Y.-C. Chung, C.-H. Hsu, and S.-W. Bai. A basic-cycle calculation technique for efficient dynamic data redistribution. IEEE Transactions on Parallel and Distributed Systems, 9(4), April 1998. Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
Optimization of Data Remapping in Data-Parallel Languages - Mehofer (1998) (Correct)
....on this representation remapping algorithms are discussed. One of the significant contributions is being able to handle arbitrary source and target processor sets while performing remappings. Also an arbitrary number of array dimensions can be handled in a scalable manner. Y. C. Chung et al. [13] present a basic cycle calculation technique to efficiently perform a cyclic(s) to cyclic(t) remapping. The idea is to compute for some specific array elements in a basic cycle, which is defined by lcm(s; t) gcd(s; t) the communication sets. The communication sets of the basic cycle are used to ....
Y.-C. Chung, C.-H. Hsu, and S.-W. Bai. A basic-cycle calculation technique for efficient dynamic data redistribution. IEEE Transactions on Parallel and Distributed Systems, 9(4), April 1998.
Efficient Algorithms for Block-Cyclic Array Redistribution.. - Park, Prasanna, al. (Correct)
....start up cost can be reduced by minimizing the number of message transfer steps. The transmission cost is incurred in transferring the bits over the network and depends on the network bandwidth. Table 1 summarizes the key features of the well known data distribution algorithms in the literature [4, 13, 14, 15, 21]. All of the known algorithms ignore one or more of the above costs. Some schemes focus only on efficient index set computation and completely ignore scheduling the communication events. Based on the index of a block, these schemes focus on finding its destination processor and generating messages ....
....in [11] It uses a simple round robin schedule to avoid node contention. Key Features Schedule Index Computation Communication PITFALLS [14] No communication scheduling . Index computation using a line segment formalism . Node contention occurs . Does not minimize the transmission cost BCC [21] . No communication scheduling . Efficient index computation . Source and destination sets are same . Node contention occurs . Does not minimize the transmission cost Caterpillar [11] Simple scheduling algorithm . Index computation by scanning the array segments . No node contention . Does not ....
Y.C. Chung, C.H. Hsu, and S.W. Bai. A Basic-Cycle Calculation Technique for Efficient Dynamic Data Redistribution. In IEEE Tans. on Parallel and Distributed Systems, Vol. 9, No. 4, April 1998.
On Compiling Block-Cyclic Data Redistribution - Kuei-Ping Shih (1997) Self-citation (Chung Sheu) (Correct)
No context found.
Y.-C. Chung and C.-S. Sheu. A basic-cycle calculation technique for efficient dynamic data redistribution. In Proceedings of the Internation Computer Symposium, Kaohsiung, Taiwan, December 1996.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC