{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T14:47:33Z","timestamp":1776782853969,"version":"3.51.2"},"reference-count":86,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2011,1,7]],"date-time":"2011-01-07T00:00:00Z","timestamp":1294358400000},"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":[[2011,6]]},"DOI":"10.1007\/s10766-010-0161-2","type":"journal-article","created":{"date-parts":[[2011,1,6]],"date-time":"2011-01-06T07:36:48Z","timestamp":1294299408000},"page":"296-327","source":"Crossref","is-referenced-by-count":157,"title":["Milepost GCC: Machine Learning Enabled Self-tuning Compiler"],"prefix":"10.1007","volume":"39","author":[{"given":"Grigori","family":"Fursin","sequence":"first","affiliation":[]},{"given":"Yuriy","family":"Kashnikov","sequence":"additional","affiliation":[]},{"given":"Abdul Wahid","family":"Memon","sequence":"additional","affiliation":[]},{"given":"Zbigniew","family":"Chamski","sequence":"additional","affiliation":[]},{"given":"Olivier","family":"Temam","sequence":"additional","affiliation":[]},{"given":"Mircea","family":"Namolaru","sequence":"additional","affiliation":[]},{"given":"Elad","family":"Yom-Tov","sequence":"additional","affiliation":[]},{"given":"Bilha","family":"Mendelson","sequence":"additional","affiliation":[]},{"given":"Ayal","family":"Zaks","sequence":"additional","affiliation":[]},{"given":"Eric","family":"Courtois","sequence":"additional","affiliation":[]},{"given":"Francois","family":"Bodin","sequence":"additional","affiliation":[]},{"given":"Phil","family":"Barnard","sequence":"additional","affiliation":[]},{"given":"Elton","family":"Ashton","sequence":"additional","affiliation":[]},{"given":"Edwin","family":"Bonilla","sequence":"additional","affiliation":[]},{"given":"John","family":"Thomson","sequence":"additional","affiliation":[]},{"given":"Christopher K. I.","family":"Williams","sequence":"additional","affiliation":[]},{"given":"Michael","family":"O\u2019Boyle","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2011,1,7]]},"reference":[{"key":"161_CR1","unstructured":"ACOVEA: Using Natural Selection to Investigate Software Complexities. http:\/\/www.coyotegulch.com\/products\/acovea"},{"key":"161_CR2","unstructured":"Agakov, F., Bonilla, E., Cavazos, J., Franke, B., Fursin, G., O\u2019Boyle, M., Thomson, J., Toussaint, M., Williams, C.: Using machine learning to focus iterative optimization. In: Proceedings of the International Symposium on Code Generation and Optimization (CGO) (2006)"},{"key":"161_CR3","doi-asserted-by":"crossref","unstructured":"Anderson, J., Berc, L., Dean, J., Ghemawat, S., Henzinger, M., Leung, S., Sites, D., Vandevoorde, M., Waldspurger, C., Weihl, W.: Continuous profiling: Where have all the cycles gone? In: Proceedings of the 30th Symposium on Microarchitecture (MICRO-30), (1997)","DOI":"10.1145\/268998.266637"},{"key":"161_CR4","doi-asserted-by":"crossref","unstructured":"Arcuri, A., White, D.R., Clark, J., Yao, X.: Multi-objective improvement of software using co-evolution and smart seeding. In: Proceedings of the 7th International Conference on Simulated Evolution And Learning (SEAL\u201908) (2008)","DOI":"10.1007\/978-3-540-89694-4_7"},{"key":"161_CR5","doi-asserted-by":"crossref","unstructured":"Arnold, M., Welc, A., Rajan, V.T.: Improving virtual machine performance using a cross-run profile repository. In: Proceedings of the ACM Conference on Object-Oriented Programming, Systems, Languages and Applications (OOPSLA\u201905) (2005)","DOI":"10.1145\/1094811.1094835"},{"key":"161_CR6","doi-asserted-by":"crossref","unstructured":"Barthou, D., Donadio, S., Carribault, P., Duchateau, A., Jalby, W.: Loop optimization using hierarchical compilation and kernel decomposition. In: Proceedings of the International Symposium on Code Generation and Optimization (CGO) (2007)","DOI":"10.1109\/CGO.2007.22"},{"key":"161_CR7","unstructured":"Bodin, F., Kisuki, T., Knijnenburg, P., O\u2019Boyle, M., Rohou, E.: Iterative compilation in a non-linear optimisation space. In: Proceedings of the Workshop on Profile and Feedback Directed Compilation (1998)"},{"key":"161_CR8","unstructured":"Bonilla, E.V., Williams, C.K.I., Agakov, F.V., Cavazos, J., Thomson, J., O\u2019Boyle, M.F.P.: Predictive search distributions. In: Proceedings of the 23rd International Conference on Machine Learning. pp. 121\u2013128, New York, NY, USA, (2006)"},{"key":"161_CR9","doi-asserted-by":"crossref","unstructured":"Brewer E. High-level optimization via automated statistical modeling. In: Proceedings of the 5th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, pp. 80\u201391, (1995)","DOI":"10.1145\/209937.209946"},{"key":"161_CR10","doi-asserted-by":"crossref","unstructured":"Calder, B., Grunwald, D., Jones, M., Lindsay, D., Martin, J., Mozer, M., Zorn, B.: Evidence-based static branch prediction using machine learning. ACM Transactions on Programming Languages and Systems (TOPLAS) (1997)","DOI":"10.1145\/239912.239923"},{"key":"161_CR11","doi-asserted-by":"crossref","unstructured":"Cavazos, J., Fursin, G., Agakov, F., Bonilla, E., O\u2019Boyle, M., Temam, O.: Rapidly selecting good compiler optimizations using performance counters. In: Proceedings of the International Symposium on Code Generation and Optimization (CGO) March (2007)","DOI":"10.1109\/CGO.2007.32"},{"key":"161_CR12","doi-asserted-by":"crossref","unstructured":"Cavazos J., Moss J. Inducing heuristics to decide whether to schedule. In: Proceedings of the ACM SIGPLAN Conference on Programming Language Design and Implementation (PLDI) (2004)","DOI":"10.1145\/996841.996864"},{"key":"161_CR13","unstructured":"CCC: Continuous Collective Compilation Framework for iterative multi-objective optimization. http:\/\/cTuning.org\/ccc"},{"key":"161_CR14","unstructured":"COD: Public collaborative repository and tools for program and architecture characterization and optimization. http:\/\/cTuning.org\/cdatabase"},{"key":"161_CR15","doi-asserted-by":"crossref","unstructured":"Chen, Y., Huang, Y., Eeckhout, L., Fursin, G., Peng, L., Temam, O., Wu, C.: Evaluating iterative optimization across 1000 data sets. In: Proceedings of the ACM SIGPLAN Conference on Programming Language Design and Implementation (PLDI) June (2010)","DOI":"10.1145\/1806596.1806647"},{"key":"161_CR16","doi-asserted-by":"crossref","unstructured":"Cooper, K., Grosul, A., Harvey, T., Reeves, S., Subramanian, D., Torczon, L., Waterman, T.: ACME: adaptive compilation made efficient. In: Proceedings of the Conference on Languages, Compilers, and Tools for Embedded Systems (LCTES) (2005)","DOI":"10.1145\/1065910.1065921"},{"key":"161_CR17","unstructured":"Cooper, K., Schielke, P., Subramanian, D.: Optimizing for reduced code space using genetic algorithms. In: Proceedings of the Conference on Languages, Compilers, and Tools for Embedded Systems (LCTES), pp. 1\u20139, (1999)"},{"key":"161_CR18","doi-asserted-by":"crossref","unstructured":"Cooper, K., Subramanian, D., Torczon, L.: Adaptive optimizing compilers for the 21st century. J. Supercomput. 23(1) (2002)","DOI":"10.1023\/A:1015729001611"},{"key":"161_CR19","unstructured":"cTuning CC: cTuning Compiler Collection that can convert any traditional compiler into adaptive, machine learning enabled self-tuning infrastructure using Milepost GCC with ICI, CCC framework, cBench, COD public repository and cTuning.org web-services. http:\/\/cTuning.org\/ctuning-cc"},{"key":"161_CR20","unstructured":"cTuning.org: public collaborative optimization center with open source tools and repository to systematize, simplify and automate design and optimization of computing systems while enabling reproducibility of results"},{"key":"161_CR21","doi-asserted-by":"crossref","unstructured":"Donadio, S., Brodman, J.C., Roeder, T., Yotov, K., Barthou, D., Cohen, A., Garzaran, M.J., Padua, D.A., Pingali, K.: A language for the compact representation of multiple program versions. In: Proceedings of the International Workshop on Languages and Compilers for Parallel computing (LCPC) (2005)","DOI":"10.1007\/978-3-540-69330-7_10"},{"key":"161_CR22","doi-asserted-by":"crossref","unstructured":"Dubach, C., Jones, T.M., Bonilla, E.V., Fursin, G., O\u2019Boyle, M.F.: Portable compiler optimization across embedded programs and microarchitectures using machine learning. In: Proceedings of the IEEE\/ACM International Symposium on Microarchitecture (MICRO) December (2009)","DOI":"10.1145\/1669112.1669124"},{"key":"161_CR23","volume-title":"Pattern Classification","author":"R. Duda","year":"2001","unstructured":"Duda R., Hart P., Stork D.: Pattern Classification. Wiley, New-York (2001)"},{"issue":"14","key":"161_CR24","doi-asserted-by":"crossref","first-page":"1954","DOI":"10.1016\/j.patrec.2008.06.012","volume":"29","author":"R. El-Yaniv","year":"2008","unstructured":"El-Yaniv R., Pechyony D., Yom-Tov E.: Better multiclass classification via a margin-optimized single binary problem. Pattern Recognit Lett 29(14), 1954\u20131959 (2008)","journal-title":"Pattern Recognit Lett"},{"key":"161_CR25","unstructured":"ESTO: Expert System for Tuning Optimizations. http:\/\/www.haifa.ibm.com\/projects\/systems\/cot\/esto\/index.html"},{"key":"161_CR26","doi-asserted-by":"crossref","unstructured":"Franke, B., O\u2019Boyle, M., Thomson, J., Fursin, G.: Probabilistic source-level optimisation of embedded programs. In: Proceedings of the Conference on Languages, Compilers, and Tools for Embedded Systems (LCTES) (2005)","DOI":"10.1145\/1065910.1065922"},{"key":"161_CR27","unstructured":"Fursin, G.: Iterative Compilation and Performance Prediction for Numerical Applications. PhD thesis, University of Edinburgh, United Kingdom (2004)"},{"key":"161_CR28","unstructured":"Fursin, G.: Collective tuning initiative: automating and accelerating development and optimization of computing systems. In: Proceedings of the GCC Developers\u2019 Summit, June (2009)"},{"key":"161_CR29","doi-asserted-by":"crossref","unstructured":"Fursin, G., Cavazos, J., O\u2019Boyle, M., Temam, O.: MiDataSets: creating the conditions for a more realistic evaluation of iterative optimization. In: Proceedings of the International Conference on High Performance Embedded Architectures & Compilers (HiPEAC 2007), January (2007)","DOI":"10.1007\/978-3-540-69338-3_17"},{"key":"161_CR30","doi-asserted-by":"crossref","unstructured":"Fursin, G., Cohen, A., O\u2019Boyle, M., Temam, O.: A practical method for quickly evaluating program optimizations. In: Proceedings of the International Conference on High Performance Embedded Architectures & Compilers (HiPEAC 2005), pp. 29\u201346, November (2005)","DOI":"10.1007\/11587514_4"},{"issue":"2\u20133","key":"161_CR31","doi-asserted-by":"crossref","first-page":"271","DOI":"10.1002\/cpe.774","volume":"16","author":"G. Fursin","year":"2004","unstructured":"Fursin G., O\u2019Boyle M., Temam O., Watts G.: Fast and accurate method for determining a lower bound on execution time. Concurrency 16(2\u20133), 271\u2013292 (2004)","journal-title":"Concurrency"},{"key":"161_CR32","doi-asserted-by":"crossref","unstructured":"Fursin, G., Temam, O.: Collective optimization. In: Proceedings of the International Conference on High Performance Embedded Architectures & Compilers (HiPEAC 2009), January (2009)","DOI":"10.1007\/978-3-540-92990-1_5"},{"key":"161_CR33","doi-asserted-by":"crossref","unstructured":"Georges, A., Buytaert, D., Eeckhout, L.: Statistically rigorous java performance evaluation. In: Proceedings of the Twenty-Second ACM SIGPLAN Conference on Object-Oriented Programming, Systems, Languages & Applications (OOPSLA) (2007)","DOI":"10.1145\/1297027.1297033"},{"key":"161_CR34","unstructured":"GCC: the GNU Compiler Collection. http:\/\/gcc.gnu.org"},{"key":"161_CR35","unstructured":"GRID5000: A nationwide infrastructure for large scale parallel and distributed computing research. http:\/\/www.grid5000.fr"},{"key":"161_CR36","unstructured":"Guthaus, M.R., Ringenberg, M.R., Ernst, D., Austin, T.M., Mudge, T., Brown, R.B.: Mibench: A free, commercially representative embedded benchmark suite. In: Proceedings of the IEEE 4th Annual Workshop on Workload Characterization, Austin, TX, December (2001)"},{"key":"161_CR37","unstructured":"Heydemann, K., Bodin, F.: Iterative compilation for two antagonistic criteria: Application to code size and performance. In: Proceedings of the 4th Workshop on Optimizations for DSP and Embedded Systems, colocated with CGO (2006)"},{"key":"161_CR38","doi-asserted-by":"crossref","unstructured":"Hoste, K., Eeckhout, L.: Cole: Compiler optimization level exploration. In: Proceedings of the International Symposium on Code Generation and Optimization (CGO) (2008)","DOI":"10.1145\/1356058.1356080"},{"key":"161_CR39","doi-asserted-by":"crossref","unstructured":"Hoste, K., Eeckhout, L.: Comparing benchmarks using key microarchitecture-independent characteristics. In: Proceedings of the IEEE International Symposium on Workload Characterization (IISWC), pp. 83\u201392, California,USA, October (2006)","DOI":"10.1109\/IISWC.2006.302732"},{"key":"161_CR40","unstructured":"Huang, Y., Peng, L., Wu, C., Kashnikov, Y., Renneke, J., Fursin, G.: Transforming GCC into a research-friendly environment: plugins for optimization tuning and reordering, function cloning and program instrumentation. In: 2nd International Workshop on GCC Research Opportunities (GROW), Colocated with HiPEAC\u201910 Conference, January (2010)"},{"key":"161_CR41","unstructured":"ICI: Interactive Compilation Interface is a unified plugin system to convert black-box production compilers into interactive research toolsets for application and architecture characterization and optimization. http:\/\/cTuning.org\/ici"},{"key":"161_CR42","doi-asserted-by":"crossref","unstructured":"Ipek, E., McKee, S.A., de Supinski, B.R., Schulz, M., Caruana, R.: Efficiently exploring architectural design spaces via predictive modeling. In: Proceedings of the 12th International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS), pp. 195\u2013206 (2006)","DOI":"10.1145\/1168857.1168882"},{"key":"161_CR43","doi-asserted-by":"crossref","unstructured":"Jimenez, V., Gelado, I., Vilanova, L., Gil, M., Fursin, G., Navarro, N.: Predictive runtime code scheduling for heterogeneous architectures. In: Proceedings of the International Conference on High Performance Embedded Architectures & Compilers (HiPEAC 2009), January (2009)","DOI":"10.1007\/978-3-540-92990-1_4"},{"key":"161_CR44","doi-asserted-by":"crossref","unstructured":"Kisuki, T., Knijnenburg, P., O\u2019Boyle, M.: Combined selection of tile sizes and unroll factors using iterative compilation. In: Proceedings of the International Conference on Parallel Architectures and Compilation Techniques (PACT), pp. 237\u2013246, (2000)","DOI":"10.1109\/PACT.2000.888348"},{"key":"161_CR45","doi-asserted-by":"crossref","unstructured":"Kisuki T., Knijnenburg P., O\u2019Boyle M.: Combined selection of tile sizes and unroll factors using iterative compilation. In: Proceedings of IEEE International Conference on Parallel Architectures and Compilation Techniques (PACT), pp. 237\u2013246, (2000)","DOI":"10.1109\/PACT.2000.888348"},{"key":"161_CR46","doi-asserted-by":"crossref","unstructured":"Kulkarni, P., Zhao, W., Moon, H., Cho, K., Whalley, D., Davidson, J., Bailey, M., Paek, Y., Gallivan, K.: Finding effective optimization phase sequences. In: Proceedings of the Conference on Languages, Compilers, and Tools for Embedded Systems (LCTES), pp. 12\u201323 (2003)","DOI":"10.1145\/780731.780735"},{"key":"161_CR47","volume-title":"Estimation of Distribution Algorithms: A New Tool for Evolutionary Computation","author":"P. Larra naga","year":"2001","unstructured":"Larra naga P., Lozano J.A.: Estimation of Distribution Algorithms: A New Tool for Evolutionary Computation. Kluwer, Norwell (2001)"},{"key":"161_CR48","unstructured":"Lattner, C., Adve, V.: LLVM: A compilation framework for lifelong program analysis & transformation. In: Proceedings of the 2004 International Symposium on Code Generation and Optimization (CGO\u201904), Palo Alto, California, March (2004)"},{"key":"161_CR49","doi-asserted-by":"crossref","unstructured":"Lau, J., Arnold, M., Hind, M., Calder, B.: Online performance auditing: Using hot optimizations without getting burned. In: Proceedings of the ACM SIGPLAN Conference on Programming Languaged Design and Implementation (PLDI\u201906) (2006)","DOI":"10.1145\/1133981.1134010"},{"key":"161_CR50","doi-asserted-by":"crossref","unstructured":"Li, X., Garzaran, M.J., Padua, D.A.: Optimizing sorting with machine learning algorithms. In: Proceedings of the International Parallel and Distributed Processing Symposium (IPDPS) (2007)","DOI":"10.1109\/IPDPS.2007.370499"},{"key":"161_CR51","unstructured":"Long, S., Fursin, G.: A heuristic search algorithm based on unified transformation framework. In: Proceedings of the 7th International Workshop on High Performance Scientific and Engineering Computing (HPSEC-05), pp. 137\u2013144, (2005)"},{"key":"161_CR52","doi-asserted-by":"crossref","unstructured":"Long, S., Fursin, G., Franke, B.: A cost-aware parallel workload allocation approach based on machine learning techniques. In: Proceedings of the IFIP International Conference on Network and Parallel Computing (NPC 2007), number 4672 in LNCS, pp. 506\u2013515. Springer, September (2007)","DOI":"10.1007\/978-3-540-74784-0_51"},{"key":"161_CR53","unstructured":"LLVM: the low level virtual machine compiler infrastructure. http:\/\/llvm.org"},{"key":"161_CR54","unstructured":"Lu, J., Chen, H., Yew, P.-C., Hsu, W.-C.: Design and implementation of a lightweight dynamic optimization system. J. Instruction-Level Parallel. 6 (2004)"},{"key":"161_CR55","unstructured":"Luo, L., Chen, Y., Wu, C., Long, S., Fursin, G.: Finding representative sets of optimizations for adaptive multiversioning applications. In: 3rd Workshop on Statistical and Machine Learning Approaches Applied to Architectures and Compilation (SMART\u201909), Colocated with HiPEAC\u201909 Conference, January (2009)"},{"key":"161_CR56","doi-asserted-by":"crossref","unstructured":"Matteo, F., Johnson, S.: FFTW: An adaptive software architecture for the FFT. In: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, vol. 3, pp. 1381\u20131384, Seattle, WA, May (1998)","DOI":"10.1109\/ICASSP.1998.681704"},{"key":"161_CR57","unstructured":"MILEPOST GCC: public collaborative R&D website. http:\/\/cTuning.org\/milepost-gcc"},{"key":"161_CR58","unstructured":"MILEPOST project archive (MachIne Learning for Embedded PrOgramS opTimization). http:\/\/cTuning.org\/project-milepost"},{"key":"161_CR59","unstructured":"McGovern, A., Moss, E.: Scheduling straight-line code using reinforcement learning and rollouts. In: Advances in Neural Information Processing Systems (NIPS). Morgan Kaufmann, San Mateo (1998)"},{"key":"161_CR60","doi-asserted-by":"crossref","unstructured":"Monsifrot, A., Bodin, F., Quiniou, R.: A machine learning approach to automatic production of compiler heuristics. In: Proceedings of the International Conference on Artificial Intelligence: Methodology, Systems, Applications, LNCS 2443, pp. 41\u201350 (2002)","DOI":"10.1007\/3-540-46148-5_5"},{"key":"161_CR61","unstructured":"Monsifrot, A., Bodin, F., Quiniou, R.: A machine learning approach to automatic production of compiler heuristics. In: Proceedings of the Tenth International Conference on Artificial Intelligence: Methodology, Systems, Applications (AIMSA), LNCS 2443, pp. 41\u201350, (2002)"},{"key":"161_CR62","unstructured":"Moss, J., Utgoff, P., Cavazos, J., Precup, D., Stefanovic, D., Brodley, C., Scheeff, D.: Learning to schedule straight-line code. In: Advances in Neural Information Processing Systems (NIPS), pp. 929\u2013935. Morgan Kaufmann, (1997)"},{"key":"161_CR63","doi-asserted-by":"crossref","unstructured":"Namolaru, M., Cohen, A., Fursin, G., Zaks, A., Freund, A.: Practical aggregation of semantical program properties for machine learning based optimization. In: Proceedings of the International Conference on Compilers, Architecture, and Synthesis For Embedded Systems (CASES 2010), October (2010)","DOI":"10.1145\/1878921.1878951"},{"key":"161_CR64","unstructured":"Nisbet, A.: Iterative feedback directed parallelisation using genetic algorithms. In: Proceedings of the Workshop on Profile and Feedback Directed Compilation in Conjunction with International Conference on Parallel Architectures and Compilation Technique (PACT) (1998)"},{"key":"161_CR65","unstructured":"Open64: an open source optimizing compiler suite. http:\/\/www.open64.net"},{"key":"161_CR66","unstructured":"OProfile: system-wide profiler for Linux systems, capable of profiling all running code at low overhead. http:\/\/oprofile.sourceforge.net"},{"key":"161_CR67","unstructured":"Pan, Z., Eigenmann, R.: Fast and effective orchestration of compiler optimizations for automatic performance tuning. In: Proceedings of the International Symposium on Code Generation and Optimization (CGO), pp. 319\u2013332 (2006)"},{"key":"161_CR68","unstructured":"PathScale EKOPath Compilers. http:\/\/www.pathscale.com"},{"key":"161_CR69","unstructured":"Phoenix: software optimization and analysis framework for microsoft compiler technologies. https:\/\/connect.microsoft.com\/Phoenix"},{"key":"161_CR70","unstructured":"ROSE: an open source compiler infrastructure to build source-to-source program transformation and analysis tools. http:\/\/www.rosecompiler.org\/"},{"key":"161_CR71","unstructured":"Singer, B., Veloso, M.: Learning to predict performance from formula modeling and training data. In: Proceedings of the Conference on Machine Learning (2000)"},{"key":"161_CR72","doi-asserted-by":"crossref","unstructured":"Stephenson, M., Amarasinghe, S.: Predicting unroll factors using supervised classification. In: Proceedings of International Symposium on Code Generation and Optimization (CGO), pp. 123\u2013134, (2005)","DOI":"10.1109\/CGO.2005.29"},{"key":"161_CR73","doi-asserted-by":"crossref","unstructured":"Stephenson, M., Amarasinghe, S., Martin, M., O\u2019Reilly, U.-M.: Meta optimization: Improving compiler heuristics with machine learning. In: Proceedings of the ACM SIGPLAN Conference on Programming Language Design and Implementation (PLDI\u201903), pp. 77\u201390, June (2003)","DOI":"10.1145\/781139.781141"},{"key":"161_CR74","unstructured":"Stephenson, M.W.: Automating the construction of compiler heuristics using machine learning. PhD thesis, MIT, USA, (2006)"},{"key":"161_CR75","unstructured":"Touati, S., Worms, J., Briais, S.: The speedup test. In: INRIA Technical Report HAL-inria-00443839 (2010)"},{"key":"161_CR76","doi-asserted-by":"crossref","unstructured":"Tournavitis, G., Wang, Z., Franke, B., O\u2019Boyle, M.F.: Towards a holistic approach to auto-parallelization: Integrating profile-driven parallelism detection and machine-learning based mapping. In: Proceedings of the Conference on Programming Language Design and Implementation (PLDI) (2009)","DOI":"10.1145\/1542476.1542496"},{"key":"161_CR77","unstructured":"Triantafyllis, S., Vachharajani, M., Vachharajani, N., August, D.: Compiler optimization-space exploration. In: Proceedings of the International Symposium on Code Generation and Optimization (CGO), pp. 204\u2013215 (2003)"},{"key":"161_CR78","unstructured":"Trifunovic, K., Cohen, A., Edelsohn, D., Feng, L., Grosser, T., Jagasia, H., Ladelsky, R., Pop, S., Sjoedin, J., Upadrasta, R.: Graphite two years after: First lessons learned from real-world polyhedral compilation. In: 2nd International Workshop on GCC Research Opportunities (GROW) (2010)"},{"key":"161_CR79","volume-title":"Principles of database and knowledge systems, vol. 1","author":"J. Ullman","year":"1988","unstructured":"Ullman J.: Principles of database and knowledge systems, vol. 1. Computer Science Press, New York (1988)"},{"key":"161_CR80","unstructured":"Voss, M., Eigenmann, R.: ADAPT: Automated de-coupled adaptive program transformation. In: Proceedings of International Conference on Parallel Processing (2000)"},{"key":"161_CR81","doi-asserted-by":"crossref","first-page":"521","DOI":"10.1088\/1742-6596\/16\/1\/071","volume":"16","author":"R. Vuduc","year":"2005","unstructured":"Vuduc R., Demmel J.W., Yelick K.A.: OSKI: A library of automatically tuned sparse matrix kernels. J. Phys. Conf. Ser. 16, 521\u2013530 (2005)","journal-title":"J. Phys. Conf. Ser."},{"key":"161_CR82","doi-asserted-by":"crossref","unstructured":"wei Liao, S., han Hung, T., Nguyen, D., Chou, C., Tu, C., Zhou, H.: Machine learning-based prefetch optimization for data center applications. In: Proceedings of the IEEE\/ACM Conference on Supercomputing (SC) (2009)","DOI":"10.1145\/1654059.1654116"},{"key":"161_CR83","doi-asserted-by":"crossref","unstructured":"Whaley, J., Lam, M.S.: Cloning based context sensitive pointer alias analysis using binary decision diagrams. In: Proceedings of the Conference on Programming Language Design and Implementation (PLDI), (2004)","DOI":"10.1145\/996841.996859"},{"key":"161_CR84","doi-asserted-by":"crossref","unstructured":"Whaley, R., Dongarra, J.: Automatically tuned linear algebra software. In: Proceedings of the Conference on High Performance Networking and Computing (1998)","DOI":"10.1109\/SC.1998.10004"},{"key":"161_CR85","doi-asserted-by":"crossref","unstructured":"Williams, S., Oliker, L., Vuduc, R., Shalf, J., Yelick, K., Demmel, J.: Optimization of sparse matrix-vector multiplication on emerging multicore platforms. In: Proceedings of the IEEE\/ACM Conference on Supercomputing (SC) (2007)","DOI":"10.1145\/1362622.1362674"},{"key":"161_CR86","doi-asserted-by":"crossref","unstructured":"Yi, Q., Seymour, K., You, H., Vuduc, R., Quinlan, D.: Poet: Parameterized optimizations for empirical tuning. In: Proceedings of the Workshop on Performance Optimization of High-level Languages and Libraries (POHLL) Co-located with IEEE International Parallel and Distributed Processing Symposium (IPDPS) (2007)","DOI":"10.1109\/IPDPS.2007.370637"}],"container-title":["International Journal of Parallel Programming"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10766-010-0161-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10766-010-0161-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10766-010-0161-2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T13:12:53Z","timestamp":1740834773000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10766-010-0161-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011,1,7]]},"references-count":86,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2011,6]]}},"alternative-id":["161"],"URL":"https:\/\/doi.org\/10.1007\/s10766-010-0161-2","relation":{},"ISSN":["0885-7458","1573-7640"],"issn-type":[{"value":"0885-7458","type":"print"},{"value":"1573-7640","type":"electronic"}],"subject":[],"published":{"date-parts":[[2011,1,7]]}}}