Two Hardware-Based Approaches for Deterministic Multiprocessor Replay.
Many shared-memory multithreaded executions behave nondeterministically when run on multiprocessor hardware such as emerging multicore systems. Recording nondeterministic events in such executions can enable deterministic replay—e.g., for debugging. Most challenging to record are memory races that c...
| Publicado en: | Communications of the ACM Vol. 52; no. 6; pp. 93 - 101 |
|---|---|
| Autores principales: | , , , , |
| Formato: | Artículo |
| Publicado: |
Association for Computing Machinery
Jun2009
|
| Materias: | |
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=hlh&AN=40217620&site=ehost-live header: @attributes: shortDbName: hlh uiTerm: 40217620 longDbName: Humanities International Complete uiTag: AN controlInfo: bkinfo: jinfo: jid: 00010782 ACM jtl: Communications of the ACM issn: 00010782 maglogo: N pubinfo: dt: Jun2009 vid: 52 iid: 6 pid: 68 pub: Association for Computing Machinery artinfo: ui: 40217620 10.1145/1516046.1516068 ppf: 93 ppct: 8 formats: tig: atl: Two Hardware-Based Approaches for Deterministic Multiprocessor Replay. aug: au: Hower, Derek R. Montesinos, Pablo Ceze, Luis Hill, Mark D. Torrellas, Josep affil: Computer sciences Department, University of Wisconsin-Madison. Computer science Department, University of Illinois, Urbana-Champaign. Department of computer science and engineering, University of Washington. su: Parallel programs (Computer programs) Threads (Computer programs) Multiprocessors Multiprogramming (Electronic computers) Parallel processing Microprocessors sug: subj: Parallel programs (Computer programs) Threads (Computer programs) Multiprocessors Multiprogramming (Electronic computers) Parallel processing Microprocessors ab: Many shared-memory multithreaded executions behave nondeterministically when run on multiprocessor hardware such as emerging multicore systems. Recording nondeterministic events in such executions can enable deterministic replay—e.g., for debugging. Most challenging to record are memory races that can potentially occur on almost all memory references. For this reason, researchers have previously proposed hardware to record key memory race interactions among threads. The two research groups coauthoring this paper independently uncovered a dual approach: focus on recording how long threads execute without interacting. From this common insight, the groups developed two significantly different hardware proposals. Wisconsin Rerun makes few changes to standard multicore hardware, while Illinois DeLorean promises much smaller log sizes and higher replay speeds. By presenting both proposals in one paper, we seek to illuminate the promise of the joint insight and inspire future designs. pubtype: Periodical doctype: Article src: R language: English refInfo: copyright: @attributes: flag: Y dt: @attributes: year: 2009 holdings: @attributes: islocal: N |
|---|