Github user MLnick commented on a diff in the pull request:
https://github.com/apache/spark/pull/17742#discussion_r114401026
--- Diff:
mllib/src/main/scala/org/apache/spark/mllib/recommendation/MatrixFactorizationModel.scala
---
@@ -276,44 +277,53 @@ object MatrixFactorizationModel extends
Loader[MatrixFactorizationModel] {
num: Int): RDD[(Int, Array[(Int, Double)])] = {
val srcBlocks = blockify(rank, srcFeatures)
val dstBlocks = blockify(rank, dstFeatures)
- val ratings = srcBlocks.cartesian(dstBlocks).flatMap {
- case ((srcIds, srcFactors), (dstIds, dstFactors)) =>
- val m = srcIds.length
- val n = dstIds.length
- val ratings = srcFactors.transpose.multiply(dstFactors)
- val output = new Array[(Int, (Int, Double))](m * n)
- var k = 0
- ratings.foreachActive { (i, j, r) =>
- output(k) = (srcIds(i), (dstIds(j), r))
- k += 1
+ /**
+ * Use dot to replace blas 3 gemm is the key approach to improve
efficiency.
--- End diff --
I think we should say something like:
> The previous approach used for computing top-k recommendations aimed to
group individual factor vectors into blocks, so that Level 3 BLAS operations
(gemm) could be used for efficiency. However, this causes excessive GC pressure
due to the large arrays required for intermediate result storage, as well as a
high sensitivity to the block size used.
>
> The following approach still groups factors into blocks, but instead
computes the top-k elements per block, using Level 1 BLAS (dot) and an
efficient BoundedPriorityQueue. This avoids any large intermediate
datastructures and results in significantly reduced GC pressure as well as
shuffle data, which far outweighs any cost incurred from not using Level 3 BLAS
operations.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
