{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T08:13:11Z","timestamp":1783498391378,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":40,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T00:00:00Z","timestamp":1778025600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,5,6]]},"DOI":"10.1145\/3811257.3811260","type":"proceedings-article","created":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T06:38:57Z","timestamp":1783492737000},"page":"1-12","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Comparing the Performance of Heterogeneous Conjugate Gradient and Cholesky Solvers on Various Hardware Using SYCL"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-1762-8429","authenticated-orcid":false,"given":"Tim","family":"Th\u00fcring","sequence":"first","affiliation":[{"name":"University of Stuttgart, Stuttgart, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9939-9044","authenticated-orcid":false,"given":"Alexander","family":"Strack","sequence":"additional","affiliation":[{"name":"University of Stuttgart, Stuttgart, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4360-0212","authenticated-orcid":false,"given":"Dirk","family":"Pfl\u00fcger","sequence":"additional","affiliation":[{"name":"University of Stuttgart, Stuttgart, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,7]]},"reference":[{"key":"e_1_3_3_2_2_2","doi-asserted-by":"crossref","unstructured":"Ahmad Abdelfattah Natalie Beams Robert Carson Pieter Ghysels Tzanio Kolev Thomas Stitt Arturo Vargas Stanimire Tomov and Jack Dongarra. 2024. MAGMA: Enabling exascale performance with accelerated BLAS and LAPACK for diverse GPU architectures. The International Journal of High Performance Computing Applications 38 5 (2024) 468\u2013490. doi:10.1177\/10943420241261960","DOI":"10.1177\/10943420241261960"},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISPA.2012.16"},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/3388333.3388658"},{"key":"e_1_3_3_2_5_2","unstructured":"AMD. 2022. AMD INSTINCT\u2122 MI210 ACCELERATOR. https:\/\/www.amd.com\/content\/dam\/amd\/en\/documents\/instinct-business-docs\/product-briefs\/instinct-mi210-brochure.pdf"},{"key":"e_1_3_3_2_6_2","unstructured":"AMD. 2023. AMD EPYC\u2122 9004 SERIES PROCESSORS. https:\/\/www.amd.com\/content\/dam\/amd\/en\/documents\/epyc-business-docs\/datasheets\/amd-epyc-9004-series-processors-datasheet.pdf"},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/3529538.3529993"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"crossref","unstructured":"Ravi Bhargava and Kai Troester. 2024. AMD Next-Generation \u201cZen 4\u201d Core and 4th Gen AMD EPYC Server CPUs. IEEE Micro 44 3 (2024) 8\u201317. doi:10.1109\/MM.2024.3375070","DOI":"10.1109\/MM.2024.3375070"},{"key":"e_1_3_3_2_9_2","unstructured":"Salvatore Cali William Detmold Grzegorz Korcyl Piotr Korcyl and Phiala Shanahan. 2021. Implementation of the conjugate gradient algorithm for heterogeneous systems. doi:10.48550\/arXiv.2111.14958"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"crossref","unstructured":"S. Chakraborty and B. Bhattacharyya. 2002. An efficient 3D stochastic finite element method. International Journal of Solids and Structures 39 9 (2002) 2465\u20132475. doi:10.1016\/S0020-7683(02)00080-X","DOI":"10.1016\/S0020-7683(02)00080-X"},{"key":"e_1_3_3_2_11_2","unstructured":"DeepL SE. 2026. DeepL Translator. https:\/\/www.deepl.com\/translator. Accessed: 2026-01-14."},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"crossref","unstructured":"Jack Dongarra Mark Gates Azzam Haidar Jakub Kurzak Piotr Luszczek Panruo Wu Ichitaro Yamazaki Asim Yarkhan Maksims Abalenkovs Negin Bagherpour Sven Hammarling Jakub \u0160\u00edstek David Stevens Mawussi Zounon and Samuel\u00a0D. Relton. 2019. PLASMA: Parallel Linear Algebra Software for Multicore Using OpenMP. ACM Trans. Math. Softw. 45 2 Article 16 (2019) 35\u00a0pages. doi:10.1145\/3264491","DOI":"10.1145\/3264491"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46079-6_37"},{"key":"e_1_3_3_2_14_2","volume-title":"Optimizing Parallel Reduction in CUDA","author":"Harris Mark","unstructured":"Mark Harris. [n. d.]. Optimizing Parallel Reduction in CUDA. https:\/\/developer.download.nvidia.com\/assets\/cuda\/files\/reduction.pdf"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-97196-9_7"},{"key":"e_1_3_3_2_16_2","volume-title":"Replication Data for: GPRat: Gaussian Process Regression with Asynchronous Tasks","author":"Helmann Maksim","year":"2025","unstructured":"Maksim Helmann, Alexander Strack, and Dirk Pfl\u00fcger. 2025. Replication Data for: GPRat: Gaussian Process Regression with Asynchronous Tasks. doi:10.18419\/DARUS-4743"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"crossref","unstructured":"Magnus\u00a0R Hestenes and Eduard Stiefel. 1952. Methods of conjugate gradients for solving linear systems. Journal of research of the National Bureau of Standards 49 6 (1952) 409\u2013436. https:\/\/nvlpubs.nist.gov\/nistpubs\/jres\/049\/jresv49n6p409_a1b.pdf","DOI":"10.6028\/jres.049.044"},{"key":"e_1_3_3_2_18_2","unstructured":"Intel. 2019. Intel\u00ae Core\u2122 i9-10980XE Extreme Edition Processor. https:\/\/www.intel.com\/content\/www\/us\/en\/products\/sku\/198017\/intel-core-i910980xe-extreme-edition-processor-24-75m-cache-3-00-ghz\/specifications.html"},{"key":"e_1_3_3_2_19_2","unstructured":"Intel. 2024. Intel\u00ae Arc\u2122 B580 Grafik. https:\/\/www.intel.de\/content\/www\/de\/de\/products\/sku\/241598\/intel-arc-b580-graphics\/specifications.html"},{"key":"e_1_3_3_2_20_2","volume-title":"SYCL - C++ Programming for Heterogeneous Parallel Computing","unstructured":"Khronos-Group. [n. d.]. SYCL - C++ Programming for Heterogeneous Parallel Computing. https:\/\/www.khronos.org\/sycl\/"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-21021-6"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"crossref","unstructured":"Jens Lang and Gudula R\u00fcnger. 2013. Dynamic Distribution of Workload between CPU and GPU for a Parallel Conjugate Gradient Method in an Adaptive FEM. Procedia Computer Science 18 (2013) 299\u2013308. doi:10.1016\/j.procs.2013.05.1932013 International Conference on Computational Science.","DOI":"10.1016\/j.procs.2013.05.193"},{"key":"e_1_3_3_2_23_2","unstructured":"Hatem Ltaief Stanimire Tomov Rajib Nath and Jack Dongarra. 2010. Hybrid multicore cholesky factorization with multiple gpu accelerators. (2010). https:\/\/www.netlib.org\/utk\/people\/JD\/JackDongarra\/PAPERS\/hybrid-multicore-cholesky.pdf"},{"key":"e_1_3_3_2_24_2","volume-title":"Proceeding of the 2011 International Conference on Power System Transients (IPST-2011), Delft, The Netherlands","author":"Maguire Trevor","year":"2011","unstructured":"Trevor Maguire. 2011. Multi-processor cholesky decomposition of conductance matrices. In Proceeding of the 2011 International Conference on Power System Transients (IPST-2011), Delft, The Netherlands. https:\/\/www.ipstconf.org\/papers\/Proc_IPST2011\/11IPST106.pdf"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/2063384.2063392"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87809-2_27"},{"key":"e_1_3_3_2_27_2","unstructured":"NVIDIA. 2021. NVIDIA AMPERE GA102 GPU ARCHITECTURE. https:\/\/www.nvidia.com\/content\/PDF\/nvidia-ampere-ga-102-gpu-architecture-whitepaper-v2.pdf"},{"key":"e_1_3_3_2_28_2","unstructured":"NVIDIA. 2022. NVIDIA A30 TENSOR CORE GPU. https:\/\/www.nvidia.com\/content\/dam\/en-zz\/Solutions\/data-center\/products\/a30-gpu\/pdf\/a30-datasheet.pdf"},{"key":"e_1_3_3_2_29_2","unstructured":"OpenAI. 2025. ChatGPT 5. https:\/\/openai.com\/chatgpt. Accessed: 2026-01-14."},{"key":"e_1_3_3_2_30_2","unstructured":"Superhuman Platform. 2026. Grammarly. https:\/\/www.grammarly.com\/. Accessed: 2026-01-14."},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-28924-8"},{"key":"e_1_3_3_2_32_2","unstructured":"Jonathan\u00a0Richard Shewchuk. 1994. An Introduction to the Conjugate Gradient Method Without the Agonizing Pain. (1994)."},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"crossref","unstructured":"Fengguang Song and Jack Dongarra. 2015. A scalable approach to solving dense linear algebra problems on hybrid CPU-GPU systems. Concurrency and Computation: Practice and Experience 27 14 (2015) 3702\u20133723. doi:10.1002\/cpe.3403","DOI":"10.1002\/cpe.3403"},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/2304576.2304625"},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1145\/2063384.2063431"},{"key":"e_1_3_3_2_36_2","unstructured":"Tim Th\u00fcring. 2025. Heterogeneous Solvers for Linear Systems with Symmetric Positive-Definite Matrices Using SYCL. Master Thesis. University of Stuttgart."},{"key":"e_1_3_3_2_37_2","unstructured":"Manasi Tiwari and Sathish Vadhiyar. 2021. Efficient executions of Pipelined Conjugate Gradient Method on Heterogeneous Architectures. doi:10.48550\/arXiv.2105.06176"},{"key":"e_1_3_3_2_38_2","volume-title":"Magma library","author":"Tomov S","year":"2009","unstructured":"S Tomov, J Dongarra, V Volkov, and J Demmel. 2009. Magma library. https:\/\/icl.utk.edu\/projectsfiles\/magma\/docs\/magma.pdf"},{"key":"e_1_3_3_2_39_2","volume-title":"oneAPI Math Library (oneMath)","author":"Foundation Unified Acceleration (UXL)","unstructured":"Unified Acceleration (UXL) Foundation. [n. d.]. oneAPI Math Library (oneMath). https:\/\/github.com\/uxlfoundation\/oneMath"},{"key":"e_1_3_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW55747.2022.00138"},{"key":"e_1_3_3_2_41_2","volume-title":"The science of programming matrix computations (1 ed.)","author":"De\u00a0Geijn Robert\u00a0A Van","year":"2007","unstructured":"Robert\u00a0A Van De\u00a0Geijn and Enrique\u00a0S Quintana-Ort\u00ed. 2007. The science of programming matrix computations (1 ed.). https:\/\/www.cs.utexas.edu\/\u00a0rvdg\/tmp\/TSoPMC.pdf"}],"event":{"name":"IWOCL '26: International Workshop on OpenCL and SYCL","location":"Heilbronn Germany","acronym":"IWOCL '26"},"container-title":["Proceedings of the International Workshop on OpenCL and SYCL"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3811257.3811260","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T07:13:36Z","timestamp":1783494816000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3811257.3811260"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,6]]},"references-count":40,"alternative-id":["10.1145\/3811257.3811260","10.1145\/3811257"],"URL":"https:\/\/doi.org\/10.1145\/3811257.3811260","relation":{},"subject":[],"published":{"date-parts":[[2026,5,6]]},"assertion":[{"value":"2026-07-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}