{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,7,20]],"date-time":"2024-07-20T15:40:21Z","timestamp":1721490021981},"reference-count":161,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100002809","name":"Generalitat de Catalunya","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000780","name":"European Union","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100014440","name":"Gobierno de Espa\u00f1a Ministerio de Ciencia, Innovaci\u00f3n y Universidades","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100014440","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003030","name":"AGAUR","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003030","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Journal of Parallel and Distributed Computing"],"published-print":{"date-parts":[[2024,10]]},"DOI":"10.1016\/j.jpdc.2024.104941","type":"journal-article","created":{"date-parts":[[2024,6,17]],"date-time":"2024-06-17T15:41:29Z","timestamp":1718638889000},"page":"104941","update-policy":"http:\/\/dx.doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["SpChar: Characterizing the sparse puzzle via decision trees"],"prefix":"10.1016","volume":"192","author":[{"ORCID":"http:\/\/orcid.org\/0000-0001-8319-7491","authenticated-orcid":false,"given":"Francesco","family":"Sgherzi","sequence":"first","affiliation":[]},{"given":"Marco","family":"Siracusa","sequence":"additional","affiliation":[]},{"given":"Ivan","family":"Fernandez","sequence":"additional","affiliation":[]},{"given":"Adri\u00e0","family":"Armejach","sequence":"additional","affiliation":[]},{"given":"Miquel","family":"Moret\u00f3","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.jpdc.2024.104941_br0010","series-title":"2021 58th ACM\/IEEE Design Automation Conference (DAC)","first-page":"799","article-title":"Scaling up HBM efficiency of Top-K SpMV for approximate embedding similarity on FPGAs","author":"Parravicini","year":"2021"},{"key":"10.1016\/j.jpdc.2024.104941_br0020","series-title":"2021 26th Asia and South Pacific Design Automation Conference (ASP-DAC)","first-page":"378","article-title":"A reduced-precision streaming SpMV architecture for Personalized PageRank on FPGA","author":"Parravicini","year":"2021"},{"issue":"2","key":"10.1016\/j.jpdc.2024.104941_br0030","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1038\/s41588-018-0316-4","article-title":"Fast and accurate genomic analyses using genome graphs","volume":"51","author":"Rakocevic","year":"2019","journal-title":"Nat. Genet."},{"key":"10.1016\/j.jpdc.2024.104941_br0040","series-title":"2012 IEEE Conference on High Performance Extreme Computing","first-page":"1","article-title":"Efficient and scalable computations with sparse tensors","author":"Baskaran","year":"2012"},{"key":"10.1016\/j.jpdc.2024.104941_br0050","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.jpdc.2024.104941_br0060","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"10684","article-title":"High-resolution image synthesis with latent diffusion models","author":"Rombach","year":"2022"},{"key":"10.1016\/j.jpdc.2024.104941_br0070","author":"Sharir"},{"key":"10.1016\/j.jpdc.2024.104941_br0080","author":"Strubell"},{"key":"10.1016\/j.jpdc.2024.104941_br0090","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"3599","article-title":"Effective sparsification of neural networks with global sparsity constraint","author":"Zhou","year":"2021"},{"key":"10.1016\/j.jpdc.2024.104941_br0100","series-title":"2022 IEEE 40th International Conference on Computer Design (ICCD)","first-page":"272","article-title":"Towards sparsification of graph neural networks","author":"Peng","year":"2022"},{"key":"10.1016\/j.jpdc.2024.104941_br0110","first-page":"15216","article-title":"Efficient neural network training via forward and backward propagation sparsification","volume":"34","author":"Zhou","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"1","key":"10.1016\/j.jpdc.2024.104941_br0120","first-page":"10882","article-title":"Sparsity in deep learning: pruning and growth for efficient inference and training in neural networks","volume":"22","author":"Hoefler","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.jpdc.2024.104941_br0130","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1016\/j.micpro.2016.02.015","article-title":"Random access schemes for efficient FPGA SpMV acceleration","volume":"47","author":"Umuroglu","year":"2016","journal-title":"Microprocess. Microsyst."},{"issue":"1","key":"10.1016\/j.jpdc.2024.104941_br0140","doi-asserted-by":"crossref","DOI":"10.1145\/3508041","article-title":"SparseP: towards efficient sparse matrix vector multiplication on real processing-in-memory architectures","volume":"6","author":"Giannoula","year":"2022","journal-title":"Proc. ACM Meas. Anal. Comput. Syst."},{"key":"10.1016\/j.jpdc.2024.104941_br0150","series-title":"2008 International Symposium on Parallel Architectures, Algorithms, and Networks (i-span 2008)","first-page":"19","article-title":"A taxonomy of data prefetching mechanisms","author":"Byna","year":"2008"},{"key":"10.1016\/j.jpdc.2024.104941_br0160","series-title":"2018 IEEE\/ACM Performance Modeling, Benchmarking and Simulation of High Performance Computer Systems (PMBS)","first-page":"33","article-title":"Benchmarking machine learning methods for performance modeling of scientific applications","author":"Malakar","year":"2018"},{"issue":"3","key":"10.1016\/j.jpdc.2024.104941_br0170","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3494523","article-title":"A survey of machine learning for computer architecture and systems","volume":"55","author":"Wu","year":"2022","journal-title":"ACM Comput. Surv."},{"key":"10.1016\/j.jpdc.2024.104941_br0180","author":"Lowe-Power"},{"key":"10.1016\/j.jpdc.2024.104941_br0190","doi-asserted-by":"crossref","DOI":"10.1016\/j.micpro.2022.104599","article-title":"Evaluation of gem5 for performance modeling of ARM Cortex-R based embedded SoCs","volume":"93","author":"Wang","year":"2022","journal-title":"Microprocess. Microsyst."},{"key":"10.1016\/j.jpdc.2024.104941_br0200","series-title":"2018 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)","first-page":"1056","article-title":"Effective machine learning based format selection and performance modeling for SpMV on GPUs","author":"Nisa","year":"2018"},{"key":"10.1016\/j.jpdc.2024.104941_br0210","series-title":"2016 IEEE 22nd International Conference on Parallel and Distributed Systems (ICPADS)","first-page":"894","article-title":"Machine learning approach for the predicting performance of SpMV on GPU","author":"Benatia","year":"2016"},{"issue":"1","key":"10.1016\/j.jpdc.2024.104941_br0220","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1007\/s10766-019-00646-x","article-title":"Characterizing scalability of sparse matrix\u2013vector multiplications on phytium ft-2000+","volume":"48","author":"Chen","year":"2020","journal-title":"Int. J. Parallel Program."},{"issue":"20","key":"10.1016\/j.jpdc.2024.104941_br0230","doi-asserted-by":"crossref","DOI":"10.1002\/cpe.6512","article-title":"Execution-Cache-Memory modeling and performance tuning of sparse matrix-vector multiplication and Lattice quantum chromodynamics on A64FX","volume":"34","author":"Alappat","year":"2022","journal-title":"Concurr. Comput., Pract. Exp."},{"key":"10.1016\/j.jpdc.2024.104941_br0240","series-title":"Templates for the Solution of Linear Systems: Building Blocks for Iterative Methods","author":"Barrett","year":"1994"},{"key":"10.1016\/j.jpdc.2024.104941_br0250","unstructured":"E. jin Im, K. Yelick, Optimizing Sparse Matrix Computations for Register Reuse in SPARSITY, in: Proceedings of the International Conference on Computational Science, in: LNCS, vol. 2073, Springer, pp. 127\u2013136,."},{"issue":"2","key":"10.1016\/j.jpdc.2024.104941_br0260","doi-asserted-by":"crossref","first-page":"428","DOI":"10.1109\/TPDS.2015.2401575","article-title":"Evaluation criteria for sparse matrix storage formats","volume":"27","author":"Langr","year":"2016","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"issue":"3","key":"10.1016\/j.jpdc.2024.104941_br0270","doi-asserted-by":"crossref","first-page":"250","DOI":"10.1145\/355791.355796","article-title":"Two fast algorithms for sparse matrices: multiplication and permuted transposition","volume":"4","author":"Gustavson","year":"1978","journal-title":"ACM Trans. Math. Softw."},{"key":"10.1016\/j.jpdc.2024.104941_br0280","series-title":"SC '07: Proceedings of the 2007 ACM\/IEEE Conference on Supercomputing","first-page":"1","article-title":"Optimization of sparse matrix-vector multiplication on emerging multicore platforms","author":"Williams","year":"2007"},{"key":"10.1016\/j.jpdc.2024.104941_br0290","author":"Beamer"},{"key":"10.1016\/j.jpdc.2024.104941_br0300","series-title":"Proceedings of the 26th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming","first-page":"292","article-title":"Efficiently running SpMV on long vector architectures","author":"G\u00f3mez","year":"2021"},{"key":"10.1016\/j.jpdc.2024.104941_br0310","series-title":"2021 ACM\/IEEE 48th Annual International Symposium on Computer Architecture (ISCA)","first-page":"1069","article-title":"SpZip: architectural support for effective data compression in irregular applications","author":"Yang","year":"2021"},{"key":"10.1016\/j.jpdc.2024.104941_br0320","series-title":"Proceedings of the 52nd Annual IEEE\/ACM International Symposium on Microarchitecture","first-page":"600","article-title":"Smash: co-designing software compression and hardware-accelerated indexing for efficient sparse matrix operations","author":"Kanellopoulos","year":"2019"},{"key":"10.1016\/j.jpdc.2024.104941_br0330","series-title":"Euro-Par 2018: Parallel Processing: 24th International Conference on Parallel and Distributed Computing, Proceedings","first-page":"672","article-title":"Design principles for sparse matrix multiplication on the gpu","author":"Yang","year":"2018"},{"key":"10.1016\/j.jpdc.2024.104941_br0340","series-title":"2022 IEEE International Parallel and Distributed Processing Symposium (IPDPS)","first-page":"952","article-title":"Sparsity-aware tensor decomposition","author":"Kurt","year":"2022"},{"key":"10.1016\/j.jpdc.2024.104941_br0350","author":"Gao"},{"key":"10.1016\/j.jpdc.2024.104941_br0360","author":"Hussain"},{"issue":"OOPSLA","key":"10.1016\/j.jpdc.2024.104941_br0370","doi-asserted-by":"crossref","DOI":"10.1145\/3133901","article-title":"The tensor algebra compiler","volume":"1","author":"Kjolstad","year":"2017","journal-title":"Proc. ACM Program. Lang."},{"key":"10.1016\/j.jpdc.2024.104941_br0380","article-title":"On spectral clustering: analysis and an algorithm","volume":"14","author":"Ng","year":"2001","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"1","key":"10.1016\/j.jpdc.2024.104941_br0390","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1137\/0720013","article-title":"Estimation of sparse Jacobian matrices and graph coloring blems","volume":"20","author":"Coleman","year":"1983","journal-title":"SIAM J. Numer. Anal."},{"issue":"4","key":"10.1016\/j.jpdc.2024.104941_br0400","doi-asserted-by":"crossref","first-page":"1525","DOI":"10.1109\/TMAG.2007.892459","article-title":"Hardware acceleration for finite-element electromagnetics: efficient sparse matrix floating-point computations with FPGAs","volume":"43","author":"El-Kurdi","year":"2007","journal-title":"IEEE Trans. Magn."},{"key":"10.1016\/j.jpdc.2024.104941_br0410","doi-asserted-by":"crossref","unstructured":"J. Dongarra, M.A. Heroux, P. Luszczek, Hpcg benchmark: a new metric for ranking high performance computing systems, Knoxville, Tennessee 42, 2015.","DOI":"10.1177\/1094342015593158"},{"key":"10.1016\/j.jpdc.2024.104941_br0420","series-title":"International Conference on Parallel Computing Technologies","first-page":"549","article-title":"D-sab: a sparse matrix benchmark suite","author":"Stathis","year":"2003"},{"key":"10.1016\/j.jpdc.2024.104941_br0430","first-page":"323","article-title":"Vectorization algorithms of block linear algebra operations using SIMD instructions","volume":"535","author":"Andreev","year":"2015","journal-title":"Commun. Comput. Inf. Sci."},{"key":"10.1016\/j.jpdc.2024.104941_br0440","series-title":"2021 IEEE Symposium on Computers and Communications (ISCC)","first-page":"1","article-title":"Lightweight deep learning applications on AVX-512","author":"Carneiro","year":"2021"},{"issue":"1","key":"10.1016\/j.jpdc.2024.104941_br0450","doi-asserted-by":"crossref","first-page":"72","DOI":"10.1109\/TPDS.2020.3011893","article-title":"GPU tensor cores for fast arithmetic reductions","volume":"32","author":"Navarro","year":"2020","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"10.1016\/j.jpdc.2024.104941_br0460","series-title":"SC18: International Conference for High Performance Computing, Networking, Storage and Analysis","first-page":"603","article-title":"Harnessing GPU tensor cores for fast FP16 arithmetic to speed up mixed-precision iterative refinement solvers","author":"Haidar","year":"2018"},{"key":"10.1016\/j.jpdc.2024.104941_br0470","series-title":"SC20: International Conference for High Performance Computing, Networking, Storage and Analysis","first-page":"1","article-title":"FBLAS: streaming linear algebra on FPGA","author":"De Matteis","year":"2020"},{"key":"10.1016\/j.jpdc.2024.104941_br0480","series-title":"2017 IEEE 25th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM)","first-page":"160","article-title":"FPGA-accelerated dense linear machine learning: a precision-convergence trade-off","author":"Kara","year":"2017"},{"key":"10.1016\/j.jpdc.2024.104941_br0490","series-title":"European Conference on Parallel Processing","first-page":"444","article-title":"Benchmarking the nvidia v100 gpu and tensor cores","author":"Martineau","year":"2019"},{"key":"10.1016\/j.jpdc.2024.104941_br0500","series-title":"2022 IEEE International Symposium on Circuits and Systems (ISCAS)","first-page":"1259","article-title":"A mixed precision, multi-GPU design for large-scale Top-K sparse eigenproblems","author":"Sgherzi","year":"2022"},{"issue":"1","key":"10.1016\/j.jpdc.2024.104941_br0510","doi-asserted-by":"crossref","first-page":"66","DOI":"10.1177\/1094342019886628","article-title":"Sparse matrix partitioning for optimizing SpMV on CPU-GPU heterogeneous platforms","volume":"34","author":"Benatia","year":"2020","journal-title":"Int. J. High Perform. Comput. Appl."},{"issue":"3","key":"10.1016\/j.jpdc.2024.104941_br0520","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3134442","article-title":"SparseX: a library for high-performance sparse matrix-vector multiplication on multicore platforms","volume":"44","author":"Elafrou","year":"2018","journal-title":"ACM Trans. Math. Softw."},{"issue":"8","key":"10.1016\/j.jpdc.2024.104941_br0530","doi-asserted-by":"crossref","first-page":"1903","DOI":"10.1109\/TC.2021.3111761","article-title":"A comprehensive methodology to optimize FPGA designs via the roofline model","volume":"71","author":"Siracusa","year":"2022","journal-title":"IEEE Trans. Comput."},{"key":"10.1016\/j.jpdc.2024.104941_br0540","series-title":"2017 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)","first-page":"1389","article-title":"Performance analysis and optimization of sparse matrix-vector multiplication on intel xeon phi","author":"Elafrou","year":"2017"},{"key":"10.1016\/j.jpdc.2024.104941_br0550","series-title":"16th Euromicro Conference on Parallel, Distributed and Network-Based Processing (PDP 2008)","first-page":"283","article-title":"Understanding the performance of sparse matrix-vector multiplication","author":"Goumas","year":"2008"},{"issue":"1","key":"10.1016\/j.jpdc.2024.104941_br0560","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1177\/1094342004041296","article-title":"Sparsity: optimization framework for sparse matrix kernels","volume":"18","author":"Im","year":"2004","journal-title":"Int. J. High Perform. Comput. Appl."},{"issue":"10","key":"10.1016\/j.jpdc.2024.104941_br0570","doi-asserted-by":"crossref","first-page":"2329","DOI":"10.1109\/TPDS.2020.2990429","article-title":"aeSpTV: an adaptive and efficient framework for sparse tensor-vector product kernel on a high-performance computing platform","volume":"31","author":"Chen","year":"2020","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"10.1016\/j.jpdc.2024.104941_br0580","author":"Tian"},{"issue":"OOPSLA2","key":"10.1016\/j.jpdc.2024.104941_br0590","doi-asserted-by":"crossref","DOI":"10.1145\/3563338","article-title":"Compilation of dynamic sparse tensor algebra","volume":"6","author":"Chou","year":"2022","journal-title":"Proc. ACM Program. Lang."},{"key":"10.1016\/j.jpdc.2024.104941_br0600","series-title":"2008 37th International Conference on Parallel Processing","first-page":"503","article-title":"Challenges and advances in parallel sparse matrix-matrix multiplication","author":"Buluc","year":"2008"},{"issue":"5\u20136","key":"10.1016\/j.jpdc.2024.104941_br0610","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1016\/j.parco.2014.03.012","article-title":"Sparse matrix multiplication: the distributed block-compressed sparse row library","volume":"40","author":"Bor\u0161tnik","year":"2014","journal-title":"Parallel Comput."},{"key":"10.1016\/j.jpdc.2024.104941_br0620","series-title":"Proceedings of the 27th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming","first-page":"90","article-title":"TileSpGEMM: a tiled algorithm for parallel sparse general matrix-matrix multiplication on GPUs","author":"Niu","year":"2022"},{"issue":"3","key":"10.1016\/j.jpdc.2024.104941_br0630","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3015144","article-title":"Hypergraph partitioning for sparse matrix-matrix multiplication","volume":"3","author":"Ballard","year":"2016","journal-title":"ACM Trans. Parallel Comput."},{"key":"10.1016\/j.jpdc.2024.104941_br0640","doi-asserted-by":"crossref","first-page":"245","DOI":"10.1613\/jair.1.12228","article-title":"A survey on the explainability of supervised machine learning","volume":"70","author":"Burkart","year":"2021","journal-title":"J. Artif. Intell. Res."},{"issue":"12","key":"10.1016\/j.jpdc.2024.104941_br0650","first-page":"962","article-title":"Multivariate polynomial regression in data mining: methodology, problems and solutions","volume":"4","author":"Sinha","year":"2013","journal-title":"Int. J. Sci. Eng. Res."},{"key":"10.1016\/j.jpdc.2024.104941_br0660","series-title":"Ecological Statistics","article-title":"Generalised linear models","author":"Buckley","year":"2014"},{"issue":"3","key":"10.1016\/j.jpdc.2024.104941_br0670","first-page":"297","article-title":"Generalized additive models","volume":"1","author":"Hastie","year":"1986","journal-title":"Stat. Sci."},{"key":"10.1016\/j.jpdc.2024.104941_br0680","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"4460","article-title":"A unified framework for knowledge intensive gradient boosting: leveraging human experts for noisy sparse domains","volume":"vol. 34","author":"Kokel","year":"2020"},{"issue":"1","key":"10.1016\/j.jpdc.2024.104941_br0690","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1002\/widm.8","article-title":"Classification and regression trees","volume":"1","author":"Loh","year":"2011","journal-title":"Wiley Interdiscip. Rev. Data Min. Knowl. Discov."},{"key":"10.1016\/j.jpdc.2024.104941_br0700","series-title":"2019 56th ACM\/IEEE Design Automation Conference (DAC)","first-page":"1","article-title":"Napel: near-memory computing application performance prediction via ensemble learning","author":"Singh","year":"2019"},{"key":"10.1016\/j.jpdc.2024.104941_br0710","series-title":"2007 IEEE International Symposium on Performance Analysis of Systems & Software","first-page":"116","article-title":"Using model trees for computer architecture performance analysis of software applications","author":"Ould-Ahmed-Vall","year":"2007"},{"issue":"1","key":"10.1016\/j.jpdc.2024.104941_br0720","doi-asserted-by":"crossref","first-page":"188","DOI":"10.1145\/239912.239923","article-title":"Evidence-based static branch prediction using machine learning","volume":"19","author":"Calder","year":"1997","journal-title":"ACM Trans. Program. Lang. Syst."},{"key":"10.1016\/j.jpdc.2024.104941_br0730","doi-asserted-by":"crossref","first-page":"11994","DOI":"10.1109\/ACCESS.2022.3142240","article-title":"Comparative analysis of machine learning models for performance prediction of the SPEC benchmarks","volume":"10","author":"Tousi","year":"2022","journal-title":"IEEE Access"},{"key":"10.1016\/j.jpdc.2024.104941_br0740","series-title":"Proceedings of the 2016 International Conference on Parallel Architectures and Compilation","first-page":"57","article-title":"Integrating algorithmic parameters into benchmarking and design space exploration in 3D scene understanding","author":"Bodin","year":"2016"},{"key":"10.1016\/j.jpdc.2024.104941_br0750","series-title":"International Conference on Learning and Intelligent Optimization","first-page":"507","article-title":"Sequential model-based optimization for general algorithm configuration","author":"Hutter","year":"2011"},{"key":"10.1016\/j.jpdc.2024.104941_br0760","author":"Cianfriglia"},{"key":"10.1016\/j.jpdc.2024.104941_br0770","series-title":"Proceedings of the 13th International Workshop on Software & Compilers for Embedded Systems","first-page":"1","article-title":"Workload characterization supporting the development of domain-specific compiler optimizations using decision trees for data mining","author":"Fenacci","year":"2010"},{"key":"10.1016\/j.jpdc.2024.104941_br0780","series-title":"Proceedings of the 3rd International Workshop on Systems and Network Telemetry and Analytics","first-page":"33","article-title":"HPC workload characterization using feature selection and clustering","author":"Bang","year":"2020"},{"key":"10.1016\/j.jpdc.2024.104941_br0790","series-title":"SC20: International Conference for High Performance Computing, Networking, Storage and Analysis","first-page":"1","article-title":"Co-design for A64FX manycore processor and \u201cfugaku\u201d","author":"Sato","year":"2020"},{"issue":"5","key":"10.1016\/j.jpdc.2024.104941_br0800","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1109\/MM.2021.3085578","article-title":"Kunpeng 920: the first 7-nm chiplet-based 64-Core ARM SoC for cloud services","volume":"41","author":"Xia","year":"2021","journal-title":"IEEE MICRO"},{"key":"10.1016\/j.jpdc.2024.104941_br0810","author":"AWS"},{"key":"10.1016\/j.jpdc.2024.104941_br0820","author":"Rajamanickam"},{"issue":"1","key":"10.1016\/j.jpdc.2024.104941_br0830","first-page":"1","article-title":"Neon technology introduction","volume":"4","author":"Reddy","year":"2008","journal-title":"ARM Corp."},{"issue":"2","key":"10.1016\/j.jpdc.2024.104941_br0840","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1109\/MM.2017.35","article-title":"The ARM scalable vector extension","volume":"37","author":"Stephens","year":"2017","journal-title":"IEEE MICRO"},{"key":"10.1016\/j.jpdc.2024.104941_br0850","series-title":"SC'14: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","first-page":"769","article-title":"Efficient sparse matrix-vector multiplication on GPUs using the CSR storage format","author":"Greathouse","year":"2014"},{"key":"10.1016\/j.jpdc.2024.104941_br0860","doi-asserted-by":"crossref","DOI":"10.1016\/j.parco.2023.102997","article-title":"Heterogeneous sparse matrix-vector multiplication via compressed sparse row format","author":"Lane","year":"2023","journal-title":"Parallel Comput."},{"key":"10.1016\/j.jpdc.2024.104941_br0870","series-title":"2022 International Conference on Electronics, Information, and Communication (ICEIC)","first-page":"1","article-title":"Roofline model and profiling of HPC benchmarks","author":"Eo","year":"2022"},{"key":"10.1016\/j.jpdc.2024.104941_br0880","series-title":"Proceedings of the Seventh Workshop on Irregular Applications: Architectures and Algorithms","first-page":"1","article-title":"Overcoming load imbalance for irregular sparse matrices","author":"Flegar","year":"2017"},{"key":"10.1016\/j.jpdc.2024.104941_br0890","series-title":"2022 13th International Conference on Information and Communication Technology Convergence (ICTC)","first-page":"629","article-title":"Analysis of several sparse formats for matrices used in sparse-matrix dense-matrix multiplication for machine learning on GPUs","author":"Kim","year":"2022"},{"key":"10.1016\/j.jpdc.2024.104941_br0900","series-title":"2013 42nd International Conference on Parallel Processing","first-page":"11","article-title":"AdELL: an adaptive warp-balancing ELL format for efficient sparse matrix-vector multiplication on GPUs","author":"Maggioni","year":"2013"},{"key":"10.1016\/j.jpdc.2024.104941_br0910","author":"Chen"},{"key":"10.1016\/j.jpdc.2024.104941_br0920","series-title":"Proceedings of the 20th Annual International Conference on Supercomputing","first-page":"307","article-title":"Accelerating sparse matrix computations via data compression","author":"Willcock","year":"2006"},{"key":"10.1016\/j.jpdc.2024.104941_br0930","series-title":"Slides from Linux Kongress","first-page":"1","article-title":"The new Linux \u2018perf\u2019 tools","volume":"vol. 18","author":"De Melo","year":"2010"},{"key":"10.1016\/j.jpdc.2024.104941_br0940","series-title":"2010 39th International Conference on Parallel Processing Workshops","first-page":"207","article-title":"Likwid: a lightweight performance-oriented tool suite for x86 multicore environments","author":"Treibig","year":"2010"},{"key":"10.1016\/j.jpdc.2024.104941_br0950","article-title":"Using PAPI for Hardware Performance Monitoring on Linux Systems","volume":"vol. 5","author":"Dongarra","year":"2001"},{"key":"10.1016\/j.jpdc.2024.104941_br0960","series-title":"PRACE: Partnership for Advanced Computing in Europe","first-page":"1","article-title":"Profiling and tracing tools for performance analysis of large scale applications","author":"Eriksson","year":"2016"},{"issue":"2","key":"10.1016\/j.jpdc.2024.104941_br0980","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1145\/356616.356618","article-title":"A survey of indexing techniques for sparse matrices","volume":"5","author":"Pooch","year":"1973","journal-title":"ACM Comput. Surv."},{"issue":"112","key":"10.1016\/j.jpdc.2024.104941_br0990","doi-asserted-by":"crossref","first-page":"937","DOI":"10.1090\/S0025-5718-1970-0275643-8","article-title":"Some results on sparse matrices","volume":"24","author":"Brayton","year":"1970","journal-title":"Math. Comput."},{"key":"10.1016\/j.jpdc.2024.104941_br1000","series-title":"SODA","first-page":"132","article-title":"Directed scale-free graphs","volume":"vol. 3","author":"Bollob\u00e1s","year":"2003"},{"key":"10.1016\/j.jpdc.2024.104941_br1010","series-title":"Random Graphs","author":"Bollob\u00e1s","year":"1998"},{"key":"10.1016\/j.jpdc.2024.104941_br1020","series-title":"International Conference on Machine Learning, PMLR","first-page":"17117","article-title":"Scalable deep Gaussian Markov random fields for general graphs","author":"Oskarsson","year":"2022"},{"key":"10.1016\/j.jpdc.2024.104941_br1030","series-title":"Computational Methods for Inverse Problems","author":"Vogel","year":"2002"},{"key":"10.1016\/j.jpdc.2024.104941_br1040","series-title":"2020 IEEE 38th International Conference on Computer Design (ICCD)","first-page":"601","article-title":"Exploring better speculation and data locality in sparse matrix-vector multiplication on intel xeon","author":"Zhao","year":"2020"},{"key":"10.1016\/j.jpdc.2024.104941_br1050","series-title":"Proceedings of the 5th Conference on Computing Frontiers","first-page":"87","article-title":"Optimizing sparse matrix-vector multiplication using index and value compression","author":"Kourtis","year":"2008"},{"key":"10.1016\/j.jpdc.2024.104941_br1060","series-title":"International Conference on Architecture of Computing Systems","first-page":"273","article-title":"Potentials of branch predictors: from entropy viewpoints","author":"Yokota","year":"2008"},{"key":"10.1016\/j.jpdc.2024.104941_br1070","series-title":"Program Locality and Dynamic Memory Management","author":"Spirn","year":"1973"},{"issue":"6","key":"10.1016\/j.jpdc.2024.104941_br1080","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/1552309.1552310","article-title":"Program locality analysis using reuse distance","volume":"31","author":"Zhong","year":"2009","journal-title":"ACM Trans. Program. Lang. Syst."},{"key":"10.1016\/j.jpdc.2024.104941_br1090","series-title":"2007 25th International Conference on Computer Design","first-page":"245","article-title":"Cache replacement based on reuse-distance prediction","author":"Keramidas","year":"2007"},{"key":"10.1016\/j.jpdc.2024.104941_br1100","series-title":"2008 IEEE International Symposium on Modeling, Analysis and Simulation of Computers and Telecommunication Systems","first-page":"1","article-title":"Quantifying temporal and spatial localities in storage workloads and transformations by data path components","author":"Fox","year":"2008"},{"key":"10.1016\/j.jpdc.2024.104941_br1110","series-title":"2014 Federated Conference on Computer Science and Information Systems","first-page":"569","article-title":"Performance analysis of multicore and multinodal implementation of SpMV operation","author":"Bylina","year":"2014"},{"key":"10.1016\/j.jpdc.2024.104941_br1120","series-title":"Proceedings of the ACM International Conference on Supercomputing","first-page":"94","article-title":"IA-SpGEMM: an input-aware auto-tuning framework for parallel sparse matrix-matrix multiplication","author":"Xie","year":"2019"},{"issue":"4","key":"10.1016\/j.jpdc.2024.104941_br1130","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1016\/0169-7439(89)80095-4","article-title":"Analysis of variance (ANOVA)","volume":"6","author":"St","year":"1989","journal-title":"Chemom. Intell. Lab. Syst."},{"key":"10.1016\/j.jpdc.2024.104941_br1140","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1007\/s11749-016-0481-7","article-title":"A random forest guided tour","volume":"25","author":"Biau","year":"2016","journal-title":"Test"},{"key":"10.1016\/j.jpdc.2024.104941_br1150","series-title":"Empirical Inference: Festschrift in Honor of Vladimir N. Vapnik","first-page":"37","article-title":"Explaining adaboost","author":"Schapire","year":"2013"},{"key":"10.1016\/j.jpdc.2024.104941_br1160","series-title":"The Elements of Statistical Learning: Data Mining, Inference, and Prediction","first-page":"337","article-title":"Boosting and additive trees","author":"Hastie","year":"2009"},{"key":"10.1016\/j.jpdc.2024.104941_br1170","series-title":"Proceedings of the 22nd International Conference on Parallel Architectures and Compilation Techniques","first-page":"257","article-title":"Starchart: hardware and software optimization using recursive partitioning regression trees","author":"Jia","year":"2013"},{"key":"10.1016\/j.jpdc.2024.104941_br1180","series-title":"2008 20th International Symposium on Computer Architecture and High Performance Computing","first-page":"159","article-title":"Using analytical models to efficiently explore hardware transactional memory and multi-core co-design","author":"Poe","year":"2008"},{"key":"10.1016\/j.jpdc.2024.104941_br1190","series-title":"MBMV 2021; 24th Workshop","first-page":"1","article-title":"Decision tree-based throughput estimation to accelerate design space exploration for multi-core applications","author":"Letras","year":"2021"},{"key":"10.1016\/j.jpdc.2024.104941_br1200","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1007\/s11222-009-9153-8","article-title":"Estimation of prediction error by using K-fold cross-validation","volume":"21","author":"Fushiki","year":"2011","journal-title":"Stat. Comput."},{"key":"10.1016\/j.jpdc.2024.104941_br1210","doi-asserted-by":"crossref","unstructured":"D. Berrar, Cross-Validation, 2019.","DOI":"10.1016\/B978-0-12-809633-8.20349-X"},{"issue":"2","key":"10.1016\/j.jpdc.2024.104941_br1220","first-page":"1017","article-title":"Classification of epileptiform EEG using a hybrid system based on decision tree classifier and fast Fourier transform","volume":"187","author":"Polat","year":"2007","journal-title":"Appl. Math. Comput."},{"issue":"1","key":"10.1016\/j.jpdc.2024.104941_br1230","doi-asserted-by":"crossref","first-page":"173","DOI":"10.1109\/TPAMI.2007.250609","article-title":"A comparison of decision tree ensemble creation techniques","volume":"29","author":"Banfield","year":"2006","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.jpdc.2024.104941_br1240","series-title":"MBMV 2021; 24th Workshop","first-page":"1","article-title":"Exploration of DDR5 with the open-source simulator DRAMSys","author":"Steiner","year":"2021"},{"key":"10.1016\/j.jpdc.2024.104941_br1250","series-title":"2020 IEEE\/ACM Performance Modeling, Benchmarking and Simulation of High Performance Computer Systems (PMBS)","first-page":"1","article-title":"Performance modeling of streaming kernels and sparse matrix-vector multiplication on A64FX","author":"Alappat","year":"2020"},{"key":"10.1016\/j.jpdc.2024.104941_br1260","series-title":"A Tensor Marshaling Unit for Sparse Tensor Algebra on General-Purpose Processors, MICRO '23","first-page":"1332","author":"Siracusa","year":"2023"},{"issue":"7","key":"10.1016\/j.jpdc.2024.104941_br1270","doi-asserted-by":"crossref","first-page":"2639","DOI":"10.1016\/j.jpdc.2014.03.002","article-title":"BiELL: a bisection ELLPACK-based storage format for optimizing SpMV on GPUs","volume":"74","author":"Zheng","year":"2014","journal-title":"J. Parallel Distrib. Comput."},{"issue":"4","key":"10.1016\/j.jpdc.2024.104941_br1280","doi-asserted-by":"crossref","first-page":"44","DOI":"10.4236\/jcc.2020.84004","article-title":"PELLR: a permutated ELLPACK-R format for SpMV on GPUs","volume":"8","author":"Wang","year":"2020","journal-title":"J. Comput. Commun."},{"issue":"2","key":"10.1016\/j.jpdc.2024.104941_br1290","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1002\/sam.10071","article-title":"Seriation and matrix reordering methods: an historical overview","volume":"3","author":"Liiv","year":"2010","journal-title":"Stat. Anal. Data Min. ASA Data Sci. J."},{"issue":"2","key":"10.1016\/j.jpdc.2024.104941_br1300","doi-asserted-by":"crossref","first-page":"656","DOI":"10.1137\/080737770","article-title":"On two-dimensional sparse matrix partitioning: models, methods, and a recipe","volume":"32","author":"\u00c7ataly\u00fcrek","year":"2010","journal-title":"SIAM J. Sci. Comput."},{"key":"10.1016\/j.jpdc.2024.104941_br1310","series-title":"2014 IEEE 28th International Parallel and Distributed Processing Symposium","first-page":"529","article-title":"A medium-grain method for fast 2D bipartitioning of sparse matrices","author":"Pelt","year":"2014"},{"key":"10.1016\/j.jpdc.2024.104941_br1320","series-title":"2016 IEEE International Symposium on High Performance Computer Architecture (HPCA)","first-page":"469","article-title":"Best-offset hardware prefetching","author":"Michaud","year":"2016"},{"key":"10.1016\/j.jpdc.2024.104941_br1330","series-title":"Proceedings of the 48th International Symposium on Microarchitecture","first-page":"178","article-title":"Imp: indirect memory prefetcher","author":"Yu","year":"2015"},{"key":"10.1016\/j.jpdc.2024.104941_br1340","doi-asserted-by":"crossref","first-page":"800","DOI":"10.1016\/j.future.2020.06.033","article-title":"Performance and energy consumption of HPC workloads on a cluster based on Arm ThunderX2 CPU","volume":"112","author":"Mantovani","year":"2020","journal-title":"Future Gener. Comput. Syst."},{"issue":"9","key":"10.1016\/j.jpdc.2024.104941_br1350","doi-asserted-by":"crossref","first-page":"5717","DOI":"10.1007\/s11227-019-02819-4","article-title":"Design trade-offs for emerging HPC processors based on mobile market technology","volume":"75","author":"Armejach","year":"2019","journal-title":"J. Supercomput."},{"key":"10.1016\/j.jpdc.2024.104941_br1360","series-title":"Presentation in AHUG ISC 21 Workshop","article-title":"An evaluation of the Fujitsu A64FX for HPC applications","author":"Poenaru","year":"2021"},{"issue":"1","key":"10.1016\/j.jpdc.2024.104941_br1370","doi-asserted-by":"crossref","first-page":"20","DOI":"10.3390\/computation8010020","article-title":"ThunderX2 performance and energy-efficiency for HPC workloads","volume":"8","author":"Calore","year":"2020","journal-title":"Computation"},{"key":"10.1016\/j.jpdc.2024.104941_br1380","doi-asserted-by":"crossref","first-page":"3315","DOI":"10.1007\/s11227-020-03397-6","article-title":"On the use of many-core Marvell ThunderX2 processor for HPC workloads","volume":"77","author":"Soria-Pardos","year":"2021","journal-title":"J. Supercomput."},{"key":"10.1016\/j.jpdc.2024.104941_br1390","doi-asserted-by":"crossref","first-page":"134457","DOI":"10.1109\/ACCESS.2021.3110993","article-title":"DAMOV: a new methodology and benchmark suite for evaluating data movement bottlenecks","volume":"9","author":"Oliveira","year":"2021","journal-title":"IEEE Access"},{"key":"10.1016\/j.jpdc.2024.104941_br1400","series-title":"2015 International Conference on ReConFigurable Computing and FPGAs (ReConFig)","first-page":"1","article-title":"G-DMA: improving memory access performance for hardware accelerated sparse graph computation","author":"Bean","year":"2015"},{"key":"10.1016\/j.jpdc.2024.104941_br1410","series-title":"2014 IEEE International Symposium on Workload Characterization (IISWC)","first-page":"222","article-title":"Extending the roofline model: bottleneck analysis with microarchitectural constraints","author":"Cabezas","year":"2014"},{"key":"10.1016\/j.jpdc.2024.104941_br1420","series-title":"2021 IEEE International Symposium on Workload Characterization (IISWC)","first-page":"1","article-title":"Copernicus: characterizing the performance implications of compression formats used in sparse workloads","author":"Asgari","year":"2021"},{"key":"10.1016\/j.jpdc.2024.104941_br1430","series-title":"2014 IEEE 22nd Annual International Symposium on Field-Programmable Custom Computing Machines","first-page":"36","article-title":"A high memory bandwidth fpga accelerator for sparse matrix-vector multiplication","author":"Fowers","year":"2014"},{"key":"10.1016\/j.jpdc.2024.104941_br1440","series-title":"2015 IEEE 23rd Annual International Symposium on Field-Programmable Custom Computing Machines","first-page":"64","article-title":"Accelerating SpMV on FPGAs by compressing nonzero values","author":"Grigoras","year":"2015"},{"issue":"2","key":"10.1016\/j.jpdc.2024.104941_br1450","doi-asserted-by":"crossref","first-page":"205","DOI":"10.1002\/cta.796","article-title":"Design space exploration for sparse matrix-matrix multiplication on FPGAs","volume":"41","author":"Lin","year":"2013","journal-title":"Int. J. Circuit Theory Appl."},{"key":"10.1016\/j.jpdc.2024.104941_br1460","series-title":"2014 IEEE 32nd International Conference on Computer Design (ICCD)","first-page":"432","article-title":"An energy efficient column-major backend for FPGA SpMV accelerators","author":"Umuroglu","year":"2014"},{"issue":"20","key":"10.1016\/j.jpdc.2024.104941_br1470","doi-asserted-by":"crossref","DOI":"10.1002\/cpe.6570","article-title":"FPGA-based HPC accelerators: an evaluation on performance and energy efficiency","volume":"34","author":"Nguyen","year":"2022","journal-title":"Concurr. Comput., Pract. Exp."},{"key":"10.1016\/j.jpdc.2024.104941_br1480","series-title":"2015 International Conference on Compilers, Architecture and Synthesis for Embedded Systems (CASES)","first-page":"109","article-title":"A sparse matrix vector multiply accelerator for support vector machine","author":"Nurvitadhi","year":"2015"},{"key":"10.1016\/j.jpdc.2024.104941_br1490","series-title":"2020 IEEE International Symposium on High Performance Computer Architecture (HPCA)","first-page":"249","article-title":"Alrescha: a lightweight reconfigurable sparse-computation accelerator","author":"Asgari","year":"2020"},{"key":"10.1016\/j.jpdc.2024.104941_br1500","series-title":"Proceedings of the 52nd Annual IEEE\/ACM International Symposium on Microarchitecture","first-page":"319","article-title":"Extensor: an accelerator for sparse tensor algebra","author":"Hegde","year":"2019"},{"key":"10.1016\/j.jpdc.2024.104941_br1510","series-title":"2020 ACM\/IEEE 47th Annual International Symposium on Computer Architecture (ISCA)","first-page":"968","article-title":"Centaur: a chiplet-based, hybrid sparse-dense accelerator for personalized recommendations","author":"Hwang","year":"2020"},{"key":"10.1016\/j.jpdc.2024.104941_br1520","series-title":"2017 22nd Asia and South Pacific Design Automation Conference (ASP-DAC)","first-page":"635","article-title":"Fine-grained accelerators for sparse machine learning workloads","author":"Mishra","year":"2017"},{"key":"10.1016\/j.jpdc.2024.104941_br1530","series-title":"2016 Design, Automation & Test in Europe Conference & Exhibition (DATE)","first-page":"1616","article-title":"Hardware accelerator for analytics of sparse data","author":"Nurvitadhi","year":"2016"},{"key":"10.1016\/j.jpdc.2024.104941_br1540","series-title":"2018 IEEE International Symposium on High Performance Computer Architecture (HPCA)","first-page":"724","article-title":"Outerspace: an outer product based sparse matrix multiplication accelerator","author":"Pal","year":"2018"},{"issue":"2","key":"10.1016\/j.jpdc.2024.104941_br1550","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1145\/3140659.3080254","article-title":"SCNN: an accelerator for compressed-sparse convolutional neural networks","volume":"45","author":"Parashar","year":"2017","journal-title":"Comput. Archit. News"},{"key":"10.1016\/j.jpdc.2024.104941_br1560","series-title":"2020 IEEE International Symposium on High Performance Computer Architecture (HPCA)","first-page":"58","article-title":"A sparse and irregular gemm accelerator with flexible interconnects for dnn training","author":"Qin","year":"2020"},{"key":"10.1016\/j.jpdc.2024.104941_br1570","series-title":"Proceedings of the 26th ACM International Conference on Architectural Support for Programming Languages and Operating Systems","first-page":"687","article-title":"Gamma: leveraging Gustavson's algorithm to accelerate sparse matrix multiplication","author":"Zhang","year":"2021"},{"key":"10.1016\/j.jpdc.2024.104941_br1580","series-title":"2016 49th Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO)","first-page":"1","article-title":"Cambricon-X: an accelerator for sparse neural networks","author":"Zhang","year":"2016"},{"key":"10.1016\/j.jpdc.2024.104941_br1590","series-title":"2020 IEEE International Symposium on High Performance Computer Architecture (HPCA)","first-page":"261","article-title":"Sparch: efficient architecture for sparse matrix multiplication","author":"Zhang","year":"2020"},{"key":"10.1016\/j.jpdc.2024.104941_br1600","series-title":"2018 51st Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO)","first-page":"15","article-title":"Cambricon-S: addressing irregularity in sparse neural networks through a cooperative software\/hardware approach","author":"Zhou","year":"2018"},{"key":"10.1016\/j.jpdc.2024.104941_br1610","series-title":"Proceedings of the 52nd Annual IEEE\/ACM International Symposium on Microarchitecture","first-page":"347","article-title":"Efficient SpMV operation for large and highly sparse matrices using scalable multi-way merge parallelization","author":"Sadi","year":"2019"},{"key":"10.1016\/j.jpdc.2024.104941_br1620","series-title":"Proceedings of the 37th Annual International Symposium on Computer Architecture","first-page":"451","article-title":"Debunking the 100X GPU vs. CPU myth: an evaluation of throughput computing on CPU and GPU","author":"Lee","year":"2010"}],"container-title":["Journal of Parallel and Distributed Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0743731524001059?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0743731524001059?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2024,7,20]],"date-time":"2024-07-20T15:01:35Z","timestamp":1721487695000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0743731524001059"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10]]},"references-count":161,"alternative-id":["S0743731524001059"],"URL":"https:\/\/doi.org\/10.1016\/j.jpdc.2024.104941","relation":{},"ISSN":["0743-7315"],"issn-type":[{"value":"0743-7315","type":"print"}],"subject":[],"published":{"date-parts":[[2024,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"SpChar: Characterizing the sparse puzzle via decision trees","name":"articletitle","label":"Article Title"},{"value":"Journal of Parallel and Distributed Computing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.jpdc.2024.104941","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2024 Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"104941"}}
