{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T06:46:23Z","timestamp":1785912383769,"version":"3.56.0"},"reference-count":84,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"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":[],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1109\/isca66397.2026.00182","type":"proceedings-article","created":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T19:12:51Z","timestamp":1785870771000},"page":"2615-2631","source":"Crossref","is-referenced-by-count":0,"title":["Bridging Efficiency and Scalability in Llm System Via 3D Hybrid Pim With 2D in-Transit Computation"],"prefix":"10.1109","author":[{"given":"Hongyi","family":"Li","sequence":"first","affiliation":[{"name":"Tsinghua University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Songchen","family":"Ma","sequence":"additional","affiliation":[{"name":"HKUST","place":["Hong Kong SAR, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huanyu","family":"Qu","sequence":"additional","affiliation":[{"name":"University of Macau","place":["Macau SAR, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weihao","family":"Zhang","sequence":"additional","affiliation":[{"name":"HKUST","place":["Hong Kong SAR, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jia","family":"Chen","sequence":"additional","affiliation":[{"name":"HKUST","place":["Hong Kong SAR, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junfeng","family":"Lin","sequence":"additional","affiliation":[{"name":"Tsinghua University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fengbin","family":"Tu","sequence":"additional","affiliation":[{"name":"HKUST","place":["Hong Kong SAR, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rong","family":"Zhao","sequence":"additional","affiliation":[{"name":"Tsinghua University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2017.21"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.5555\/3291168.3291211"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC49661.2025.10904646"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.13"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358276"},{"key":"ref6","volume-title":"Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning","author":"DeepSeek-AI","year":"2025"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/HOTCHIPS.2019.8875680"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/DAC56929.2023.10247913"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/hpca.2014.6835959"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2025.3561245"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3037697.3037702"},{"issue":"3","key":"ref12","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1109\/MM.2024.3373763","article-title":"Ai and memory wall","volume":"44","author":"Gholami","year":"2024","journal-title":"IEEE Micro"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3676641.3716267"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42615.2023.10067260"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IGSC54211.2021.9651614"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO61859.2024.00051"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00040"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651380"},{"key":"ref19","volume-title":"Cacti."},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1017\/cbo9780511809835"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/MNANO.2024.3358714"},{"key":"ref22","volume-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2021"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/hpca.2019.00018"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCPMT.2024.3483445"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00029"},{"key":"ref26","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-031-01755-1","volume-title":"On-Chip Networks","author":"Jerger","year":"2017"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2013.6557149"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3649329.3657373"},{"key":"ref29","volume-title":"Processing-in-Memory for AI: From Circuits to Systems","author":"Joo-Young","year":"2023"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589350"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3140659.3080246"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2021.3082003"},{"key":"ref33","volume-title":"Scaling laws for neural language models","author":"Kaplan","year":"2020"},{"key":"ref34","volume-title":"Cinm (cinnamon): A compilation infrastructure for heterogeneous compute in-memory and compute near-memory paradigms","author":"Khan","year":"2023"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC49661.2025.10904606"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC49657.2024.10454447"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.41"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2008.4771803"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/1250662.1250681"},{"key":"ref40","volume-title":"Lol-pim: Long-context llm decoding with scalable dram-pim system","author":"Kwon","year":"2024"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42613.2021.9365862"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/isscc42613.2021.9365862"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42614.2022.9731711"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3695053.3731008"},{"key":"ref45","volume-title":"Awq: Activation-aware weight quantization for llm compression and acceleration","author":"Lin","year":"2023"},{"key":"ref46","volume-title":"Make llm inference affordable to everyone: Augmenting gpu memory with ndp-dimm","author":"Liu","year":"2025"},{"key":"ref47","volume-title":"Deja vu: Contextual sparsity for efficient 1lms at inference time","author":"Liu","year":"2023"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378497"},{"key":"ref49","author":"Luo","year":"2023","journal-title":"Ramulator 2.0: A modern, modular, and extensible dram simulator"},{"key":"ref50","volume-title":"Memory-centric computing","author":"Mutlu","year":"2023"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2023.3285095"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42614.2022.9731694"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3453483.3454083"},{"key":"ref54","volume-title":"Nvidia a100 tensor core gpu architecture","year":"2020"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00024"},{"key":"ref56","year":"2020","journal-title":"Gpt-3: Language models are few-shot learners"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640422"},{"key":"ref58","first-page":"210","article-title":"Opportunistic computing in gpu architectures","volume-title":"2019 ACM\/IEEE 46th Annual International Symposium on Computer Architecture (ISCA)","author":"Pattnaik","year":"2019"},{"key":"ref59","volume-title":"Pci-sig releases pcie\u00ae 4.0, version 1.0","year":"2019"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC55821.2022.9926331"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/hpca47549.2020.00045"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/980152.980156"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/3470496.3527379"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651324"},{"key":"ref65","first-page":"185","article-title":"Rowclone: Fast and energy-efficient in-dram bulk data copy and initialization","volume-title":"2013 46th Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO)","author":"Seshadri","year":"2013"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1145\/3579990.3580009"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC49661.2025.10904790"},{"key":"ref68","volume-title":"Powerinfer: Fast large language model serving with a consumer-grade gpu","author":"Song","year":"2023"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2003.1253203"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCD50377.2020.00070"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00052"},{"key":"ref72","first-page":"01","article-title":"Breaking the beachfront limitations with silicon photonics","volume-title":"2024 Conference on Lasers and Electro-Optics (CLEO)","author":"Totovic","year":"2024"},{"key":"ref73","author":"Touvron","year":"2023","journal-title":"Llama 2: Open foundation and fine-tuned chat models"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/isscc42615.2023.10067285"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC49661.2025.10904738"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1145\/216585.216588"},{"key":"ref78","volume-title":"Towards large reasoning models: A survey of reinforced reasoning with large language models","author":"Xu","year":"2025"},{"key":"ref79","article-title":"Qwen2 technical report","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC49657.2024.10454313"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC49661.2025.10904659"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00037"},{"key":"ref83","volume-title":"Opt: Open pre-trained transformer language models","author":"Zhang","year":"2022"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00053"}],"event":{"name":"2026 ACM\/IEEE 53rd Annual International Symposium on Computer Architecture (ISCA)","location":"Raleigh, NC, USA","start":{"date-parts":[[2026,6,27]]},"end":{"date-parts":[[2026,7,1]]}},"container-title":["2026 ACM\/IEEE 53rd Annual International Symposium on Computer Architecture (ISCA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11617393\/11617394\/11617417.pdf?arnumber=11617417","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T05:59:24Z","timestamp":1785909564000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11617417\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":84,"URL":"https:\/\/doi.org\/10.1109\/isca66397.2026.00182","relation":{},"subject":[],"published":{"date-parts":[[2026,6]]}}}