Github user mengxr commented on a diff in the pull request:
https://github.com/apache/spark/pull/1932#discussion_r16221793
--- Diff:
mllib/src/main/scala/org/apache/spark/mllib/feature/Word2Vec.scala ---
@@ -321,42 +320,46 @@ class Word2Vec extends Serializable with Logging {
// Hierarchical softmax
var d = 0
while (d < bcVocab.value(word).codeLen) {
- val l2 = bcVocab.value(word).point(d) * vectorSize
+ val ind = bcVocab.value(word).point(d)
+ val l2 = ind * vectorSize
// Propagate hidden -> output
- var f = blas.sdot(vectorSize, syn0, l1, 1, syn1, l2,
1)
+ synModify(ind) += 1
+ var f = blas.sdot(vectorSize, syn, l1, 1, syn, l2, 1)
if (f > -MAX_EXP && f < MAX_EXP) {
val ind = ((f + MAX_EXP) * (EXP_TABLE_SIZE /
MAX_EXP / 2.0)).toInt
f = expTable.value(ind)
val g = ((1 - bcVocab.value(word).code(d) - f) *
alpha).toFloat
- blas.saxpy(vectorSize, g, syn1, l2, 1, neu1e, 0, 1)
- blas.saxpy(vectorSize, g, syn0, l1, 1, syn1, l2, 1)
+ blas.saxpy(vectorSize, g, syn, l2, 1, neu1e, 0, 1)
+ blas.saxpy(vectorSize, g, syn, l1, 1, syn, l2, 1)
}
d += 1
}
- blas.saxpy(vectorSize, 1.0f, neu1e, 0, 1, syn0, l1, 1)
+ blas.saxpy(vectorSize, 1.0f, neu1e, 0, 1, syn, l1, 1)
+ synModify(lastWord) += 1
}
}
a += 1
}
pos += 1
}
- (syn0, syn1, lwc, wc)
+ (syn, lwc, wc)
}
- Iterator(model)
- }
- val (aggSyn0, aggSyn1, _, _) =
- partial.treeReduce { case ((syn0_1, syn1_1, lwc_1, wc_1), (syn0_2,
syn1_2, lwc_2, wc_2)) =>
- val n = syn0_1.length
- val weight1 = 1.0f * wc_1 / (wc_1 + wc_2)
- val weight2 = 1.0f * wc_2 / (wc_1 + wc_2)
- blas.sscal(n, weight1, syn0_1, 1)
- blas.sscal(n, weight1, syn1_1, 1)
- blas.saxpy(n, weight2, syn0_2, 1, syn0_1, 1)
- blas.saxpy(n, weight2, syn1_2, 1, syn1_1, 1)
- (syn0_1, syn1_1, lwc_1 + lwc_2, wc_1 + wc_2)
+ val synLocal = model._1
+ val synOut = new PrimitiveKeyOpenHashMap[Int,
Array[Float]](vocabSize * 2)
+ var index = 0
+ while(index < 2 * vocabSize) {
+ if (synModify(index) != 0) {
+ synOut.update(index, synLocal.slice(index * vectorSize, (index
+ 1) * vectorSize))
+ }
+ index += 1
}
- syn0Global = aggSyn0
- syn1Global = aggSyn1
+ Iterator(synOut)
+ }
+ synGlobal = partial.flatMap(x => x).reduceByKey {
+ case (v1,v2) =>
+ blas.saxpy(vectorSize, 1.0f, v2, 1, v1, 1)
+ v1
+ }.collect().sortBy(_._1).flatMap(x => x._2)
--- End diff --
updating `synGlobal` in-place is more memory-efficient. We don't need to
allocate new storage and sort.
---
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 infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
