Data processing: software development – installation – and managem – Software program development tool – Translation of code
Reexamination Certificate
2007-01-23
2007-01-23
Kim, Hong (Department: 2185)
Data processing: software development, installation, and managem
Software program development tool
Translation of code
C717S154000, C711S137000, C711S119000, C712S227000
Reexamination Certificate
active
10853304
ABSTRACT:
A method and system for reducing or avoiding store misses with a data cache block zero (DCBZ) instruction in cooperation with the underlying hardware load stream prefetching support for helping to increase effective aggregate bandwith. The method identifies and classifies unique streams in a loop based on dependency and reuse analysis, and performs loop transformations, such as node splitting, loop distribution or stream unrolling to get the proper number of streams. Static prediction and run-time profile information are used to guide loop and stream selection. Compile-time loop cost analysis and run-time check code and versioning are used to determine the number of cache lines ahead of each reference for data cache line zeroing and to tolerate required data alignment relative to data cache lines.
REFERENCES:
patent: 4991088 (1991-02-01), Kam
patent: 5551001 (1996-08-01), Cohen et al.
patent: 5692152 (1997-11-01), Cohen et al.
patent: 5704053 (1997-12-01), Santhanam
patent: 5797013 (1998-08-01), Mahadevan et al.
patent: 5854934 (1998-12-01), Hsu et al.
patent: 5953531 (1999-09-01), Megiddo et al.
patent: 6148439 (2000-11-01), Nishiyama
patent: 6249845 (2001-06-01), Nunez et al.
patent: 6301641 (2001-10-01), Verhoeven et al.
patent: 6374330 (2002-04-01), Arimilli et al.
patent: 6421826 (2002-07-01), Kosche et al.
patent: 6539541 (2003-03-01), Geva
patent: 6567976 (2003-05-01), Wolf
patent: 6571318 (2003-05-01), Sander et al.
patent: 2002/0007484 (2002-01-01), Tirumalai et al.
patent: 2002/0010913 (2002-01-01), Ronstrom
patent: 2003/0005419 (2003-01-01), Pieper et al.
patent: 2003/0088864 (2003-05-01), Tirumalai et al.
patent: 2004/0123081 (2004-06-01), Knies et al.
patent: 2004/0154019 (2004-08-01), Aamodt et al.
Barua, R. “Communication-Minimal Partitioning of Parallel Loops and Data Arrays for Cache-Coherent Distributed-Memory Multiprocessors”, Proceedings Languages and Compilers for Parallel Computing, 9thInternational Workshop, LCPC '96, p. 350-368 Aug. 1996.
Aschenbrenner, J. M. “Zeroing Memory Using Data Cache Line”, IBM TDB, v 40 n 2, p. 221-222, Feb. 1997.
Archambault Roch Georges
Blainey Robert James
Gao Yaoging
Heisch Randall Ray
White Steven Wayne
International Business Machines - Corporation
Irvin David R.
Kim Hong
LandOfFree
Aggregate bandwidth through management using insertion of... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Aggregate bandwidth through management using insertion of..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Aggregate bandwidth through management using insertion of... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3822572