{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T11:46:04Z","timestamp":1785843964940,"version":"3.56.0"},"publisher-location":"Cham","reference-count":37,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031998560","type":"print"},{"value":"9783031998577","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T00:00:00Z","timestamp":1755907200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T00:00:00Z","timestamp":1755907200000},"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":[[2026]]},"DOI":"10.1007\/978-3-031-99857-7_9","type":"book-chapter","created":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T05:16:54Z","timestamp":1755839814000},"page":"118-131","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["CacheC: LLM-Based GPU Cache Management to\u00a0Enhance Kernel Concurrency"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-5711-3110","authenticated-orcid":false,"given":"Mengyue","family":"Xi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8672-9817","authenticated-orcid":false,"given":"Jingyi","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3507-4299","authenticated-orcid":false,"given":"Xianwei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,8,23]]},"reference":[{"key":"9_CR1","unstructured":"https:\/\/www.amd.com\/zh-cn\/products\/graphics\/desktops\/radeon\/7000-series\/amd-radeon-rx-7900xtx.html"},{"key":"9_CR2","unstructured":"https:\/\/www.amd.com\/zh-cn\/products\/graphics\/desktops\/radeon\/6000-series\/amd-radeon-rx-6900-xt.html"},{"key":"9_CR3","doi-asserted-by":"crossref","unstructured":"Pai, S., et\u00a0al.: Improving GPGPU concurrency with elastic kernels. In: ACM SIGARCH Computer Architecture News (2013)","DOI":"10.1145\/2451116.2451160"},{"key":"9_CR4","doi-asserted-by":"crossref","unstructured":"Wen, Y., et\u00a0al.: Merge or separate?: multi-job scheduling for opencl kernels on CPU\/GPU platforms. In: Proceedings of the General Purpose GPUs (2017)","DOI":"10.1145\/3038228.3038235"},{"key":"9_CR5","doi-asserted-by":"crossref","unstructured":"Dai, H., et\u00a0al.: Accelerate GPU concurrent kernel execution by mitigating memory pipeline stalls. In: 2018 HPCA (2018)","DOI":"10.1109\/HPCA.2018.00027"},{"key":"9_CR6","doi-asserted-by":"crossref","unstructured":"Wu, W., et\u00a0al.: TurboMGNN: improving concurrent GNN training tasks on GPU with fine-grained kernel fusion (2023)","DOI":"10.1109\/TPDS.2023.3267943"},{"key":"9_CR7","doi-asserted-by":"crossref","unstructured":"Jiao, Q., et\u00a0al.: Improving GPGPU energy-efficiency through concurrent kernel execution and DVFS. In: 2015 CGO (2015)","DOI":"10.1109\/CGO.2015.7054182"},{"key":"9_CR8","doi-asserted-by":"crossref","unstructured":"Yu, L., et\u00a0al.: Moka: model-based concurrent kernel analysis. In: 2017 IEEE International Symposium on Workload Characterization (IISWC) (2017)","DOI":"10.1109\/IISWC.2017.8167777"},{"key":"9_CR9","doi-asserted-by":"crossref","unstructured":"Wen, Y., et\u00a0al.: MaxPair: enhance OpenCL concurrent kernel execution by weighted maximum matching (2018)","DOI":"10.1145\/3180270.3180272"},{"key":"9_CR10","doi-asserted-by":"publisher","first-page":"766","DOI":"10.1109\/TPDS.2019.2944602","volume":"31","author":"SK Shekofteh","year":"2020","unstructured":"Shekofteh, S.K., et al.: cCUDA: Effective co-scheduling of concurrent kernels on gpus. IEEE Trans. Parallel Distrib. Syst. 31, 766\u2013788 (2020)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"9_CR11","doi-asserted-by":"crossref","unstructured":"L\u00f3pez-Albelda, B., et\u00a0al.: Flexsched: efficient scheduling techniques for concurrent kernel execution on gpus. J. Supercomput. (2022)","DOI":"10.1007\/s11227-021-03819-z"},{"key":"9_CR12","doi-asserted-by":"crossref","unstructured":"Shobaki, G., et\u00a0al.: Optimizing occupancy and ILP on the GPU using a combinatorial approach. In: CGO (2020)","DOI":"10.1145\/3368826.3377918"},{"key":"9_CR13","doi-asserted-by":"crossref","unstructured":"Alizadeh, N.B., et\u00a0al.: Multi-objective concurrent kernel scheduling for multi-GPU systems. In: 2024 ICEE (2024)","DOI":"10.1109\/ICEE63041.2024.10667973"},{"key":"9_CR14","doi-asserted-by":"crossref","unstructured":"Adufu, T., et\u00a0al.: L2 cache access pattern analysis using static profiling of an application. In: 2023 COMPSAC (2023)","DOI":"10.1109\/COMPSAC57700.2023.00022"},{"key":"9_CR15","unstructured":"Adufu, T., et\u00a0al.: Optimizing performance using gpu cache data residency based on application\u2019s access patterns. In: 2023 APNOMS (2023)"},{"key":"9_CR16","doi-asserted-by":"crossref","unstructured":"Xi, M., et\u00a0al.: Mpache: interaction aware multi-level cache bypassing on gpus. In: ASPDAC 2025 (2025)","DOI":"10.1145\/3658617.3697568"},{"key":"9_CR17","doi-asserted-by":"crossref","unstructured":"Jadidi, A., et\u00a0al.: Selective caching: avoiding performance valleys in massively parallel architectures (2020)","DOI":"10.1109\/PDP50117.2020.00051"},{"key":"9_CR18","doi-asserted-by":"crossref","unstructured":"Do, C.T., et\u00a0al.: Aggressive GPU cache bypassing with monolithic 3D-based NoC. J. Supercomput. (2023)","DOI":"10.1007\/s11227-022-04878-6"},{"key":"9_CR19","doi-asserted-by":"crossref","unstructured":"Xu, X., et\u00a0al.: ATA-cache: contention mitigation for GPU shared L1 cache with aggregated tag array (2024)","DOI":"10.1109\/TCAD.2023.3337192"},{"key":"9_CR20","doi-asserted-by":"crossref","unstructured":"Hadi, M.U., et\u00a0al.: A survey on large language models: applications, challenges, limitations, and practical usage. Authorea Preprints (2023)","DOI":"10.36227\/techrxiv.23589741.v1"},{"key":"9_CR21","doi-asserted-by":"crossref","unstructured":"Zhai, Q., Zhang, Z., Xiao, R.: Llm based end-to-end branch predictor optimization generator. In: ASAP (2024)","DOI":"10.1109\/ASAP61560.2024.00050"},{"key":"9_CR22","doi-asserted-by":"crossref","unstructured":"Long, Y., et\u00a0al.: Discuss before moving: visual language navigation via multi-expert discussions (2023)","DOI":"10.1109\/ICRA57147.2024.10611565"},{"key":"9_CR23","unstructured":"Sahoo, P., et\u00a0al.: A systematic survey of prompt engineering in large language models: techniques and applications. arXiv preprint arXiv:2402.07927 (2024)"},{"key":"9_CR24","unstructured":"AMD RDNA Whitepaper. https:\/\/www.amd.com\/system\/files\/documents\/rdna-whitepaper.pdf"},{"key":"9_CR25","unstructured":"NVIDIA Ampere GPU Architecture Tuning Guide. https:\/\/docs.nvidia.com\/cuda\/ampere-tuning-guide\/index.html"},{"key":"9_CR26","unstructured":"Syntax of AMDGPU Instruction Modifiers. https:\/\/llvm.org\/docs\/AMDGPUModifierSyntax.html"},{"key":"9_CR27","doi-asserted-by":"crossref","unstructured":"Jin, Z., et\u00a0al.: A benchmark suite for improving performance portability of the sycl programming model. In: 2023 ISPASS (2023)","DOI":"10.1109\/ISPASS57527.2023.00041"},{"key":"9_CR28","doi-asserted-by":"crossref","unstructured":"Che, S., et\u00a0al.: Rodinia: a benchmark suite for heterogeneous computing. In: 2009 IEEE International Symposium on Workload Characterization (IISWC) (2009)","DOI":"10.1109\/IISWC.2009.5306797"},{"key":"9_CR29","unstructured":"Stratton, J.A., et al.: Parboil: a revised benchmark suite for scientific and commercial throughput computing (2012)"},{"key":"9_CR30","unstructured":"Hello GPT-4o. https:\/\/openai.com\/index\/hello-gpt-4o\/"},{"key":"9_CR31","unstructured":"HIP Runtime API Reference: Stream Management"},{"key":"9_CR32","unstructured":"NVIDIA CUDA Toolkit. https:\/\/developer.nvidia.com\/cuda-toolkit"},{"key":"9_CR33","unstructured":"rocm_smi_lib. https:\/\/github.com\/ROCm\/rocm_smi_lib"},{"key":"9_CR34","unstructured":"NVIDIA PTX ISA 8.3. https:\/\/docs.nvidia.com\/cuda\/parallel-thread-execution\/\/#cache-operators"},{"key":"9_CR35","doi-asserted-by":"crossref","unstructured":"Zhao, H., et\u00a0al.: Tacker: tensor-CUDA core kernel fusion for improving the GPU utilization while ensuring QoS. In: 2022 HPCA (2022)","DOI":"10.1109\/HPCA53966.2022.00064"},{"key":"9_CR36","doi-asserted-by":"crossref","unstructured":"Sun, H., et\u00a0al.: Ncache: a machine-learning cache management scheme for computational ssds. TCAD (2023)","DOI":"10.1109\/TCAD.2022.3208769"},{"key":"9_CR37","unstructured":"Kim, et\u00a0al.: New two-level L1 data cache bypassing technique for high performance GPUs. J. Inf. Process. Syst. (2021)"}],"container-title":["Lecture Notes in Computer Science","Euro-Par 2025: Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-99857-7_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T11:19:56Z","timestamp":1785842396000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-99857-7_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,23]]},"ISBN":["9783031998560","9783031998577"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-99857-7_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,23]]},"assertion":[{"value":"23 August 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","label":"Disclosure of Interests","group":{"name":"EthicsHeading","label":"Ethics"}},{"value":"Euro-Par","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Parallel Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Dresden","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 April 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 April 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"europar2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2025.euro-par.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}