{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T14:54:43Z","timestamp":1764341683421,"version":"3.46.0"},"reference-count":44,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"the Shandong Provincial Natural Science Foundation","award":["ZR2022LZH018","ZR2022LZH018","ZR2022LZH018","ZR2022LZH018","ZR2022LZH018"],"award-info":[{"award-number":["ZR2022LZH018","ZR2022LZH018","ZR2022LZH018","ZR2022LZH018","ZR2022LZH018"]}]},{"name":"the \"Haiyou Plan\" Industrial Leading Talent Support Program; and the Shandong Provincial Key Research and Development Program","award":["2022SFGC0901","2022SFGC0901","2022SFGC0901","2022SFGC0901","2022SFGC0901"],"award-info":[{"award-number":["2022SFGC0901","2022SFGC0901","2022SFGC0901","2022SFGC0901","2022SFGC0901"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Parallel Prog"],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1007\/s10766-025-00806-2","type":"journal-article","created":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T08:02:51Z","timestamp":1763366571000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["MICPAT: Micro-Architecture Independent Characteristics Profiling Analysis Tool for GPU Programs"],"prefix":"10.1007","volume":"53","author":[{"given":"Peng","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kaiyuan","family":"Qi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhibin","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guangfeng","family":"Su","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,11,14]]},"reference":[{"issue":"2","key":"806_CR1","doi-asserted-by":"publisher","first-page":"140","DOI":"10.1080\/17445760.2023.2173752","volume":"38","author":"A Masola","year":"2023","unstructured":"Masola, A., Capodieci, N.: Optimization strategies for gpus: an overview of architectural approaches. Int. J. Parallel Emergent Distrib. Syst. 38(2), 140\u2013154 (2023). https:\/\/doi.org\/10.1080\/17445760.2023.2173752","journal-title":"Int. J. Parallel Emergent Distrib. Syst."},{"key":"806_CR2","doi-asserted-by":"publisher","unstructured":"Mao, R., Zhang, M., Wang, Y., et al.: An integrated framework for accelerating reactive flow simulation using GPU and machine learning models. Proc. Combust. Inst. 40(1\u20134), 105512 (2024). https:\/\/doi.org\/10.1016\/j.proci.2024.105512","DOI":"10.1016\/j.proci.2024.105512"},{"key":"806_CR3","doi-asserted-by":"publisher","unstructured":"Vieira, J.V.A., Souza, M.A., de Freitas, H.C.: Performance evaluation of intel and AMD memory hierarchies using a Simulation-driven approach with Gem5. In: Anais estendidos do XXIV Simp\u00f3sio Em Sistemas computacionais de Alto desempenho. SBC. pp. 17\u201324 (2023). https:\/\/doi.org\/10.5753\/wscad_estendido.2023.235791","DOI":"10.5753\/wscad_estendido.2023.235791"},{"key":"806_CR4","doi-asserted-by":"publisher","unstructured":"Wang, Q., Li, L., Luo, W., et al.: DSO: A GPU energy efficiency optimizer by fusing dynamic and static Information. arXiv preprint arXiv:2407.13096, (2024). https:\/\/doi.org\/10.48550\/arXiv. 2407.13096","DOI":"10.48550\/arXiv"},{"key":"806_CR5","doi-asserted-by":"publisher","unstructured":"Moses, W.S., Ivanov, I.R., Domke, J., et al.: High-performance gpu-to-cpu transpilation and optimization via high-level parallel constructs. In: Proceedings of the 28th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming, pp. 119\u2013134 (2023). https:\/\/doi.org\/10.1145\/3572848.3577475","DOI":"10.1145\/3572848.3577475"},{"issue":"2","key":"806_CR6","doi-asserted-by":"publisher","first-page":"890","DOI":"10.3390\/en16020890","volume":"16","author":"B Kocot","year":"2023","unstructured":"Kocot, B., Czarnul, P., Proficz, J.: Energy-aware scheduling for high-performance computing systems: a survey. Energies. 16(2), 890 (2023). https:\/\/doi.org\/10.3390\/en16020890","journal-title":"Energies"},{"key":"806_CR7","doi-asserted-by":"publisher","unstructured":"Faqir-Rhazoui, Y., Garc\u00eda, C.: Exploring heterogeneous computing environments: a preliminary analysis of python and SYCL performance. In: Conference on Cloud Computing, Big Data & Emerging Topics, pp. 3\u201316. Springer Nature Switzerland, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-40942-4_1","DOI":"10.1007\/978-3-031-40942-4_1"},{"key":"806_CR8","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2023.3317672","author":"E Pagliari","year":"2023","unstructured":"Pagliari, E., Davoli, L., Ferrari, G.: Harnessing communication heterogeneity: architectural design, analytical modeling, and performance evaluation of an IoT multi-interface gateway. IEEE Internet Things J. (2023). https:\/\/doi.org\/10.1109\/JIOT.2023.3317672","journal-title":"IEEE Internet Things J."},{"issue":"3","key":"806_CR9","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1038\/s42256-022-00463-x","volume":"4","author":"M Pandey","year":"2022","unstructured":"Pandey, M., Fernandez, M., Gentile, F., et al.: The transformational role of GPU computing and deep learning in drug discovery. Nat. Mach. Intell. 4(3), 211\u2013221 (2022). https:\/\/doi.org\/10.1038\/s42256-022-00463-x","journal-title":"Nat. Mach. Intell."},{"issue":"10","key":"806_CR10","doi-asserted-by":"publisher","first-page":"9177","DOI":"10.1109\/JIOT.2022.3233830","volume":"10","author":"S Ki","year":"2023","unstructured":"Ki, S., Byun, G., Cho, K., et al.: Co-optimizing CPU voltage, memory placement, and task offloading for energy-efficient mobile systems[. IEEE Internet Things J. 10(10), 9177\u20139192 (2023). https:\/\/doi.org\/10.1109\/JIOT.2022.3233830","journal-title":"IEEE Internet Things J."},{"key":"806_CR11","doi-asserted-by":"publisher","unstructured":"Esmaili-Dokht, P., Sgherzi, F., Girelli, V.S., et al.: A mess of memory system benchmarking, simulation and application profiling. arXiv preprint arXiv:2405.10170 (2024). https:\/\/doi.org\/10.48550\/arXiv.2405.10170","DOI":"10.48550\/arXiv.2405.10170"},{"issue":"4","key":"806_CR12","doi-asserted-by":"publisher","first-page":"608","DOI":"10.3390\/e25040608","volume":"25","author":"D Pomarico","year":"2023","unstructured":"Pomarico, D., Cosmai, L., Facchi, P., et al.: Dynamical quantum phase transitions of the schwinger model: real-time dynamics on IBM quantum. Entropy. 25(4), 608 (2023). https:\/\/doi.org\/10.3390\/e25040608","journal-title":"Entropy"},{"issue":"2","key":"806_CR13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3649510","volume":"11","author":"S Darche","year":"2024","unstructured":"Darche, S., Dagenais, M.R.: Low-overhead trace collection and profiling on GPU compute kernels. ACM Trans. Parallel Comput. 11(2), 1\u201324 (2024). https:\/\/doi.org\/10.1145\/3649510","journal-title":"ACM Trans. Parallel Comput."},{"issue":"11","key":"806_CR14","doi-asserted-by":"publisher","first-page":"11051","DOI":"10.1109\/TKDE.2023.3235941","volume":"35","author":"L Zou","year":"2023","unstructured":"Zou, L., Zhang, F., Lin, Y., et al.: An efficient data structure for dynamic graph on GPUS. IEEE Trans. Knowl. Data Eng. 35(11), 11051\u201311066 (2023). https:\/\/doi.org\/10.1109\/TKDE.2023.3235941","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"806_CR15","doi-asserted-by":"publisher","unstructured":"Majee, A.: DeepOps & SLURM: your GPU cluster guide. arXiv preprint arXiv:2405.00030 (2024). https:\/\/doi.org\/10.48550\/arXiv.2405.00030","DOI":"10.48550\/arXiv.2405.00030"},{"key":"806_CR16","doi-asserted-by":"publisher","unstructured":"Ukidave, Y., Gong, X., Kaeli, D.: Performance evaluation and optimization mechanisms for inter-operable graphics and computation on gpus. In: Proceedings of Workshop on General Purpose Processing Using GPUs, pp. 37\u201345 (2014). https:\/\/doi.org\/10.1145\/2588768.2576784","DOI":"10.1145\/2588768.2576784"},{"key":"806_CR17","doi-asserted-by":"publisher","unstructured":"Baumann, T.M., Gracia, J., Cudagrind: memory-usage checking for cuda. In: Tools for High Performance Computing 2013: Proceedings of the 7th International Workshop on Parallel Tools for High Performance Computing, September 2013, ZIH, Dresden, Germany, pp. 67\u201378. Springer International Publishing (2014). https:\/\/doi.org\/10.1007\/978-3-319-08144-1_6","DOI":"10.1007\/978-3-319-08144-1_6"},{"key":"806_CR18","doi-asserted-by":"publisher","unstructured":"Alatalo, T., Koskela, T., Pouke, M., et al.: VirtualOulu: collaborative, immersive and extensible 3D city model on the web. In: Proceedings of the 21st International Conference on Web3D Technology, pp. 95\u2013103 (2016). https:\/\/doi.org\/10.1109\/ISPASS.2012.6189206","DOI":"10.1109\/ISPASS.2012.6189206"},{"key":"806_CR19","doi-asserted-by":"publisher","unstructured":"Farooqui, N., Kerr, A., Eisenhauer, G., et al.: Lynx: a dynamic instrumentation system for data-parallel applications on GPGPU architectures. In: 2012 IEEE International Symposium on Performance Analysis of Systems & Software, pp. 58\u201367. IEEE (2012). https:\/\/doi.org\/10.1109\/ISPASS.2012.6189206","DOI":"10.1109\/ISPASS.2012.6189206"},{"key":"806_CR20","unstructured":"Bradley, T.: GPU performance analysis and optimisation. NVIDIA Corporation (2012). https:\/\/people.maths.ox.ac.uk\/gilesm\/cuda\/lecs\/NV_Profiling_lowres.pdf"},{"key":"806_CR21","unstructured":"Upton, D., Hazelwood, K.: Leveraging binary translation for heterogeneous profiling. Microarchitect. Support Binary Transl. (2011). https:\/\/citeseerx.ist.psu.edu\/document?repid=rep1&type=pdf&doi=bc46c8c2e25ea75f8fcd9c428676fa046e075840"},{"key":"806_CR22","doi-asserted-by":"publisher","unstructured":"Leng, J., Hetherington, T., ElTantawy, A., et al.: GPUWattch: Enabling energy optimizations in GPGPUs. ACM SIGARCH Comput. Archit. News. 41(3), 487\u2013498 (2013). https:\/\/doi.org\/10.1145\/2508148.2485964","DOI":"10.1145\/2508148.2485964"},{"key":"806_CR23","doi-asserted-by":"publisher","unstructured":"Zheng, M., Ravi, V.T., Ma, W., et al.: Gmprof: A low-overhead, fine-grained profiling approach for gpu programs. In: 2012 19th International Conference on High Performance Computing. pp. 1\u201310. IEEE (2012). https:\/\/doi.org\/10.1109\/HiPC.2012.6507475","DOI":"10.1109\/HiPC.2012.6507475"},{"key":"806_CR24","unstructured":"Kurylev, A.: Profiling Heterogeneous Computing Performance with VTune Profiler. Intel. Intel VTune Amplifier. https:\/\/www.intel.com\/content\/www\/us\/en\/developer\/overview.html"},{"key":"806_CR25","doi-asserted-by":"publisher","unstructured":"Otterness, N., Anderson, J.H.: AMD GPUs as an alternative to NVIDIA for supporting real-time workloads. In: 32nd Euromicro Conference on Real-Time Systems (ECRTS 2020). Schloss Dagstuhl-Leibniz-Zentrum f\u00fcr Informatik (2020). https:\/\/doi.org\/10.4230\/LIPIcs.ECRTS.2020.10","DOI":"10.4230\/LIPIcs.ECRTS.2020.10"},{"key":"806_CR26","doi-asserted-by":"publisher","unstructured":"Richter, S.R., Vineet, V., Roth, S., et al.: Playing for data: Ground truth from computer games. In: Computer Vision\u2013ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11\u201314, 2016, Proceedings, Part II 14. pp. 102\u2013118. Springer International Publishing (2016). https:\/\/doi.org\/10.1007\/978-3-319-46475-6_7","DOI":"10.1007\/978-3-319-46475-6_7"},{"key":"806_CR27","doi-asserted-by":"publisher","unstructured":"Lin, W.C., McIntosh-Smith, S., Deakin, T.: Preliminary report: Initial evaluation of StdPar implementations on AMD GPUs for HPC. (2024). https:\/\/doi.org\/10.48550\/arXiv.2401.02680","DOI":"10.48550\/arXiv.2401.02680"},{"key":"806_CR28","doi-asserted-by":"publisher","unstructured":"Shafie Khorassani, K., Hashmi, J., Chu, C.H., et al.: Designing a ROCm-aware MPI library for AMD GPUs: early experiences. In: International Conference on High Performance Computing, pp. 118\u2013136. Springer International Publishing, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-78713-4_7","DOI":"10.1007\/978-3-030-78713-4_7"},{"key":"806_CR29","doi-asserted-by":"publisher","unstructured":"Hari, S.K.S., Tsai, T., Stephenson, M., et al.: SASSIFI: An architecture-level fault injection tool for GPU application resilience evaluation. In: 2017 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS). pp. 249\u2013258. IEEE (2017). https:\/\/doi.org\/10.1109\/ISPASS.2017.7975296","DOI":"10.1109\/ISPASS.2017.7975296"},{"key":"806_CR30","doi-asserted-by":"publisher","unstructured":"Stephenson, M., Sastry Hari, S.K., Lee, Y., et al.: Flexible software profiling of gpu architectures. In: Proceedings of the 42nd Annual International Symposium on Computer Architecture. pp. 185\u2013197 (2015). https:\/\/doi.org\/10.1145\/2749469.2750375","DOI":"10.1145\/2749469.2750375"},{"key":"806_CR31","doi-asserted-by":"publisher","unstructured":"Gu, J., Liu, H., Zhou, Y., et al.: Deepprof: performance analysis for deep learning applications via mining Gpu execution patterns. (2017). https:\/\/doi.org\/10.48550\/arXiv.1707.03750","DOI":"10.48550\/arXiv.1707.03750"},{"key":"806_CR32","doi-asserted-by":"publisher","unstructured":"Zhou, K., Hao, Y., Mellor-Crummey, J., et al.: GVProf: A value profiler for GPU-based clusters. In: SC20: International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 1\u201316. IEEE (2020). https:\/\/doi.org\/10.1109\/SC41405.2020.00093","DOI":"10.1109\/SC41405.2020.00093"},{"key":"806_CR33","unstructured":"Gleeson, J., Gabel, M., Pekhimenko, G., et al.: RL-Scope: Cross-stack profiling for deep reinforcement learning workloads. Proc. Mach. Learn. Syst. 3, 783\u2013799 (2021). https:\/\/proceedings.mlsys.org\/paper_files\/paper\/2021\/file\/676638b91bc90529e09b22e58abb01d6-Paper.pdf"},{"key":"806_CR34","doi-asserted-by":"publisher","unstructured":"Buelow, M., Guthe, S., Fellner, D.W.: \/\/Computer Graphics Forum. 41(7), 227\u2013235 (2022). https:\/\/doi.org\/10.1111\/cgf.14671 Fine-Grained Memory Profiling of GPGPU Kernels","DOI":"10.1111\/cgf.14671"},{"key":"806_CR35","doi-asserted-by":"publisher","unstructured":"Shin, C., Yang, G., Yoo, Y., et al.: Xonar: Profiling-based job orderer for distributed deep learning. In: 2022 IEEE 15th International Conference on Cloud Computing (CLOUD), pp. 112\u2013114. IEEE (2022). https:\/\/doi.org\/10.1109\/CLOUD55607.2022.00030","DOI":"10.1109\/CLOUD55607.2022.00030"},{"key":"806_CR36","doi-asserted-by":"publisher","unstructured":"Shende, S., Chaimov, N., Malony, A., et al.: Multi-level performance instrumentation for Kokkos applications using TAU. In: 2019 IEEE\/ACM International Workshop on Programming and Performance Visualization Tools (ProTools), pp. 48\u201354. IEEE (2019). https:\/\/doi.org\/10.1109\/ProTools49597.2019.00012","DOI":"10.1109\/ProTools49597.2019.00012"},{"key":"806_CR37","unstructured":"Snider, D., Chevalier, F., Pekhimenko, G.: Hotline Profiler: Automatic annotation and a multi-scale timeline for visualizing time-use in DNN Training. Proc. Mach. Learn. Syst. 5 (2023). https:\/\/proceedings.mlsys.org\/paper_files\/paper\/2023\/hash\/347330dd540c72b2c9b0cc304bcf43c6-Abstract-mlsys2023.html"},{"key":"806_CR38","doi-asserted-by":"publisher","unstructured":"Cohen, R., Wang, T., Cohen, R., et al.: The low-power design of android application and intel graphics performance analyzers (Intel GPA): assisted power optimization. Android Application Dev. Intel\u00ae Platf. pp. 445\u2013482 (2014). https:\/\/doi.org\/10.1007\/978-1-4842-0100-8_13","DOI":"10.1007\/978-1-4842-0100-8_13"},{"key":"806_CR39","doi-asserted-by":"publisher","unstructured":"Umar, M., Jong, M., PTI-GPU: Kernel Profiling and Assessment on Intel GPUs. In: Proceedings of the SC\u201923 Workshops of The International Conference on High Performance Computing, Network, Storage, and Analysis, pp. 681\u2013684 (2023). https:\/\/doi.org\/10.1145\/3624062.3624144","DOI":"10.1145\/3624062.3624144"},{"key":"806_CR40","doi-asserted-by":"publisher","unstructured":"Hao, Y., Jain, N., Van der Wijngaart, R., et al.: Drgpu: a top-down profiler for gpu applications. In: Proceedings of the 2023 ACM\/SPEC International Conference on Performance Engineering, pp. 43\u201353 (2023). https:\/\/doi.org\/10.1145\/3578244.3583736","DOI":"10.1145\/3578244.3583736"},{"key":"806_CR41","doi-asserted-by":"publisher","unstructured":"Che, S., Boyer, M., Meng, J., et al.: Rodinia: A benchmark suite for heterogeneous computing. In: 2009 IEEE International Symposium on Workload Characterization (IISWC), pp. 44\u201354. IEEE (2009). https:\/\/doi.org\/10.1109\/IISWC.2009.5306797","DOI":"10.1109\/IISWC.2009.5306797"},{"key":"806_CR42","unstructured":"Stratton, J.A., Rodrigues, C., Sung, I.J., et al.: Parboil: A revised benchmark suite for scientific and commercial throughput computing. Cent. Reliable High-Perform Comput. 127(7.2). (2012). http:\/\/impact.crhc.illinois.edu\/Shared\/Docs\/impact-12-01.parboil.pdf"},{"issue":"19","key":"806_CR43","doi-asserted-by":"publisher","first-page":"4124","DOI":"10.3390\/electronics12194124","volume":"12","author":"P Wang","year":"2023","unstructured":"Wang, P., Yu, Z.: RayBench: an advanced NVIDIA-Centric GPU rendering benchmark suite for optimal performance analysis. Electronics 12(19), 4124 (2023). https:\/\/doi.org\/10.3390\/electronics12194124","journal-title":"Electronics"},{"key":"806_CR44","doi-asserted-by":"publisher","unstructured":"Meng, F.Y., Zhang, Z.: Research on interior scene design based on Cinema4d technology. J. Phys. Conf. Ser. IOP Publishing, 1848(1): 012086. (2021). https:\/\/doi.org\/10.1088\/1742-6596\/1848\/1\/012086","DOI":"10.1088\/1742-6596\/1848\/1\/012086"}],"container-title":["International Journal of Parallel Programming"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10766-025-00806-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10766-025-00806-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10766-025-00806-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T14:49:46Z","timestamp":1764341386000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10766-025-00806-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":44,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2025,10]]}},"alternative-id":["806"],"URL":"https:\/\/doi.org\/10.1007\/s10766-025-00806-2","relation":{},"ISSN":["0885-7458","1573-7640"],"issn-type":[{"type":"print","value":"0885-7458"},{"type":"electronic","value":"1573-7640"}],"subject":[],"published":{"date-parts":[[2025,10]]},"assertion":[{"value":"11 November 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 October 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 November 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing Interests"}}],"article-number":"28"}}