Github user davies commented on a diff in the pull request:
https://github.com/apache/spark/pull/12440#discussion_r60526133
--- Diff:
sql/core/src/test/scala/org/apache/spark/sql/execution/BenchmarkWholeStageCodegen.scala
---
@@ -224,6 +224,127 @@ class BenchmarkWholeStageCodegen extends
SparkFunSuite {
*/
}
+ ignore("aggregate with string key") {
+ val N = 20 << 20
+
+ val benchmark = new Benchmark("Aggregate w string key", N)
+ def f(): Unit = sqlContext.range(N).selectExpr("id", "cast(id & 1023
as string) as k")
+ .groupBy("k").count().collect()
+
+ benchmark.addCase(s"codegen = F") { iter =>
+ sqlContext.setConf("spark.sql.codegen.wholeStage", "false")
+ f()
+ }
+
+ benchmark.addCase(s"codegen = T hashmap = F") { iter =>
+ sqlContext.setConf("spark.sql.codegen.wholeStage", "true")
+ sqlContext.setConf("spark.sql.codegen.aggregate.map.enabled",
"false")
+ f()
+ }
+
+ benchmark.addCase(s"codegen = T hashmap = T") { iter =>
+ sqlContext.setConf("spark.sql.codegen.wholeStage", "true")
+ sqlContext.setConf("spark.sql.codegen.aggregate.map.enabled", "true")
+ f()
+ }
+
+ benchmark.run()
+
+ /*
+ Java HotSpot(TM) 64-Bit Server VM 1.8.0_73-b02 on Mac OS X 10.11.4
+ Intel(R) Core(TM) i7-4960HQ CPU @ 2.60GHz
+ Aggregate w string key: Best/Avg Time(ms) Rate(M/s)
Per Row(ns) Relative
+
-------------------------------------------------------------------------------------------
+ codegen = F 3307 / 3376 6.3
157.7 1.0X
+ codegen = T hashmap = F 2364 / 2471 8.9
112.7 1.4X
+ codegen = T hashmap = T 1740 / 1841 12.0
83.0 1.9X
+ */
+ }
+
+ ignore("aggregate with decimal key") {
+ val N = 20 << 20
+
+ val benchmark = new Benchmark("Aggregate w decimal key", N)
+ def f(): Unit = sqlContext.range(N).selectExpr("id", "cast(id & 65535
as decimal) as k")
+ .groupBy("k").count().collect()
+
+ benchmark.addCase(s"codegen = F") { iter =>
+ sqlContext.setConf("spark.sql.codegen.wholeStage", "false")
+ f()
+ }
+
+ benchmark.addCase(s"codegen = T hashmap = F") { iter =>
+ sqlContext.setConf("spark.sql.codegen.wholeStage", "true")
+ sqlContext.setConf("spark.sql.codegen.aggregate.map.enabled",
"false")
+ f()
+ }
+
+ benchmark.addCase(s"codegen = T hashmap = T") { iter =>
+ sqlContext.setConf("spark.sql.codegen.wholeStage", "true")
+ sqlContext.setConf("spark.sql.codegen.aggregate.map.enabled", "true")
+ f()
+ }
+
+ benchmark.run()
+
+ /*
+ Java HotSpot(TM) 64-Bit Server VM 1.8.0_73-b02 on Mac OS X 10.11.4
+ Intel(R) Core(TM) i7-4960HQ CPU @ 2.60GHz
+ Aggregate w decimal key: Best/Avg Time(ms) Rate(M/s)
Per Row(ns) Relative
+
-------------------------------------------------------------------------------------------
+ codegen = F 2756 / 2817 7.6
131.4 1.0X
+ codegen = T hashmap = F 1580 / 1647 13.3
75.4 1.7X
+ codegen = T hashmap = T 641 / 662 32.7
30.6 4.3X
+ */
+ }
+
+ ignore("aggregate with multiple key types") {
+ val N = 20 << 20
+
+ val benchmark = new Benchmark("Aggregate w multiple keys", N)
+ def f(): Unit = sqlContext.range(N)
+ .selectExpr(
+ "id",
+ "(id & 1023) as k1",
+ "cast(id & 1023 as string) as k2",
+ "cast(id & 1023 as int) as k3",
+ "cast(id & 1023 as double) as k4",
+ "cast(id & 1023 as float) as k5",
+ "id > 1023 as k6")
+ .groupBy("k1", "k2", "k3", "k4", "k5", "k6")
+ .sum()
+ .collect()
+
+ benchmark.addCase(s"codegen = F") { iter =>
+ sqlContext.setConf("spark.sql.codegen.wholeStage", "false")
+ f()
+ }
+
+ benchmark.addCase(s"codegen = T hashmap = F") { iter =>
+ sqlContext.setConf("spark.sql.codegen.wholeStage", "true")
+ sqlContext.setConf("spark.sql.codegen.aggregate.map.enabled",
"false")
+ f()
+ }
+
+ benchmark.addCase(s"codegen = T hashmap = T") { iter =>
+ sqlContext.setConf("spark.sql.codegen.wholeStage", "true")
+ sqlContext.setConf("spark.sql.codegen.aggregate.map.enabled", "true")
+ f()
+ }
+
+ benchmark.run()
+
+ /*
+ Java HotSpot(TM) 64-Bit Server VM 1.8.0_73-b02 on Mac OS X 10.11.4
+ Intel(R) Core(TM) i7-4960HQ CPU @ 2.60GHz
+ Aggregate w decimal key: Best/Avg Time(ms) Rate(M/s)
Per Row(ns) Relative
+
-------------------------------------------------------------------------------------------
+ codegen = F 6876 / 7216 3.1
327.8 1.0X
+ codegen = T hashmap = F 5297 / 5478 4.0
252.6 1.3X
+ codegen = T hashmap = T 5395 / 5668 3.9
257.2 1.3X
--- End diff --
Why we does not see improvements here? two many columns or depends on types?
---
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]
