================================================================================================
Dataset Benchmark
================================================================================================

OpenJDK 64-Bit Server VM 11.0.10+9-LTS on Linux 5.4.0-1043-azure
Intel(R) Xeon(R) Platinum 8171M CPU @ 2.60GHz
back-to-back map long:                    Best Time(ms)   Avg Time(ms)   Stdev(ms)    Rate(M/s)   Per Row(ns)   Relative
------------------------------------------------------------------------------------------------------------------------
RDD                                               13660          13836         249          7.3         136.6       1.0X
DataFrame                                          2103           2125          30         47.5          21.0       6.5X
Dataset                                            2899           2910          16         34.5          29.0       4.7X

OpenJDK 64-Bit Server VM 11.0.10+9-LTS on Linux 5.4.0-1043-azure
Intel(R) Xeon(R) Platinum 8171M CPU @ 2.60GHz
back-to-back map:                         Best Time(ms)   Avg Time(ms)   Stdev(ms)    Rate(M/s)   Per Row(ns)   Relative
------------------------------------------------------------------------------------------------------------------------
RDD                                               14939          14940           2          6.7         149.4       1.0X
DataFrame                                          5377           5529         216         18.6          53.8       2.8X
Dataset                                           15861          15923          88          6.3         158.6       0.9X

OpenJDK 64-Bit Server VM 11.0.10+9-LTS on Linux 5.4.0-1043-azure
Intel(R) Xeon(R) Platinum 8171M CPU @ 2.60GHz
back-to-back filter Long:                 Best Time(ms)   Avg Time(ms)   Stdev(ms)    Rate(M/s)   Per Row(ns)   Relative
------------------------------------------------------------------------------------------------------------------------
RDD                                                3803           3842          56         26.3          38.0       1.0X
DataFrame                                          1359           1369          14         73.6          13.6       2.8X
Dataset                                            3667           3668           1         27.3          36.7       1.0X

OpenJDK 64-Bit Server VM 11.0.10+9-LTS on Linux 5.4.0-1043-azure
Intel(R) Xeon(R) Platinum 8171M CPU @ 2.60GHz
back-to-back filter:                      Best Time(ms)   Avg Time(ms)   Stdev(ms)    Rate(M/s)   Per Row(ns)   Relative
------------------------------------------------------------------------------------------------------------------------
RDD                                                4572           4595          33         21.9          45.7       1.0X
DataFrame                                           212            261          45        471.6           2.1      21.6X
Dataset                                            5629           5776         208         17.8          56.3       0.8X

OpenJDK 64-Bit Server VM 11.0.10+9-LTS on Linux 5.4.0-1043-azure
Intel(R) Xeon(R) Platinum 8171M CPU @ 2.60GHz
aggregate:                                Best Time(ms)   Avg Time(ms)   Stdev(ms)    Rate(M/s)   Per Row(ns)   Relative
------------------------------------------------------------------------------------------------------------------------
RDD sum                                            3528           3563          50         28.3          35.3       1.0X
DataFrame sum                                        81            111          23       1240.3           0.8      43.8X
Dataset sum using Aggregator                       5140           5164          34         19.5          51.4       0.7X
Dataset complex Aggregator                         9815           9921         150         10.2          98.1       0.4X


