affiliation":[{"name":"Google DeepMind, Mountain View, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0429-1015","authenticated-orcid":false,"given":"David","family":"Patterson","sequence":"additional","affiliation":[{"name":"Google DeepMind, Mountain View, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"AI inference chip market insights","year":"2025"},{"key":"ref2","article-title":"OpenAI sees roughly ${\\$}$$5 billion loss this year on ${\\$}$$3.7 billion in revenue","author":"Field","year":"2024","journal-title":"CNBC"},{"key":"ref3","article-title":"Microsoft is losing a staggering amount of money on AI","author":"Tangermann","year":"2024","journal-title":"Futurism"},{"key":"ref4","article-title":"A survey on efficient inference for large language models","author":"Zhou","year":"2024"},{"key":"ref5","volume-title":"Global semiconductors","author":"Lee","year":"2024"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3637867"},{"key":"ref7","article-title":"SanDisks new high bandwidth flash memory enables 4TB of VRAM on GPUs, matches HBM bandwidth at higher capacity","author":"Shilov","year":"2025","journal-title":"Toms Hardware"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/2.612252"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/hcs52781.2021.9567191"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/hcs55958.2022.9895629"},{"key":"ref11","article-title":"Benchmarking a new paradigm: An experimental analysis of a real processing-in-memory architecture","author":"Gmez-Luna","year":"2021"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO61859.2024.00105"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3460971"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/isscc42615.2023.10067810"},{"key":"ref15","volume-title":"Structera A 2504 memory-expansion controller","year":"2024"},{"key":"ref16","article-title":"Managed-retention memory: A new class of memory for the AI era","author":"Legtchenko","year":"2025"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/hpca61900.2025.00128"},{"key":"ref18","volume-title":"Tutorial on memory-centric computing: Processing-near-memory","author":"Oliveira","year":"2024"},{"key":"ref19","article-title":"Advancing performance with NVIDIA SHARP in-network computing","author":"Schultz","year":"2024","journal-title":"NVIDIA"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3544216.3544262"}],"container-title":["Computer"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/2\/11503331\/11503334.pdf?arnumber=11503334","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T19:35:31Z","timestamp":1777923331000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11503334\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":20,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/mc.2026.3652916","relation":{},"ISSN":["0018-9162","1558-0814"],"issn-type":[{"value":"0018-9162","type":"print"},{"value":"1558-0814","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5]]}}}