{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:15:15Z","timestamp":1783437315709,"version":"3.54.6"},"reference-count":63,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,12,13]],"date-time":"2024-12-13T00:00:00Z","timestamp":1734048000000},"content-version":"vor","delay-in-days":12,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100012165","name":"Key Technologies Research and Development Program","doi-asserted-by":"publisher","award":["2023YFB4503205"],"award-info":[{"award-number":["2023YFB4503205"]}],"id":[{"id":"10.13039\/501100012165","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62202123"],"award-info":[{"award-number":["62202123"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["CCF Trans. HPC"],"published-print":{"date-parts":[[2024,12]]},"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>The integration of Large Language Models (LLMs) with Convolutional Neural Networks (CNNs) is significantly advancing the development of large models. However, the computational cost of large models is high, necessitating optimization for greater efficiency. One effective way to optimize the CNN is the use of depthwise separable convolution (DSC), which decouples spatial and channel convolutions to reduce the number of parameters and enhance efficiency. In this study, we focus on porting and optimizing DSC kernel functions from the GPU to the Deep Computing Unit (DCU), a computing accelerator developed in China. For depthwise convolution, we implement a row data reuse algorithm to minimize redundant data loading and memory access overhead. For pointwise convolution, we extend our dynamic tiling strategy to improve hardware utilization by balancing resource allocation among blocks and threads, and we enhance arithmetic intensity through a channel distribution algorithm. We implement depthwise and pointwise convolution kernel functions and integrate them into PyTorch as extension modules. Experiments demonstrate that our optimized kernel functions outperform the MIOpen library on the DCU, achieving up to a 3.59<jats:inline-formula>\n              <jats:alternatives>\n                <jats:tex-math>$$\\times$$<\/jats:tex-math>\n                <mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\">\n                  <mml:mo>\u00d7<\/mml:mo>\n                <\/mml:math>\n              <\/jats:alternatives>\n            <\/jats:inline-formula> speedup in depthwise convolution and up to a 3.54<jats:inline-formula>\n              <jats:alternatives>\n                <jats:tex-math>$$\\times$$<\/jats:tex-math>\n                <mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\">\n                  <mml:mo>\u00d7<\/mml:mo>\n                <\/mml:math>\n              <\/jats:alternatives>\n            <\/jats:inline-formula> speedup in pointwise convolution. These results highlight the effectiveness of our approach in leveraging the DCU\u2019s architecture to accelerate deep learning operations.<\/jats:p>","DOI":"10.1007\/s42514-024-00200-3","type":"journal-article","created":{"date-parts":[[2024,12,13]],"date-time":"2024-12-13T18:54:01Z","timestamp":1734116041000},"page":"646-664","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Optimizing depthwise separable convolution on DCU"],"prefix":"10.1007","volume":"6","author":[{"given":"Zheng","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Meng","family":"Hao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4783-876X","authenticated-orcid":false,"given":"Weizhe","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gangzhao","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xueyang","family":"Tian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siyu","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingdong","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Dai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenyu","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Desheng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongwei","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,12,13]]},"reference":[{"key":"200_CR1","unstructured":"Achiam, J., Adler, S., Agarwal, S., Ahmad, L., Akkaya, I., Aleman, F.L., Almeida, D., Altenschmidt, J., Altman, S., Anadkat, S., et\u00a0al.: Gpt-4 technical report. arXiv:2303.08774 (2023)"},{"key":"200_CR2","unstructured":"AMD: AMD $$\\text{ROCm}^{TM}$$ Documentation. https:\/\/rocm.docs.amd.com\/en\/latest Accessed 15 May 2024"},{"issue":"6","key":"200_CR3","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1109\/MSP.2017.2743240","volume":"34","author":"K Arulkumaran","year":"2017","unstructured":"Arulkumaran, K., Deisenroth, M.P., Brundage, M., Bharath, A.A.: Deep reinforcement learning: A brief survey. IEEE Signal Process. Magaz. 34(6), 26\u201338 (2017)","journal-title":"IEEE Signal Process. Magaz."},{"issue":"10","key":"200_CR4","doi-asserted-by":"publisher","first-page":"1415","DOI":"10.1109\/TCSII.2018.2865896","volume":"65","author":"L Bai","year":"2018","unstructured":"Bai, L., Zhao, Y., Huang, X.: A cnn accelerator on fpga using depthwise separable convolution. IEEE Trans. Circuits Syst. II: Express Briefs 65(10), 1415\u20131419 (2018). https:\/\/doi.org\/10.1109\/TCSII.2018.2865896","journal-title":"IEEE Trans. Circuits Syst. II: Express Briefs"},{"key":"200_CR5","unstructured":"Bochkovskiy, A., Wang, C.-Y., Liao, H.-Y.M.: Yolov4: Optimal speed and accuracy of object detection. arXiv:2004.10934 (2020)"},{"key":"200_CR6","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J.D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A.: Language models are few-shot learners. Adv. Neural Inf. Process. Syst. 33, 1877\u20131901 (2020)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"200_CR7","doi-asserted-by":"crossref","unstructured":"Chollet, F.: Xception: Deep learning with depthwise separable convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1251\u20131258 (2017)","DOI":"10.1109\/CVPR.2017.195"},{"key":"200_CR8","first-page":"3965","volume":"34","author":"Z Dai","year":"2021","unstructured":"Dai, Z., Liu, H., Le, Q.V., Tan, M.: Coatnet: Marrying convolution and attention for all data sizes. Adv. Neural Inf. Process. Syst. 34, 3965\u20133977 (2021)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"200_CR9","unstructured":"Devlin, J., Chang, M.-W., Lee, K., Toutanova, K.: Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv:1810.04805 (2018)"},{"key":"200_CR10","doi-asserted-by":"publisher","unstructured":"Ferrari, V., Sousa, R., Pereira, M., L.\u00a0De\u00a0Carvalho, J.a.P., Amaral, J.N., Moreira, J., Araujo, G.: Advancing direct convolution using convolution slicing optimization and isa extensions. ACM Trans. Architect. Code Opt. 20(4), (2023) https:\/\/doi.org\/10.1145\/3625004","DOI":"10.1145\/3625004"},{"issue":"4","key":"200_CR11","first-page":"96","volume":"20","author":"N Gao","year":"2022","unstructured":"Gao, N., Yu, Y., Hua, X., Feng, F., Jiang, T.: A content-aware bitrate selection method using multi-step prediction for 360-degree video streaming. ZTE Commun. 20(4), 96 (2022)","journal-title":"ZTE Commun."},{"key":"200_CR12","unstructured":"Goldsborough, P.: Custom C and cuda extensions. https:\/\/pytorch.org\/tutorials\/advanced\/cpp_extension.html#custom-c-and-cuda-extensions Accessed 16 May 2024"},{"key":"200_CR13","unstructured":"Guide, D.: Cuda c++ programming guide. NVIDIA, July (2020)"},{"key":"200_CR14","doi-asserted-by":"crossref","unstructured":"Guo, H., Wang, H., Chen, W., Zhang, C., Han, Y., Zhu, S., Zhang, D., Guo, Y., Shang, J., Wan, T., et\u00a0al.: Optimizing sparse general matrix\u2013matrix multiplication for dcus. J. Supercomput. 1\u201325 (2024)","DOI":"10.1007\/s11227-024-06234-2"},{"key":"200_CR15","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"200_CR16","unstructured":"Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., Adam, H.: Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv:1704.04861 (2017)"},{"key":"200_CR17","unstructured":"Hygon: Deep Computing Unit. https:\/\/www.hygon.cn\/product\/accelerator Accessed 16 May 2024"},{"key":"200_CR18","doi-asserted-by":"crossref","unstructured":"Iandola, F.N., Sheffield, D., Anderson, M.J., Phothilimthana, P.M., Keutzer, K.: Communication-minimizing 2d convolution in gpu registers. In: 2013 IEEE International Conference on Image Processing, pp. 2116\u20132120 (2013). IEEE","DOI":"10.1109\/ICIP.2013.6738436"},{"key":"200_CR19","unstructured":"Jakob, W.: Pybind11 Documentation. https:\/\/pybind11.readthedocs.io\/en\/stable\/index.html Accessed 16 May 2024"},{"issue":"1","key":"200_CR20","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1109\/LES.2021.3087707","volume":"14","author":"E Jeong","year":"2021","unstructured":"Jeong, E., Kim, J., Tan, S., Lee, J., Ha, S.: Deep learning inference parallelization on heterogeneous processors with tensorrt. IEEE Embedded Syst. Lett. 14(1), 15\u201318 (2021)","journal-title":"IEEE Embedded Syst. Lett."},{"issue":"3","key":"200_CR21","first-page":"70","volume":"21","author":"Y Ji","year":"2023","unstructured":"Ji, Y., Han, J., Zhao, Y., Zhang, S., Gong, Z.: Log anomaly detection through gpt-2 for large scale systems. ZTE Commun. 21(3), 70 (2023)","journal-title":"ZTE Commun."},{"key":"200_CR22","doi-asserted-by":"crossref","unstructured":"Jouppi, N.P., Young, C., Patil, N., Patterson, D., Agrawal, G., Bajwa, R., Bates, S., Bhatia, S., Boden, N., Borchers, A., Boyle, R., Cantin, P.-l., Chao, C., Clark, C., Coriell, J., Daley, M., Dau, M., Dean, J., Gelb, B., Ghaemmaghami, T.V., Gottipati, R., Gulland, W., Hagmann, R., Ho, C.R., Hogberg, D., Hu, J., Hundt, R., Hurt, D., Ibarz, J., Jaffey, A., Jaworski, A., Kaplan, A., Khaitan, H., Koch, A., Kumar, N., Lacy, S., Laudon, J., Law, J., Le, D., Leary, C., Liu, Z., Lucke, K., Lundin, A., MacKean, G., Maggiore, A., Mahony, M., Miller, K., Nagarajan, R., Narayanaswami, R., Ni, R., Nix, K., Norrie, T., Omernick, M., Penukonda, N., Phelps, A., Ross, J.: In-datacenter performance analysis of a tensor processing unit. (2017). arXiv: https:\/\/arxiv.org\/pdf\/1704.04760pdf","DOI":"10.1145\/3140659.3080246"},{"key":"200_CR23","doi-asserted-by":"crossref","unstructured":"Jun, H., Cho, J., Lee, K., Son, H.-Y., Kim, K., Jin, H., Kim, K.: Hbm (high bandwidth memory) dram technology and architecture. In: 2017 IEEE International Memory Workshop (IMW), pp. 1\u20134 (2017). IEEE","DOI":"10.1109\/IMW.2017.7939084"},{"key":"200_CR24","unstructured":"Khan, J., Fultz, P., Tamazov, A., Lowell, D., Liu, C., Melesse, M., Nandhimandalam, M., Nasyrov, K., Perminov, I., Shah, T., et\u00a0al.: Miopen: An open source library for deep learning primitives. arXiv:1910.00078 (2019)"},{"key":"200_CR25","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. Adv. Neural Inf. Process. Syst. 25, (2012)"},{"key":"200_CR26","doi-asserted-by":"crossref","unstructured":"Li, Z., Jia, H., Zhang, Y., Chen, T., Yuan, L., Cao, L., Wang, X.: Autofft: a template-based fft codes auto-generation framework for arm and x86 cpus. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 1\u201315 (2019)","DOI":"10.1145\/3295500.3356138"},{"key":"200_CR27","doi-asserted-by":"crossref","unstructured":"Li, X., Liang, Y., Yan, S., Jia, L., Li, Y.: A coordinated tiling and batching framework for efficient gemm on gpus. In: Proceedings of the 24th Symposium on Principles and Practice of Parallel Programming, pp. 229\u2013241 (2019)","DOI":"10.1145\/3293883.3295734"},{"key":"200_CR28","unstructured":"Li, Z., Wallace, E., Shen, S., Lin, K., Keutzer, K., Klein, D., Gonzalez, J.: Train big, then compress: Rethinking model size for efficient training and inference of transformers. In: International Conference on Machine Learning, pp. 5958\u20135968 (2020). PMLR"},{"issue":"2","key":"200_CR29","doi-asserted-by":"publisher","first-page":"206","DOI":"10.1007\/s42514-023-00153-z","volume":"6","author":"Y Liu","year":"2024","unstructured":"Liu, Y., Zhang, F., Pan, Z., Guo, X., Hu, Y., Zhang, X., Du, X.: Compressed data direct computing for chinese dataset on dcu. CCF Trans. High Perform. Comput. 6(2), 206\u2013220 (2024)","journal-title":"CCF Trans. High Perform. Comput."},{"issue":"1","key":"200_CR30","first-page":"64","volume":"21","author":"J Lu","year":"2023","unstructured":"Lu, J., Zheng, Q.: Ultra-lightweight face animation method for ultra-low bitrate video conferencing. ZTE Commun. 21(1), 64 (2023)","journal-title":"ZTE Commun."},{"issue":"1","key":"200_CR31","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1109\/TPDS.2021.3084813","volume":"33","author":"G Lu","year":"2021","unstructured":"Lu, G., Zhang, W., Wang, Z.: Optimizing depthwise separable convolution operations on gpus. IEEE Trans. Parallel Distribut. Syst. 33(1), 70\u201387 (2021)","journal-title":"IEEE Trans. Parallel Distribut. Syst."},{"key":"200_CR32","doi-asserted-by":"crossref","unstructured":"Ma, N., Zhang, X., Zheng, H.-T., Sun, J.: Shufflenet v2: Practical guidelines for efficient cnn architecture design. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 116\u2013131 (2018)","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"200_CR33","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/2258\/1\/012065","volume":"2258","author":"K Ma","year":"2022","unstructured":"Ma, K., Han, L., Shang, J.-D., Xie, J.-M., Zhang, H.: Optimized realization of quantum fourier transform for domestic dcu accelerator. J Phys Conf Ser 2258, 012065 (2022)","journal-title":"J Phys Conf Ser"},{"issue":"1","key":"200_CR34","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1109\/TPDS.2016.2549523","volume":"28","author":"X Mei","year":"2016","unstructured":"Mei, X., Chu, X.: Dissecting gpu memory hierarchy through microbenchmarking. IEEE Trans. Parallel Distribut. Syst. 28(1), 72\u201386 (2016)","journal-title":"IEEE Trans. Parallel Distribut. Syst."},{"key":"200_CR35","doi-asserted-by":"crossref","unstructured":"Narayanan, D., Harlap, A., Phanishayee, A., Seshadri, V., Devanur, N.R., Ganger, G.R., Gibbons, P.B., Zaharia, M.: Pipedream: Generalized pipeline parallelism for dnn training. In: Proceedings of the 27th ACM Symposium on Operating Systems Principles, pp. 1\u201315 (2019)","DOI":"10.1145\/3341301.3359646"},{"key":"200_CR36","unstructured":"Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., et\u00a0al.: Pytorch: An imperative style, high-performance deep learning library. Adv. Neural Inf. Process. Syst. 32, (2019)"},{"key":"200_CR37","doi-asserted-by":"crossref","unstructured":"Qin, Z., Zhang, Z., Li, D., Zhang, Y., Peng, Y.: Diagonalwise refactorization: An efficient training method for depthwise convolutions. In: 2018 International Joint Conference on Neural Networks (IJCNN), pp. 1\u20138 (2018). IEEE","DOI":"10.1109\/IJCNN.2018.8489312"},{"key":"200_CR38","doi-asserted-by":"crossref","unstructured":"Real, E., Aggarwal, A., Huang, Y., Le, Q.V.: Regularized evolution for image classifier architecture search. In: Proceedings of the Aaai Conference on Artificial Intelligence, vol. 33, pp. 4780\u20134789 (2019)","DOI":"10.1609\/aaai.v33i01.33014780"},{"key":"200_CR39","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: Unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779\u2013788 (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"200_CR40","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M.: Imagenet large scale visual recognition challenge. Int. J. Comput. Vision 115, 211\u2013252 (2015)","journal-title":"Int. J. Comput. Vision"},{"key":"200_CR41","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.-C.: Mobilenetv2: Inverted residuals and linear bottlenecks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4510\u20134520 (2018)","DOI":"10.1109\/CVPR.2018.00474"},{"key":"200_CR42","unstructured":"Shoeybi, M., Patwary, M., Puri, R., LeGresley, P., Casper, J., Catanzaro, B.: Megatron-lm: Training multi-billion parameter language models using model parallelism. arXiv:1909.08053 (2019)"},{"key":"200_CR43","doi-asserted-by":"crossref","unstructured":"Srinivas, A., Lin, T.-Y., Parmar, N., Shlens, J., Abbeel, P., Vaswani, A.: Bottleneck transformers for visual recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16519\u201316529 (2021)","DOI":"10.1109\/CVPR46437.2021.01625"},{"key":"200_CR44","unstructured":"Sun, Y., Wang, S., Feng, S., Ding, S., Pang, C., Shang, J., Liu, J., Chen, X., Zhao, Y., Lu, Y., et\u00a0al.: Ernie 3.0: Large-scale knowledge enhanced pre-training for language understanding and generation. arXiv:2107.02137 (2021)"},{"key":"200_CR45","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., Rabinovich, A.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1\u20139 (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"200_CR46","doi-asserted-by":"crossref","unstructured":"Tan, M., Chen, B., Pang, R., Vasudevan, V., Sandler, M., Howard, A., Le, Q.V.: Mnasnet: Platform-aware neural architecture search for mobile. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2820\u20132828 (2019)","DOI":"10.1109\/CVPR.2019.00293"},{"key":"200_CR47","unstructured":"Tan, M., Le, Q.: Efficientnet: Rethinking model scaling for convolutional neural networks. In: International Conference on Machine Learning, pp. 6105\u20136114 (2019). PMLR"},{"key":"200_CR48","unstructured":"Thompson, N.C., Greenewald, K., Lee, K., Manso, G.F.: The computational limits of deep learning. arXiv:2007.0555810 (2020)"},{"key":"200_CR49","doi-asserted-by":"crossref","unstructured":"Vasudevan, A., Anderson, A., Gregg, D.: Parallel multi channel convolution using general matrix multiplication. In: 2017 IEEE 28th International Conference on Application-specific Systems, Architectures and Processors (ASAP), pp. 19\u201324 (2017). IEEE","DOI":"10.1109\/ASAP.2017.7995254"},{"key":"200_CR50","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., Polosukhin, I.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30, (2017)"},{"key":"200_CR51","doi-asserted-by":"crossref","unstructured":"Wang, G., Lin, Y., Yi, W.: Kernel fusion: An effective method for better power efficiency on multithreaded gpu. In: 2010 IEEE\/ACM Int\u2019l Conference on Green Computing and Communications & Int\u2019l Conference on Cyber, Physical and Social Computing, pp. 344\u2013350 (2010). IEEE","DOI":"10.1109\/GreenCom-CPSCom.2010.102"},{"key":"200_CR52","doi-asserted-by":"crossref","unstructured":"Wang, Q., Mei, S., Liu, J., Gong, C.: Parallel convolution algorithm using implicit matrix multiplication on multi-core cpus. In: 2019 International Joint Conference on Neural Networks (ijcnn), pp. 1\u20137 (2019). IEEE","DOI":"10.1109\/IJCNN.2019.8852012"},{"key":"200_CR53","doi-asserted-by":"publisher","first-page":"162","DOI":"10.1016\/j.aiopen.2022.10.002","volume":"3","author":"T Wei","year":"2022","unstructured":"Wei, T., Tian, Y., Wang, Y., Liang, Y., Chen, C.W.: Optimized separable convolution: Yet another efficient convolution operator. AI Open 3, 162\u2013171 (2022)","journal-title":"AI Open"},{"key":"200_CR54","doi-asserted-by":"crossref","unstructured":"Wu, H.-N., Huang, C.-T.: Data locality optimization of depthwise separable convolutions for cnn inference accelerators. In: 2019 Design, Automation & Test in Europe Conference & Exhibition (DATE), pp. 120\u2013125 (2019). IEEE","DOI":"10.23919\/DATE.2019.8715097"},{"key":"200_CR55","doi-asserted-by":"crossref","unstructured":"Xiang, P., Yang, Y., Zhou, H.: Warp-level divergence in gpus: Characterization, impact, and mitigation. In: 2014 IEEE 20th International Symposium on High Performance Computer Architecture (HPCA), pp. 284\u2013295 (2014). IEEE","DOI":"10.1109\/HPCA.2014.6835939"},{"key":"200_CR56","doi-asserted-by":"crossref","unstructured":"Xu, C., Kirk, S.R., Jenkins, S.: Tiling for performance tuning on different models of gpus. In: 2009 Second International Symposium on Information Science and Engineering, pp. 500\u2013504 (2009). IEEE","DOI":"10.1109\/ISISE.2009.60"},{"key":"200_CR57","doi-asserted-by":"crossref","unstructured":"Yan, D., Wang, W., Chu, X.: Optimizing batched winograd convolution on gpus. In: Proceedings of the 25th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, pp. 32\u201344 (2020)","DOI":"10.1145\/3332466.3374520"},{"key":"200_CR58","first-page":"27168","volume":"35","author":"Z Yao","year":"2022","unstructured":"Yao, Z., Yazdani Aminabadi, R., Zhang, M., Wu, X., Li, C., He, Y.: Zeroquant: Efficient and affordable post-training quantization for large-scale transformers. Adv. Neural Inf. Process. Syst. 35, 27168\u201327183 (2022)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"200_CR59","doi-asserted-by":"crossref","unstructured":"Yuan, K., Guo, S., Liu, Z., Zhou, A., Yu, F., Wu, W.: Incorporating convolution designs into visual transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 579\u2013588 (2021)","DOI":"10.1109\/ICCV48922.2021.00062"},{"key":"200_CR60","unstructured":"Zhang, J., Franchetti, F., Low, T.M.: High performance zero-memory overhead direct convolutions. In: International Conference on Machine Learning, pp. 5776\u20135785 (2018). PMLR"},{"key":"200_CR61","unstructured":"Zhao, W.X., Zhou, K., Li, J., Tang, T., Wang, X., Hou, Y., Min, Y., Zhang, B., Zhang, J., Dong, Z., et\u00a0al.: A survey of large language models. arXiv:2303.18223 (2023)"},{"key":"200_CR62","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/2558\/1\/012003","volume":"2558","author":"Q-W Zhou","year":"2023","unstructured":"Zhou, Q.-W., Li, J.-N., Zhao, R.-C., Han, L., Wang, X.: Compilation optimization of dcu-oriented openmp thread scheduling. J Phys Conf Ser 2558, 012003 (2023)","journal-title":"J Phys Conf Ser"},{"key":"200_CR63","doi-asserted-by":"crossref","unstructured":"Zhu, X., Li, J., Liu, Y., Ma, C., Wang, W.: A survey on model compression for large language models. arXiv:2308.07633 (2023)","DOI":"10.1162\/tacl_a_00704"}],"container-title":["CCF Transactions on High Performance Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42514-024-00200-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s42514-024-00200-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42514-024-00200-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,22]],"date-time":"2025-01-22T06:51:20Z","timestamp":1737528680000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s42514-024-00200-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":63,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2024,12]]}},"alternative-id":["200"],"URL":"https:\/\/doi.org\/10.1007\/s42514-024-00200-3","relation":{},"ISSN":["2524-4922","2524-4930"],"issn-type":[{"value":"2524-4922","type":"print"},{"value":"2524-4930","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12]]},"assertion":[{"value":"24 July 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 October 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 December 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"On behalf of all authors, the corresponding author states that there is no Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}