{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:23:23Z","timestamp":1750220603757,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":18,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,1,18]],"date-time":"2021-01-18T00:00:00Z","timestamp":1610928000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Key R&D Program","award":["2019YFB2204200"],"award-info":[{"award-number":["2019YFB2204200"]}]},{"name":"NSFC","award":["61674094, 61934005, 61720106013"],"award-info":[{"award-number":["61674094, 61934005, 61720106013"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,1,18]]},"DOI":"10.1145\/3394885.3431532","type":"proceedings-article","created":{"date-parts":[[2021,1,29]],"date-time":"2021-01-29T11:32:48Z","timestamp":1611919968000},"page":"813-818","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Block-Circulant Neural Network Accelerator Featuring Fine-Grained Frequency-Domain Quantization and Reconfigurable FFT Modules"],"prefix":"10.1145","author":[{"given":"Yifan","family":"He","sequence":"first","affiliation":[{"name":"Dept. of Electronic Engineering, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinshan","family":"Yue","sequence":"additional","affiliation":[{"name":"Dept. of Electronic Engineering, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongpan","family":"Liu","sequence":"additional","affiliation":[{"name":"Dept. of Electronic Engineering, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huazhong","family":"Yang","sequence":"additional","affiliation":[{"name":"Dept. of Electronic Engineering, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2021,1,29]]},"reference":[{"volume-title":"Proceedings of the 50th Annual IEEE\/ACM International Symposium on Microarchitecture. ACM, 395--408","author":"Caiwen","key":"e_1_3_2_1_1_1"},{"doi-asserted-by":"crossref","unstructured":"Caiwen Ding and etal 2019. REQ-YOLO: A Resource-Aware Efficient Quantization Framework for Object Detection on FPGAs. In FPGA. 33--42.  Caiwen Ding and et al. 2019. REQ-YOLO: A Resource-Aware Efficient Quantization Framework for Object Detection on FPGAs. In FPGA. 33--42.","key":"e_1_3_2_1_2_1","DOI":"10.1145\/3289602.3293904"},{"doi-asserted-by":"crossref","unstructured":"S. Lin et al. 2018. FFT-based deep learning deployment in embedded systems. In DATE. 1045--1050.  S. Lin et al. 2018. FFT-based deep learning deployment in embedded systems. In DATE. 1045--1050.","key":"e_1_3_2_1_3_1","DOI":"10.23919\/DATE.2018.8342166"},{"unstructured":"J. S. Garofolo and etal 1993. DARPA TIMIT acoustic-phonetic continous speech corpus CD-ROM. NET speech disc 1--1.1. Nasa Sti\/recon Technical Report N 93 (1993).  J. S. Garofolo and et al. 1993. DARPA TIMIT acoustic-phonetic continous speech corpus CD-ROM. NET speech disc 1--1.1. Nasa Sti\/recon Technical Report N 93 (1993).","key":"e_1_3_2_1_4_1"},{"volume-title":"ESE: Efficient Speech Recognition Engine with Sparse LSTM on FPGA. In Acm\/sigda International Symposium on Field-programmable Gate Arrays.","year":"2016","author":"Han Song","key":"e_1_3_2_1_5_1"},{"volume-title":"Howard and et al","year":"2017","author":"Andrew","key":"e_1_3_2_1_6_1"},{"doi-asserted-by":"crossref","unstructured":"Kellerer and et al. 2004. Knapsack Problems.  Kellerer and et al. 2004. Knapsack Problems.","key":"e_1_3_2_1_7_1","DOI":"10.1007\/978-3-540-24777-7"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_8_1","DOI":"10.1109\/LSSC.2019.2937440"},{"doi-asserted-by":"crossref","unstructured":"B. Moons and etal 2016. Energy-efficient ConvNets through approximate computing. In WACV. 1--8.  B. Moons and et al. 2016. Energy-efficient ConvNets through approximate computing. In WACV. 1--8.","key":"e_1_3_2_1_9_1","DOI":"10.1109\/WACV.2016.7477614"},{"doi-asserted-by":"crossref","unstructured":"Eunhyeok Park and etal 2018. Energy-Efficient Neural Network Accelerator Based on Outlier-Aware Low-Precision Computation. In ISCA. 688--698.  Eunhyeok Park and et al. 2018. Energy-Efficient Neural Network Accelerator Based on Outlier-Aware Low-Precision Computation. In ISCA. 688--698.","key":"e_1_3_2_1_10_1","DOI":"10.1109\/ISCA.2018.00063"},{"doi-asserted-by":"crossref","unstructured":"Ha\u015fim Sak and etal 2014. Long Short-Term Memory Based Recurrent Neural Network Architectures for Large Vocabulary Speech Recognition. Computer Science (2014) 338--342.  Ha\u015fim Sak and et al. 2014. Long Short-Term Memory Based Recurrent Neural Network Architectures for Large Vocabulary Speech Recognition. Computer Science (2014) 338--342.","key":"e_1_3_2_1_11_1","DOI":"10.21437\/Interspeech.2014-80"},{"volume-title":"CVPR","key":"e_1_3_2_1_12_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_13_1","DOI":"10.1145\/3007787.3001163"},{"doi-asserted-by":"crossref","unstructured":"Wang and et al. 2018. C-LSTM: Enabling Efficient LSTM Using Structured Compression Techniques on FPGAs. In FPGA 11--20.  Wang and et al. 2018. C-LSTM: Enabling Efficient LSTM Using Structured Compression Techniques on FPGAs. In FPGA 11--20.","key":"e_1_3_2_1_14_1","DOI":"10.1145\/3174243.3174253"},{"volume-title":"HAQ: Hardware-Aware Automated Quantization. CoRR abs\/1811.08886","year":"2018","author":"Wang Kuan","key":"e_1_3_2_1_15_1"},{"unstructured":"Shaokai Ye and etal 2018. A Unified Framework of DNN Weight Pruning and Weight Clustering\/Quantization Using ADMM. (2018).  Shaokai Ye and et al. 2018. A Unified Framework of DNN Weight Pruning and Weight Clustering\/Quantization Using ADMM. (2018).","key":"e_1_3_2_1_16_1"},{"volume-title":"2018 IEEE Symposium on VLSI Circuits.","author":"Zhe","key":"e_1_3_2_1_17_1"},{"doi-asserted-by":"crossref","unstructured":"J. Yue and etal 2019. 7.5 A 65nm 0.39-to-140.3TOPS\/W l-to-12b Unified Neural Network Processor Using Block-Circulant-Enabled Transpose-Domain Acceleration with 8.1x Higher TOPS\/mm2and 6T HBST-TRAM-Based 2D Data-Reuse Architecture. In ISSCC. 138--140.  J. Yue and et al. 2019. 7.5 A 65nm 0.39-to-140.3TOPS\/W l-to-12b Unified Neural Network Processor Using Block-Circulant-Enabled Transpose-Domain Acceleration with 8.1x Higher TOPS\/mm2and 6T HBST-TRAM-Based 2D Data-Reuse Architecture. In ISSCC. 138--140.","key":"e_1_3_2_1_18_1","DOI":"10.1109\/ISSCC.2019.8662360"}],"event":{"sponsor":["SIGDA ACM Special Interest Group on Design Automation","IEEE CAS","IEEE CEDA"],"acronym":"ASPDAC '21","name":"ASPDAC '21: 26th Asia and South Pacific Design Automation Conference","location":"Tokyo Japan"},"container-title":["Proceedings of the 26th Asia and South Pacific Design Automation Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3394885.3431532","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3394885.3431532","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T21:32:02Z","timestamp":1750195922000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3394885.3431532"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,18]]},"references-count":18,"alternative-id":["10.1145\/3394885.3431532","10.1145\/3394885"],"URL":"https:\/\/doi.org\/10.1145\/3394885.3431532","relation":{},"subject":[],"published":{"date-parts":[[2021,1,18]]},"assertion":[{"value":"2021-01-29","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}