000055539 001__ 55539
000055539 005__ 20190416220412.0
000055539 037__ $$aARTICLE
000055539 245__ $$aTreadMarks: Shared Memory Computing on Networks of Workstations,
000055539 269__ $$a1996
000055539 260__ $$c1996
000055539 336__ $$aJournal Articles
000055539 520__ $$aTreadMarks supports parallel computing on networks of workstations by providing the application with a shared memory abstraction. Shared memory facilitates the transition from sequential to parallel programs. After identifying possible sources of parallelism in the code, most of the data structures can be retained without change, and only synchronization needs to be added to achieve a correct shared memory parallel program_ Additional transformations may be necessary to optimize performance, but this can be done in an incremental fashion. We discuss the techniques used in TreadMarks to provide efficient shared memory, and our experience with two large applications, mixed integer programming and genetic linkage analysis.
000055539 700__ $$aAmza, C.
000055539 700__ $$aCox, A.L.
000055539 700__ $$aDwarkadas, S.
000055539 700__ $$aKeleher, P.
000055539 700__ $$aLu, H.
000055539 700__ $$aRajamony, R.
000055539 700__ $$aYu, W.
000055539 700__ $$0243160$$g155705$$aZwaenepoel, W.
000055539 773__ $$j29$$tIEEE Computer$$k2$$q18-28
000055539 8564_ $$uhttps://infoscience.epfl.ch/record/55539/files/computer96.pdf$$zn/a$$s282134
000055539 909C0 $$xU10700$$0252226$$pLABOS
000055539 909CO $$ooai:infoscience.tind.io:55539$$qGLOBAL_SET$$pIC$$particle
000055539 937__ $$aLABOS-ARTICLE-2005-007
000055539 973__ $$rREVIEWED$$sPUBLISHED$$aOTHER
000055539 980__ $$aARTICLE