{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T06:15:59Z","timestamp":1778566559428,"version":"3.51.4"},"reference-count":38,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CNS-2106237"],"award-info":[{"award-number":["CNS-2106237"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. VLSI Syst."],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1109\/tvlsi.2026.3658251","type":"journal-article","created":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T21:02:19Z","timestamp":1771534939000},"page":"1206-1216","source":"Crossref","is-referenced-by-count":0,"title":["LOgIQ: Log-Domain Optimization for Hardware-Efficient Inference and Quantization of Transformers"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-1310-3027","authenticated-orcid":false,"given":"Tanzeel-ur-Rehman","family":"Khan","sequence":"first","affiliation":[{"name":"Electrical and Computer Engineering Department, USU BRIDGE Laboratory, Utah State University, Logan, UT, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3927-1612","authenticated-orcid":false,"given":"Sanghamitra","family":"Roy","sequence":"additional","affiliation":[{"name":"Electrical and Computer Engineering Department, USU BRIDGE Laboratory, Utah State University, Logan, UT, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0228-2737","authenticated-orcid":false,"given":"Koushik","family":"Chakraborty","sequence":"additional","affiliation":[{"name":"Electrical and Computer Engineering Department, USU BRIDGE Laboratory, Utah State University, Logan, UT, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref2","article-title":"The llama 3 herd of models","author":"Grattafiori","year":"2024","journal-title":"arXiv:2407.21783"},{"key":"ref3","article-title":"Mistral 7B","author":"Jiang","year":"2023","journal-title":"arXiv:2310.06825"},{"key":"ref4","first-page":"1","article-title":"OpenChat: Advancing open-source language models with mixed-quality data","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Wang"},{"key":"ref5","article-title":"DeepSeek LLM: Scaling open-source language models with longtermism","author":"Bi","year":"2024","journal-title":"arXiv:2401.02954"},{"key":"ref6","article-title":"Bloom: A 176B-parameter open-access multilingual language model","author":"Workshop","year":"2022","journal-title":"arXiv:2211.05100"},{"key":"ref7","article-title":"The falcon series of open language models","author":"Almazrouei","year":"2023","journal-title":"arXiv:2311.16867"},{"key":"ref8","article-title":"Gemma: Open models based on Gemini research and technology","author":"Team","year":"2024","journal-title":"arXiv:2403.08295"},{"key":"ref9","article-title":"DeepSeek-r1: Incentivizing reasoning capability in LLMs via reinforcement learning","author":"Guo","year":"2025","journal-title":"arXiv:2501.12948"},{"key":"ref10","first-page":"1","article-title":"Exploiting LLM quantization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Egashira"},{"key":"ref11","article-title":"Spinquant: LLM quantization with learned rotations","volume-title":"Proc. 13th Int. Conf. Learn. Represent. (ICLR)","author":"Liu","year":"2025"},{"issue":"4","key":"ref12","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1145\/3714983.3714987","article-title":"AWQ: Activation-aware weight quantization for on-device LLM compression and acceleration","volume":"28","author":"Lin","year":"2025","journal-title":"GetMobile: Mobile Comput. Commun."},{"key":"ref13","first-page":"1","article-title":"QLLM: Accurate and efficient low-bitwidth quantization for large language models","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Liu"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3649329.3656221"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589038"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v40i27.39406"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00063"},{"key":"ref18","first-page":"38087","article-title":"SmoothQuant: Accurate and efficient post-training quantization for large language models","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","author":"Xiao"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00071"},{"key":"ref20","first-page":"7708","article-title":"LRQ: Optimizing post-training quantization for large language models by learning low-rank weight-scaling matrices","volume-title":"Proc. Conf. Nations Americas Chapter Assoc. Comput. Linguistics, Human Lang. Technol.","author":"Lee"},{"key":"ref21","first-page":"1","article-title":"OmniQuant: Omnidirectionally calibrated quantization for large language models","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Shao"},{"key":"ref22","first-page":"27168","article-title":"ZeroQuant: Efficient and affordable post-training quantization for large-scale transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yao"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2025.117270"},{"key":"ref24","volume-title":"NanGate","year":"2026"},{"key":"ref25","first-page":"1","article-title":"BiScaled-DNN: Quantizing long-tailed datastructures with two scale factors for deep neural networks","volume-title":"Proc. 56th Annu. Design Autom. Conf.","author":"Jain"},{"key":"ref26","author":"Cowlishaw","year":"2008","journal-title":"IEEE Standard for Floating-point Arithmetic"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"ref28","volume-title":"The Falcon 3 Family of Open Models","author":"Team","year":"2024"},{"key":"ref29","volume-title":"The Llama 3.2 Collection: 3 B Instruction-Tuned Model (Llama-3.2-3b-Instruct)","year":"2024"},{"key":"ref30","article-title":"Instella: Fully open language models with stellar performance","author":"Liu","year":"2025","journal-title":"arXiv:2511.10628"},{"key":"ref31","volume-title":"Gemma 2 2b It: Instructiontuned Gemma 2 Model (2 B Parameters)","author":"DeepMind","year":"2024"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.229"},{"key":"ref33","article-title":"Training verifiers to solve math word problems","author":"Cobbe","year":"2021","journal-title":"arXiv:2110.14168"},{"key":"ref34","volume-title":"Code Evaluation Prompts Dataset","year":"2023"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1206"},{"key":"ref36","volume-title":"Nemotron-Personas-USA: Synthetic Personas Aligned to Real-World Distributions","author":"Meyer","year":"2025"},{"key":"ref37","first-page":"1","article-title":"GreenTPU: Improving timing error resilience of a near-threshold tensor processing unit","volume-title":"Proc. 56th ACM\/IEEE Design Autom. Conf. (DAC)","author":"Pandey"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/T-C.1975.224172"}],"container-title":["IEEE Transactions on Very Large Scale Integration (VLSI) Systems"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/92\/11514136\/11399922-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/92\/11514136\/11399922.pdf?arnumber=11399922","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T05:41:20Z","timestamp":1778564480000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11399922\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":38,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tvlsi.2026.3658251","relation":{},"ISSN":["1063-8210","1557-9999"],"issn-type":[{"value":"1063-8210","type":"print"},{"value":"1557-9999","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4]]}}}