spark-instrumented-optimizer/sql/catalyst
Wenchen Fan c5f745ede0 [SPARK-13072] [SQL] simplify and improve murmur3 hash expression codegen
simplify(remove several unnecessary local variables) the generated code of hash expression, and avoid null check if possible.

generated code comparison for `hash(int, double, string, array<string>)`:
**before:**
```
  public UnsafeRow apply(InternalRow i) {
    /* hash(input[0, int],input[1, double],input[2, string],input[3, array<int>],42) */
    int value1 = 42;
    /* input[0, int] */
    int value3 = i.getInt(0);
    if (!false) {
      value1 = org.apache.spark.unsafe.hash.Murmur3_x86_32.hashInt(value3, value1);
    }
    /* input[1, double] */
    double value5 = i.getDouble(1);
    if (!false) {
      value1 = org.apache.spark.unsafe.hash.Murmur3_x86_32.hashLong(Double.doubleToLongBits(value5), value1);
    }
    /* input[2, string] */
    boolean isNull6 = i.isNullAt(2);
    UTF8String value7 = isNull6 ? null : (i.getUTF8String(2));
    if (!isNull6) {
      value1 = org.apache.spark.unsafe.hash.Murmur3_x86_32.hashUnsafeBytes(value7.getBaseObject(), value7.getBaseOffset(), value7.numBytes(), value1);
    }
    /* input[3, array<int>] */
    boolean isNull8 = i.isNullAt(3);
    ArrayData value9 = isNull8 ? null : (i.getArray(3));
    if (!isNull8) {
      int result10 = value1;
      for (int index11 = 0; index11 < value9.numElements(); index11++) {
        if (!value9.isNullAt(index11)) {
          final int element12 = value9.getInt(index11);
          result10 = org.apache.spark.unsafe.hash.Murmur3_x86_32.hashInt(element12, result10);
        }
      }
      value1 = result10;
    }
  }
```
**after:**
```
  public UnsafeRow apply(InternalRow i) {
    /* hash(input[0, int],input[1, double],input[2, string],input[3, array<int>],42) */
    int value1 = 42;
    /* input[0, int] */
    int value3 = i.getInt(0);
    value1 = org.apache.spark.unsafe.hash.Murmur3_x86_32.hashInt(value3, value1);
    /* input[1, double] */
    double value5 = i.getDouble(1);
    value1 = org.apache.spark.unsafe.hash.Murmur3_x86_32.hashLong(Double.doubleToLongBits(value5), value1);
    /* input[2, string] */
    boolean isNull6 = i.isNullAt(2);
    UTF8String value7 = isNull6 ? null : (i.getUTF8String(2));

    if (!isNull6) {
      value1 = org.apache.spark.unsafe.hash.Murmur3_x86_32.hashUnsafeBytes(value7.getBaseObject(), value7.getBaseOffset(), value7.numBytes(), value1);
    }

    /* input[3, array<int>] */
    boolean isNull8 = i.isNullAt(3);
    ArrayData value9 = isNull8 ? null : (i.getArray(3));
    if (!isNull8) {
      for (int index10 = 0; index10 < value9.numElements(); index10++) {
        final int element11 = value9.getInt(index10);
        value1 = org.apache.spark.unsafe.hash.Murmur3_x86_32.hashInt(element11, value1);
      }
    }

    rowWriter14.write(0, value1);
    return result12;
  }
```

Author: Wenchen Fan <wenchen@databricks.com>

Closes #10974 from cloud-fan/codegen.
2016-01-29 10:24:23 -08:00
..
src [SPARK-13072] [SQL] simplify and improve murmur3 hash expression codegen 2016-01-29 10:24:23 -08:00
pom.xml [SPARK-12573][SPARK-12574][SQL] Move SQL Parser from Hive to Catalyst 2016-01-06 11:16:53 -08:00