{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T17:40:12Z","timestamp":1743529212399,"version":"3.40.3"},"publisher-location":"Berlin, Heidelberg","reference-count":27,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642311246"},{"type":"electronic","value":"9783642311253"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2012]]},"DOI":"10.1007\/978-3-642-31125-3_2","type":"book-chapter","created":{"date-parts":[[2012,6,18]],"date-time":"2012-06-18T09:24:23Z","timestamp":1340011463000},"page":"15-28","source":"Crossref","is-referenced-by-count":0,"title":["Feedback-Based Global Instruction Scheduling for GPGPU Applications"],"prefix":"10.1007","author":[{"given":"Constantin","family":"Timm","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Markus","family":"G\u00f6rlich","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Frank","family":"Weichert","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peter","family":"Marwedel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Heinrich","family":"M\u00fcller","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"2_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"1074","DOI":"10.1007\/BFb0002855","volume-title":"Euro-Par \u201997 Parallel Processing","author":"S. Banerjia","year":"1997","unstructured":"Banerjia, S., Havanki, W.A., Conte, T.M.: Treegion Scheduling for Highly Parallel Processors. In: Lengauer, C., Griebl, M., Gorlatch, S. (eds.) Euro-Par 1997. LNCS, vol.\u00a01300, pp. 1074\u20131078. Springer, Heidelberg (1997)"},{"key":"2_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1007\/978-3-540-71528-3_2","volume-title":"Transactions on High-Performance Embedded Architectures and Compilers I","author":"K. Bosschere De","year":"2007","unstructured":"De Bosschere, K., Luk, W., Martorell, X., Navarro, N., O\u2019Boyle, M., Pnevmatikatos, D., Ram\u00edrez, A., Sainrat, P., Seznec, A., Stenstr\u00f6m, P., Temam, O.: High-Performance Embedded Architecture and Compilation Roadmap. In: Stenstr\u00f6m, P. (ed.) Transactions on High-Performance Embedded Architectures and Compilers I. LNCS, vol.\u00a04050, pp. 5\u201329. Springer, Heidelberg (2007)"},{"key":"2_CR3","doi-asserted-by":"crossref","unstructured":"Che, S., Boyer, M., Meng, J., Tarjan, D., Sheaffer, J.W., Lee, S.H., Skadron, K.: Rodinia: A Benchmark Suite for Heterogeneous Computing. In: Proceedings of the IEEE International Symposium on Workload Characterization (IISWC), pp. 44\u201354 (2009)","DOI":"10.1109\/IISWC.2009.5306797"},{"key":"2_CR4","doi-asserted-by":"crossref","unstructured":"Cho, S., Melhem, R.: Corollaries to Amdahl\u2019s Law for Energy. IEEE Computer Architecture Letters, 25\u201328 (2008)","DOI":"10.1109\/L-CA.2007.18"},{"key":"2_CR5","unstructured":"Dominguez, R., Kaeli, D.R.: Improving the open64 backend for GPUs. Poster at Google Summer School (2009)"},{"key":"2_CR6","unstructured":"G\u00f6rlich, M.: Untersuchung und Verbesserung der Speicherzugriffsverteilung in GPGPU-Programmen unter Nutzung von lokalen Schedulingmethoden. Master\u2019s thesis, Embedded System Group, Faculty of Computer Science, TU Dortmund (2011)"},{"key":"2_CR7","doi-asserted-by":"crossref","unstructured":"Han, T.D., Abdelrahman, T.S.: Reducing branch Divergence in GPU Programs. In: Proceedings of the Fourth Workshop on General Purpose Processing on Graphics Processing Units, pp. 1\u20138 (2011)","DOI":"10.1145\/1964179.1964184"},{"key":"2_CR8","doi-asserted-by":"crossref","unstructured":"Hong, S., Kim, H.: An Analytical Model for a GPU Architecture with Memory-level and Thread-level Parallelism Awareness. In: Proceedings of the 36th Annual International Symposium on Computer Architecture (ISCA), pp. 152\u2013163 (2009)","DOI":"10.1145\/1555754.1555775"},{"key":"2_CR9","doi-asserted-by":"crossref","unstructured":"Kerns, D.R., Eggers, S.J.: Balanced Scheduling: Instruction Scheduling When Memory Latency is Uncertain. In: Proceedings of the ACM SIGPLAN Conference on Programming Language Design and Implementation (PLDI), pp. 278\u2013289 (1993)","DOI":"10.1145\/173262.155117"},{"key":"2_CR10","unstructured":"Kerr, A., Campbell, D., Richards, M.: GPU VSIPL: High-Performance VSIPL Implementation for GPUs. In: Proceedings of the 12th High Performance Embedded Computing Workshop (HPEC), Lexington, Massachusetts, USA (2008)"},{"key":"2_CR11","doi-asserted-by":"crossref","unstructured":"Kung, S.Y., Kailath, T., Whitehouse, H.J.: VLSI and Modern Signal Processing. Prentice Hall Professional Technical Reference (1984)","DOI":"10.1016\/0165-1684(85)90048-9"},{"key":"2_CR12","doi-asserted-by":"crossref","unstructured":"Leupers, R.: Instruction Scheduling for Clustered VLIW DSPs. In: Proceedings of the International Conference on Parallel Architecture and Compilation Techniques (PACT), pp. 291\u2013300 (2000)","DOI":"10.1109\/PACT.2000.888353"},{"key":"2_CR13","unstructured":"Machanick, P.: Approaches to Addressing the Memory Wall. Technical report, School of IT and Electrical Engineering, University of Queensland (2002)"},{"key":"2_CR14","unstructured":"NVIDIA Corporation: CUDA Architecture (2009)"},{"key":"2_CR15","unstructured":"NVIDIA Corporation: The CUDA Compiler Driver NVCC (2009)"},{"key":"2_CR16","unstructured":"Open64 Project at Rice University: Open64 Compiler: Whirl Intermediate Representation (2007), www.mcs.anl.gov\/OpenAD\/open64A.pdf"},{"issue":"1","key":"2_CR17","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1111\/j.1467-8659.2007.01012.x","volume":"26","author":"John D. Owens","year":"2007","unstructured":"Owens, J., Luebke, D., Govindaraju, N., Harris, M., Kr\u00fcger, J., Lefohn, A., Purcell, T.: A Survey of General-Purpose Computation on Graphics Hardware. Computer Graphics Forum, 80\u2013113 (2007)","journal-title":"Computer Graphics Forum"},{"key":"2_CR18","unstructured":"Risco-Martin, J.: Java Evolutionary COmputation library (JECO) (2012), https:\/\/sourceforge.net\/projects\/jeco"},{"key":"2_CR19","unstructured":"Rofouei, M., Stathopoulos, T., Ryffel, S., Kaiser, W., Sarrafzadeh, M.: Energy-Aware High Performance Computing with Graphic Processing Units. In: Proceedings of the Workshop on Power Aware Computing and Systems, HotPower (2008)"},{"key":"2_CR20","doi-asserted-by":"crossref","unstructured":"Timm, C., Gelenberg, A., Marwedel, P., Weichert, F.: Energy Considerations within the Integration of General Purpose GPUs in Embedded Systems. In: Proceedigns of the Annual Internation Conference on Advances in Distributed and Parallel Computing, ADPC (2010)","DOI":"10.5176\/978-981-08-7656-2_A-51"},{"key":"2_CR21","doi-asserted-by":"crossref","unstructured":"Timm, C., Weichert, F., Marwedel, P., M\u00fcller, H.: Multi-Objective Local Instruction Scheduling for GPGPU Applications. In: Proceedings of the International Conference on Parallel and Distributed Computing Systems, PDCS (2011)","DOI":"10.2316\/P.2011.757-044"},{"key":"2_CR22","doi-asserted-by":"crossref","unstructured":"Tseng, C.J., Siewiorek, D.: Automated Synthesis of Data Paths in Digital Systems. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 379\u2013395 (1986)","DOI":"10.1109\/TCAD.1986.1270207"},{"key":"2_CR23","doi-asserted-by":"crossref","unstructured":"Valluri, M., John, L.: Is Compiling for Performance == Compiling for Power? In: Proceedings oh the Workshop on Interaction between Compilers and Computer Architectures, INTERACT (2001)","DOI":"10.1007\/978-1-4757-3337-2_6"},{"issue":"1","key":"2_CR24","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1016\/S0167-6377(02)00189-X","volume":"31","author":"Mark Voorneveld","year":"2003","unstructured":"Voorneveld, M.: Characterization of Pareto Dominance. Operations Research Letters, 7\u201311 (2003)","journal-title":"Operations Research Letters"},{"issue":"2","key":"2_CR25","doi-asserted-by":"crossref","first-page":"369","DOI":"10.1145\/1059876.1059885","volume":"10","author":"Zhong Wang","year":"2005","unstructured":"Wang, Z., Hu, X.S.: Energy-Aware Variable Partitioning and Instruction Scheduling for Multibank Memory Architectures. ACM Transactions on Design Automation of Electronic Systems (TODAES), 369\u2013388 (2005)","journal-title":"ACM Transactions on Design Automation of Electronic Systems"},{"key":"2_CR26","doi-asserted-by":"crossref","unstructured":"Woo, D.H., Lee, H.H.: Extending Amdahl\u2019s Law for Energy-Efficient Computing in the Many-Core Era. IEEE Computer, 24\u201331 (2008)","DOI":"10.1109\/MC.2008.494"},{"key":"2_CR27","unstructured":"Zitzler, E., Giannakoglou, K., Tsahalis, D., Periaux, J., Papailiou, K., Fogarty, T., Ler, E.Z., Laumanns, M., Thiele, L.: SPEA2: Improving the Strength Pareto Evolutionary Algorithm For Multiobjective Optimization. In: Proceedings of the International Conference on Evolutionary and Deterministic Methods for Design, Optimization and Control with Applications to Industrial and Societal Problems, EUROGEN (2001)"}],"container-title":["Lecture Notes in Computer Science","Computational Science and Its Applications \u2013 ICCSA 2012"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-31125-3_2.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T17:03:39Z","timestamp":1743527019000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-31125-3_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012]]},"ISBN":["9783642311246","9783642311253"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-31125-3_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2012]]}}}