Skip to content

[SPARK-21389][ML][MLLIB] Optimize ALS recommendForAll by gemm #18624

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
mpjlu wants to merge 9 commits into from
Closed

[SPARK-21389][ML][MLLIB] Optimize ALS recommendForAll by gemm #18624

Changes from 1 commit
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
5ca3fd1
add poll for PriorityQueue
Jul 13, 2017
215efc3
test pass
Jul 13, 2017
7c587f4
fix bug
Jul 13, 2017
e8a40ed
code style change
Jul 13, 2017
963dae2
Code style fix
Jul 13, 2017
e5881f0
fix build error
Jul 14, 2017
4a9b350
fix DenseMatrix Store bugs
Jul 17, 2017
a5bf101
change poll to sortBy
Jul 17, 2017
f36706a
reset code
Dec 12, 2017
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
fix build error
  • Loading branch information
Peng Meng committed Jul 14, 2017
commit e5881f037db5b0cc66ca2e4eb74879d1bc9df9b1
2 changes: 1 addition & 1 deletion mllib/src/main/scala/org/apache/spark/mllib/recommendation/MatrixFactorizationModel.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -319,7 +319,7 @@ object MatrixFactorizationModel extends Loader[MatrixFactorizationModel] {
j += num
pq.clear()
}
index -> (srcIds, dstIdMatrix, new DenseMatrix(m, num, scoreMatrix))
(index, (srcIds, dstIdMatrix, new DenseMatrix(m, num, scoreMatrix)))
}
ratings.aggregateByKey(null: Array[Int], null: Array[Int], null: DenseMatrix)(
Copy link
Contributor

@MLnick MLnick Jul 14, 2017

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This is aggregating by key which in this case appears to be the "block index". What is the benefit then? Since each block will have a unique index, there would be no intermediate aggregation.

(rateSum, rate) => mergeFunc(rateSum, rate, num),
Expand Down