adriangbot commented on PR #27559: URL: https://github.com/apache/datafusion/pull/27559#issuecomment-6985873324
🤖 Benchmark completed (GKE) | [trigger](https://github.com/apache/datafusion/pull/27559#issuecomment-6984436626) **Instance:** `c4-highmem-16` (12 vCPU / 65 GiB) Comparing hash-nulls-blend (257331c88c1457e2d93b847e58978b92ddd5b05e) to 0d231e9e90c45022f9510c684f1e41cdec65a814 [diff](https://github.com/apache/datafusion/compare/0d231e9e90c45022f9510c684f1e41cdec65a814..257331c88c1457e2d93b847e58978b92ddd5b05e) <details><summary>Run configuration</summary> ```yaml run benchmark with_hashes env: RUSTFLAGS: "-C llvm-args=-align-all-functions=6 -C llvm-args=-align-all-nofallthru-blocks=6" baseline: ref: "0d231e9e90c45022f9510c684f1e41cdec65a814" resources: arch: "amd64" ``` </details> <details><summary>CPU Details (lscpu)</summary> ``` Architecture: x86_64 CPU op-mode(s): 32-bit, 64-bit Address sizes: 52 bits physical, 57 bits virtual Byte Order: Little Endian CPU(s): 16 On-line CPU(s) list: 0-15 Vendor ID: GenuineIntel Model name: INTEL(R) XEON(R) PLATINUM 8581C CPU @ 2.30GHz CPU family: 6 Model: 207 Thread(s) per core: 2 Core(s) per socket: 8 Socket(s): 1 Stepping: 2 BogoMIPS: 4600.00 Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ss ht syscall nx pdpe1gb rdtscp lm constant_tsc rep_good nopl xtopology nonstop_tsc cpuid tsc_known_freq pni pclmulqdq monitor ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch ssbd ibrs ibpb stibp ibrs_enhanced fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms invpcid rtm avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves avx_vnni avx512_bf16 wbnoinvd arat avx512vbmi umip avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq rdpid cldemote movdiri movdir64b fsrm md_clear serialize tsxldtrk amx_bf16 avx512_fp16 amx_tile amx_int8 arch_capabilities Hypervisor vendor: KVM Virtualization type: full L1d cache: 384 KiB (8 instances) L1i cache: 256 KiB (8 instances) L2 cache: 16 MiB (8 instances) L3 cache: 260 MiB (1 instance) NUMA node(s): 1 NUMA node0 CPU(s): 0-15 Vulnerability Gather data sampling: Not affected Vulnerability Indirect target selection: Not affected Vulnerability Itlb multihit: Not affected Vulnerability L1tf: Not affected Vulnerability Mds: Not affected Vulnerability Meltdown: Not affected Vulnerability Mmio stale data: Not affected Vulnerability Reg file data sampling: Not affected Vulnerability Retbleed: Not affected Vulnerability Spec rstack overflow: Not affected Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S Vulnerability Srbds: Not affected Vulnerability Tsa: Not affected Vulnerability Tsx async abort: Not affected Vulnerability Vmscape: Not affected ``` </details> <details><summary>Details</summary> <p> ``` group HEAD hash-nulls-blend ----- ---- ---------------- decimal128: multiple, 25% nulls 1.00 20.4±0.56µs ? ?/sec 1.65 33.6±0.36µs ? ?/sec decimal128: multiple, 40% nulls 1.00 17.2±0.58µs ? ?/sec 1.16 19.9±0.19µs ? ?/sec decimal128: multiple, 50% nulls 1.20 14.7±0.15µs ? ?/sec 1.00 12.3±0.18µs ? ?/sec decimal128: multiple, 75% nulls 1.46 10.3±0.54µs ? ?/sec 1.00 7.1±0.29µs ? ?/sec decimal128: multiple, 99% nulls 1.00 1427.5±64.54ns ? ?/sec 1.24 1764.3±122.75ns ? ?/sec decimal128: multiple, no nulls 1.03 12.4±0.63µs ? ?/sec 1.00 12.0±0.17µs ? ?/sec decimal128: multiple, nulls 1.00 24.5±0.42µs ? ?/sec 1.38 33.8±0.65µs ? ?/sec decimal128: single, 25% nulls 1.00 6.5±0.16µs ? ?/sec 1.74 11.3±0.13µs ? ?/sec decimal128: single, 40% nulls 1.00 5.7±0.08µs ? ?/sec 1.26 7.1±0.06µs ? ?/sec decimal128: single, 50% nulls 1.11 4.9±0.13µs ? ?/sec 1.00 4.4±0.04µs ? ?/sec decimal128: single, 75% nulls 1.17 3.2±0.23µs ? ?/sec 1.00 2.8±0.07µs ? ?/sec decimal128: single, 99% nulls 1.00 1212.5±59.52ns ? ?/sec 1.06 1280.0±82.59ns ? ?/sec decimal128: single, no nulls 1.00 4.6±0.10µs ? ?/sec 1.00 4.6±0.06µs ? ?/sec decimal128: single, nulls 1.00 7.4±0.09µs ? ?/sec 1.54 11.4±0.17µs ? ?/sec dense_union: multiple, no nulls 1.01 48.8±0.93µs ? ?/sec 1.00 48.2±1.82µs ? ?/sec dense_union: single, no nulls 1.01 17.0±0.31µs ? ?/sec 1.00 16.9±0.45µs ? ?/sec dense_union_sliced: 1/10 of 81920 rows 1.14 26.0±0.52µs ? ?/sec 1.00 22.8±1.00µs ? ?/sec dense_union_sliced: 1/2 of 16384 rows 1.03 23.2±1.50µs ? ?/sec 1.00 22.4±0.98µs ? ?/sec dense_union_sliced: 1/5 of 40960 rows 1.05 23.6±1.44µs ? ?/sec 1.00 22.4±0.67µs ? ?/sec dictionary_sliced: 1/128 of 1048576 values 1.01 97.9±3.96µs ? ?/sec 1.00 96.7±3.58µs ? ?/sec dictionary_sliced: 1/8 of 65536 values 1.01 97.5±4.30µs ? ?/sec 1.00 96.1±3.54µs ? ?/sec dictionary_utf8_int32: multiple, 50% nulls 1.02 13.4±0.62µs ? ?/sec 1.00 13.2±0.31µs ? ?/sec dictionary_utf8_int32: multiple, 97% nulls 1.00 3.6±0.07µs ? ?/sec 1.02 3.7±0.11µs ? ?/sec dictionary_utf8_int32: multiple, no nulls 1.00 12.1±0.35µs ? ?/sec 1.02 12.4±0.31µs ? ?/sec dictionary_utf8_int32: multiple, nulls 1.00 22.4±1.89µs ? ?/sec 1.01 22.5±0.29µs ? ?/sec dictionary_utf8_int32: single, 50% nulls 1.00 4.2±0.19µs ? ?/sec 1.02 4.3±0.10µs ? ?/sec dictionary_utf8_int32: single, 97% nulls 1.00 1799.1±55.10ns ? ?/sec 1.02 1828.7±28.13ns ? ?/sec dictionary_utf8_int32: single, no nulls 1.00 3.9±0.04µs ? ?/sec 1.00 3.9±0.06µs ? ?/sec dictionary_utf8_int32: single, nulls 1.00 6.9±0.13µs ? ?/sec 1.00 6.9±0.22µs ? ?/sec fixed_size_list_array: multiple, no nulls 1.09 129.8±2.28µs ? ?/sec 1.00 119.1±8.89µs ? ?/sec fixed_size_list_array: multiple, nulls 1.15 140.7±4.18µs ? ?/sec 1.00 122.1±3.54µs ? ?/sec fixed_size_list_array: single, no nulls 1.08 44.6±1.00µs ? ?/sec 1.00 41.3±2.32µs ? ?/sec fixed_size_list_array: single, nulls 1.15 48.7±0.81µs ? ?/sec 1.00 42.4±1.95µs ? ?/sec int32: multiple, 100% nulls 1.19 1255.2±11.63ns ? ?/sec 1.00 1055.8±26.00ns ? ?/sec int32: multiple, 25% nulls 1.00 16.7±0.29µs ? ?/sec 2.14 35.8±1.33µs ? ?/sec int32: multiple, 40% nulls 1.00 14.0±0.13µs ? ?/sec 1.41 19.8±1.02µs ? ?/sec int32: multiple, 50% nulls 1.18 11.9±0.17µs ? ?/sec 1.00 10.1±0.20µs ? ?/sec int32: multiple, 99% nulls 1.00 1189.7±57.71ns ? ?/sec 1.36 1614.2±34.37ns ? ?/sec int32: multiple, no nulls 1.00 13.8±0.14µs ? ?/sec 1.05 14.4±0.83µs ? ?/sec int32: multiple, nulls 1.00 19.4±0.22µs ? ?/sec 1.86 36.1±1.18µs ? ?/sec int32: single, 100% nulls 1.02 1083.6±51.39ns ? ?/sec 1.00 1064.1±48.27ns ? ?/sec int32: single, 25% nulls 1.00 5.3±0.05µs ? ?/sec 2.19 11.6±0.78µs ? ?/sec int32: single, 40% nulls 1.00 4.6±0.05µs ? ?/sec 1.49 6.9±0.25µs ? ?/sec int32: single, 50% nulls 1.00 3.9±0.04µs ? ?/sec 1.04 4.1±0.23µs ? ?/sec int32: single, 99% nulls 1.00 1023.4±10.84ns ? ?/sec 1.20 1229.4±64.16ns ? ?/sec int32: single, no nulls 1.00 4.2±0.05µs ? ?/sec 1.09 4.6±0.19µs ? ?/sec int32: single, nulls 1.00 6.1±0.08µs ? ?/sec 1.94 11.8±0.89µs ? ?/sec int64 (offset 5): multiple, nulls 1.00 23.4±0.24µs ? ?/sec 1.67 39.1±1.85µs ? ?/sec int64 (offset 5): single, nulls 1.00 7.1±0.25µs ? ?/sec 1.75 12.5±0.83µs ? ?/sec int64: multiple, 1% nulls 1.00 19.4±0.48µs ? ?/sec 2.07 40.3±1.87µs ? ?/sec int64: multiple, 10% nulls 1.00 19.2±0.56µs ? ?/sec 1.94 37.3±1.73µs ? ?/sec int64: multiple, 100% nulls 1.12 1244.1±17.29ns ? ?/sec 1.00 1110.0±58.65ns ? ?/sec int64: multiple, 25% nulls 1.00 16.8±0.27µs ? ?/sec 2.19 36.7±1.90µs ? ?/sec int64: multiple, 30% nulls 1.00 15.8±0.25µs ? ?/sec 2.28 35.9±2.35µs ? ?/sec int64: multiple, 35% nulls 1.00 14.9±0.17µs ? ?/sec 2.14 32.0±1.42µs ? ?/sec int64: multiple, 40% nulls 1.00 14.4±0.87µs ? ?/sec 1.63 23.5±0.40µs ? ?/sec int64: multiple, 45% nulls 1.00 13.3±0.33µs ? ?/sec 1.18 15.6±0.56µs ? ?/sec int64: multiple, 50% nulls 1.00 12.0±0.06µs ? ?/sec 1.09 13.1±0.36µs ? ?/sec int64: multiple, 50% nulls in 64-row blocks 1.00 12.8±0.31µs ? ?/sec 1.60 20.5±1.06µs ? ?/sec int64: multiple, 75% nulls 1.00 6.3±0.19µs ? ?/sec 1.16 7.3±0.11µs ? ?/sec int64: multiple, 90% nulls 1.00 3.4±0.05µs ? ?/sec 1.29 4.3±0.09µs ? ?/sec int64: multiple, 90% nulls in 64-row blocks 1.00 3.4±0.12µs ? ?/sec 1.61 5.4±0.41µs ? ?/sec int64: multiple, 99% nulls 1.00 1162.1±16.25ns ? ?/sec 1.56 1818.0±124.02ns ? ?/sec int64: multiple, no nulls 1.00 13.7±0.22µs ? ?/sec 1.10 15.1±0.68µs ? ?/sec int64: multiple, nulls 1.00 19.5±0.46µs ? ?/sec 1.91 37.3±1.62µs ? ?/sec int64: single, 1% nulls 1.00 6.1±0.15µs ? ?/sec 2.13 12.9±0.74µs ? ?/sec int64: single, 10% nulls 1.00 6.1±0.26µs ? ?/sec 2.01 12.2±0.89µs ? ?/sec int64: single, 100% nulls 1.00 1065.5±9.54ns ? ?/sec 1.08 1154.7±67.42ns ? ?/sec int64: single, 25% nulls 1.00 5.4±0.22µs ? ?/sec 2.18 11.8±0.78µs ? ?/sec int64: single, 30% nulls 1.00 5.1±0.10µs ? ?/sec 2.20 11.2±0.73µs ? ?/sec int64: single, 35% nulls 1.00 4.8±0.04µs ? ?/sec 2.14 10.3±0.61µs ? ?/sec int64: single, 40% nulls 1.00 4.7±0.07µs ? ?/sec 1.76 8.2±0.39µs ? ?/sec int64: single, 45% nulls 1.00 4.5±0.28µs ? ?/sec 1.28 5.7±0.09µs ? ?/sec int64: single, 50% nulls 1.00 4.1±0.16µs ? ?/sec 1.21 4.9±0.20µs ? ?/sec int64: single, 50% nulls in 64-row blocks 1.00 4.3±0.15µs ? ?/sec 1.53 6.6±0.42µs ? ?/sec int64: single, 75% nulls 1.00 2.5±0.03µs ? ?/sec 1.25 3.1±0.05µs ? ?/sec int64: single, 90% nulls 1.00 1827.6±22.31ns ? ?/sec 1.24 2.3±0.02µs ? ?/sec int64: single, 90% nulls in 64-row blocks 1.00 1743.3±50.45ns ? ?/sec 1.37 2.4±0.11µs ? ?/sec int64: single, 99% nulls 1.00 1027.0±19.88ns ? ?/sec 1.33 1368.5±66.13ns ? ?/sec int64: single, no nulls 1.00 4.9±0.06µs ? ?/sec 1.14 5.6±0.23µs ? ?/sec int64: single, nulls 1.00 6.1±0.21µs ? ?/sec 2.06 12.6±0.96µs ? ?/sec large_utf8: multiple, no nulls 1.00 177.2±2.66µs ? ?/sec 1.00 177.7±4.72µs ? ?/sec large_utf8: multiple, nulls 1.01 197.9±4.15µs ? ?/sec 1.00 196.3±2.29µs ? ?/sec large_utf8: single, no nulls 1.01 47.2±0.82µs ? ?/sec 1.00 46.6±1.31µs ? ?/sec large_utf8: single, nulls 1.00 39.9±0.58µs ? ?/sec 1.00 40.1±0.57µs ? ?/sec list_array: multiple, no nulls 1.00 180.8±8.11µs ? ?/sec 1.00 181.7±6.41µs ? ?/sec list_array: multiple, nulls 1.00 218.2±5.53µs ? ?/sec 1.01 221.1±3.76µs ? ?/sec list_array: single, no nulls 1.05 63.8±1.15µs ? ?/sec 1.00 61.0±1.45µs ? ?/sec list_array: single, nulls 1.00 74.4±1.29µs ? ?/sec 1.00 74.2±3.25µs ? ?/sec list_array_sliced: 1/10 of 81920 rows 1.03 60.9±2.91µs ? ?/sec 1.00 58.9±2.53µs ? ?/sec list_array_sliced: 1/2 of 16384 rows 1.10 57.0±2.87µs ? ?/sec 1.00 52.0±1.96µs ? ?/sec list_array_sliced: 1/5 of 40960 rows 1.18 62.6±2.67µs ? ?/sec 1.00 53.2±2.19µs ? ?/sec list_view_array: multiple, no nulls 1.14 170.7±5.32µs ? ?/sec 1.00 149.7±6.37µs ? ?/sec list_view_array: multiple, nulls 1.06 188.6±4.20µs ? ?/sec 1.00 178.7±8.09µs ? ?/sec list_view_array: single, no nulls 1.17 58.3±0.83µs ? ?/sec 1.00 50.0±1.94µs ? ?/sec list_view_array: single, nulls 1.12 63.3±0.76µs ? ?/sec 1.00 56.3±3.28µs ? ?/sec map_array: multiple, no nulls 1.00 247.7±7.35µs ? ?/sec 1.02 253.0±6.52µs ? ?/sec map_array: multiple, nulls 1.00 263.1±12.17µs ? ?/sec 1.02 267.6±3.34µs ? ?/sec map_array: single, no nulls 1.00 83.0±2.92µs ? ?/sec 1.01 83.5±2.24µs ? ?/sec map_array: single, nulls 1.00 88.1±2.30µs ? ?/sec 1.01 89.3±2.18µs ? ?/sec map_array_sliced: 1/10 of 81920 rows 1.07 82.6±1.83µs ? ?/sec 1.00 77.1±3.81µs ? ?/sec map_array_sliced: 1/2 of 16384 rows 1.02 75.0±5.08µs ? ?/sec 1.00 73.7±3.67µs ? ?/sec map_array_sliced: 1/5 of 40960 rows 1.09 79.6±3.29µs ? ?/sec 1.00 73.2±2.74µs ? ?/sec mixed: 3 columns (int64, utf8, utf8_view) 1.00 87.9±3.90µs ? ?/sec 1.00 88.1±4.65µs ? ?/sec null: multiple, no nulls 1.14 5.1±0.13µs ? ?/sec 1.00 4.5±0.20µs ? ?/sec null: single, no nulls 1.10 2.6±0.04µs ? ?/sec 1.00 2.4±0.10µs ? ?/sec run_array_int32: multiple, no nulls 1.10 7.3±0.28µs ? ?/sec 1.00 6.7±0.38µs ? ?/sec run_array_int32: multiple, nulls 1.00 8.9±0.21µs ? ?/sec 1.00 8.9±0.49µs ? ?/sec run_array_int32: single, no nulls 1.00 3.2±0.12µs ? ?/sec 1.01 3.3±0.11µs ? ?/sec run_array_int32: single, nulls 1.06 3.9±0.04µs ? ?/sec 1.00 3.7±0.19µs ? ?/sec sparse_union (2 types): multiple, no nulls 1.02 115.3±2.55µs ? ?/sec 1.00 113.0±3.42µs ? ?/sec sparse_union (2 types): single, no nulls 1.03 40.0±0.70µs ? ?/sec 1.00 39.0±0.79µs ? ?/sec sparse_union (utf8): multiple, no nulls 1.01 219.7±6.15µs ? ?/sec 1.00 218.5±14.13µs ? ?/sec sparse_union (utf8): single, no nulls 1.04 73.2±1.33µs ? ?/sec 1.00 70.5±2.77µs ? ?/sec sparse_union: multiple, no nulls 1.00 99.1±3.11µs ? ?/sec 1.01 100.1±1.76µs ? ?/sec sparse_union: single, no nulls 1.01 34.3±0.67µs ? ?/sec 1.00 33.9±0.95µs ? ?/sec sparse_union_sliced: 1/10 of 81920 rows 1.14 34.7±1.05µs ? ?/sec 1.00 30.4±1.47µs ? ?/sec sparse_union_sliced: 1/2 of 16384 rows 1.01 30.0±1.56µs ? ?/sec 1.00 29.7±1.04µs ? ?/sec sparse_union_sliced: 1/5 of 40960 rows 1.05 31.1±1.76µs ? ?/sec 1.00 29.7±1.26µs ? ?/sec struct_array: multiple, no nulls 1.00 172.0±5.71µs ? ?/sec 1.00 171.3±10.48µs ? ?/sec struct_array: multiple, nulls 1.00 183.7±5.83µs ? ?/sec 1.01 184.7±7.21µs ? ?/sec struct_array: single, no nulls 1.01 59.4±1.10µs ? ?/sec 1.00 58.7±2.47µs ? ?/sec struct_array: single, nulls 1.01 62.7±1.81µs ? ?/sec 1.00 62.2±2.21µs ? ?/sec utf8: multiple, no nulls 1.09 176.3±4.50µs ? ?/sec 1.00 161.4±6.34µs ? ?/sec utf8: multiple, nulls 1.03 203.5±3.47µs ? ?/sec 1.00 198.0±6.38µs ? ?/sec utf8: single, no nulls 1.11 57.2±1.05µs ? ?/sec 1.00 51.6±3.24µs ? ?/sec utf8: single, nulls 1.02 40.9±0.78µs ? ?/sec 1.00 40.3±1.26µs ? ?/sec utf8_view (small): multiple, no nulls 1.01 16.8±0.30µs ? ?/sec 1.00 16.6±0.28µs ? ?/sec utf8_view (small): multiple, nulls 1.00 31.1±0.42µs ? ?/sec 1.01 31.4±0.55µs ? ?/sec utf8_view (small): single, no nulls 1.03 6.6±0.25µs ? ?/sec 1.00 6.4±0.20µs ? ?/sec utf8_view (small): single, nulls 1.00 10.6±0.17µs ? ?/sec 1.00 10.5±0.19µs ? ?/sec utf8_view: multiple, no nulls 1.01 128.0±4.58µs ? ?/sec 1.00 126.7±5.74µs ? ?/sec utf8_view: multiple, nulls 1.00 171.5±2.36µs ? ?/sec 1.00 171.8±2.87µs ? ?/sec utf8_view: single, no nulls 1.00 26.0±0.61µs ? ?/sec 1.01 26.3±0.89µs ? ?/sec utf8_view: single, nulls 1.00 42.2±0.51µs ? ?/sec 1.01 42.4±0.57µs ? ?/sec ``` </p> </details> <details><summary>Resource Usage</summary> **with_hashes — base (merge-base)** | Metric | Value | |--------|-------| | Wall time | 1520.4s | | Peak memory | 66.1 MiB | | Avg memory | 38.8 MiB | | CPU user | 1901.3s | | CPU sys | 1.5s | | Peak spill | 0 B | **with_hashes — branch** | Metric | Value | |--------|-------| | Wall time | 1485.4s | | Peak memory | 70.6 MiB | | Avg memory | 43.3 MiB | | CPU user | 1911.1s | | CPU sys | 1.4s | | Peak spill | 0 B | </details> --- [File an issue](https://github.com/adriangb/datafusion-benchmarking/issues) against this benchmark runner -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
