{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,22]],"date-time":"2025-05-22T06:10:12Z","timestamp":1747894212432,"version":"3.41.0"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,3,31]],"date-time":"2025-03-31T00:00:00Z","timestamp":1743379200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,3,31]],"date-time":"2025-03-31T00:00:00Z","timestamp":1743379200000},"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":[[2025,3,31]]},"DOI":"10.23919\/date64628.2025.10992907","type":"proceedings-article","created":{"date-parts":[[2025,5,21]],"date-time":"2025-05-21T17:36:35Z","timestamp":1747848995000},"page":"1-7","source":"Crossref","is-referenced-by-count":0,"title":["LCache: Log-Structured SSD Caching for Training Deep Learning Models"],"prefix":"10.23919","author":[{"given":"Shucheng","family":"Wang","sequence":"first","affiliation":[{"name":"China Mobile (Suzhou) Software Technology Co., Ltd.,Suzhou,China"}]},{"given":"Zhiguo","family":"Xu","sequence":"additional","affiliation":[{"name":"China Mobile (Suzhou) Software Technology Co., Ltd.,Suzhou,China"}]},{"given":"Zhandong","family":"Guo","sequence":"additional","affiliation":[{"name":"China Mobile (Suzhou) Software Technology Co., Ltd.,Suzhou,China"}]},{"given":"Jian","family":"Sheng","sequence":"additional","affiliation":[{"name":"Suzhou City University,Suzhou,China"}]},{"given":"Kaiye","family":"Zhou","sequence":"additional","affiliation":[{"name":"China Mobile (Suzhou) Software Technology Co., Ltd.,Suzhou,China"}]},{"given":"Qiang","family":"Cao","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology,Wuhan,China"}]}],"member":"263","reference":[{"key":"ref1","article-title":"OPT: open pretrained transformer language models","author":"Zhang","year":"2022","journal-title":"CoRR"},{"volume-title":"OpenAI","key":"ref2","article-title":"Chatgpt"},{"key":"ref3","article-title":"Imagenet-21k pretraining for the masses","volume-title":"Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks 1, NeurIPS Datasets and Benchmarks 2021, December 2021, virtual","author":"Ridnik","year":"2021"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref5","article-title":"Is your code generated by chatgpt really correct? rigorous evaluation of large language models for code generation","author":"Liu","year":"2023","journal-title":"NeurIPS 2023"},{"key":"ref6","first-page":"26 106","article-title":"LEVER: learning to verify language-to-code generation with execution","volume":"202","author":"Ni","year":"2023","journal-title":"ICML 2023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613145"},{"key":"ref8","first-page":"283","article-title":"Quiver: An informed storage cache for deep learning","volume-title":"18th USENIX Conference on File and Storage Technologies, FAST 2020, Santa Clara, CA, USA, February 24\u201327, 2020","author":"Kumar","year":"2020"},{"key":"ref9","first-page":"135","article-title":"SHADE: enable fundamental cacheability for distributed deep learning training","volume-title":"21st USENIX Conference on File and Storage Technologies, FAST 2023, Santa Clarax, CA, USA, February 21\u201323, 2023","author":"Khan","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3552326.3567499"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.14778\/3446095.3446100"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3406703"},{"key":"ref13","first-page":"58","article-title":"Efficient large-scale language model training on GPU clusters using megatron-lm","volume-title":"International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2021, St. Louis, Missouri, USA, November 14\u201319,2021","author":"Narayanan","year":"2021"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/MASCOTS.2018.00023"},{"key":"ref15","first-page":"8024","article-title":"Pytorch: An imperative style, high-performance deep learning library","author":"Paszke","year":"2019","journal-title":"NeurIPS 2019"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476181"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1137\/16M1080173"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-019-01440-w"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.5555\/3026877.3026899"},{"issue":"4","key":"ref20","article-title":"Learning multiple layers of features from tiny images","volume":"1","author":"Krizhevsky","year":"2009","journal-title":"Handbook of Systemic Autoimmune Diseases"},{"key":"ref21","article-title":"LAION-5B: an open large-scale dataset for training next generation image-text models","volume-title":"Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans, LA, USA, November 28 - December 9, 2022","author":"Schuhmann","year":"2022"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.5555\/2999134.2999257"},{"key":"ref23","article-title":"Squeezenet: Alexnet-level accuracy with 50x fewer parameters and < 1mb model size","volume-title":"CoRR","volume":"abs\/1602.07360","author":"Iandola","year":"2016"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref25","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3\u20137, 2021","author":"Dosovitskiy","year":"2021"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00041"},{"volume-title":"NVIDIA","key":"ref27","article-title":"Nvidia hgx ai supercomputer"},{"volume-title":"NVIDIA","key":"ref28","article-title":"Nvidia dgx-2"},{"key":"ref29","first-page":"603","article-title":"Asynchronous I\/O stack: A low-latency kernel I\/O stack for ultra-low latency ssds","volume-title":"Proceedings of the 2019 USENIX Annual Technical Conference, USENIX ATC 2019","author":"Lee"},{"key":"ref30","first-page":"877","article-title":"Max: A multicore-accelerated file system for flash storage","volume-title":"Proceedings of the 2021 USENIX Annual Technical Conference, USENIX ATC 2021, July 14\u201316, 2021","author":"Liao","year":"2021"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CCGrid49817.2020.00-76"},{"key":"ref32","first-page":"203","article-title":"Checkfreq: Frequent, fine-grained DNN checkpointing","volume-title":"FAST 2021","author":"Mohan","year":"2021"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3404397.3404472"},{"volume-title":"Alluxio: A virtual distributed file system","year":"2018","author":"Li","key":"ref34"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10070964"}],"event":{"name":"2025 Design, Automation &amp; Test in Europe Conference (DATE)","start":{"date-parts":[[2025,3,31]]},"location":"Lyon, France","end":{"date-parts":[[2025,4,2]]}},"container-title":["2025 Design, Automation &amp;amp; Test in Europe Conference (DATE)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10992638\/10992588\/10992907.pdf?arnumber=10992907","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,22]],"date-time":"2025-05-22T05:32:32Z","timestamp":1747891952000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10992907\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,31]]},"references-count":35,"URL":"https:\/\/doi.org\/10.23919\/date64628.2025.10992907","relation":{},"subject":[],"published":{"date-parts":[[2025,3,31]]}}}