Method and structure for producing high performance linear algebra routines using register block data format routines
US8316072B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Aug 21, 2008 |
| Grant date | Nov 20, 2012 |
| Priority date | — |
| Expiry date | Sep 21, 2031 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06F17/16
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A method (and structure) of executing a matrix operation, includes, for a matrix A, separating the matrix A into blocks, each block having a size p-by-q. The blocks of size p-by-q are then stored in a cache or memory in at least one of the two following ways. The elements in at least one of the blocks is stored in a format in which elements of the block occupy a location different from an original location in the block, and/or the blocks of size p-by-q are stored in a format in which at least one block occupies a position different relative to its original position in the matrix A.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.