High-performance data-parallel input/output Public Deposited

http://ir.library.oregonstate.edu/concern/graduate_thesis_or_dissertations/736667681

Descriptions

Attribute NameValues
Creator
Abstract or Summary
  • Existing parallel file systems are proving inadequate in two important arenas: programmability and performance. Both of these inadequacies can largely be traced to the fact that nearly all parallel file systems evolved from Unix and rely on a Unix-oriented, single-stream, block-at-a-time approach to file I/O. This one-size-fits-all approach to parallel file systems is inadequate for supporting applications running on distributed-memory parallel computers. This research provides a migration path away from the traditional approaches to parallel I/O at two levels. At the level seen by the programmer, we show how file operations can be closely integrated with the semantics of a parallel language. Principles for this integration are illustrated in their application to C*, a virtual-processor- oriented language. The result is that traditional C file operations with familiar semantics can be used in C* where the programmer works--at the virtual processor level. To facilitate high performance within this framework, machine-independent modes are used. Modes change the performance of file operations, not their semantics, so programmers need not use ambiguous operations found in many parallel file systems. An automatic mode detection technique is presented that saves the programmer from extra syntax and low-level file system details. This mode detection system ensures that the most commonly encountered file operations are performed using high-performance modes. While the high-performance modes allow fast collective movement of file data, they must include optimizations for redistribution of file data, a common operation in production scientific code. This need is addressed at the file system level, where we provide enhancements to Disk-Directed I/O for redistributing file data. Two enhancements are geared to speeding fine-grained redistributions. One uses a two-phase, or indirect, approach to redistributing data among compute nodes. The other relies on I/O nodes to guide the redistribution by building packets bound for compute nodes. We model the performance of these enhancements and determine the key parameters determining when each approach should be used. Finally, we introduce the notion of collective prefetching and identify its performance benefits and implementation tradeoffs.
Resource Type
Date Available
Date Copyright
Date Issued
Degree Level
Degree Name
Degree Field
Degree Grantor
Commencement Year
Advisor
Academic Affiliation
Non-Academic Affiliation
Subject
Rights Statement
Peer Reviewed
Language
Digitization Specifications
  • File scanned at 300 ppi (Monochrome, 8-bit Grayscale) using ScandAll PRO 1.8.1 on a Fi-6770A in PDF format. CVista PdfCompressor 4.0 was used for pdf compression and textual OCR.
Replaces
Additional Information
  • description.provenance : Approved for entry into archive by Patricia Black(patricia.black@oregonstate.edu) on 2012-10-16T19:38:38Z (GMT) No. of bitstreams: 1 MooreJasonA1997.pdf: 8448453 bytes, checksum: 841eb5e3690815bd058506f6f832fa15 (MD5)
  • description.provenance : Made available in DSpace on 2012-10-16T20:48:28Z (GMT). No. of bitstreams: 1 MooreJasonA1997.pdf: 8448453 bytes, checksum: 841eb5e3690815bd058506f6f832fa15 (MD5) Previous issue date: 1996-07-19
  • description.provenance : Approved for entry into archive by Patricia Black(patricia.black@oregonstate.edu) on 2012-10-16T20:48:28Z (GMT) No. of bitstreams: 1 MooreJasonA1997.pdf: 8448453 bytes, checksum: 841eb5e3690815bd058506f6f832fa15 (MD5)
  • description.provenance : Submitted by Kaylee Patterson (kdpscanner@gmail.com) on 2012-10-15T15:24:44Z No. of bitstreams: 1 MooreJasonA1997.pdf: 8448453 bytes, checksum: 841eb5e3690815bd058506f6f832fa15 (MD5)

Relationships

Parents:

This work has no parents.

Last modified

Downloadable Content

Download PDF

Items