{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,21]],"date-time":"2025-09-21T17:17:27Z","timestamp":1758475047960,"version":"3.40.3"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030178710"},{"type":"electronic","value":"9783030178727"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-17872-7_5","type":"book-chapter","created":{"date-parts":[[2019,4,23]],"date-time":"2019-04-23T22:03:00Z","timestamp":1556056980000},"page":"74-89","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Polyhedral Optimization of TensorFlow Computation Graphs"],"prefix":"10.1007","author":[{"given":"Beno\u00eet","family":"Pradelle","sequence":"first","affiliation":[]},{"given":"Beno\u00eet","family":"Meister","sequence":"additional","affiliation":[]},{"given":"Muthu","family":"Baskaran","sequence":"additional","affiliation":[]},{"given":"Jonathan","family":"Springer","sequence":"additional","affiliation":[]},{"given":"Richard","family":"Lethin","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,4,24]]},"reference":[{"key":"5_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"308","DOI":"10.1007\/978-3-642-10445-9_16","volume-title":"Middleware 2009","author":"R Khandekar","year":"2009","unstructured":"Khandekar, R., et al.: COLA: optimizing stream processing applications via graph partitioning. In: Bacon, J.M., Cooper, B.F. (eds.) Middleware 2009. LNCS, vol. 5896, pp. 308\u2013327. Springer, Heidelberg (2009). https:\/\/doi.org\/10.1007\/978-3-642-10445-9_16"},{"key":"5_CR2","unstructured":"Abadi, M., et al.: Tensorflow: large-scale machine learning on heterogeneous distributed systems (2015). http:\/\/download.tensorflow.org\/paper\/whitepaper2015.pdf"},{"key":"5_CR3","doi-asserted-by":"crossref","unstructured":"Atasu, K., Pozzi, L., Ienne, P.: Automatic application-specific instruction-set extensions under microarchitectural constraints. In: Proceedings of the 40th Annual Design Automation Conference, pp. 256\u2013261. ACM (2003)","DOI":"10.1145\/775832.775897"},{"key":"5_CR4","unstructured":"Baghdadi, R., et al.: PENCIL: a platform-neutral compute intermediate language for accelerator programming. In: Parallel Architectures and Compilation Techniques (PACT), San Francisco, CA, USA (2015). https:\/\/hal.archives-ouvertes.fr\/hal-01257236"},{"key":"5_CR5","unstructured":"Bastoul, C., et al.: System, methods and apparatus for program optimization for multi-threaded processor architectures, April 2010"},{"key":"5_CR6","doi-asserted-by":"crossref","unstructured":"Bergstra, J., et al.: Theano: a CPU and GPU math compiler in Python (2011)","DOI":"10.25080\/Majora-92bf1922-003"},{"key":"5_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"132","DOI":"10.1007\/978-3-540-78791-4_9","volume-title":"Compiler Construction","author":"U Bondhugula","year":"2008","unstructured":"Bondhugula, U., Baskaran, M., Krishnamoorthy, S., Ramanujam, J., Rountev, A., Sadayappan, P.: Automatic transformations for communication-minimized parallelization and locality optimization in the polyhedral model. In: Hendren, L. (ed.) CC 2008. LNCS, vol. 4959, pp. 132\u2013146. Springer, Heidelberg (2008). https:\/\/doi.org\/10.1007\/978-3-540-78791-4_9"},{"key":"5_CR8","unstructured":"Chen, T., et al.: MXNet: a flexible and efficient machine learning library for heterogeneous distributed systems. CoRR abs\/1512.01274 (2015). http:\/\/arxiv.org\/abs\/1512.01274"},{"issue":"1","key":"5_CR9","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1145\/346023.346031","volume":"28","author":"P Clauss","year":"2000","unstructured":"Clauss, P., Meister, B.: Automatic memory layout transformation to optimize spatial locality in parameterized loop nests. ACM SIGARCH Comput. Archit. News 28(1), 11\u201319 (2000)","journal-title":"ACM SIGARCH Comput. Archit. News"},{"key":"5_CR10","unstructured":"Collobert, R., Kavukcuoglu, K., Farabet, C.: Torch7: a matlab-like environment for machine learning. In: BigLearn, NIPS Workshop No. EPFL-CONF-192376 (2011)"},{"issue":"4","key":"5_CR11","doi-asserted-by":"publisher","first-page":"543","DOI":"10.1007\/s10619-013-7130-x","volume":"31","author":"M Dayarathna","year":"2013","unstructured":"Dayarathna, M., Suzumura, T.: Automatic optimization of stream programs via source program operator graph transformations. Distrib. Parallel Databases 31(4), 543\u2013599 (2013). https:\/\/doi.org\/10.1007\/s10619-013-7130-x","journal-title":"Distrib. Parallel Databases"},{"key":"5_CR12","doi-asserted-by":"crossref","unstructured":"Feautrier, P.: Some efficient solutions to the affine scheduling problem. Part I. One-dimensional time. Int. J. Parallel Program. 21(5), 313\u2013348 (1992). citeseer.ist.psu.edu\/feautrier92some.html","DOI":"10.1007\/BF01407835"},{"issue":"04","key":"5_CR13","doi-asserted-by":"publisher","first-page":"1250010","DOI":"10.1142\/S0129626412500107","volume":"22","author":"T Grosser","year":"2012","unstructured":"Grosser, T., Groesslinger, A., Lengauer, C.: Polly-performing polyhedral optimizations on a low-level intermediate representation. Parallel Process. Lett. 22(04), 1250010 (2012)","journal-title":"Parallel Process. Lett."},{"key":"5_CR14","doi-asserted-by":"crossref","unstructured":"Irigoin, F., Triolet, R.: Supernode partitioning. In: Proceedings of the 15th ACM SIGPLAN-SIGACT Symposium on Principles of programming languages, pp. 319\u2013329. ACM Press, New York, January 1988","DOI":"10.1145\/73560.73588"},{"key":"5_CR15","doi-asserted-by":"crossref","unstructured":"Jia, Y., et al.: Caffe: convolutional architecture for fast feature embedding (2014)","DOI":"10.1145\/2647868.2654889"},{"issue":"11","key":"5_CR16","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278\u20132324 (1998)","journal-title":"Proc. IEEE"},{"key":"5_CR17","unstructured":"Lethin, R.A., Leung, A.K., Meister, B.J., Vasilache, N.T.: Methods and apparatus for joint parallelism and locality optimization in source code compilation, September 2009"},{"key":"5_CR18","unstructured":"Meister, B., Baskaran, M.M., Pradelle, B., Henretty, T., Lethin, R.: Efficient compilation to event-driven task programs. CoRR abs\/1601.05458 (2016). http:\/\/arxiv.org\/abs\/1601.05458"},{"key":"5_CR19","doi-asserted-by":"publisher","first-page":"1756","DOI":"10.1007\/978-0-387-09766-4","volume-title":"Encyclopedia of Parallel Computing","author":"B Meister","year":"2011","unstructured":"Meister, B., Vasilache, N., Wohlford, D., Baskaran, M.M., Leung, A., Lethin, R.: R-stream compiler. In: Padua, D. (ed.) Encyclopedia of Parallel Computing, pp. 1756\u20131765. Springer, Boston (2011). https:\/\/doi.org\/10.1007\/978-0-387-09766-4"},{"key":"5_CR20","unstructured":"Meister, B., et al.: SANE: an array language for sensor applications. In: Proceedings of a Workshop on Domain-Specific Languages and High-Level Frameworks for High Performance Computing, Salt Lake City, UT, USA, November 16 2012"},{"key":"5_CR21","unstructured":"Pop, S., et al.: GRAPHITE: loop optimizations based on the polyhedral model for GCC. In: Proceedings of the 4th GCC Developper\u2019s Summit, pp. 179\u2013198. Ottawa, Canada, June 2006"},{"key":"5_CR22","doi-asserted-by":"crossref","unstructured":"Pradelle, B., Meister, B., Baskaran, M.M., Konstantinidis, A., Henretty, T., Lethin, R.: Scalable hierarchical polyhedral compilation. In: International Conference on Parallel Processing (ICPP) (2016)","DOI":"10.1109\/ICPP.2016.56"},{"key":"5_CR23","unstructured":"Vasilache, N., et al.: A tale of three runtimes. arXiv:1409.1914"},{"key":"5_CR24","doi-asserted-by":"crossref","unstructured":"Verdoolaege, S.: isl: an integer set library for the polyhedral model. In: Proceedings of the Third international congress conference on Mathematical software (ICMS 2010), pp. 299\u2013302. ACM Press (2010)","DOI":"10.1007\/978-3-642-15582-6_49"},{"key":"5_CR25","unstructured":"Verdoolaege, S., Janssens, G.: Scheduling for PPCG. Technical report, Department of Computer Science, KU Leuven (2017)"},{"issue":"4","key":"5_CR26","doi-asserted-by":"publisher","first-page":"54:1","DOI":"10.1145\/2400682.2400713","volume":"9","author":"S Verdoolaege","year":"2013","unstructured":"Verdoolaege, S., Juega, J.C., Cohen, A., G\u00f3mez, J.I., Tenllado, C., Catthoor, F.: Polyhedral parallel code generation for CUDA. ACM Trans. Archit. Code Optim. 9(4), 54:1\u201354:23 (2013)","journal-title":"ACM Trans. Archit. Code Optim."},{"issue":"6","key":"5_CR27","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1109\/MSP.2015.2462371","volume":"32","author":"D Yu","year":"2015","unstructured":"Yu, D., Yao, K., Zhang, Y.: The computational network toolkit [best of the web]. IEEE Signal Process. Mag. 32(6), 123\u2013126 (2015)","journal-title":"IEEE Signal Process. Mag."}],"container-title":["Lecture Notes in Computer Science","Programming and Performance Visualization Tools"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-17872-7_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,12,7]],"date-time":"2020-12-07T07:55:19Z","timestamp":1607327719000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-17872-7_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030178710","9783030178727"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-17872-7_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"24 April 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ESPT","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Workshop on Extreme-Scale Programming Tools","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Denver, CO","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2017","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 November 2017","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 November 2017","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"espt2017","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.vi-hps.org\/symposia\/archive\/espt-workshop-series\/espt-sc17.html","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}