{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,3]],"date-time":"2026-11-03T06:28:50Z","timestamp":1793687330585,"version":"4.5.1"},"reference-count":60,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2019,6,12]],"date-time":"2019-06-12T00:00:00Z","timestamp":1560297600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2019,6,12]],"date-time":"2019-06-12T00:00:00Z","timestamp":1560297600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61802412"],"award-info":[{"award-number":["61802412"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61732014"],"award-info":[{"award-number":["61732014"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["CCF Trans. HPC"],"published-print":{"date-parts":[[2019,8]]},"DOI":"10.1007\/s42514-019-00008-6","type":"journal-article","created":{"date-parts":[[2019,6,12]],"date-time":"2019-06-12T05:04:36Z","timestamp":1560315876000},"page":"131-143","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Performance evaluation and analysis of sparse matrix and graph kernels on heterogeneous processors"],"prefix":"10.1007","volume":"1","author":[{"given":"Feng","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1983-7321","authenticated-orcid":false,"given":"Weifeng","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ningxuan","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jidong","family":"Zhai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoyong","family":"Du","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2019,6,12]]},"reference":[{"key":"8_CR1","doi-asserted-by":"crossref","unstructured":"Agarwal, N., Nellans, D., Ebrahimi, E., Wenisch, T.F., Danskin, J., Keckler, S.W.: Selective GPU caches to eliminate CPU\u2013GPU HW cache coherence. In: 2016 IEEE International Symposium on High Performance Computer Architecture (HPCA), pp. 494\u2013506 (2016)","DOI":"10.1109\/HPCA.2016.7446089"},{"key":"8_CR2","doi-asserted-by":"crossref","unstructured":"Barik, R., Kaleem, R., Majeti, D., Lewis, B.T., Shpeisman, T., Hu, C., Ni, Y., Adl-Tabatabai, A.R.: Efficient mapping of irregular C++ applications to integrated GPUs. In: Proceedings of Annual IEEE\/ACM International Symposium on Code Generation and Optimization, p.\u00a033, ACM (2014)","DOI":"10.1145\/2544137.2544165"},{"issue":"2","key":"8_CR3","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1109\/MM.2015.12","volume":"35","author":"D Boggs","year":"2015","unstructured":"Boggs, D., Brown, G., Tuck, N., Venkatraman, K.S.: Denver: Nvidia\u2019s first 64-bit ARM processor. IEEE Micro 35(2), 46\u201355 (2015)","journal-title":"IEEE Micro"},{"issue":"2","key":"8_CR4","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1109\/MM.2012.2","volume":"32","author":"A Branover","year":"2012","unstructured":"Branover, A., Foley, D., Steinman, M.: AMD Fusion APU: Llano. IEEE Micro 32(2), 28\u201337 (2012)","journal-title":"IEEE Micro"},{"issue":"4","key":"8_CR5","doi-asserted-by":"publisher","first-page":"C170","DOI":"10.1137\/110848244","volume":"34","author":"A Bulu\u00e7","year":"2012","unstructured":"Bulu\u00e7, A., Gilbert, J.: Parallel sparse matrix\u2013matrix multiplication and indexing: implementation and experiments. SIAM J. Sci. Comput. 34(4), C170\u2013C191 (2012)","journal-title":"SIAM J. Sci. Comput."},{"key":"8_CR6","doi-asserted-by":"crossref","unstructured":"Daga, M., Aji, A.M., Feng, W.C: On the efficacy of a fused CPU+GPU processor (or APU) for parallel computing. In: 2011 Symposium on Application Accelerators in High-Performance Computing, pp. 141\u2013149 (2011)","DOI":"10.1109\/SAAHPC.2011.29"},{"key":"8_CR7","doi-asserted-by":"crossref","unstructured":"Daga, M., Nutter, M., Meswani, M.: Efficient breadth-first search on a heterogeneous processor. In: 2014 IEEE International Conference on Big Data (Big Data), pp. 373\u2013382 (2014)","DOI":"10.1109\/BigData.2014.7004254"},{"key":"8_CR8","doi-asserted-by":"crossref","unstructured":"Daga, M., Nutter, M.: Exploiting coarse-grained parallelism in B+ tree searches on an APU. In: 2012 SC Companion: High Performance Computing, Networking Storage and Analysis, pp. 240\u2013247 (2012)","DOI":"10.1109\/SC.Companion.2012.40"},{"key":"8_CR9","doi-asserted-by":"crossref","unstructured":"Dashti, M., Fedorova, A.: Analyzing Memory Management Methods on Integrated CPU\u2013GPU Systems. In: Proceedings of the 2017 ACM SIGPLAN International Symposium on Memory Management, ISMM 2017, pp. 59\u201369 (2017)","DOI":"10.1145\/3092255.3092256"},{"issue":"1","key":"8_CR10","first-page":"1:1","volume":"38","author":"TA Davis","year":"2011","unstructured":"Davis, T.A., Hu, Y.: The University of Florida sparse matrix collection. ACM Trans. Math. Softw. 38(1), 1:1\u20131:25 (2011)","journal-title":"ACM Trans. Math. Softw."},{"key":"8_CR11","doi-asserted-by":"crossref","unstructured":"Doerksen, M., Solomon, S., Thulasiraman, P.: Designing APU oriented scientific computing applications in opencl. In: High Performance Computing and Communications (HPCC), 2011 IEEE 13th International Conference on, pp. 587\u2013592, IEEE (2011)","DOI":"10.1109\/HPCC.2011.83"},{"issue":"2","key":"8_CR12","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1109\/MM.2017.38","volume":"37","author":"J Doweck","year":"2017","unstructured":"Doweck, J., Kao, W., Lu, A.K., Mandelblat, J., Rahatekar, A., Rappoport, L., Rotem, E., Yasin, A., Yoaz, A.: Inside 6th-generation intel core: new microarchitecture code-named skylake. IEEE Micro 37(2), 52\u201362 (2017)","journal-title":"IEEE Micro"},{"issue":"2","key":"8_CR13","doi-asserted-by":"publisher","first-page":"239","DOI":"10.1145\/567806.567810","volume":"28","author":"IS Duff","year":"2002","unstructured":"Duff, I.S., Heroux, M.A., Pozo, R.: An overview of the sparse basic linear algebra subprograms: the new standard from the BLAS technical forum. ACM Trans. Math. Softw. (TOMS) 28(2), 239\u2013267 (2002)","journal-title":"ACM Trans. Math. Softw. (TOMS)"},{"issue":"1","key":"8_CR14","doi-asserted-by":"publisher","first-page":"114","DOI":"10.1007\/s11227-016-1643-9","volume":"73","author":"EM Garz\u00f3n","year":"2017","unstructured":"Garz\u00f3n, E.M., Moreno, J., Mart\u00ednez, J.: An approach to optimise the energy efficiency of iterative computation on integrated GPU\u2013CPU systems. J. Supercomput. 73(1), 114\u2013125 (2017)","journal-title":"J. Supercomput."},{"key":"8_CR15","doi-asserted-by":"crossref","unstructured":"Greathouse, J.L., Daga, M.: Efficient sparse matrix\u2013vector multiplication on GPUs using the CSR storage format. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, SC \u201914, pp. 769\u2013780 (2014)","DOI":"10.1109\/SC.2014.68"},{"key":"8_CR16","doi-asserted-by":"crossref","unstructured":"Gregg, C., Hazelwood, K.: Where is the data? Why you cannot debate CPU vs. GPU performance without the answer. In: (IEEE ISPASS) IEEE International Symposium on Performance Analysis of Systems and Software, pp. 134\u2013144 (2011)","DOI":"10.1109\/ISPASS.2011.5762730"},{"key":"8_CR17","doi-asserted-by":"crossref","unstructured":"Kaleem, R., Barik, R., Shpeisman, T., Hu, C., Lewis, B.T., Pingali, K.: Adaptive heterogeneous scheduling for integrated GPUs. In: Parallel Architecture and Compilation Techniques (PACT), 2014 23rd International Conference on, pp. 151\u2013162. IEEE (2014)","DOI":"10.1145\/2628071.2628088"},{"issue":"2","key":"8_CR18","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1109\/MM.2016.24","volume":"36","author":"G Krishnan","year":"2016","unstructured":"Krishnan, G., Bouvier, D., Naffziger, S.: Energy-efficient graphics and multimedia in 28-nm Carrizo accelerated processing unit. IEEE Micro 36(2), 22\u201333 (2016)","journal-title":"IEEE Micro"},{"key":"8_CR19","doi-asserted-by":"crossref","unstructured":"Lee, V.W., Kim, C., Chhugani, J., Deisher, M., Kim, D., Nguyen, A.D., Satish, N., Smelyanskiy, M., Chennupaty, S., Hammarlund, P., Singhal, R., Dubey, P.: Debunking the 100X GPU vs. CPU myth: an evaluation of throughput computing on CPU and GPU. In: Proceedings of the 37th Annual International Symposium on Computer Architecture, ISCA \u201910, pp. 451\u2013460 (2010)","DOI":"10.1145\/1815961.1816021"},{"issue":"2\u20133","key":"8_CR20","doi-asserted-by":"publisher","first-page":"175","DOI":"10.1007\/s00450-012-0209-1","volume":"28","author":"K Lee","year":"2013","unstructured":"Lee, K., Lin, H., Feng, Wc: Performance characterization of data-intensive kernels on AMD fusion architectures. Comput. Sci. Res. Dev. 28(2\u20133), 175\u2013184 (2013)","journal-title":"Comput. Sci. Res. Dev."},{"key":"8_CR21","doi-asserted-by":"crossref","unstructured":"Li, A., Liu, W., Kristensen, M.R.B., Vinter, B., Wang, H., Hou, K., Marquez, A., Song, S.L.: Exploring and analyzing the real impact of modern on-package memory on HPC scientific kernels. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, SC \u201917, pp. 26:1\u201326:14 (2017a)","DOI":"10.1145\/3126908.3126931"},{"key":"8_CR22","doi-asserted-by":"crossref","unstructured":"Li, A., Song, S.L., Liu, W., Liu, X., Kumar, A., Corporaal, H.: Locality-aware CTA clustering for modern GPUs. In: Proceedings of the Twenty-Second International Conference on Architectural Support for Programming Languages and Operating Systems, ASPLOS \u201917, pp. 297\u2013311 (2017b)","DOI":"10.1145\/3037697.3037709"},{"key":"8_CR23","unstructured":"Liu, W.: Parallel and scalable sparse basic linear algebra subprograms. Ph.D. thesis, University of Copenhagen (2015)"},{"key":"8_CR24","doi-asserted-by":"crossref","unstructured":"Liu, W., Vinter, B.: Ad-heap: an efficient heap data structure for asymmetric multicore processors. In: Proceedings of Workshop on General Purpose Processing Using GPUs, GPGPU-7, pp. 54:54\u201354:63 (2014)","DOI":"10.1145\/2588768.2576786"},{"key":"8_CR25","doi-asserted-by":"crossref","unstructured":"Liu, W., Vinter, B.: CSR5: an efficient storage format for cross-platform sparse matrix\u2013vector multiplication. In: Proceedings of the 29th ACM International Conference on Supercomputing, ICS \u201915, pp. 339\u2013350 (2015a)","DOI":"10.1145\/2751205.2751209"},{"issue":"C","key":"8_CR26","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1016\/j.jpdc.2015.06.010","volume":"85","author":"W Liu","year":"2015","unstructured":"Liu, W., Vinter, B.: A framework for general sparse matrix\u2013matrix multiplication on GPUs and heterogeneous processors. J. Parallel Distrib. Comput. 85(C), 47\u201361 (2015b)","journal-title":"J. Parallel Distrib. Comput."},{"issue":"C","key":"8_CR27","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1016\/j.parco.2015.04.004","volume":"49","author":"W Liu","year":"2015","unstructured":"Liu, W., Vinter, B.: Speculative segmented sum for sparse matrix\u2013vector multiplication on heterogeneous processors. Parallel Comput. 49(C), 179\u2013193 (2015c)","journal-title":"Parallel Comput."},{"issue":"9","key":"8_CR28","doi-asserted-by":"publisher","first-page":"1290","DOI":"10.1016\/j.microrel.2015.06.078","volume":"55","author":"T Liu","year":"2015","unstructured":"Liu, T., Chen, C.C., Kim, W., Milor, L.: Comprehensive reliability and aging analysis on SRAMs within microprocessor systems. Microelectron. Reliab. 55(9), 1290\u20131296 (2015)","journal-title":"Microelectron. Reliab."},{"key":"8_CR29","doi-asserted-by":"crossref","unstructured":"Liu, T., Chen, C.C., Wu, J., Milor, L.: SRAM stability analysis for different cache configurations due to bias temperature instability and hot carrier injection. In: Computer Design (ICCD), 2016 IEEE 34th International Conference on, pp. 225\u2013232, IEEE (2016)","DOI":"10.1109\/ICCD.2016.7753284"},{"issue":"21","key":"8_CR30","doi-asserted-by":"publisher","first-page":"e4244","DOI":"10.1002\/cpe.4244","volume":"29","author":"W Liu","year":"2017","unstructured":"Liu, W., Li, A., Hogg, J.D., Duff, I.S., Vinter, B.: Fast synchronization-free algorithms for parallel sparse triangular solves with multiple right-hand sides. Concurr. Comput. Pract. Exp. 29(21), e4244 (2017)","journal-title":"Concurr. Comput. Pract. Exp."},{"key":"8_CR31","doi-asserted-by":"crossref","unstructured":"Liu, J., He, X., Liu, W., Tan, G.: Register-based implementation of the sparse general matrix\u2013matrix multiplication on gpus. In: Proceedings of the 23rd ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, PPoPP \u201918, pp. 407\u2013408 (2018)","DOI":"10.1145\/3178487.3178529"},{"key":"8_CR32","doi-asserted-by":"publisher","DOI":"10.1007\/s10766-018-0604-","author":"J Liu","year":"2019","unstructured":"Liu, J., He, X., Liu, W., Tan, G.: Register-aware optimizations for parallel sparse matrix\u2013matrix multiplication. Int. J. Parallel Program. (2019). \n                    https:\/\/doi.org\/10.1007\/s10766-018-0604-","journal-title":"Int. J. Parallel Program."},{"key":"8_CR33","unstructured":"Mekkat, V., Holey, A., Yew, P.C., Zhai, A.: Managing shared last-level cache in a heterogeneous multicore processor. In: Proceedings of the 22nd international conference on Parallel architectures and compilation techniques, pp. 225\u2013234, IEEE Press (2013)"},{"key":"8_CR34","doi-asserted-by":"crossref","unstructured":"Merrill, D., Garland, M.: Merge-based parallel sparse matrix\u2013vector multiplication. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, p.\u00a058. IEEE Press (2016)","DOI":"10.1109\/SC.2016.57"},{"key":"8_CR35","doi-asserted-by":"crossref","unstructured":"Nai, L., Xia, Y., Tanase, I.G., Kim, H., Lin, C.Y.: GraphBIG: understanding graph computing in the context of industrial solutions. In: High Performance Computing, Networking, Storage and Analysis, 2015 SC-International Conference for, pp. 1\u201312, IEEE (2015)","DOI":"10.1145\/2807591.2807626"},{"issue":"5","key":"8_CR36","doi-asserted-by":"publisher","first-page":"879","DOI":"10.1109\/JPROC.2008.917757","volume":"96","author":"JD Owens","year":"2008","unstructured":"Owens, J.D., Houston, M., Luebke, D., Green, S., Stone, J.E., Phillips, J.C.: GPU computing. Proc. IEEE 96(5), 879\u2013899 (2008)","journal-title":"Proc. IEEE"},{"key":"8_CR37","doi-asserted-by":"crossref","unstructured":"Pandit, P., Govindarajan, R.: Fluidic kernels: Cooperative execution of opencl programs on multiple heterogeneous devices. In: Proceedings of Annual IEEE\/ACM International Symposium on Code Generation and Optimization, p. 273, ACM (2014)","DOI":"10.1145\/2544137.2544163"},{"key":"8_CR38","doi-asserted-by":"crossref","unstructured":"Power, J., Basu, A., Gu, J., Puthoor, S., Beckmann, B.M., Hill, M.D., Reinhardt, S.K., Wood, D.A.: Heterogeneous system coherence for integrated CPU\u2013GPU systems. In: 2013 46th Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO), pp. 457\u2013467 (2013)","DOI":"10.1145\/2540708.2540747"},{"key":"8_CR39","doi-asserted-by":"crossref","unstructured":"Puthoor, S., Aji, A.M., Che, S., Daga, M., Wu, W., Beckmann, B.M., Rodgers, G.: Implementing directed acyclic graphs with the heterogeneous system architecture. In: Proceedings of the 9th Annual Workshop on General Purpose Processing Using Graphics Processing Unit, GPGPU \u201916, pp. 53\u201362 (2016)","DOI":"10.1145\/2884045.2884052"},{"issue":"6","key":"8_CR40","doi-asserted-by":"publisher","first-page":"819","DOI":"10.1177\/1094342017696562","volume":"32","author":"I Said","year":"2017","unstructured":"Said, I., Fortin, P., Lamotte, J., Calandra, H.: Leveraging the accelerated processing units for seismic imaging: a performance and power efficiency comparison against CPUs and GPUs. Int. J. High Perform. Comput. Appl. 32(6), 819\u2013837 (2017)","journal-title":"Int. J. High Perform. Comput. Appl."},{"issue":"4","key":"8_CR41","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1109\/MM.2015.71","volume":"35","author":"MJ Schulte","year":"2015","unstructured":"Schulte, M.J., Ignatowski, M., Loh, G.H., Beckmann, B.M., Brantley, W.C., Gurumurthi, S., Jayasena, N., Paul, I., Reinhardt, S.K., Rodgers, G.: Achieving exascale capabilities through heterogeneous computing. IEEE Micro 35(4), 26\u201336 (2015)","journal-title":"IEEE Micro"},{"key":"8_CR42","doi-asserted-by":"crossref","unstructured":"Shen, J., Varbanescu, A.L., Sips, H., Arntzen, M., Simons, D.G.: Glinda: A framework for accelerating imbalanced applications on heterogeneous platforms. In: Proceedings of the ACM International Conference on Computing Frontiers, CF \u201913, pp. 14:1\u201314:10 (2013)","DOI":"10.1145\/2482767.2482785"},{"key":"8_CR43","doi-asserted-by":"crossref","unstructured":"Shen, J., Varbanescu, A.L., Zou, P., Lu, Y., Sips, H.: Improving performance by matching imbalanced workloads with heterogeneous platforms. In: Proceedings of the 28th ACM International Conference on Supercomputing, ICS \u201914, pp. 241\u2013250 (2014)","DOI":"10.1145\/2597652.2597675"},{"issue":"9","key":"8_CR44","doi-asserted-by":"publisher","first-page":"2766","DOI":"10.1109\/TPDS.2015.2509972","volume":"27","author":"J Shen","year":"2016","unstructured":"Shen, J., Varbanescu, A.L., Lu, Y., Zou, P., Sips, H.: Workload partitioning for accelerating applications on heterogeneous platforms. IEEE Trans. Parallel Distrib. Syst. 27(9), 2766\u20132780 (2016)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"8_CR45","doi-asserted-by":"crossref","unstructured":"Spafford, K.L., Meredith, J.S., Lee, S., Li, D., Roth, P.C., Vetter, J.S.: The tradeoffs of fused memory hierarchies in heterogeneous computing architectures. In: Proceedings of the 9th conference on Computing Frontiers, pp. 103\u2013112, ACM (2012)","DOI":"10.1145\/2212908.2212924"},{"key":"8_CR46","doi-asserted-by":"crossref","unstructured":"Tang, S., He, B., Zhang, S., Niu, Z.: Elastic multi-resource fairness: balancing fairness and efficiency in coupled CPU\u2013GPU architectures. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, p.\u00a075. IEEE Press (2016)","DOI":"10.1109\/SC.2016.74"},{"key":"8_CR47","doi-asserted-by":"crossref","unstructured":"Vijayaraghavan, T., Eckert, Y., Loh, G.H., Schulte, M.J., Ignatowski, M., Beckmann, B.M., Brantley, W.C., Greathouse, J.L., Huang, W., Karunanithi, A., Kayiran, O., Meswani, M., Paul, I., Poremba, M., Raasch, S., Reinhardt, S.K., Sadowski, G., Sridharan, V.: Design and analysis of an APU for Exascale computing. In: 2017 IEEE International Symposium on High Performance Computer Architecture (HPCA), pp. 85\u201396 (2017)","DOI":"10.1109\/HPCA.2017.42"},{"key":"8_CR48","doi-asserted-by":"crossref","unstructured":"Wang, H., Liu, W., Hou, K., Feng, W.C.: Parallel transposition of sparse data structures. In: Proceedings of the 2016 International Conference on Supercomputing, ICS \u201916, pp. 33:1\u201333:13 (2016)","DOI":"10.1145\/2925426.2926291"},{"key":"8_CR49","doi-asserted-by":"crossref","unstructured":"Wang, X., Liu, W., Xue, W., Wu, L.: swsptrsv: A fast sparse triangular solve with sparse level tile layout on sunway architectures. In: Proceedings of the 23rd ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, PPoPP \u201918, pp. 338\u2013353 (2018)","DOI":"10.1145\/3178487.3178513"},{"key":"8_CR50","doi-asserted-by":"crossref","unstructured":"Wang, H., Geng, L., Lee, R., Hou, K., Zhang, Y., Zhang, X.: Sep-graph: finding shortest execution paths for graph processing under a hybrid framework on GPU. In: Proceedings of the 24th Symposium on Principles and Practice of Parallel Programming, PPoPP \u201919, pp. 38\u201352 (2019)","DOI":"10.1145\/3293883.3295733"},{"key":"8_CR51","doi-asserted-by":"crossref","unstructured":"Yang, Y., Xiang, P., Mantor, M., Zhou, H.: CPU-assisted GPGPU on fused CPU\u2013GPU architectures. In: IEEE International Symposium on High-Performance Comp Architecture, pp. 1\u201312 (2012)","DOI":"10.1109\/HPCA.2012.6168948"},{"key":"8_CR52","doi-asserted-by":"crossref","unstructured":"Zakharenko, V., Aamodt, T., Moshovos, A.: Characterizing the performance benefits of fused CPU\/GPU systems using FusionSim. In: Proceedings of the Conference on Design, Automation and Test in Europe, pp. 685\u2013688, EDA Consortium (2013)","DOI":"10.7873\/DATE.2013.148"},{"key":"8_CR53","doi-asserted-by":"crossref","unstructured":"Zakharenko, V.: FusionSim: characterizing the performance benefits of fused CPU\/GPU systems. Ph.D. thesis (2012)","DOI":"10.7873\/DATE.2013.148"},{"key":"8_CR54","doi-asserted-by":"crossref","unstructured":"Zhang, F., Zhai, J., Chen, W., He, B., Zhang, S.: To co-run, or not to co-run: a performance study on integrated architectures. In: 2015 IEEE 23rd International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems, pp. 89\u201392 (2015)","DOI":"10.1109\/MASCOTS.2015.27"},{"key":"8_CR55","doi-asserted-by":"crossref","unstructured":"Zhang, F., Wu, B., Zhai, J., He, B., Chen, W.: FinePar: Irregularity-aware Fine-grained Workload Partitioning on Integrated Architectures. In: Proceedings of the 2017 International Symposium on Code Generation and Optimization, CGO \u201917, pp. 27\u201338 (2017a)","DOI":"10.1109\/CGO.2017.7863726"},{"issue":"3","key":"8_CR56","doi-asserted-by":"publisher","first-page":"905","DOI":"10.1109\/TPDS.2016.2586074","volume":"28","author":"F Zhang","year":"2017","unstructured":"Zhang, F., Zhai, J., He, B., Zhang, S., Chen, W.: Understanding co-running behaviors on integrated CPU\/GPU architectures. IEEE Trans. Parallel Distrib. Syst. 28(3), 905\u2013918 (2017b)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"8_CR57","doi-asserted-by":"crossref","unstructured":"Zhang, F., Lin, H., Zhai, J., Cheng, J., Xiang, D., Li, J., Chai, Y., Du, X.: An Adaptive Breadth-First Search Algorithm on Integrated Architectures. The Journal of Supercomputing (2018)","DOI":"10.1007\/s11227-018-2525-0"},{"key":"8_CR58","doi-asserted-by":"crossref","unstructured":"Zhu, Q., Wu, B., Shen, X., Shen, L., Wang, Z.: Understanding co-run degradations on integrated heterogeneous processors. In: International Workshop on Languages and Compilers for Parallel Computing, pp. 82\u201397. Springer (2014)","DOI":"10.1007\/978-3-319-17473-0_6"},{"key":"8_CR59","doi-asserted-by":"crossref","unstructured":"Zhu, Q., Wu, B., Shen, X., Shen, L., Wang, Z.: Co-run scheduling with power cap on integrated CPU\u2013GPU systems. In: 2017 IEEE International Parallel and Distributed Processing Symposium (IPDPS), pp. 967\u2013977 (2017a)","DOI":"10.1109\/IPDPS.2017.124"},{"issue":"1","key":"8_CR60","doi-asserted-by":"publisher","first-page":"130","DOI":"10.1007\/s11704-016-5468-8","volume":"11","author":"Q Zhu","year":"2017","unstructured":"Zhu, Q., Wu, B., Shen, X., Shen, K., Shen, L., Wang, Z.: Understanding co-run performance on CPU\u2013GPU integrated processors: observations, insights, directions. Front. Comput. Sci. 11(1), 130\u2013146 (2017b)","journal-title":"Front. Comput. Sci."}],"container-title":["CCF Transactions on High Performance Computing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s42514-019-00008-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s42514-019-00008-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s42514-019-00008-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,6,10]],"date-time":"2020-06-10T19:42:57Z","timestamp":1591818177000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s42514-019-00008-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,6,12]]},"references-count":60,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2019,8]]}},"alternative-id":["8"],"URL":"https:\/\/doi.org\/10.1007\/s42514-019-00008-6","relation":{},"ISSN":["2524-4922","2524-4930"],"issn-type":[{"value":"2524-4922","type":"print"},{"value":"2524-4930","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,6,12]]},"assertion":[{"value":"23 January 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 May 2019","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 June 2019","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}