| ================================================================================================ |
| aggregate without grouping |
| ================================================================================================ |
| |
| OpenJDK 64-Bit Server VM 17.0.16+8-LTS on Linux 6.11.0-1018-azure |
| AMD EPYC 7763 64-Core Processor |
| agg w/o group: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative |
| ------------------------------------------------------------------------------------------------------------------------ |
| agg w/o group wholestage off 39333 39682 494 53.3 18.8 1.0X |
| agg w/o group wholestage on 3383 3389 5 620.0 1.6 11.6X |
| |
| |
| ================================================================================================ |
| stat functions |
| ================================================================================================ |
| |
| OpenJDK 64-Bit Server VM 17.0.16+8-LTS on Linux 6.11.0-1018-azure |
| AMD EPYC 7763 64-Core Processor |
| stddev: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative |
| ------------------------------------------------------------------------------------------------------------------------ |
| stddev wholestage off 4549 4569 27 23.0 43.4 1.0X |
| stddev wholestage on 982 993 9 106.7 9.4 4.6X |
| |
| OpenJDK 64-Bit Server VM 17.0.16+8-LTS on Linux 6.11.0-1018-azure |
| AMD EPYC 7763 64-Core Processor |
| kurtosis: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative |
| ------------------------------------------------------------------------------------------------------------------------ |
| kurtosis wholestage off 20761 20856 134 5.1 198.0 1.0X |
| kurtosis wholestage on 1003 1009 6 104.5 9.6 20.7X |
| |
| |
| ================================================================================================ |
| aggregate with linear keys |
| ================================================================================================ |
| |
| OpenJDK 64-Bit Server VM 17.0.16+8-LTS on Linux 6.11.0-1018-azure |
| AMD EPYC 7763 64-Core Processor |
| Aggregate w keys: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative |
| ------------------------------------------------------------------------------------------------------------------------ |
| codegen = F 6934 6980 65 12.1 82.7 1.0X |
| codegen = T, hashmap = F 4343 4375 50 19.3 51.8 1.6X |
| codegen = T, row-based hashmap = T 1224 1258 29 68.5 14.6 5.7X |
| codegen = T, vectorized hashmap = T 855 868 13 98.1 10.2 8.1X |
| |
| |
| ================================================================================================ |
| aggregate with randomized keys |
| ================================================================================================ |
| |
| OpenJDK 64-Bit Server VM 17.0.16+8-LTS on Linux 6.11.0-1018-azure |
| AMD EPYC 7763 64-Core Processor |
| Aggregate w keys: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative |
| ------------------------------------------------------------------------------------------------------------------------ |
| codegen = F 7847 7849 4 10.7 93.5 1.0X |
| codegen = T, hashmap = F 5003 5021 22 16.8 59.6 1.6X |
| codegen = T, row-based hashmap = T 1717 1725 5 48.8 20.5 4.6X |
| codegen = T, vectorized hashmap = T 1042 1065 25 80.5 12.4 7.5X |
| |
| |
| ================================================================================================ |
| aggregate with string key |
| ================================================================================================ |
| |
| OpenJDK 64-Bit Server VM 17.0.16+8-LTS on Linux 6.11.0-1018-azure |
| AMD EPYC 7763 64-Core Processor |
| Aggregate w string key: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative |
| ------------------------------------------------------------------------------------------------------------------------ |
| codegen = F 2548 2549 1 8.2 121.5 1.0X |
| codegen = T, hashmap = F 1541 1551 13 13.6 73.5 1.7X |
| codegen = T, row-based hashmap = T 1025 1028 2 20.5 48.9 2.5X |
| codegen = T, vectorized hashmap = T 825 836 9 25.4 39.3 3.1X |
| |
| |
| ================================================================================================ |
| aggregate with decimal key |
| ================================================================================================ |
| |
| OpenJDK 64-Bit Server VM 17.0.16+8-LTS on Linux 6.11.0-1018-azure |
| AMD EPYC 7763 64-Core Processor |
| Aggregate w decimal key: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative |
| ------------------------------------------------------------------------------------------------------------------------ |
| codegen = F 2099 2152 75 10.0 100.1 1.0X |
| codegen = T, hashmap = F 1347 1396 69 15.6 64.2 1.6X |
| codegen = T, row-based hashmap = T 439 448 10 47.7 20.9 4.8X |
| codegen = T, vectorized hashmap = T 325 330 5 64.6 15.5 6.5X |
| |
| |
| ================================================================================================ |
| aggregate with multiple key types |
| ================================================================================================ |
| |
| OpenJDK 64-Bit Server VM 17.0.16+8-LTS on Linux 6.11.0-1018-azure |
| AMD EPYC 7763 64-Core Processor |
| Aggregate w multiple keys: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative |
| ------------------------------------------------------------------------------------------------------------------------ |
| codegen = F 4063 4097 49 5.2 193.7 1.0X |
| codegen = T, hashmap = F 2410 2461 71 8.7 114.9 1.7X |
| codegen = T, row-based hashmap = T 1879 1962 118 11.2 89.6 2.2X |
| codegen = T, vectorized hashmap = T 1642 1660 26 12.8 78.3 2.5X |
| |
| |
| ================================================================================================ |
| max function bytecode size of wholestagecodegen |
| ================================================================================================ |
| |
| OpenJDK 64-Bit Server VM 17.0.16+8-LTS on Linux 6.11.0-1018-azure |
| AMD EPYC 7763 64-Core Processor |
| max function bytecode size: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative |
| ------------------------------------------------------------------------------------------------------------------------ |
| codegen = F 399 425 24 1.6 609.5 1.0X |
| codegen = T, hugeMethodLimit = 10000 147 165 14 4.5 224.4 2.7X |
| codegen = T, hugeMethodLimit = 1500 144 153 11 4.6 219.0 2.8X |
| |
| |
| ================================================================================================ |
| cube |
| ================================================================================================ |
| |
| OpenJDK 64-Bit Server VM 17.0.16+8-LTS on Linux 6.11.0-1018-azure |
| AMD EPYC 7763 64-Core Processor |
| cube: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative |
| ------------------------------------------------------------------------------------------------------------------------ |
| cube wholestage off 2112 2130 26 2.5 402.8 1.0X |
| cube wholestage on 1177 1194 11 4.5 224.5 1.8X |
| |
| |
| ================================================================================================ |
| hash and BytesToBytesMap |
| ================================================================================================ |
| |
| OpenJDK 64-Bit Server VM 17.0.16+8-LTS on Linux 6.11.0-1018-azure |
| AMD EPYC 7763 64-Core Processor |
| BytesToBytesMap: Best Time(ms) Avg Time(ms) Stdev(ms) Rate(M/s) Per Row(ns) Relative |
| ------------------------------------------------------------------------------------------------------------------------ |
| UnsafeRowhash 204 208 2 102.7 9.7 1.0X |
| murmur3 hash 68 70 0 306.5 3.3 3.0X |
| fast hash 61 71 3 341.1 2.9 3.3X |
| arrayEqual 150 151 1 139.4 7.2 1.4X |
| Java HashMap (Long) 66 71 4 317.3 3.2 3.1X |
| Java HashMap (two ints) 90 94 2 233.6 4.3 2.3X |
| Java HashMap (UnsafeRow) 580 582 2 36.2 27.6 0.4X |
| LongToUnsafeRowMap (opt=false) 349 350 1 60.1 16.6 0.6X |
| LongToUnsafeRowMap (opt=true) 80 82 1 263.3 3.8 2.6X |
| BytesToBytesMap (off Heap) 630 634 4 33.3 30.0 0.3X |
| BytesToBytesMap (on Heap) 615 619 4 34.1 29.3 0.3X |
| Aggregate HashMap 31 31 0 684.6 1.5 6.7X |
| |
| |