[MAHOUT-1724] Optimizations of matrix-matrix in-core multiplication based on structural flavors

• Type: Improvement
• Status: Closed
• Priority: Major
• Resolution: Fixed
• Fix Version/s: 0.10.2
• Assignee: Dmitriy Lyubimov
• Reporter: Dmitriy Lyubimov
• Created: 02/Jun/15 23:27
• Updated: 07/Aug/15 15:56
• Resolved: 17/Jun/15 19:00

Description

Current times() operation suffers a lot. Especially when e.g. column-major iterations are done over a matrix backed by row-major sequential sparse vectors, things are dropping orders of magnitude in performance.

This issue finds optimal traversal gemm kernel order for current matrix; or rewrites matrix prior to operation to enable optimal traversals.

PR https://github.com/apache/mahout/pull/135