refs[] |
{'index': 0, 'target_release_id': None, 'extra': {'unstructured': '"Gem5," http://gem5.org.'}, 'key': 'key-10.1145/2628071.2628082-1', 'year': None, 'container_name': None, 'title': None, 'locator': None}
{'index': 1, 'target_release_id': None, 'extra': {'unstructured': '"Intel pentium 4 and intel xeon processor optimization, reference manual," http://developer.intel.com.'}, 'key': 'key-10.1145/2628071.2628082-2', 'year': None, 'container_name': None, 'title': None, 'locator': None}
{'index': 2, 'target_release_id': None, 'extra': {'unstructured': '"Intel Xscale core, developer\'s manual," http://developer.intel.com.'}, 'key': 'key-10.1145/2628071.2628082-3', 'year': None, 'container_name': None, 'title': None, 'locator': None}
{'index': 3, 'target_release_id': None, 'extra': {'unstructured': '"Open64," http://www.open64.net.'}, 'key': 'key-10.1145/2628071.2628082-4', 'year': None, 'container_name': None, 'title': None, 'locator': None}
{'index': 4, 'target_release_id': None, 'extra': {'unstructured': '"Spiral: Software/hardware generation for dsp algorithms," http://www.spiral.net/.'}, 'key': 'key-10.1145/2628071.2628082-5', 'year': None, 'container_name': None, 'title': None, 'locator': None}
{'index': 5, 'target_release_id': None, 'extra': {'unstructured': '"The PaSTiX Library," http://pastix.gforge.inria.fr/.'}, 'key': 'key-10.1145/2628071.2628082-6', 'year': None, 'container_name': None, 'title': None, 'locator': None}
{'index': 6, 'target_release_id': None, 'extra': {'unstructured': 'R. Ausavarungnirun, K. Kai-wei, C. Lavanya, S. Gabriel, H. Loh, and O. Mutlu, "Staged memory scheduling: achieving high performance and scalability in heterogeneous systems," In Proceedings of the International Symposium on Computer Architecture, 2012.'}, 'key': 'key-10.1145/2628071.2628082-7', 'year': None, 'container_name': None, 'title': None, 'locator': None}
{'index': 7, 'target_release_id': None, 'extra': {'unstructured': 'M. Awasthi, D. W. Nellans, R. Balasubramonian, and A. Davis, "Prediction based DRAM row-buffer management in the many-core era," In Proceedings of the International Conference on Parallel Architectures and Compilation Techniques, 2011.'}, 'key': 'key-10.1145/2628071.2628082-8', 'year': None, 'container_name': None, 'title': None, 'locator': None}
{'index': 8, 'target_release_id': None, 'extra': {'doi': '10.1109/tc.1987.1676942', 'unstructured': 'M. Berger and S. Bokhari, "A partitioning strategy for non-uniform problems on multiprocessors," IEEE Trans. Computers, 1987.'}, 'key': 'key-10.1145/2628071.2628082-9', 'year': None, 'container_name': None, 'title': None, 'locator': None}
{'index': 9, 'target_release_id': None, 'extra': {'unstructured': 'P. Boonserm, B. Wang, S. See, and T. Achalakul, "Improving data processing time with access sequence prediction," in Proceedings of the International Conference on Parallel and Distributed Systems, 2012.'}, 'key': 'key-10.1145/2628071.2628082-10', 'year': None, 'container_name': None, 'title': None, 'locator': None}
{'index': 10, 'target_release_id': None, 'extra': {'doi': '10.1109/pact.2005.16', 'unstructured': 'P. Carribault, S. Zuckerman, A. Cohen, and W. Jalby, "Deep jam: Conversion of coarse-grain parallelism to instruction-level and vector parallelism for irregular applications," In Proceedings of the International Conference on Parallel Architectures and Compilation Techniques, 2005.'}, 'key': 'key-10.1145/2628071.2628082-11', 'year': None, 'container_name': None, 'title': None, 'locator': None}
{'index': 11, 'target_release_id': None, 'extra': {'unstructured': 'R. Das, M. Uysal, J. Saltz, and Y. shin Hwang, "Communication optimizations for irregular scientific computations on distributed memory architectures," Journal of Parallel and Distributed Computing, 1993.'}, 'key': 'key-10.1145/2628071.2628082-12', 'year': None, 'container_name': None, 'title': None, 'locator': None}
{'index': 12, 'target_release_id': None, 'extra': {'unstructured': 'C. Ding and K. Kennedy, "Improving cache performance in dynamic applications through data and computation reorganization at run time," In Proceedings of the Conference on Programming Language Design and Implementation, 1999.'}, 'key': 'key-10.1145/2628071.2628082-13', 'year': None, 'container_name': None, 'title': None, 'locator': None}
{'index': 13, 'target_release_id': None, 'extra': {'doi': '10.1109/pact.2013.6618820', 'unstructured': 'W. Ding, J. Liu, K. Mahmut, and M. J. Irwin, "Reshaping cache misses to improve row-buffer locality in multicore systems," In Proceedings of the International Conference on Parallel Architectures and Compilation Techniques, 2013.'}, 'key': 'key-10.1145/2628071.2628082-14', 'year': None, 'container_name': None, 'title': None, 'locator': None}
{'index': 14, 'target_release_id': None, 'extra': {'unstructured': 'H. Han and C.-W. Tseng, "Exploiting locality for irregular scientific codes," IEEE Trans. Parallel Distrib. Syst., 2006.'}, 'key': 'key-10.1145/2628071.2628082-15', 'year': None, 'container_name': None, 'title': None, 'locator': None}
{'index': 15, 'target_release_id': None, 'extra': {'unstructured': 'J. L. Hennessy and D. Patterson, Computer Architecture: A Quantitative Approach. Morgan Kaufmann, 2003.'}, 'key': 'key-10.1145/2628071.2628082-16', 'year': None, 'container_name': None, 'title': None, 'locator': None}
{'index': 16, 'target_release_id': None, 'extra': {'unstructured': 'E. Ipek, O. Mutlu, J. F. Martínez, and R. Caruana, "Self-optimizing memory controllers: A reinforcement learning approach," In Proceedings of the International Symposium on Computer Architecture, 2008.'}, 'key': 'key-10.1145/2628071.2628082-17', 'year': None, 'container_name': None, 'title': None, 'locator': None}
{'index': 17, 'target_release_id': None, 'extra': {'doi': '10.1137/s1064827595287997', 'unstructured': 'G. Karypis and V. Kumar, "A fast and high quality multilevel scheme for partitioning irregular graphs," SIAM Journal on Scientific Computing, 1998.'}, 'key': 'key-10.1145/2628071.2628082-18', 'year': None, 'container_name': None, 'title': None, 'locator': None}
{'index': 18, 'target_release_id': None, 'extra': {'unstructured': 'Y. Kim, D. Han, O. Mutlu, and M. Harchol-balter, "ATLAS: A scalable and high-performance scheduling algorithm for multiple memory controllers," In Proceedings of the International Symposium On High Performance Computer Architecture, 2010.'}, 'key': 'key-10.1145/2628071.2628082-19', 'year': None, 'container_name': None, 'title': None, 'locator': None}
{'index': 19, 'target_release_id': None, 'extra': {'unstructured': 'Y. Kim, M. Papamichael, O. Mutlu, and M. Harchol-balter, "Thread cluster memory scheduling: Exploiting differences in memory access behavior," In Proceedings of the International Symposium on Microarchitecture, 2010.'}, 'key': 'key-10.1145/2628071.2628082-20', 'year': None, 'container_name': None, 'title': None, 'locator': None}
{'index': 20, 'target_release_id': None, 'extra': {'unstructured': 'D. Kroft, "Lockup-free instruction fetch/prefetch cache organization," Computer Architecture, 1981.'}, 'key': 'key-10.1145/2628071.2628082-21', 'year': None, 'container_name': None, 'title': None, 'locator': None}
{'index': 21, 'target_release_id': None, 'extra': {'unstructured': 'M. Kulkarni, M. Burtscher, R. Inkulu, K. Pingali, and C. Casçaval, "How much parallelism is there in irregular applications?" In Proceedings of the ACM SIGPLAN symposium on Principles and practice of parallel programming, pp. 3--14, 2009.'}, 'key': 'key-10.1145/2628071.2628082-22', 'year': None, 'container_name': None, 'title': None, 'locator': None}
{'index': 22, 'target_release_id': None, 'extra': {'unstructured': 'C. J. Lee, V. Narasiman, E. Ebrahimi, O. Mutlu, and Y. N. Patt, "Dram-aware last-level cache writeback: Reducing write-caused interference in memory systems," HPS Technical Report, 2010.'}, 'key': 'key-10.1145/2628071.2628082-23', 'year': None, 'container_name': None, 'title': None, 'locator': None}
{'index': 23, 'target_release_id': None, 'extra': {'doi': '10.1137/0713020', 'unstructured': 'W. Liu and A. Sherman, "Comparative analysis of the cuthill-mckee and the reverse cuthill-mckee ordering algorithms for sparse matrices," SIAM Journal on Numerical Analysis, 1976.'}, 'key': 'key-10.1145/2628071.2628082-24', 'year': None, 'container_name': None, 'title': None, 'locator': None}
{'index': 24, 'target_release_id': None, 'extra': {'unstructured': 'J. Mellor-Crummey, D. Whalley, and K. Kennedy, "Improving memory hierarchy performance for irregular applications," In Proceedings of the International Conference on Supercomputing, 1999.'}, 'key': 'key-10.1145/2628071.2628082-25', 'year': None, 'container_name': None, 'title': None, 'locator': None}
{'index': 25, 'target_release_id': None, 'extra': {'doi': '10.1145/1163641.1163645', 'unstructured': 'O. Meshar, D. Irony, and S. Toledo, "An out-of-core sparse symmetric-indefinite factorization method," ACM Trans. Math. Softw., 2006.'}, 'key': 'key-10.1145/2628071.2628082-26', 'year': None, 'container_name': None, 'title': None, 'locator': None}
{'index': 26, 'target_release_id': None, 'extra': {'unstructured': 'J. Meza, J. Li, and O. Mutlu, "Evaluating row buffer locality in future non-volatile main memories," SAFARI Technical Report, 2012.'}, 'key': 'key-10.1145/2628071.2628082-27', 'year': None, 'container_name': None, 'title': None, 'locator': None}
{'index': 27, 'target_release_id': None, 'extra': {'unstructured': 'N. Mitchell, L. Carter, and J. Ferrante, "Localizing non-affine array references," In Proceedings of the International Conference on Parallel Architectures and Compilation Techniques, 1999.'}, 'key': 'key-10.1145/2628071.2628082-28', 'year': None, 'container_name': None, 'title': None, 'locator': None}
{'index': 28, 'target_release_id': None, 'extra': {'unstructured': 'O. Mutlu and T. Moscibroda, "Stall-time fair memory access scheduling for chip multiprocessors," In Proceedings of the International Symposium on Microarchitecture, 2007.'}, 'key': 'key-10.1145/2628071.2628082-29', 'year': None, 'container_name': None, 'title': None, 'locator': None}
{'index': 29, 'target_release_id': None, 'extra': {'unstructured': 'E. Petrank and D. Rawitz, "The hardness of cache conscious data placement," In Proceedings of the Conference on Principles of Programming Languages, 2002.'}, 'key': 'key-10.1145/2628071.2628082-30', 'year': None, 'container_name': None, 'title': None, 'locator': None}
{'index': 30, 'target_release_id': None, 'extra': {'unstructured': 'K. Pingali, D. Nguyen, M. Kulkarni, M. Burtscher, M. A. Hassaan, R. Kaleem, T.-H. Lee, A. Lenharth, R. Manevich, M. Méndez-Lojo, D. Prountzos, and X. Sui, "The tao of parallelism in algorithms," In Proceedings of the Conference on Programming Language Design and Implementation., 2011.'}, 'key': 'key-10.1145/2628071.2628082-31', 'year': None, 'container_name': None, 'title': None, 'locator': None}
{'index': 31, 'target_release_id': None, 'extra': {'unstructured': 'S. Rixner, W. J. Dally, U. J. Kapasi, P. Mattson, and J. D. Owens, "Memory access scheduling," In Proceedings of the International Symposium on Computer Architecture, 2000.'}, 'key': 'key-10.1145/2628071.2628082-32', 'year': None, 'container_name': None, 'title': None, 'locator': None}
{'index': 32, 'target_release_id': None, 'extra': {'unstructured': 'M. F. Sakr, S. P. Levitan, D. M. Chiarulli, B. G. Horne, and C. L. Giles, "Predicting multiprocessor memory access patterns with learning models," In Proceedings of the International Conference on Machine Learning, 1997.'}, 'key': 'key-10.1145/2628071.2628082-33', 'year': None, 'container_name': None, 'title': None, 'locator': None}
{'index': 33, 'target_release_id': None, 'extra': {'unstructured': 'J. Shin, J. Chame, and M. W. Hall, "A compiler algorithm for exploiting pagemode memory access in embedded dram devices," In Proceedings of the Workshop on Media Streaming Process, 2002.'}, 'key': 'key-10.1145/2628071.2628082-34', 'year': None, 'container_name': None, 'title': None, 'locator': None}
{'index': 34, 'target_release_id': None, 'extra': {'unstructured': 'M. M. Strout, L. Carter, and J. Ferrante, "Compile-time composition of run-time data and iteration reorderings," In Proceedings of the Conference on Programming Language Design and Implementation, 2003.'}, 'key': 'key-10.1145/2628071.2628082-35', 'year': None, 'container_name': None, 'title': None, 'locator': None}
{'index': 35, 'target_release_id': None, 'extra': {'unstructured': 'K. Sudan, N. Chatterjee, D. Nellans, M. Awasthi, R. Balasubramonian, and A. Davis, "Micro-pages: increasing dram efficiency with locality-aware data placement," In Proceedings of the International Conference on Architectural Support for Programming Languages and Operating Systems, 2010.'}, 'key': 'key-10.1145/2628071.2628082-36', 'year': None, 'container_name': None, 'title': None, 'locator': None}
{'index': 36, 'target_release_id': None, 'extra': {'unstructured': 'K. Thabit, "Cache management by the compiler," Ph.D. dissertation, Rice University, Houston, TX, USA, 1982.'}, 'key': 'key-10.1145/2628071.2628082-37', 'year': None, 'container_name': None, 'title': None, 'locator': None}
{'index': 37, 'target_release_id': None, 'extra': {'unstructured': 'H. Yoon, J. Meza, R. Ausavarungnirun, R. Harding, and O. Mutlu, "Row buffer locality-aware data placement in hybrid memories," SAFARI Technical Report, 2011.'}, 'key': 'key-10.1145/2628071.2628082-38', 'year': None, 'container_name': None, 'title': None, 'locator': None}
{'index': 38, 'target_release_id': None, 'extra': {'unstructured': 'G. L. Yuan, A. Bakhoda, and T. M. Aamodt, "Complexity effective memory access scheduling for many-core accelerator architectures," In Proceedings of the International Symposium on Microarchitecture, 2009.'}, 'key': 'key-10.1145/2628071.2628082-39', 'year': None, 'container_name': None, 'title': None, 'locator': None}
{'index': 39, 'target_release_id': None, 'extra': {'unstructured': 'C. Zhang, C. Ding, M. Ogihara, Y. Zhong, and Y. Wu, "A hierarchical model of data locality," In Proceedings of the Conference on Principles of Programming Languages, 2006.'}, 'key': 'key-10.1145/2628071.2628082-40', 'year': None, 'container_name': None, 'title': None, 'locator': None}
{'index': 40, 'target_release_id': None, 'extra': {'unstructured': 'Z. Zhang, Z. Zhu, and X. Zhang, "A permutation-based page interleaving scheme to reduce row-buffer conflicts and exploit data locality," In Proceedings of the International Symposium on Microarchitecture, 2000.'}, 'key': 'key-10.1145/2628071.2628082-41', 'year': None, 'container_name': None, 'title': None, 'locator': None}
{'index': 41, 'target_release_id': None, 'extra': {'unstructured': 'Y. Zhong, M. Orlovich, X. Shen, and C. Ding, "Array regrouping and structure splitting using whole-program reference affinity," In Proceedings of the Conference on Programming Language Design and Implementation, 2004.'}, 'key': 'key-10.1145/2628071.2628082-42', 'year': None, 'container_name': None, 'title': None, 'locator': None}
{'index': 42, 'target_release_id': None, 'extra': {'unstructured': 'Z. Zhu and Z. Zhang, "A performance comparison of dram memory system optimizations for SMT processors," In Proceedings of the International Symposium on High-Performance Computer Architecture, 2005.'}, 'key': 'key-10.1145/2628071.2628082-43', 'year': None, 'container_name': None, 'title': None, 'locator': None}
|