C. C. Chen, J. P. Singh, and R. B. Altman, "Parallel Hierarchical Molecular Structure Estimation", in Proc. Supercomputing '96, Pittsburgh, PA, 1996. Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
Pthreads for Dynamic and Irregular Parallelism - Narlikar, Blelloch (1998) (4 citations) (Correct)
....threads to result in high performance. Keywords: Multithreading, Pthreads, space efficiency, dynamic scheduling, irregular parallelism, lightweight threads. 1 Introduction Recently, shared memory multiprocessors have been used to implement a wide range of high performance applications [16, 20, 50, 55, 56]. The use of multithreading to program such applications is becoming popular, and POSIX threads or Pthreads [27] are now a standard supported on most platforms. Pthreads may be implemented either at the kernel level, or as a user level threads library. Kernel level implementations require a ....
Cheng Che Chen, Jaswinder Pal Singh, and Russ B. Altman. Parallel hierarchical molecular structure estimation. In Supercomputing '96 Conference Proceedings: November 17--22, Pittsburgh, PA, 1996.
Molecular Structure Computation from Multiple Data Sources - Chen (2000) Self-citation (Chen) (Correct)
....in the measurement. For NMR data, R may be 1 2 , while cross linking experiments may have 4 20 variance. An observation z may be vector valued; in particular, we may batch constraints into composite vectors of some uniform length to improve data reuse in the computer memory hierarchy [15, 19]. Furthermore, the functional dependency of h on the state vector x may be sparse (as in a distance constraint, which depends on two points) or dense (such as in the overall volume of a molecule, which involves all the atoms) The probabilistic least squares algorithm employed here transforms a ....
....suggests that we should not use too large a batching factor m, in order not to be bogged down in the Cholesky factorization and the Kalman filter matrix formation. Empirical measurements reveal that too small values of m are just as bad, due to the hierarchical nature of the computer memory system [15, 19]. For example, when we apply a single scalar constraint at a time (m = 1) the computation within the linearization loop of the update procedure reduces to vector operations, and the covariance matrix update becomes a rank one outer product update. These operations involve little data reuse in the ....
[Article contains additional citation context not shown here]
C. C. Chen, J. P. Singh, and R. B. Altman, "Parallel Hierarchical Molecular Structure Estimation", in Proc. Supercomputing '96, Pittsburgh, PA, 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