Tools
Sorted by:
Try your query at:
 |
 |
 |
 |
 |
 |
Results 1 - 10
of
64,942
Table 10-15. Results for the sherman3 matrix level iters. opcnt mem lunz fronts ftime stime ttime 107 105 105
1995
"... In PAGE 101: ... Table10 -1. The complete LU memory usage pattern step fmem cmem lumem totmem 1b 15 0 0 15 1e 0 8 7 15 2b 12 8 7 27 2e 0 14 13 27 3b 12 14 13 41 3e 0 14 19 33 4b 9 14 19 42 4e 0 10 24 34 5b 6 10 24 40 5e 0 2 28 30 6b 4 2 28 34 6e 0 1 31 32 7b 1 1 31 33 7e 0 0 32 32 Table 10-2.... In PAGE 101: ...Table 10-1. The complete LU memory usage pattern step fmem cmem lumem totmem 1b 15 0 0 15 1e 0 8 7 15 2b 12 8 7 27 2e 0 14 13 27 3b 12 14 13 41 3e 0 14 19 33 4b 9 14 19 42 4e 0 10 24 34 5b 6 10 24 40 5e 0 2 28 30 6b 4 2 28 34 6e 0 1 31 32 7b 1 1 31 33 7e 0 0 32 32 Table10 -2. The ILU memory usage pattern step fmem cmem lumem totmem 1b 15 0 0 15 1e 0 8 7 15 2b 10 8 7 25 2e 0 12 13 25 3b 8 12 13 33 3e 0 14 19 33 4b 4 14 19 37 4e 0 14 23 37 5b 5 14 23 42 5e 0 3 27 30 6b 3 3 27 33 6e 0 2 30 32 7b 1 2 30 33 7e 0 0 31... In PAGE 102: ... We fur- ther discuss this issue in the next section when we present the results of the numerical experiments. Table10 -3. The complete LU memory usage with garbage collection step fmem cmem lumem totmem 1b 15 0 0 15 1e 0 8 7 15 2b 12 8 7 27 2e 0 10 13 23 3b 12 10 13 35 3e 0 10 19 29 4b 9 10 19 38 4e 0 6 24 30 5b 6 6 24 36 5e 0 2 28 30 6b 4 2 28 34 6e 0 1 31 32 7b 1 1 31 33 7e 0 0 32 32 10.... In PAGE 103: ... Table10 -4. The ILU memory usage with garbage collection step fmem cmem lumem totmem 1b 15 0 0 15 1e 0 8 7 15 2b 10 8 7 25 2e 0 10 13 23 3b 8 10 13 31 3e 0 7 19 26 4b 4 7 19 30 4e 0 4 23 27 5b 5 4 23 32 5e 0 2 27 29 6b 3 2 27 32 6e 0 1 30 31 7b 1 1 30 32 7e 0 0 31 31 closer to zero the better.... In PAGE 104: ... Table10 -5. Matrix Statistics: A name discipline comments pores3 petroleum eng.... In PAGE 104: ... basis sherman3 petroleum eng. 35 11 13 grid Table10 -6. Matrix Statistics: B name n nz sym.... In PAGE 105: ... The ftime, stime, ttime columns give the incomplete factorization time, the time to solve the preconditioned system, and the total time (ftime plus stime), respectively. Table10 -7. Numerical Results: A for pores3 level iters.... In PAGE 106: ...14 .74 Table10 -9. Numerical Results: A for mcfe level iters.... In PAGE 106: ...53 8.01 64 Table10 -10. Numerical Results: B for mcfe level ftime stime ttime (sec) (sec) (sec) I ? ? ? 1 2.... In PAGE 107: ... Table10 -11. Numerical Results: A for orsirr2 level iters.... In PAGE 107: ...94 4.14 172 Table10 -12. Numerical Results: B for or- sirr2 level ftime stime ttime (sec) (sec) (sec) I ? ? ? 1 ? ? ? 2 1.... In PAGE 107: ...18 1.89 Table10 -13. Results for the saylr4 matrix level iters.... In PAGE 108: ... Table10 -14. Results for the gemat11 matrix... ..."
Table 32: Expected versus Actual performance of RAID-I for operations issued from the No-Copy special system call and from Sprite user level. I/O rates were measured for 4 KByte random read operations. Bandwidth was measured for 32 KBytes sequential read operations. Bandwidth for the \Best Ever quot; case was for 128 KByte sequential reads. Note that the \expected quot; 10-15 MByte/sec bandwidth for the array is the expected limit of the VME backplane.
1990
"... In PAGE 53: ... 5 Conclusions The goal of RAID-I was to discover whether a disk array built from commercially available compo- nents could provide adequate performance both for traditional le system and database applications (small, random I/Os) and for large scienti c and image processing applications (large, sequential I/Os). Table32 compares the expected performance of the components of RAID-I with those actually measured. It reveals a hierarchy of bottlenecks in the system.... ..."
Cited by 16
Table 1: Load Balancing Statistics [18] Shasha D. and Goodman N. Concurrent Search Tree Algorithms, ACM Transactions on Database Systems, 13(1), 1988, pp. 53-90. [19] Weihl E. W. and Wang P. Multi-version Memory: Software cache Management for Concurrent B- Trees, Proceedings of the 2nd IEEE Symposium on Parallel and Distributed Processing, 1990, pp. 650-655. [20] Yen I. and Bastani F. Hash Table in Massively Parallel Systems, Proceedings of the 1992 Interna- tional Conferences on Computer Languages, April 20-23, 1992, pp. 660-664.
1992
"... In PAGE 16: ... With hot spots the variation is much greater, indicating the nice e ect load balancing has for smoothing the variation and reducing the gradient. Finally Table1 shows the calculated average number of moves made by a node in the entire system, with and without hot spots and with and without load balancing, and the normalized variation of the capacity at each processor from the mean. The table shows that the load balancing reduces the coe cient of variation at the cost of a very small increase in the average moves in the system, indicating that load balancing is e ective with low overhead.... ..."
Cited by 4
Table 1 reports the value obtained. Protocol based PMT characterization PM nr. V1s (V) EPSp HVs (V) 10?15
"... In PAGE 5: ... Table1 : The required database quantities 6 Additional measurements Some additional measurements have been carried out to have a more precise evaluation of the phototube features.... ..."
Table 12: Data for ATUM Traces on 32K Caches [3] J. H. Chang, H. Chao, and K. So, \Cache Design of A Sub-Micron CMOS System/370, quot; in Proceedings of the 14th Annual International Symposium on Computer Architecture, Pittsburgh, Pennsylvania, pp. 208{213, IEEE Computer Society and ACM SIGARCH, June 2{5, 1987. Computer Architecture News, 15(2), June 1987. [4] John L. Hennessy and David A. Patterson, Computer Architecture: A Quantitative Ap- proach. Morgan Kaufmann Publishers, Inc., 1990. [5] Mark D. Hill, \A Case for Direct-Mapped Caches, quot; Computer, 21(12):25{40, December 1988.
1993
Cited by 1
Table 2. Reassembled Document Fragments in Top f5, 10, 15, 20g Candidates in a Single Pass
2002
"... In PAGE 6: ... Figure 5 shows the average compression ratio of sample document types and as we compare this to Figure 4 it is clear that more structure a document has bet- ter the accuracy of reassembly. Table2 presents most accurate reassembly in top-n, that is (fi 2 f5; 10; 15; 20g), candidate reorderings. At first sight the numbers in Table 2 may appear to be low.... In PAGE 6: ... Table 2 presents most accurate reassembly in top-n, that is (fi 2 f5; 10; 15; 20g), candidate reorderings. At first sight the numbers in Table2 may appear to be low. However, it should be noted that a forensic analyst can examine the top fi potential orderings by our system and... ..."
Cited by 3
Table 13: Data for ATUM Traces on 128K Caches [6] Norman P. Jouppi, \Improving Direct-Mapped Cache Performance by the Addition of a Small Fully-Associative Cache and Prefetch Bu ers, quot; in Proceedings of the 17th Annual International Symposium on Computer Architecture, Seattle, Washington, pp. 364{373, IEEE Computer Society and ACM SIGARCH, May 28{31, 1990. Computer Architecture News, 18(2), June 1990. [7] S. Przybylski, M. Horowitz, and J. Hennessy, \Performance Tradeo s in Cache Design, quot; in Proceedings of the 15th Annual International Symposium on Computer Architecture, Honolulu, Hawaii, pp. 290{298, IEEE Computer Society and ACM SIGARCH, May 30{ June 2, 1988. Computer Architecture News, 16(2), May 1988. 36
1993
Cited by 1
Table 3: Comparing Modified XP Practices in Large Projects and Agile Principles
2004
"... In PAGE 7: ... These practices still are guided by the agile principles. Table3 shows the mapping between Proceedings of the 37th Hawaii International Conference on System Sciences - 2004 0-7695-2056-1/04 $17.00 (C) 2004 IEEE... ..."
Cited by 1
Table 2. Recognition rates [in %] of different recognition systems for noisy speech with and without speech enhancement. MFCC / HMM : CCITT noise [dB SNR] algorithm -10 -5 0 5 10 15
Table 2. Recognition rates [in %] of different recognition systems for noisy speech with and without speech enhancement. MFCC / HMM : CCITT noise [dB SNR] algorithm -10 -5 0 5 10 15
Results 1 - 10
of
64,942
