{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,23]],"date-time":"2025-04-23T04:20:32Z","timestamp":1745382032324,"version":"3.40.4"},"reference-count":28,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2012,11,29]],"date-time":"2012-11-29T00:00:00Z","timestamp":1354147200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int J Parallel Prog"],"published-print":{"date-parts":[[2014,2]]},"DOI":"10.1007\/s10766-012-0232-7","type":"journal-article","created":{"date-parts":[[2012,11,29]],"date-time":"2012-11-29T11:59:18Z","timestamp":1354190358000},"page":"30-48","source":"Crossref","is-referenced-by-count":2,"title":["Aggressive Value Prediction on a GPU"],"prefix":"10.1007","volume":"42","author":[{"given":"Enqiang","family":"Sun","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Kaeli","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2012,11,29]]},"reference":[{"key":"232_CR1","unstructured":"Advanced Micro Devices, Inc: Heterogeneous Computing Open CL and the ATI Radeon HD 5870 (Evergreen) Architecture (2010)"},{"key":"232_CR2","unstructured":"NVIDIA Tesla Computing Solutions, http:\/\/www.nvidia.com\/object\/tesla_computing_solutions.html"},{"key":"232_CR3","unstructured":"Hammond, L., Willey, M., Olukotun, K.: Data speculation support for a chip multiprocessor. In: Proceedings of the Eighth International Conference on Architectural Support for Programming Languages and Operating Systems"},{"key":"232_CR4","doi-asserted-by":"crossref","unstructured":"Steffan, J., Mowry, T.: The potential for using thread-level data speculation to facilitate automatic parallelization. In: Proceedings of the 4th International Symposium on High-Performance Computer, Architecture, pp. 2\u201313 (1998)","DOI":"10.1109\/HPCA.1998.650541"},{"issue":"6","key":"232_CR5","doi-asserted-by":"crossref","first-page":"759","DOI":"10.1109\/TC.2009.28","volume":"58","author":"S Liu","year":"2009","unstructured":"Liu, S., Gaudiot, J.-L.: Potential impact of value prediction on communication in many-core architectures. IEEE Trans. Comput. 58(6), 759\u2013769 (2009)","journal-title":"IEEE Trans. Comput."},{"key":"232_CR6","doi-asserted-by":"crossref","unstructured":"Liu, S., Eisenbeis, C., Gaudiot, J.-L.: Speculative execution on GPU: An exploratory study. In: 2010 39th International Conference on Parallel Processing (ICPP), pp. 453\u2013461 sept. (2010)","DOI":"10.1109\/ICPP.2010.53"},{"key":"232_CR7","doi-asserted-by":"crossref","unstructured":"Lipasti, M.H., Shen, J.P.: Exceeding the dataflow limit via value prediction. In: Proceedings of the 29th Annual ACM\/IEEE International Symposium on Microarchitecture","DOI":"10.1109\/MICRO.1996.566464"},{"key":"232_CR8","doi-asserted-by":"crossref","unstructured":"Sazeides, Y., Vassiliadis, S., Smith, J.E.: The performance potential of data dependence speculation& collapsing. In: Proceedings of the 29th Annual ACM\/IEEE International Symposium on Microarchitecture","DOI":"10.1109\/MICRO.1996.566465"},{"key":"232_CR9","unstructured":"Sazeides, Y., Smith, J.E.: The predictability of data values. In: Proceedings of the 30th annual ACM\/IEEE International Symposium on Microarchitecture"},{"key":"232_CR10","first-page":"1-20","volume":"11","author":"S Liu","year":"2010","unstructured":"Liu, S., Eisenbeis, C., Gaudiot, J.-L.: Value prediction and speculative execution on GPU. Int. J. Parallel Programm. 11, 1-20\u201320 (2010)","journal-title":"Int. J. Parallel Programm."},{"key":"232_CR11","doi-asserted-by":"crossref","unstructured":"Gupta, M., Nim, R.: Techniques for speculative run-time parallelization of loops. In: Proceedings of the 1998 ACM\/IEEE Conference on Supercomputing","DOI":"10.1109\/SC.1998.10053"},{"key":"232_CR12","doi-asserted-by":"crossref","unstructured":"Dang, F., Yu, H., Rauchwerger, L.: The R-LRPD test: Speculative parallelization of partially parallel loops, Technical report. College Station, TX, USA (2001)","DOI":"10.1109\/IPDPS.2002.1015493"},{"key":"232_CR13","unstructured":"Cintra, M., Llanos, D.R.: Toward efficient and robust software speculative parallelization on multiprocessors. In: Proceedings of the 9th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming"},{"key":"232_CR14","doi-asserted-by":"crossref","unstructured":"Marcuello, P., Tubella, J., Gonzalez, A.: Value prediction for speculative multithreaded architectures. In: Proceedings of the 32nd Annual ACM\/IEEE International Symposium on Microarchitecture, pp. 230\u2013236 (1999)","DOI":"10.1109\/MICRO.1999.809461"},{"key":"232_CR15","doi-asserted-by":"crossref","unstructured":"Oplinger, J.T., Heine, D.L., Lam, M.S.: In search of speculative thread-level parallelism. In: Proceedings of the 1999 International Conference on Parallel Architectures and Compilation Techniques","DOI":"10.21236\/ADA419602"},{"key":"232_CR16","unstructured":"CUDA Zone - the resource for CUDA developers http:\/\/www.nvidia.com\/object\/cuda_home_new.html"},{"key":"232_CR17","unstructured":"OpenCL\u2014The open standard for parallel programming of heterogeneous systems, http:\/\/www.khronos.org\/opencl\/"},{"issue":"5","key":"232_CR18","doi-asserted-by":"crossref","first-page":"879","DOI":"10.1109\/JPROC.2008.917757","volume":"96","author":"J Owens","year":"2008","unstructured":"Owens, J., Houston, M., Luebke, D., Green, S., Stone, J., Phillips, J.: GPU computing. Proc. IEEE 96(5), 879\u2013899 (2008)","journal-title":"Proc. IEEE"},{"key":"232_CR19","doi-asserted-by":"crossref","unstructured":"Jang, B., Kaeli, D., Do, S., Pien, H.: Multi GPU implementation of iterative tomographic reconstruction algorithms. In: ISBI\u201909: Proceedings of the Sixth IEEE International Conference on Symposium on Biomedical Imaging, pp. 185\u2013188. IEEE Press, Piscataway, NJ, USA (2009)","DOI":"10.1109\/ISBI.2009.5193014"},{"key":"232_CR20","unstructured":"ATI Radeon HD 5870 Graphics, http:\/\/www.amd.com\/us\/products\/desktop\/graphics\/ati-radeon-hd-5000\/hd-5870\/Pages\/ati-radeon-hd-5870-overview.aspx"},{"key":"232_CR21","unstructured":"2nd Generation Intel Core i7 Processor, http:\/\/www.intel.com\/products\/processor\/corei7\/index.htm"},{"key":"232_CR22","unstructured":"Intel Xeon Processor E5530, http:\/\/ark.intel.com\/Product.aspx?spec=SLBF7"},{"key":"232_CR23","doi-asserted-by":"crossref","first-page":"130","DOI":"10.1145\/1241601.1241625","volume":"35","author":"CD Spradling","year":"2007","unstructured":"Spradling, C.D.: SPEC CPU 2006 benchmark tools. SIGARCH Comput. Archit. News 35, 130\u2013134 (2007)","journal-title":"SIGARCH Comput. Archit. News"},{"key":"232_CR24","unstructured":"Bienia, C.: Benchmarking Modern Multiprocessors, Ph.D. dissertation. Princeton University, Jan. (2011)"},{"key":"232_CR25","unstructured":"ASC Sequoia Benchmark Codes, http:\/\/www.llnl.gov\/asc\/sequoia\/benchmarks"},{"key":"232_CR26","unstructured":"IRSmk source code from LLNL, http:\/\/www.llnl.gov\/asc\/sequoia\/benchmarks\/IRSmk_v0.9.0.tar"},{"key":"232_CR27","unstructured":"Kejariwal, A., Cas\u00e7aval, C.: Parallelization spectroscopy: analysis of thread-level parallelism in hpc programs. In: Proceedings of the 14th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming"},{"key":"232_CR28","unstructured":"SPEC 2006 benchmark suite, http:\/\/www.spec.org\/cpu2006\/"}],"container-title":["International Journal of Parallel Programming"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10766-012-0232-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10766-012-0232-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10766-012-0232-7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,22]],"date-time":"2025-04-22T23:13:03Z","timestamp":1745363583000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10766-012-0232-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,11,29]]},"references-count":28,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2014,2]]}},"alternative-id":["232"],"URL":"https:\/\/doi.org\/10.1007\/s10766-012-0232-7","relation":{},"ISSN":["0885-7458","1573-7640"],"issn-type":[{"type":"print","value":"0885-7458"},{"type":"electronic","value":"1573-7640"}],"subject":[],"published":{"date-parts":[[2012,11,29]]}}}