{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T19:12:44Z","timestamp":1672600364433},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2017,2,28]],"date-time":"2017-02-28T00:00:00Z","timestamp":1488240000000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Sign Process Syst"],"published-print":{"date-parts":[[2018,1]]},"DOI":"10.1007\/s11265-017-1229-7","type":"journal-article","created":{"date-parts":[[2017,2,28]],"date-time":"2017-02-28T07:30:42Z","timestamp":1488267042000},"page":"3-27","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Loop Parallelization Techniques for FPGA Accelerator Synthesis"],"prefix":"10.1007","volume":"90","author":[{"given":"Oliver","family":"Reiche","sequence":"first","affiliation":[]},{"given":"M. Akif","family":"\u00d6zkan","sequence":"additional","affiliation":[]},{"given":"Frank","family":"Hannig","sequence":"additional","affiliation":[]},{"given":"J\u00fcrgen","family":"Teich","sequence":"additional","affiliation":[]},{"given":"Moritz","family":"Schmid","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2017,2,28]]},"reference":[{"key":"1229_CR1","doi-asserted-by":"publisher","unstructured":"Aditya, S., & Kathail, V. (2008). Algorithmic synthesis using PICO: An integrated framework for application engine synthesis and verification from high level C algorithms. In P. Coussy & A. Morawiec (Eds.), High-level synthesis: from algorithm to digital circuit (chap. 4, pp. 53\u201374). Springer. doi:\n                        10.1007\/978-1-4020-8588-8_4\n                        \n                    .","DOI":"10.1007\/978-1-4020-8588-8_4"},{"key":"1229_CR2","first-page":"575","volume-title":"Proceedings of the conference on design, automation and test in europe (DATE)","author":"C Alias","year":"2013","unstructured":"Alias, C., Darte, A., & Plesco, A. (2013). Optimizing remote accesses for offloaded kernels: application to high-level synthesis for FPGA, Proceedings of the conference on design, automation and test in europe (DATE) (pp. 575\u2013580)."},{"key":"1229_CR3","first-page":"483","volume-title":"Proceedings of the spring joint computer conference (AFIPS)","author":"G Amdahl","year":"1967","unstructured":"Amdahl, G. (1967). Validity of the single processor approach to achieving large scale computing capabilities, Proceedings of the spring joint computer conference (AFIPS) (pp. 483\u2013485)."},{"key":"1229_CR4","doi-asserted-by":"crossref","unstructured":"Bailey, D. (2011). Design for embedded image processing on FPGAs. Wiley.","DOI":"10.1002\/9780470828519"},{"key":"1229_CR5","doi-asserted-by":"crossref","unstructured":"Bondhugula, U., Hartono, A., Ramanujam, J., & Sadayappan, P. (2008). A practical automatic polyhedral parallelizer and locality optimizer (Vol. 43, no. 6, pp. 101\u2013113).","DOI":"10.1145\/1375581.1375595"},{"key":"1229_CR6","doi-asserted-by":"crossref","unstructured":"Canis, A., Choi, J., Aldham, M., Zhang, V., Kammoona, A., Anderson, J., Brown, S., & Czajkowski, T. (2011). LegUp: High-level synthesis for FPGA-based processor\/accelerator systems, Proceedings of the international symposium on field programmable gate arrays (FPGA) (pp. 33\u201336).","DOI":"10.1145\/1950413.1950423"},{"key":"1229_CR7","first-page":"270","volume-title":"Proceedings of the international conference on field-programmable technology (FPT)","author":"J Choi","year":"2013","unstructured":"Choi, J., Brown, S., & Anderson, J. (2013). From software threads to parallel hardware in high-level synthesis for FPGAs, Proceedings of the international conference on field-programmable technology (FPT) (pp. 270\u2013277)."},{"key":"1229_CR8","doi-asserted-by":"publisher","unstructured":"Feautrier, P., & Lengauer, C. (2011). Polyhedron model. In D. Padua (Ed.), Encyclopedia of parallel computing (pp. 1581\u20131592). Springer. doi:\n                        10.1007\/978-0-387-09766-4_502\n                        \n                    .","DOI":"10.1007\/978-0-387-09766-4_502"},{"key":"1229_CR9","first-page":"120","volume-title":"Proceedings of the international conference on field-programmable technology (FPT)","author":"N George","year":"2013","unstructured":"George, N., Novo, D., Rompf, T., Odersky, M., & Ienne, P. (2013). Making domain-specific hardware synthesis tools cost-efficient, Proceedings of the international conference on field-programmable technology (FPT) (pp. 120\u2013127)."},{"key":"1229_CR10","doi-asserted-by":"publisher","unstructured":"Hannig, F., Ruckdeschel, H., Dutta, H., & Teich, J. (2008). PARO: Synthesis of hardware accelerators for multi-dimensional dataflow-intensive applications, Proceedings of the 4th international workshop on applied reconfigurable computing (ARC), Lecture Notes in Computer Science (LNCS) (Vol. 4943, pp. 287\u2013293).\n                    \n                        10.1007\/978-3-540-78610-8_30\n                        \n                    : Springer.","DOI":"10.1007\/978-3-540-78610-8_30"},{"key":"1229_CR11","first-page":"144:1","volume-title":"Proceedings of the 41st international conference on computer graphics and interactive techniques (SIGGRAPH)","author":"J Hegarty","year":"2014","unstructured":"Hegarty, J., Brunhaver, J., DeVito, Z., Ragan-Kelley, J., Cohen, N., Bell, S., Vasilyev, A., Horowitz, M., & Hanrahan, P. (2014). Darkroom: Compiling high-level image processing code into hardware pipelines, Proceedings of the 41st international conference on computer graphics and interactive techniques (SIGGRAPH) (pp. 144:1\u2013144:11)."},{"key":"1229_CR12","first-page":"51","volume-title":"Proceedings of the international conference on parallel processing (ICPP)","author":"D Hwang","year":"1993","unstructured":"Hwang, D., Cho, S., Kim, Y., & Han, S. (1993). Exploiting spatial and temporal parallelism in the multithreaded node architecture implemented on superscalar RISC processors, Proceedings of the international conference on parallel processing (ICPP) (pp. 51\u201354)."},{"key":"1229_CR13","doi-asserted-by":"publisher","first-page":"318","DOI":"10.1145\/53990.54022","volume-title":"Proceedings of the ACM SIGPLAN Conference on Programming Language Design and Implementation (PLDI)","author":"M Lam","year":"1988","unstructured":"Lam, M. (1988). Software pipelining: An effective scheduling technique for VLIW machines, Proceedings of the ACM SIGPLAN Conference on Programming Language Design and Implementation (PLDI). doi:\n                        10.1145\/53990.54022\n                        \n                     (pp. 318\u2013328)."},{"key":"1229_CR14","doi-asserted-by":"crossref","unstructured":"Lattuada, M., & Ferrandi, F. (2015). Exploiting outer loops vectorization in high level synthesis, Proceedings of the 28th international conference on architecture of computing systems (ARCS), lecture notes in computer science (LNCS) (Vol. 9017, pp. 31\u201342) . Springer.","DOI":"10.1007\/978-3-319-16086-3_3"},{"key":"1229_CR15","unstructured":"Li, P., Pouchet, L. N., & Cong, J. (2014). Throughput optimization for high-level synthesis using resource constraints. In S. Rajopadhye, & S. Verdoolaege (Eds.), Proceedings of the 4th international workshop on polyhedral compilation techniques. Vienna, Austria."},{"key":"1229_CR16","doi-asserted-by":"publisher","first-page":"86:1","DOI":"10.7873\/DATE.2014.099","volume-title":"Proceedings of the conference on design, automation and test in Europe (DATE)","author":"R Membarth","year":"2014","unstructured":"Membarth, R., Reiche, O., Hannig, F., & Teich, J. (2014). Code Generation for Embedded Heterogeneous Architectures on Android, Proceedings of the conference on design, automation and test in Europe (DATE). doi:\n                        10.7873\/DATE.2014.099\n                        \n                     (pp. 86:1\u201386:6). Dresden, Germany: IEEE."},{"issue":"1","key":"1229_CR17","doi-asserted-by":"publisher","first-page":"210","DOI":"10.1109\/TPDS.2015.2394802","volume":"27","author":"R Membarth","year":"2016","unstructured":"Membarth, R., Reiche, O., Hannig, F., Teich, J., K\u00f6rner, M., & Eckert, W. (2016). HIPAcc: A domain-specific language and compiler for image processing. IEEE Transactions on Parallel and Distributed Systems, 27(1), 210\u2013224. doi:\n                        10.1109\/TPDS.2015.2394802\n                        \n                    .","journal-title":"IEEE Transactions on Parallel and Distributed Systems"},{"key":"1229_CR18","unstructured":"Mentor Graphics (2016). Catapult High-Level Synthesis. \n                        https:\/\/www.mentor.com\/hls-lp\/catapult-high-level-synthesis\/\n                        \n                    ."},{"key":"1229_CR19","doi-asserted-by":"publisher","unstructured":"Meredith, M. (2008). High-level SystemC synthesis with Forte\u2019s Cynthesizer. In P. Coussy & A. Morawiec (Eds.), High-level synthesis: from algorithm to digital circuit (chap. 5, pp. 75\u201397). Springer. doi:\n                        10.1007\/978-1-4020-8588-8_5\n                        \n                    .","DOI":"10.1007\/978-1-4020-8588-8_5"},{"key":"1229_CR20","first-page":"186","volume-title":"Proceedings of the international symposium on field-programmable custom computing machines (FCCM)","author":"M Owaida","year":"2011","unstructured":"Owaida, M., Bellas, N., Daloukas, K., & Antonopoulos, C. (2011). Synthesis of platform architectures from openCL programs, Proceedings of the international symposium on field-programmable custom computing machines (FCCM) (pp. 186\u2013193)."},{"key":"1229_CR21","doi-asserted-by":"publisher","unstructured":"\u00d6zkan, M., Reiche, O., Hannig, F., & Teich, J. FPGA-based accelerator design from a domain-specific language, Proceedings of the 26th international conference on field-programmable logic and applications (FPL). doi:\n                        10.1109\/FPL.2016.7577357\n                        \n                    .","DOI":"10.1109\/FPL.2016.7577357"},{"key":"1229_CR22","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1109\/SASP.2009.5226333","volume-title":"Proceedings of the IEEE 7th symposium on application specific processors (SASP)","author":"A Papakonstantinou","year":"2009","unstructured":"Papakonstantinou, A., Gururaj, K., Stratton, J., Chen, D., Cong, J., & Hwu, W. M. (2009). FCUDA: Enabling efficient compilation of CUDA kernels onto FPGAs, Proceedings of the IEEE 7th symposium on application specific processors (SASP). doi:\n                        10.1109\/SASP.2009.5226333\n                        \n                     (pp. 35\u201342)."},{"issue":"4","key":"1229_CR23","first-page":"16:1","volume":"6","author":"F Plavec","year":"2013","unstructured":"Plavec, F., Vranesic, Z., & Brown, S. (2013). Exploiting task- and data-level parallelism in streaming applications implemented in FPGAs. ACM Transactions on Reconfigurable Technology and Systems (TRETS), 6(4), 16:1\u201316:37.","journal-title":"ACM Transactions on Reconfigurable Technology and Systems (TRETS)"},{"key":"1229_CR24","doi-asserted-by":"crossref","unstructured":"Pouchet, L. N., Zhang, P., Sadayappan, P., & Cong, J. (2013). Polyhedral-based data reuse optimization for configurable computing, Proceedings of the ACM\/SIGDA international symposium on field programmable gate arrays (pp. 29\u201338). ACM.","DOI":"10.1145\/2435264.2435273"},{"key":"1229_CR25","doi-asserted-by":"publisher","unstructured":"P\u00fcschel, M., Franchetti, F., & Voronenko, Y. (2011). Spiral. In D. Padua (Ed.), Encyclopedia of parallel computing (pp. 1920\u20131933). Springer. doi:\n                        10.1007\/978-0-387-09766-4\n                        \n                    .","DOI":"10.1007\/978-0-387-09766-4"},{"issue":"1","key":"1229_CR26","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1109\/71.744833","volume":"10","author":"N Ratha","year":"1999","unstructured":"Ratha, N., & Jain, A. (1999). Computer vision algorithms on reconfigurable logic arrays. IEEE Transactions on Parallel and Distributed Systems (TPDS), 10(1), 29\u201343.","journal-title":"IEEE Transactions on Parallel and Distributed Systems (TPDS)"},{"key":"1229_CR27","doi-asserted-by":"publisher","unstructured":"Reiche, O., Schmid, M., Hannig, F., Membarth, R., & Teich, J. (2014). Code generation from a domain-specific language for C-based HLS of hardware accelerators, Proceedings of the international conference on hardware\/software codesign and system synthesis (CODES+ISSS) (pp. 17:1\u201317:10). \n                        10.1145\/2656075.2656081\n                        \n                    : ACM.","DOI":"10.1145\/2656075.2656081"},{"key":"1229_CR28","doi-asserted-by":"crossref","unstructured":"Schmid, M., Reiche, O., Hannig, F., & Teich, J. (2015). Loop coarsening in C-based high-level synthesis, Proceedings of the 26th IEEE international conference on application-specific systems, architectures and processors (ASAP) (pp. 166\u2013173). IEEE.","DOI":"10.1109\/ASAP.2015.7245730"},{"key":"1229_CR29","doi-asserted-by":"publisher","first-page":"180","DOI":"10.1109\/ISORCW.2012.39","volume-title":"Proceedings of the 15th IEEE international symposium on object\/component\/service-oriented real-time distributed computing workshops (ISORCW)","author":"M Schmidt","year":"2012","unstructured":"Schmidt, M., Reichenbach, M., & Fey, D. (2012). A generic VHDL template for 2D stencil code applications on FPGAs, Proceedings of the 15th IEEE international symposium on object\/component\/service-oriented real-time distributed computing workshops (ISORCW). doi:\n                        10.1109\/ISORCW.2012.39\n                        \n                     (pp. 180\u2013187)."},{"key":"1229_CR30","unstructured":"Singh, D. (2011). Implementing FPGA design with the openCL standard Altera whitepaper."},{"key":"1229_CR31","doi-asserted-by":"crossref","unstructured":"Tomasi, C., & Manduchi, R. (1998). Bilateral filtering for gray and color images, Proceedings of the 6th international conference on computer vision (ICCV) (pp. 839\u2013846). IEEE.","DOI":"10.1109\/ICCV.1998.710815"},{"key":"1229_CR32","doi-asserted-by":"crossref","unstructured":"Trifunovic, K., Nuzman, D., Cohen, A., Zaks, A., & Rosen, I. (2009). Polyhedral-model guided loop-nest auto-vectorization, Proceedings of the 18th international conference on parallel architectures and compilation techniques (PACT) (pp. 327\u2013337). IEEE.","DOI":"10.1109\/PACT.2009.18"},{"key":"1229_CR33","first-page":"127","volume-title":"Proceedings of the international symposium on field-programmable custom computing machines (FCCM)","author":"J Villarreal","year":"2010","unstructured":"Villarreal, J., Park, A., Najjar, W., & Halstead, R. (2010). Designing modular hardware accelerators in C with ROCCC 2.0, Proceedings of the international symposium on field-programmable custom computing machines (FCCM) (pp. 127\u2013134)."},{"issue":"12","key":"1229_CR34","doi-asserted-by":"crossref","first-page":"1507","DOI":"10.1109\/43.898829","volume":"19","author":"K Wakabayashi","year":"2000","unstructured":"Wakabayashi, K., & Okamoto, T. (2000). C-based SoC design flow and EDA tools: An ASIC and system vendor perspective. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD), 19(12), 1507\u20131522.","journal-title":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD)"},{"key":"1229_CR35","first-page":"460","volume-title":"Proceedings of the IEEE international solid-state circuits conference - digest of technical papers","author":"C Wang","year":"2014","unstructured":"Wang, C., Yuan, F. L., Yu, T. H., & Markovic, D. (2014). 27.5 a multi-granularity FPGA with hierarchical interconnects for efficient and flexible mobile computing, Proceedings of the IEEE international solid-state circuits conference - digest of technical papers (pp. 460\u2013461)."},{"key":"1229_CR36","doi-asserted-by":"crossref","first-page":"655","DOI":"10.1145\/76263.76337","volume-title":"Proceedings of the 1989 ACM\/IEEE conference on supercomputing","author":"M Wolfe","year":"1989","unstructured":"Wolfe, M. (1989). More iteration space tiling, Proceedings of the 1989 ACM\/IEEE conference on supercomputing (pp. 655\u2013664)."},{"key":"1229_CR37","unstructured":"Xilinx Inc. (2016). Vivado High-Level Synthesis. \n                        http:\/\/www.xilinx.com\/products\/design-tools\/vivado\/integration\/esl-design.html\n                        \n                    ."},{"key":"1229_CR38","doi-asserted-by":"publisher","unstructured":"Zhang, Z., Fan, Y., Jiang, W., Han, G., Yang, C., & Cong, J. (2008). AutoPilot: A platform-based ESL synthesis system. In P. Coussy & A. Morawiec (Eds.), High-level synthesis: from algorithm to digital circuit (chap. 6, pp. 99\u2013112). Springer. doi:\n                        10.1007\/978-1-4020-8588-8_6\n                        \n                    .","DOI":"10.1007\/978-1-4020-8588-8_6"}],"container-title":["Journal of Signal Processing Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11265-017-1229-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11265-017-1229-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11265-017-1229-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2018,1,11]],"date-time":"2018-01-11T01:11:40Z","timestamp":1515633100000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11265-017-1229-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,2,28]]},"references-count":38,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2018,1]]}},"alternative-id":["1229"],"URL":"https:\/\/doi.org\/10.1007\/s11265-017-1229-7","relation":{},"ISSN":["1939-8018","1939-8115"],"issn-type":[{"value":"1939-8018","type":"print"},{"value":"1939-8115","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,2,28]]}}}