{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T11:37:40Z","timestamp":1777635460625,"version":"3.51.4"},"reference-count":15,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T00:00:00Z","timestamp":1719792000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Institute of Information & communications Technology Planning & Evaluation"},{"name":"Korea government","award":["2022-0-01037"],"award-info":[{"award-number":["2022-0-01037"]}]},{"name":"DRAM","award":["RS-2024-00395134"],"award-info":[{"award-number":["RS-2024-00395134"]}]},{"name":"DPU-Centric Datacenter Architecture for Next-Generation AI Devices","award":["RS-2024-00402898"],"award-info":[{"award-number":["RS-2024-00402898"]}]},{"name":"Simulation-based High-speed\/High-Accuracy Data Center Workload\/System Analysis Platform"},{"DOI":"10.13039\/100014553","name":"Samsung Advanced Institute of Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100014553","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100004358","name":"Samsung","doi-asserted-by":"publisher","award":["IO201210-07974-01"],"award-info":[{"award-number":["IO201210-07974-01"]}],"id":[{"id":"10.13039\/100004358","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003836","name":"IC Design Education Center","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003836","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Comput. Arch. Lett."],"published-print":{"date-parts":[[2024,7]]},"DOI":"10.1109\/lca.2024.3422492","type":"journal-article","created":{"date-parts":[[2024,7,3]],"date-time":"2024-07-03T17:27:49Z","timestamp":1720027669000},"page":"154-157","source":"Crossref","is-referenced-by-count":4,"title":["A Quantitative Analysis of State Space Model-Based Large Language Model: Study of Hungry Hungry Hippos"],"prefix":"10.1109","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3938-2099","authenticated-orcid":false,"given":"Dongho","family":"Yoon","sequence":"first","affiliation":[{"name":"Korea Advanced Institute of Science & Technology, Daejeon, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9678-6228","authenticated-orcid":false,"given":"Taehun","family":"Kim","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science & Technology, Daejeon, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4266-4919","authenticated-orcid":false,"given":"Jae W.","family":"Lee","sequence":"additional","affiliation":[{"name":"Seoul National University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3303-8681","authenticated-orcid":false,"given":"Minsoo","family":"Rhu","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science & Technology, Daejeon, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","volume-title":"Proc. arxiv.org","year":"2024"},{"key":"ref2","article-title":"Generating long sequences with sparse transformers","author":"Child","year":"2019"},{"key":"ref3","first-page":"17283","article-title":"Big bird: Transformers for longer sequences","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Zaheer"},{"key":"ref4","article-title":"LongNet: Scaling transformers to 1,000,000,000 tokens","author":"Ding","year":"2023"},{"key":"ref5","first-page":"8828","article-title":"Blockwise parallel transformers for large context models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Liu"},{"key":"ref6","article-title":"Ring attention with blockwise transformers for near-infinite context","author":"Liu","year":"2023"},{"key":"ref7","article-title":"Hungry hungry hippos: Towards language modeling with state space models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Fu"},{"key":"ref8","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023"},{"key":"ref9","article-title":"Efficiently modeling long sequences with structured state spaces","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gu"},{"key":"ref10","first-page":"606","article-title":"Efficiently scaling transformer inference","volume-title":"Proc. Int. Conf. Mach. Learn. Syst.","volume":"5","author":"Pope"},{"key":"ref11","first-page":"10323","article-title":"SparseGPT: Massive language models can be accurately pruned in one-shot","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"202","author":"Frantar"},{"key":"ref12","article-title":"LLM.int8(): 8-bit matrix multiplication for transformers at scale","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dettmers"},{"key":"ref13","first-page":"16344","article-title":"FlashAttention: Fast and memory-efficient exact attention with IO-Awareness","volume":"35","author":"Dao","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.936"},{"key":"ref15","article-title":"Retentive network: A successor to transformer for large language models","author":"Sun","year":"2023"}],"container-title":["IEEE Computer Architecture Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10208\/10700665\/10584280.pdf?arnumber=10584280","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T17:25:31Z","timestamp":1727803531000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10584280\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7]]},"references-count":15,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/lca.2024.3422492","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":[[2024,7]]}}}