{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T01:03:26Z","timestamp":1743123806336,"version":"3.40.3"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319099668"},{"type":"electronic","value":"9783319099675"}],"license":[{"start":{"date-parts":[[2014,1,1]],"date-time":"2014-01-01T00:00:00Z","timestamp":1388534400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2014,1,1]],"date-time":"2014-01-01T00:00:00Z","timestamp":1388534400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014]]},"DOI":"10.1007\/978-3-319-09967-5_20","type":"book-chapter","created":{"date-parts":[[2014,9,30]],"date-time":"2014-09-30T15:10:04Z","timestamp":1412089804000},"page":"342-356","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Speculative Execution of Parallel Programs with Precise Exception Semantics on GPUs"],"prefix":"10.1007","author":[{"given":"Akihiro","family":"Hayashi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Max","family":"Grossman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jisheng","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Shirako","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vivek","family":"Sarkar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2014,10,1]]},"reference":[{"key":"20_CR1","unstructured":"APARAPI. API for Data Parallel Java. http:\/\/code.google.com\/p\/aparapi\/"},{"key":"20_CR2","doi-asserted-by":"crossref","unstructured":"Artigas, P.V., et al.: Automatic loop transformations and parallelization for Java. In: Proceedings of the 14th International Conference on Supercomputing, ICS \u201900, pp. 1\u201310. ACM, New York (2000)","DOI":"10.1145\/335231.335232"},{"key":"20_CR3","doi-asserted-by":"crossref","unstructured":"Cav\u00e9, V., et al.: Habanero-Java: the new adventures of old X10. In: PPPJ\u201911: Proceedings of 9th International Conference on the Principles and Practice of Programming in Java (2011)","DOI":"10.1145\/2093157.2093165"},{"key":"20_CR4","unstructured":"Android Developers. Renderscript. http:\/\/developer.android.com\/guide\/topics\/renderscript\/index.html"},{"key":"20_CR5","unstructured":"Ebcio\u011flu, K., Saraswat, V., Sarkar, V.: X10: programming for hierarchical parallelism and nonuniform data access (extended abstract). In: Language Runtimes \u201904 Workshop: Impact of Next Generation Processor Architectures On Virtual Machines (Colocated with OOPSLA 2004), October 2004. www.aurorasoft.net\/workshops\/lar04\/lar04home.htm"},{"key":"20_CR6","doi-asserted-by":"crossref","unstructured":"Hayashi, A., et al.: Accelerating Habanero-Java program with OpenCL generation. In: PPPJ\u201913: Proceedings of 10th International Conference on the Principles and Practice of Programming in Java (2013, under submission)","DOI":"10.1145\/2500828.2500840"},{"key":"20_CR7","doi-asserted-by":"crossref","unstructured":"Dubach, C., et al.: Compiling a high-level language for GPUs: (via language support for architectures and compilers). In: Proceedings of the 33rd ACM SIGPLAN Conference on Programming Language Design and Implementation, PLDI \u201912, pp. 1\u201312. ACM, New York (2012)","DOI":"10.1145\/2254064.2254066"},{"issue":"1","key":"20_CR8","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1002\/cpe.1341","volume":"21","author":"J Von Ronne","year":"2009","unstructured":"Von Ronne, J., et al.: Safe bounds check annotations. Concurrency Computat. Pract. Exper. 21(1), 41\u201357 (2009)","journal-title":"Concurrency Computat. Pract. Exper."},{"issue":"2","key":"20_CR9","doi-asserted-by":"publisher","first-page":"265","DOI":"10.1145\/349214.349222","volume":"22","author":"JE Moreira","year":"2000","unstructured":"Moreira, J.E., et al.: From flop to megaflops: Java for technical computing. ACM Trans. Program. Lang. Syst. 22(2), 265\u2013295 (2000)","journal-title":"ACM Trans. Program. Lang. Syst."},{"key":"20_CR10","doi-asserted-by":"crossref","unstructured":"Shirako, J., et al.: Phasers: a unified deadlock-free construct for collective and point-to-point synchronization. In: Proceedings of the 22nd Annual International Conference on Supercomputing, ICS \u201908, pp. 277\u2013288. ACM, New York (2008)","DOI":"10.1145\/1375527.1375568"},{"key":"20_CR11","doi-asserted-by":"crossref","unstructured":"Shirako, J., et al.: Phaser accumulators: a new reduction construct for dynamic parallelism. In: IPDPS 2009 (2009)","DOI":"10.1109\/IPDPS.2009.5161071"},{"key":"20_CR12","doi-asserted-by":"crossref","unstructured":"Samadi, M., et al.: Paragon: collaborative speculative loop execution on GPU and CPU. In: Proceedings of the 5th Annual Workshop on General Purpose Processing with Graphics Processing Units, GPGPU-5, pp. 64\u201373. ACM, New York (2012)","DOI":"10.1145\/2159430.2159438"},{"key":"20_CR13","doi-asserted-by":"crossref","unstructured":"Pratt-Szeliga, P.C., et al.: Rootbeer: seamlessly using GPUs from Java. In: 2012 IEEE 14th International Conference on High Performance Computing and Communication 2012 IEEE 9th International Conference on Embedded Software and Systems (HPCC-ICESS), June 2012, pp. 375\u2013380 (2012)","DOI":"10.1109\/HPCC.2012.57"},{"issue":"5","key":"20_CR14","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1145\/358438.349342","volume":"35","author":"R Bod\u00edk","year":"2000","unstructured":"Bod\u00edk, R., et al.: ABCD: eliminating array bounds checks on demand. SIGPLAN Not. 35(5), 321\u2013333 (2000)","journal-title":"SIGPLAN Not."},{"key":"20_CR15","doi-asserted-by":"crossref","unstructured":"Chandra, S., et al.: Type inference for locality analysis of distributed data structures. In: PPoPP \u201908: Proceedings of the 13th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, pp. 11\u201322. ACM, New York (2008)","DOI":"10.1145\/1345206.1345211"},{"key":"20_CR16","doi-asserted-by":"crossref","unstructured":"W\u00fcrthinger, T., et al.: Array bounds check elimination for the Java HotSpot client compiler. In: Proceedings of the 5th International Symposium on Principles and Practice of Programming in Java, PPPJ \u201907, pp. 125\u2013133. ACM, New York (2007)","DOI":"10.1145\/1294325.1294343"},{"key":"20_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"887","DOI":"10.1007\/978-3-642-03869-3_82","volume-title":"Euro-Par 2009 Parallel Processing","author":"Y Yan","year":"2009","unstructured":"Yan, Y., Grossman, M., Sarkar, V.: JCUDA: a programmer-friendly interface for accelerating Java programs with CUDA. In: Sips, H., Epema, D., Lin, H.-X. (eds.) Euro-Par 2009. LNCS, vol. 5704, pp. 887\u2013899. Springer, Heidelberg (2009)"},{"key":"20_CR18","unstructured":"Fan, Z., et al.: GPU cluster for high performance computing. In: Proceedings of the 2004 ACM\/IEEE Conference on Supercomputing, SC \u201904, p. 47. IEEE Computer Society, Washington, DC (2004)"},{"key":"20_CR19","unstructured":"Guo, Y., et al.: Work-first and help-first scheduling policies for async-finish task parallelism. In: IPDPS \u201909: International Parallel and Distributed Processing Symposium (2009)"},{"key":"20_CR20","unstructured":"JGF. The Java Grande Forum benchmark suite. http:\/\/www.epcc.ed.ac.uk\/javagrande\/javag.html"},{"key":"20_CR21","doi-asserted-by":"crossref","unstructured":"Lublinerman, R., et al.: Delegated isolation. In: OOPSLA \u201911: Proceeding of the 26th ACM SIGPLAN Conference on Object Oriented Programming Systems Languages and Applications (2011)","DOI":"10.1145\/2048066.2048133"},{"issue":"Suppl 2","key":"20_CR22","doi-asserted-by":"publisher","first-page":"S10","DOI":"10.1186\/1471-2105-9-S2-S10","volume":"9","author":"SA Manavski","year":"2008","unstructured":"Manavski, S.A., Valle, G.: CUDA compatible GPU cards as efficient hardware accelerators for Smith-Waterman sequence alignment. BMC Bioinform. 9(Suppl 2), S10 (2008)","journal-title":"BMC Bioinform."},{"key":"20_CR23","unstructured":"Parboil. Parboil benchmarks. http:\/\/impact.crhc.illinois.edu\/parboil.aspx"},{"key":"20_CR24","unstructured":"PolyBench. The polyhedral benchmark suite. http:\/\/www.cse.ohio-state.edu\/pouchet\/software\/polybench"}],"container-title":["Lecture Notes in Computer Science","Languages and Compilers for Parallel Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-09967-5_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,31]],"date-time":"2023-01-31T01:14:20Z","timestamp":1675127660000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-09967-5_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014]]},"ISBN":["9783319099668","9783319099675"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-09967-5_20","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2014]]},"assertion":[{"value":"1 October 2014","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}