spark-instrumented-optimizer/sql/catalyst
Takeshi Yamamuro cb0cddffe9 [SPARK-21870][SQL] Split aggregation code into small functions
## What changes were proposed in this pull request?
This pr proposed to split aggregation code into small functions in `HashAggregateExec`. In #18810, we got performance regression if JVMs didn't compile too long functions. I checked and I found the codegen of `HashAggregateExec` frequently goes over the limit when a query has too many aggregate functions (e.g., q66 in TPCDS).

The current master places all the generated aggregation code in a single function. In this pr, I modified the code to assign an individual function for each aggregate function (e.g., `SUM`
 and `AVG`). For example, in a query
`SELECT SUM(a), AVG(a) FROM VALUES(1) t(a)`, the proposed code defines two functions
for `SUM(a)` and `AVG(a)` as follows;

- generated  code with this pr (https://gist.github.com/maropu/812990012bc967a78364be0fa793f559):
```
/* 173 */   private void agg_doConsume_0(InternalRow inputadapter_row_0, long agg_expr_0_0, boolean agg_exprIsNull_0_0, double agg_expr_1_0, boolean agg_exprIsNull_1_0, long agg_expr_2_0, boolean agg_exprIsNull_2_0) throws java.io.IOException {
/* 174 */     // do aggregate
/* 175 */     // common sub-expressions
/* 176 */
/* 177 */     // evaluate aggregate functions and update aggregation buffers
/* 178 */     agg_doAggregate_sum_0(agg_exprIsNull_0_0, agg_expr_0_0);
/* 179 */     agg_doAggregate_avg_0(agg_expr_1_0, agg_exprIsNull_1_0, agg_exprIsNull_2_0, agg_expr_2_0);
/* 180 */
/* 181 */   }
...
/* 071 */   private void agg_doAggregate_avg_0(double agg_expr_1_0, boolean agg_exprIsNull_1_0, boolean agg_exprIsNull_2_0, long agg_expr_2_0) throws java.io.IOException {
/* 072 */     // do aggregate for avg
/* 073 */     // evaluate aggregate function
/* 074 */     boolean agg_isNull_19 = true;
/* 075 */     double agg_value_19 = -1.0;
...
/* 114 */   private void agg_doAggregate_sum_0(boolean agg_exprIsNull_0_0, long agg_expr_0_0) throws java.io.IOException {
/* 115 */     // do aggregate for sum
/* 116 */     // evaluate aggregate function
/* 117 */     agg_agg_isNull_11_0 = true;
/* 118 */     long agg_value_11 = -1L;
```

- generated code in the current master (https://gist.github.com/maropu/e9d772af2c98d8991a6a5f0af7841760)
```
/* 059 */   private void agg_doConsume_0(InternalRow localtablescan_row_0, int agg_expr_0_0) throws java.io.IOException {
/* 060 */     // do aggregate
/* 061 */     // common sub-expressions
/* 062 */     boolean agg_isNull_4 = false;
/* 063 */     long agg_value_4 = -1L;
/* 064 */     if (!false) {
/* 065 */       agg_value_4 = (long) agg_expr_0_0;
/* 066 */     }
/* 067 */     // evaluate aggregate function
/* 068 */     agg_agg_isNull_7_0 = true;
/* 069 */     long agg_value_7 = -1L;
/* 070 */     do {
/* 071 */       if (!agg_bufIsNull_0) {
/* 072 */         agg_agg_isNull_7_0 = false;
/* 073 */         agg_value_7 = agg_bufValue_0;
/* 074 */         continue;
/* 075 */       }
/* 076 */
/* 077 */       boolean agg_isNull_9 = false;
/* 078 */       long agg_value_9 = -1L;
/* 079 */       if (!false) {
/* 080 */         agg_value_9 = (long) 0;
/* 081 */       }
/* 082 */       if (!agg_isNull_9) {
/* 083 */         agg_agg_isNull_7_0 = false;
/* 084 */         agg_value_7 = agg_value_9;
/* 085 */         continue;
/* 086 */       }
/* 087 */
/* 088 */     } while (false);
/* 089 */
/* 090 */     long agg_value_6 = -1L;
/* 091 */
/* 092 */     agg_value_6 = agg_value_7 + agg_value_4;
/* 093 */     boolean agg_isNull_11 = true;
/* 094 */     double agg_value_11 = -1.0;
/* 095 */
/* 096 */     if (!agg_bufIsNull_1) {
/* 097 */       agg_agg_isNull_13_0 = true;
/* 098 */       double agg_value_13 = -1.0;
/* 099 */       do {
/* 100 */         boolean agg_isNull_14 = agg_isNull_4;
/* 101 */         double agg_value_14 = -1.0;
/* 102 */         if (!agg_isNull_4) {
/* 103 */           agg_value_14 = (double) agg_value_4;
/* 104 */         }
/* 105 */         if (!agg_isNull_14) {
/* 106 */           agg_agg_isNull_13_0 = false;
/* 107 */           agg_value_13 = agg_value_14;
/* 108 */           continue;
/* 109 */         }
/* 110 */
/* 111 */         boolean agg_isNull_15 = false;
/* 112 */         double agg_value_15 = -1.0;
/* 113 */         if (!false) {
/* 114 */           agg_value_15 = (double) 0;
/* 115 */         }
/* 116 */         if (!agg_isNull_15) {
/* 117 */           agg_agg_isNull_13_0 = false;
/* 118 */           agg_value_13 = agg_value_15;
/* 119 */           continue;
/* 120 */         }
/* 121 */
/* 122 */       } while (false);
/* 123 */
/* 124 */       agg_isNull_11 = false; // resultCode could change nullability.
/* 125 */
/* 126 */       agg_value_11 = agg_bufValue_1 + agg_value_13;
/* 127 */
/* 128 */     }
/* 129 */     boolean agg_isNull_17 = false;
/* 130 */     long agg_value_17 = -1L;
/* 131 */     if (!false && agg_isNull_4) {
/* 132 */       agg_isNull_17 = agg_bufIsNull_2;
/* 133 */       agg_value_17 = agg_bufValue_2;
/* 134 */     } else {
/* 135 */       boolean agg_isNull_20 = true;
/* 136 */       long agg_value_20 = -1L;
/* 137 */
/* 138 */       if (!agg_bufIsNull_2) {
/* 139 */         agg_isNull_20 = false; // resultCode could change nullability.
/* 140 */
/* 141 */         agg_value_20 = agg_bufValue_2 + 1L;
/* 142 */
/* 143 */       }
/* 144 */       agg_isNull_17 = agg_isNull_20;
/* 145 */       agg_value_17 = agg_value_20;
/* 146 */     }
/* 147 */     // update aggregation buffer
/* 148 */     agg_bufIsNull_0 = false;
/* 149 */     agg_bufValue_0 = agg_value_6;
/* 150 */
/* 151 */     agg_bufIsNull_1 = agg_isNull_11;
/* 152 */     agg_bufValue_1 = agg_value_11;
/* 153 */
/* 154 */     agg_bufIsNull_2 = agg_isNull_17;
/* 155 */     agg_bufValue_2 = agg_value_17;
/* 156 */
/* 157 */   }
```
You can check the previous discussion in https://github.com/apache/spark/pull/19082

## How was this patch tested?
Existing tests

Closes #20965 from maropu/SPARK-21870-2.

Authored-by: Takeshi Yamamuro <yamamuro@apache.org>
Signed-off-by: Wenchen Fan <wenchen@databricks.com>
2019-09-06 11:45:14 +08:00
..
benchmarks [SPARK-25657][SQL][TEST] Refactor HashBenchmark to use main method 2018-10-07 09:49:37 -07:00
src [SPARK-21870][SQL] Split aggregation code into small functions 2019-09-06 11:45:14 +08:00
pom.xml [SPARK-27521][SQL] Move data source v2 to catalyst module 2019-06-05 09:55:55 -07:00