Github user cloud-fan commented on the pull request:
https://github.com/apache/spark/pull/7018#issuecomment-115298005
the benchmark (ScalaUdf will convert from catalyst to scala and back again):
```scala
case class Floor(child: Expression) extends UnaryExpression with Predicate {
override def toString = s"Floor $child"
override def eval(input: InternalRow): Any = {
child.eval(input) match {
case null => null
case s: Seq[Int] => s.sum
}
}
}
object T {
def benchmark(count: Int, expr: Expression): Unit = {
var i = 0
val row = new GenericRow(Array[Any]((1 to 10).toSeq))
val s = System.currentTimeMillis()
while (i < count) {
expr.eval(row)
i += 1
}
val e = System.currentTimeMillis()
println (s"${expr.getClass.getSimpleName} -- ${e - s} ms")
}
def main(args: Array[String]) {
def func(s: Seq[Int]) = s.sum
val attr = BoundReference(0, ArrayType(IntegerType), true)
val udf0 = ScalaUdf(func _, IntegerType, attr :: Nil)
val udf1 = Floor(attr)
benchmark(1000000, udf0)
benchmark(1000000, udf0)
benchmark(1000000, udf0)
benchmark(1000000, udf1)
benchmark(1000000, udf1)
benchmark(1000000, udf1)
}
}
```
before:
ScalaUdf -- 321 ms
ScalaUdf -- 313 ms
ScalaUdf -- 232 ms
Floor -- 40 ms
Floor -- 7 ms
Floor -- 7 ms
after:
ScalaUdf -- 73 ms
ScalaUdf -- 26 ms
ScalaUdf -- 23 ms
Floor -- 34 ms
Floor -- 7 ms
Floor -- 7 ms
---
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
