[
https://issues.apache.org/jira/browse/MAHOUT-1780?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Suneel Marthi resolved MAHOUT-1780.
-----------------------------------
Resolution: Duplicate
Duplicate of M-1781
> Multi-threaded Matrix Multiplication is slower than Single-thread variant
> -------------------------------------------------------------------------
>
> Key: MAHOUT-1780
> URL: https://issues.apache.org/jira/browse/MAHOUT-1780
> Project: Mahout
> Issue Type: Bug
> Components: Math
> Affects Versions: 0.10.0, 0.10.1, 0.10.2, 0.11.0
> Reporter: Suneel Marthi
> Assignee: Dmitriy Lyubimov
> Priority: Critical
> Labels: performance
> Fix For: 0.12.0, 0.13.0
>
>
> Capturing the Conversation on the subject here:
> {code}
> Turns out that matrix view traversal (of dense matrices, anyway) is 4 times
> slower than regular matrix traversal in the same direction. I.e.
> Ad %*% Bd: (106.33333333333333,85.0)
> Ad(r,::) %*% Bd: (356.0,328.0)
> where r=0 until Ad.nrow.
> On investigating MatrixView, it does report correct matrix flavor (as the
> owner's) and correct algorithm is selected (the same as for the row above).
> MatrixView gives an indirection(sometimes even double indirection) but it
> still doesn't explain the 4x performance degrade. It should not be that much
> different from transpose view overhead, and transpose view overhead is very
> small in the tests (compared to the rest of the cost)
> The main difference seems to be that the algorithm over matrices ends up
> doing a dot over DenseVector and a DenseVector (even that the wrapper object
> is created inside the row iterations) whereas the inefficient algorithm does
> the same over VectorView wrappers. I wonder if VectorView has not been
> equipped to pass on the flavors of its backing vector to the vector-vector
> optimization.
> Apparently the dot algorithm on vector view goes to the in-core vector-vector
> optimization framework (calls aggregate()) but denseVector applies custom
> iteration. Hence it may boil down to experiments of avec dot bvec vs.
> avec(::) dot bvec(::).
> {code}
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
