{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,23]],"date-time":"2026-08-23T14:30:16Z","timestamp":1787495416112,"version":"build-2736575974"},"publisher-location":"Singapore","reference-count":22,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819248049","type":"print"},{"value":"9789819248056","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T00:00:00Z","timestamp":1787529600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T00:00:00Z","timestamp":1787529600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2027]]},"DOI":"10.1007\/978-981-92-4805-6_24","type":"book-chapter","created":{"date-parts":[[2026,8,23]],"date-time":"2026-08-23T13:47:54Z","timestamp":1787492874000},"page":"359-371","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Hierarchical Adaptive Posit-CIM Architecture for\u00a0Edge Transformer Inference"],"prefix":"10.1007","author":[{"given":"Xuchang","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,24]]},"reference":[{"key":"24_CR1","unstructured":"Vaswani, A., Shazeer, N., Parmar, N.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30, pp. 5998\u20136008 (2017)"},{"key":"24_CR2","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., et al.: An image is worth 16$$\\times $$16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (2021)"},{"key":"24_CR3","unstructured":"OpenAI: GPT-4 technical report. arXiv:2303.08774 (2023)"},{"key":"24_CR4","doi-asserted-by":"crossref","unstructured":"Peebles, W., Xie, S.: Scalable diffusion models with transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4195\u20134205 (2023)","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"24_CR5","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"24_CR6","unstructured":"Micikevicius, P., Narang, S., Alben, J.: FP8 formats for deep learning (2022). arXiv:2209.05433"},{"key":"24_CR7","doi-asserted-by":"crossref","unstructured":"Yue, J., He, C., Wang, Z., et al.: A 28 nm 16.9\u2013300 TOPS\/W computing-in-memory processor supporting floating-point NN inference\/training with intensive-CIM sparse-digital architecture. In: IEEE International Solid-State Circuits Conference, pp.\u00a01\u20133 (2023)","DOI":"10.1109\/ISSCC42615.2023.10067779"},{"key":"24_CR8","doi-asserted-by":"crossref","unstructured":"Yao, S., Shen, L.: ImprLM: an improved logarithmic multiplier design approach via iterative linear-compensation and modified dynamic segment. In: International Conference on Computer Design, pp. 66\u201369 (2023)","DOI":"10.1109\/ICCD58817.2023.00020"},{"issue":"2","key":"24_CR9","first-page":"71","volume":"4","author":"JL Gustafson","year":"2017","unstructured":"Gustafson, J.L., Yonemoto, I.T.: Beating floating point at its own game: posit arithmetic. Supercomput. Front. Innov. 4(2), 71\u201386 (2017)","journal-title":"Supercomput. Front. Innov."},{"key":"24_CR10","doi-asserted-by":"crossref","unstructured":"Wang, Y., Yang, X., Qin, Y.: an energy-efficient posit compute-in-memory macro for high-accuracy AI applications. IEEE J. Solid-State Circuits (2025)","DOI":"10.1109\/JSSC.2025.3532654"},{"key":"24_CR11","doi-asserted-by":"crossref","unstructured":"Tambe, T., Garg, S., Prakash, A.: A 12 nm 18.1 TFLOPs\/W sparse transformer processor with entropy-based early exit, mixed-precision predication and fine-grained power management. In: IEEE International Solid-State Circuits Conference (2023)","DOI":"10.1109\/ISSCC42615.2023.10067817"},{"key":"24_CR12","doi-asserted-by":"crossref","unstructured":"Yu, J., Prabhu, K., Urman, Y.: 8-bit transformer inference and fine-tuning for edge accelerators. In: Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, pp. 5\u201321 (2024)","DOI":"10.1145\/3620666.3651368"},{"key":"24_CR13","doi-asserted-by":"crossref","unstructured":"Prabhu, K., Radway, R.M., Yu, J., et al.: MINOTAUR: a posit-based 0.42\u20130.50-TOPS\/W edge transformer inference and training accelerator. IEEE J. Solid-State Circuits (2025)","DOI":"10.1109\/JSSC.2025.3545731"},{"key":"24_CR14","doi-asserted-by":"crossref","unstructured":"He, J., Tu, F., Cheng, K.T.: AdaP-CIM: compute-in-memory based neural network accelerator using adaptive posit. In: Design, Automation and Test in Europe Conference, pp. 1\u20132 (2024)","DOI":"10.23919\/DATE58400.2024.10546569"},{"key":"24_CR15","doi-asserted-by":"crossref","unstructured":"Stevens, J.R., Venkatesan, R., Dai, S.: SofterMax: hardware\/software co-design of an efficient Softmax for transformers. In: Proceedings of the 58th ACM\/IEEE Design Automation Conference, pp. 469\u2013474 (2021)","DOI":"10.1109\/DAC18074.2021.9586134"},{"key":"24_CR16","doi-asserted-by":"crossref","unstructured":"Wu, P.C., Su, J.W., Hong, L.Y., et al.: A 22 nm 832Kb hybrid-domain floating-point SRAM in-memory-compute macro with 16.2\u201370.2 TFLOPS\/W for high-accuracy AI-edge devices. In: IEEE International Solid-State Circuits Conference, pp.\u00a0126\u2013128 (2023)","DOI":"10.1109\/ISSCC42615.2023.10067527"},{"issue":"1","key":"24_CR17","doi-asserted-by":"publisher","first-page":"196","DOI":"10.1109\/JSSC.2023.3309966","volume":"59","author":"PC Wu","year":"2024","unstructured":"Wu, P.C., Su, J.W., Hong, L.Y., et al.: A floating-point 6T SRAM in-memory-compute macro using hybrid-domain structure for advanced AI edge chips. IEEE J. Solid-State Circuits 59(1), 196\u2013207 (2024)","journal-title":"IEEE J. Solid-State Circuits"},{"key":"24_CR18","doi-asserted-by":"crossref","unstructured":"Guo, A., Xi, C., Dong, F.: A 28-nm 64-kb 31.6-TFLOPS\/W digital-domain floating-point-computing-unit and double-Bit 6T-SRAM computing-in-memory macro for floating-point CNNs. IEEE J. Solid-State Circuits 59(9), 3032\u20133044 (2024)","DOI":"10.1109\/JSSC.2024.3375359"},{"key":"24_CR19","doi-asserted-by":"crossref","unstructured":"Dettmers, T., Lewis, M., Belkada, Y., et al.: LLM.int8(): 8-bit matrix multiplication for transformers at scale. In: Advances in Neural Information Processing Systems, vol.\u00a035, pp.\u00a04496\u20134509 (2022)","DOI":"10.52202\/068431-2198"},{"key":"24_CR20","unstructured":"Frantar, E., Ashkboos, S., Hoefler, T.: GPTQ: accurate post-training quantization for generative pre-trained transformers (2022). arXiv:2210.17323"},{"key":"24_CR21","unstructured":"Zhang, D., Shen, L., Lu, K.: Eliminate data divergence in SpMV via processor and memory co-computing framework. IEEE Trans. Comput. (2025)"},{"key":"24_CR22","doi-asserted-by":"crossref","unstructured":"Tu, F., Wang, Y., Wu, Z.: A 28nm 29.2 TFLOPS\/W BF16 and 36.5 TOPS\/W INT8 reconfigurable digital CIM processor with unified FP\/INT pipeline and bitwise in-memory booth multiplication for cloud deep learning acceleration. In: IEEE International Solid-State Circuits Conference, pp. 1\u20133 (2022)","DOI":"10.1109\/ISSCC42614.2022.9731762"}],"container-title":["Lecture Notes in Computer Science","Advanced Parallel Processing Technologies"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-92-4805-6_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,23]],"date-time":"2026-08-23T13:47:56Z","timestamp":1787492876000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-4805-6_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,24]]},"ISBN":["9789819248049","9789819248056"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-4805-6_24","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,24]]},"assertion":[{"value":"24 August 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"Artificial intelligence tools, if used, were used only for language organization and figure\/table polishing, and did not participate in the generation of the core ideas or technical content.","order":1,"name":"Ethics","label":"Statement of AI Usage","group":{"name":"EthicsHeading","label":"Ethics"}},{"value":"APPT","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Symposium on Advanced Parallel Processing Technologies","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Brussels","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Belgium","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 July 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 July 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"appt2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.appt-conference.com\/2026","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}