392 research outputs found
Transparent Real-Time Monitoring in MPI
No full textMPI has emerged as a popular way to write architecture--independent parallel programs. By modifying an MPI library and associated MPI run--time environment, transparent extraction of timestamped information is possible. The wall--clock time at which specific MPI communication events begin and end can be recorded, collected, and provided to a central scheduler. The infrastructure to create and collect these events has been implemented and tested, and a future architecture that can use this information is described. Point of Contact: Dr. Samuel H. Russ email: [email protected] Phone: (601) 325--7775 Fax: (601) 325--7692 Web: http://www.erc.msstate.edu/~russ Mail: Engineering Research Center Box 9627 Miss. State, MS 1 Transparent Real--Time Monitoring in MPI 1 Samuel H. Russ#, Rashid Jean--Baptiste#, Tangirala Shailendra Krishna Kumar#, and Marion Harmon# #Mississippi State University NSF Engineering Research Center for Computational Field Simulation #Florida A&M Unive..
JavaGRID: Providing Simplified Access to Widely Distributed Computing
No full textPresented for Consideration to the Conference on High Performance Distributed Computing Samuel H. Russ, Srikanth Batchu, Sonetra Howard, and Saneedp Musinipally Mississippi State University NSF Engineering Research Center for Computational Field Simulation Abstract ---- The era of rapid, easy access to remote computer resources is rapidly ap- proaching. Systems and collaborative efforts have been launched to experiment and determine how widely distributed, loosely coupled computing resources can be harnessed and man- aged efficiently and effectively. Such systems are sometimes called a "grid" or "information power grid". This paper discusses a grid architecture that promotes widely distributed com- puting among scientific programmers by making both access to remote resources and admins- tiration of remote users extremely simple. The architecture leverages the portability of Java, the Web, and MPI, and provides a platform for experimenting with regional--scale grids and "intrag..
An Artificial Immune System Model for Task Allocation
No full textSubmitted for Consideration to the Symposium on High Performance Distributed Computing Samuel H. Russ, Aric Lambert, Roger King, Rajesh Rajan, and Donna Reese Mississippi State University NSF Engineering Research Center for Computational Field Simulation Abstract ---- Networked computing resources can be harnessed to provide medium and large--scale computational services. Most systems to harness such resources rely on allocation heuristics and policies to perform the mapping of tasks onto hosts. Such heuristics are typical- ly statically designed and typically only the parameters that govern the heuristic can be adapt- ed over time. This paper describes a novel architecture for task mapping and performance optimization that adapts automatically to new architectures and new programming strategies and algorithms. It will not only perform allocation and performance optimization, but also will learn about new systems and bottlenecks and respond appropriately. An early implementation ..
Fault-Tolerant System for Balancing the Load of Data-Parallel Applications
No full textIn distributed computing environments, fault--tolerance is an important objective, especially for parallel applications. Many distributed computing environments achieve fault--tolerance by periodic checkpointing. This has the advantage of relative ease of implementation and can be considered equivalent to task migration. However, there are two main disadvantages of such environments. One is that any work in progress after checkpoint- ing is lost when a fault occurs. The other is that these systems are heavily reliant on task migra- tion as the only mechanism for load balancing. This paper presents a system that overcomes these shortcomings by task duplication and by the integration of data migration into task migration as a load balancing mechanism. It also presents results of a preliminary implementation. Key Words: Distributed computing, Task Migration, Load Balancing, Fault--Tolerance Point of Contact: Samuel H. Russ Phone: +1 (601) 325--7775 Fax: +1 (601) 325--7692 Mail: Engi..
Signal integrity: applied electromagnetics and professional practice
No full textThis textbook teaches how to design working systems at very high frequencies. It is designed to introduce computer engineers to the design of extremely high speed digital systems. Combining an intuitive, physics-based approach to electromagnetics with a focus on solving realistic problems, the author presents concepts that are essential for computer and electrical engineers today. The book emphasizes an intuitive approach to electromagnetics, and then uses this foundation to show the reader how both physical phenomena can cause signals to propagate incorrectly; and how to solve commonly encountered issues. Emphasis is placed on real problems that the author has encountered in his professional career, integrating problem-solving strategies and real signal-integrity case studies throughout the presentation. Students are challenged to think about managing complex design projects and implementing successful engineering and manufacturing processes. Each chapter includes exercises to test concepts introduced
Conical square function estimates in UMD Banach spaces and applications to H?-functional calculi
No full textWe study conical square function estimates for Banach-valued functions and introduce a vector-valued analogue of the Coifman-Meyer-Stein tent spaces. Following recent work of Auscher-M(c)Intosh-Russ, the tent spaces in turn are used to construct a scale of vector-valued Hardy spaces associated with a given bisectorial operator A with certain off-diagonal bounds such that A always has a bounded H-infinity-functional calculus on these spaces. This provides a new way of proving functional calculus of A on the Bochner spaces L-p(R-n; X) by checking appropriate conical square function estimates and also a conical analogue of Bourgain's extension of the Littlewood-Paley theory to the UMD-valued context. Even when X = C, our approach gives refined p-dependent versions of known resultsDelft Institute of Applied MathematicsElectrical Engineering, Mathematics and Computer Scienc
Catalytic P-H activation by Ti and Zr catalysts
No full textCatalytic dehydrocoupling of phosphines was investigated using the anionic zirconocene trihydride salts [Cp*Zr-2(mu-H)(3)Li](3) (1a) or [Cp*Zr-2(mu-H)(3)K(thf)(4)] (1b), and the metallocycles [CpTi(NPtBu3)(CH2)(4)] (6) and [Cp*M(NPtBu3)(CH2)(4)] (M = Ti 20, Zr 21) as catalyst precursors. Dehydrocoupling of primary phosphines RPH2 (R = Ph, C6H2Me3, Cy, C10H7) gave both dehydrocoupled dimers RP(H)P(H)R or cyclic oligophosphines (RP)(n) (n = 4, 5) while reaction of tBu(3)C(6)H(2)PH(2) gave the phosphaindoline tBu(2)(Me2CCH2)C6H2PH (9). Stoichiometric reactions of these catalyst precursors with primary phosphines afforded [Cp*Zr-2((PR)(2))H][K(thf)(4)] (R = Ph 2, Cy 3, C6H2Me3 4), [Cp*Zr-2((PPh)(3))H] [K(thf)(4)] (5), [CpTi(NPtBu3)(PPh)(3)] (7) and [CpTi(NPtBu3)(mu-PHPh)](2) (8), while reaction of 6 with (C(6)H(2)tBu3)PH2 in the presence of PMe3 afforded [CpTi(NPtBu3)(PMe3)(p(C(6)H(2)tBu(3))] (10). The secondary phosphines Ph2PH and (PhHPCH2)(2)CH2 also undergo dehydrocoupling affording (Ph2P)(2) and (PhPCH2)(2)CH2. The bisphosphines (CH2PH2)(2) and C6H4(PH2)(2) are dehydrocoupled to give (PCH2CH2PH)(2) (12) and (C6H4P(PH))(2) (13) while prolonged reaction of 13 gave (C6H4P2)(8) (14). The analogous bisphosphine Me2C6H4(PH)(2) (17) was prepared and dehydrocoupling catalysis afforded (Me2C6H2P(PH))(2) (18) and subsequently [(Me2C6H2P2)(2)(mu-Me2C6H2P2)](2) (19). Stoichiometric reactions with these bisphosphines gave [Cp*Zr-2(H)(PH)(2)C6H4] [Li(thf)(4)] (22), [Cp*Ti(NPtBu3)(PH)(2)C6H4](2) (23) and [Cp*Ti(NPtBu3)(PH)(2)C6H4] (24). Mechanistic implications are discussed.PT: J; CR: ALBRAND JP, 1976, J CHEM SOC CHEM COMM, P876 ANSELME JP, 1969, TETRAHEDRON, V25, P855 BASULI F, 2003, J AM CHEM SOC, V125, P10170 BAUDLER M, 1976, Z NATURFORSCH B, V31, P558 BAUDLER M, 1978, CHEM BER, V111, P1210 BAUDLER M, 1978, CHEM BER, V111, P1217 BAUDLER M, 1983, CHEM BER, V116, P2711 BAUDLER M, 1984, Z NATURFORSCH B, V39, P438 BAZAN GC, 1991, J AM CHEM SOC, V113, P6899 BOHM VPW, 2001, ANGEW CHEM, V113, P4832 CHAUVIN Y, 1971, MAKROMOL CHEM, V141, P161 COREY JY, 2004, ADV ORGANOMET CHEM, V51, P1 COURET C, 1986, ORGANOMETALLICS, V5, P113 COWLEY AH, 1984, TETRAHEDRON LETT, V25, P2125 COWLEY AH, 1990, INORG SYNTH, V27, P235 CROMER DT, 1974, INT TABLES CRYSTALLO, V4, P71 ETKIN N, 1997, J AM CHEM SOC, V119, P11420 ETKIN N, 1997, J AM CHEM SOC, V119, P2954 ETKIN N, 1997, ORGANOMETALLICS, V16, P3504 FEHLNER TP, 1992, INORGANOMETALLLICS FERMIN MC, 1995, J AM CHEM SOC, V117, P12645 FERMIN MC, 1995, ORGANOMETALLICS, V14, P4247 FU GC, 1993, J AM CHEM SOC, V115, P9856 GAUVIN F, 1998, ADV ORGANOMET CHEM, V42, P363 GRAHAM TW, 2004, ORGANOMETALLICS, V23, P3309 GRUBBS RH, 1972, J AM CHEM SOC, V94, P2538 GRUBBS RH, 2003, HDB METATHESIS HEY E, 1988, CHEM BER, V121, P561 HEY E, 1989, J ORGANOMET CHEM, V378, P375 HO JW, 1991, ORGANOMETALLICS, V10, P3001 HO JW, 1994, INORG CHEM, V33, P865 HOFFMAN PR, 1975, INORG CHEM, V14, P1997 HOSKIN AJ, 2001, ANGEW CHEM, V113, P1917 HOU ZM, 1993, ORGANOMETALLICS, V12, P3158 INAGAKI Y, 1980, B CHEM SOC JPN, V53, P205 ISSLEIB K, 1972, ANGEW CHEM, V84, P582 ISSLEIB K, 1987, J ORGANOMET CHEM, V330, P17 JACOBSEN EN, 1988, J AM CHEM SOC, V110, P1968 KATSUKI T, 1980, J AM CHEM SOC, V102, P5974 KAUFFMANN T, 1984, TETRAHEDRON LETT, V25, P1963 KAUFFMANN T, 1985, CHEM BER, V118, P1022 KITAMURA M, 1988, J AM CHEM SOC, V110, P629 KNOWLES WS, 1983, ACCOUNTS CHEM RES, V16, P106 KOEPF H, 1981, CHEM BER, V114, P2731 KOHLER EP, 1935, J AM CHEM SOC, V57, P367 KYBA EP, 1983, ORGANOMETALLICS, V2, P1877 MILLER AR, 1976, J AM CHEM SOC, V98, P1860 MILLER SJ, 1996, J AM CHEM SOC, V118, P9606 MIYASHITA A, 1980, J AM CHEM SOC, V102, P7932 MURDZEK JS, 1987, ORGANOMETALLICS, V6, P1373 NGUYEN ST, 1992, J AM CHEM SOC, V114, P3974 NGUYEN ST, 1993, J AM CHEM SOC, V115, P9858 NOVAK BM, 1988, J AM CHEM SOC, V110, P960 OHKUMA T, 1995, J AM CHEM SOC, V117, P2675 OHTA T, 1988, INORG CHEM, V27, P566 OSHIKAWA T, 1985, CHEM IND-LONDON, P126 ROCKLAGE SM, 1981, J AM CHEM SOC, V103, P1440 SCHOLL M, 1999, TETRAHEDRON LETT, V40, P2247 SCHROCK RR, 1974, J AM CHEM SOC, V96, P6796 SCHROCK RR, 1980, J MOL CATAL, V8, P73 SCHROCK RR, 1988, J MOL CATAL, V46, P243 SCHROCK RR, 1990, J AM CHEM SOC, V112, P3875 SCHWAB P, 1995, ANGEW CHEM INT EDIT, V34, P2039 SCHWAB P, 1995, ANGEW CHEM, V107, P2179 SCHWAB P, 1996, J AM CHEM SOC, V118, P100 SENDERIKHIN AI, 1988, ZH OBSHCH KHIM+, V58, P1662 SENDERIKHIN AI, 1989, ZH OBSHCH KHIM+, V59, P2141 SEYFERTH D, 1969, J ORG CHEM, V34, P1483 SHELDRICK GM, 2000, SHELXTL SHU RH, 1998, J AM CHEM SOC, V120, P12988 SMIT CN, 1983, TETRAHEDRON LETT, V24, P2031 SOUFFLET JP, 1973, CR ACAD SCI C CHIM, V276, P169 STEPHAN DW, 2000, ANGEW CHEM, V112, P322 STEPHAN DW, 2005, ORGANOMETALLICS, V24, P2548 STRADIOTTO M, 2001, HELV CHIM ACTA, V84, P2958 TILLEY TD, 1990, COMMENTS INORG CHEM, V10, P37 TILLEY TD, 1993, ACCOUNTS CHEM RES, V26, P22 TVERDOMED SN, 2003, RUSS J GEN CHEM+, V73, P319 VANDENWINKEL Y, 1991, J ORGANOMET CHEM, V405, P183 WATERMAN R, 2006, ANGEW CHEM INT EDIT, V45, P2926 WATERMAN R, 2006, ANGEW CHEM, V118, P2992 WEAST RC, 1974, HDB CHEM PHYS, P2436 WOOD CD, 1979, J AM CHEM SOC, V101, P3210 WU Z, 1995, J AM CHEM SOC, V117, P5503 XIN SX, 1997, J AM CHEM SOC, V119, P5307; NR: 85; TC: 0; J9: CHEM-EUR J; PG: 12; GA: 113PJSource type: Electronic(1
Characteristic Timing
No full textWe use differences between the attributes of stock issuers and repurchasers to forecast characteristic-related stock returns. For example, we show that large firms underperform following years when issuing firms are large relative to repurchasing firms. Our approach is useful for forecasting returns to portfolios based on book-to-market (HML), size (SMB), price, distress, payout policy, profitability, and industry. We consider interpretations of these results based on both time-varying risk premia and mispricing. Our results are primarily consistent with the view that firms issue and repurchase shares to exploit time-varying characteristic mispricing.
- …
