{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T22:19:16Z","timestamp":1776464356532,"version":"3.51.2"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,8,6]],"date-time":"2025-08-06T00:00:00Z","timestamp":1754438400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,6]],"date-time":"2025-08-06T00:00:00Z","timestamp":1754438400000},"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":[[2025,8,6]]},"DOI":"10.1109\/islped65674.2025.11261754","type":"proceedings-article","created":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T18:39:13Z","timestamp":1764787153000},"page":"1-7","source":"Crossref","is-referenced-by-count":1,"title":["Faster Ternary and Binary Neural Network Inference on CPU by Reducing Popcount Overhead"],"prefix":"10.1109","author":[{"given":"Olivier","family":"Fischer","sequence":"first","affiliation":[{"name":"ETH Zurich,Systems Group,Zurich,Switzerland"}]},{"given":"Shien","family":"Zhu","sequence":"additional","affiliation":[{"name":"ETH Zurich,Systems Group,Zurich,Switzerland"}]},{"given":"Gustavo","family":"Alonso","sequence":"additional","affiliation":[{"name":"ETH Zurich,Systems Group,Zurich,Switzerland"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1201\/9781003162810-13"},{"issue":"10","key":"ref2","first-page":"1613","article-title":"A survey of quantization methods for deep neural networks","volume":"45","author":"YANG","year":"2023","journal-title":"Chinese Journal of Engineering"},{"key":"ref3","author":"Kalamkar","year":"2019","journal-title":"A study of bfloat16 for deep learning training"},{"key":"ref4","author":"Wu","year":"2020","journal-title":"Integer quantization for deep learning inference: Principles and empirical evaluation"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00204"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16462"},{"key":"ref7","first-page":"14 651","article-title":"Fp8 quantization: The power of the exponent","volume":"35","author":"Kuzmin","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72897-6_24"},{"key":"ref9","first-page":"49 146","article-title":"Training transformers with 4-bit integers","volume":"36","author":"Xi","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref10","article-title":"Binarized neural networks","volume":"29","author":"Hubara","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_44"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00517"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5912"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICPADS51040.2020.00026"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_20"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00357"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i10.17036"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2018.00034"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350534"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3129393"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3414539"},{"key":"ref22","first-page":"578","article-title":"TVM: An automated end-to-end optimizing compiler for deep learning","volume-title":"13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18)","author":"Chen"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3508390"},{"key":"ref24","first-page":"110","article-title":"Instruction tables: Lists of instruction latencies, through-puts and micro-operation breakdowns for intel, amd and via cpus","volume":"93","author":"Fog","year":"2011","journal-title":"Copenhagen University College of Engineering"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1093\/comjnl\/bxx046"},{"key":"ref26","article-title":"Pytorch documentation"},{"key":"ref27","volume-title":"Intel Intrinsics Guide","year":"2024"},{"key":"ref28","article-title":"libpopcnt: Fast c\/c++ bit population count library","author":"Walisch","year":"2024"}],"event":{"name":"2025 IEEE\/ACM International Symposium on Low Power Electronics and Design (ISLPED)","location":"Reykjav\u00edk, Iceland","start":{"date-parts":[[2025,8,6]]},"end":{"date-parts":[[2025,8,8]]}},"container-title":["2025 IEEE\/ACM International Symposium on Low Power Electronics and Design (ISLPED)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11261694\/11261695\/11261754.pdf?arnumber=11261754","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T07:55:16Z","timestamp":1764834916000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11261754\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,6]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/islped65674.2025.11261754","relation":{},"subject":[],"published":{"date-parts":[[2025,8,6]]}}}