spark git commit: [SPARK-10100] [SQL] Eliminate hash table lookup if there is no grouping key in aggregation.

2015-08-20 Thread yhuai
Repository: spark Updated Branches: refs/heads/branch-1.5 675e22494 - 5be517584 [SPARK-10100] [SQL] Eliminate hash table lookup if there is no grouping key in aggregation. This improves performance by ~ 20 - 30% in one of my local test and should fix the performance regression from 1.4 to

spark git commit: [SPARK-10100] [SQL] Eliminate hash table lookup if there is no grouping key in aggregation.

2015-08-20 Thread yhuai
Repository: spark Updated Branches: refs/heads/master 43e013542 - b4f4e91c3 [SPARK-10100] [SQL] Eliminate hash table lookup if there is no grouping key in aggregation. This improves performance by ~ 20 - 30% in one of my local test and should fix the performance regression from 1.4 to 1.5