Skip to content

POC hash aggregate repartition subpartitions#23186

Draft
Rachelint wants to merge 34 commits into
apache:mainfrom
Rachelint:final-aggr-with-lazily-materialize-poc
Draft

POC hash aggregate repartition subpartitions#23186
Rachelint wants to merge 34 commits into
apache:mainfrom
Rachelint:final-aggr-with-lazily-materialize-poc

Conversation

@Rachelint

Copy link
Copy Markdown
Contributor

Which issue does this PR close?

  • Closes #.

Rationale for this change

What changes are included in this PR?

Are these changes tested?

Are there any user-facing changes?

@github-actions github-actions Bot added optimizer Optimizer rules core Core DataFusion crate physical-plan Changes to the physical-plan crate labels Jun 25, 2026
@Rachelint Rachelint force-pushed the final-aggr-with-lazily-materialize-poc branch 3 times, most recently from 86eb45e to ce1b786 Compare June 27, 2026 14:05
@Rachelint Rachelint force-pushed the final-aggr-with-lazily-materialize-poc branch from ce1b786 to 182c5b0 Compare June 27, 2026 14:44
@github-actions github-actions Bot added auto detected api change Auto detected API change and removed auto detected api change Auto detected API change labels Jul 1, 2026
@Rachelint

Copy link
Copy Markdown
Contributor Author

run benchmarks clickbench_partitioned

@adriangbot

Copy link
Copy Markdown

🤖 Benchmark running (GKE) | trigger
Instance: c4a-highmem-16 (12 vCPU / 65 GiB) | Linux bench-c4862758747-795-q2znf 6.12.85+ #1 SMP Mon May 11 08:17:35 UTC 2026 aarch64 GNU/Linux

CPU Details (lscpu)
Architecture:                            aarch64
CPU op-mode(s):                          64-bit
Byte Order:                              Little Endian
CPU(s):                                  16
On-line CPU(s) list:                     0-15
Vendor ID:                               ARM
Model name:                              Neoverse-V2
Model:                                   1
Thread(s) per core:                      1
Core(s) per cluster:                     16
Socket(s):                               -
Cluster(s):                              1
Stepping:                                r0p1
BogoMIPS:                                2000.00
Flags:                                   fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm jscvt fcma lrcpc dcpop sha3 sm3 sm4 asimddp sha512 sve asimdfhm dit uscat ilrcpc flagm sb paca pacg dcpodp sve2 sveaes svepmull svebitperm svesha3 svesm4 flagm2 frint svei8mm svebf16 i8mm bf16 dgh rng bti
L1d cache:                               1 MiB (16 instances)
L1i cache:                               1 MiB (16 instances)
L2 cache:                                32 MiB (16 instances)
L3 cache:                                80 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; __user pointer sanitization
Vulnerability Spectre v2:                Mitigation; CSV2, BHB
Vulnerability Srbds:                     Not affected
Vulnerability Tsa:                       Not affected
Vulnerability Tsx async abort:           Not affected
Vulnerability Vmscape:                   Not affected

Comparing final-aggr-with-lazily-materialize-poc (56181e3) to eaafba4 (merge-base) diff using: clickbench_partitioned
Results will be posted here when complete


File an issue against this benchmark runner

@adriangbot

Copy link
Copy Markdown

🤖 Benchmark completed (GKE) | trigger

Instance: c4a-highmem-16 (12 vCPU / 65 GiB)

CPU Details (lscpu)
Architecture:                            aarch64
CPU op-mode(s):                          64-bit
Byte Order:                              Little Endian
CPU(s):                                  16
On-line CPU(s) list:                     0-15
Vendor ID:                               ARM
Model name:                              Neoverse-V2
Model:                                   1
Thread(s) per core:                      1
Core(s) per cluster:                     16
Socket(s):                               -
Cluster(s):                              1
Stepping:                                r0p1
BogoMIPS:                                2000.00
Flags:                                   fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm jscvt fcma lrcpc dcpop sha3 sm3 sm4 asimddp sha512 sve asimdfhm dit uscat ilrcpc flagm sb paca pacg dcpodp sve2 sveaes svepmull svebitperm svesha3 svesm4 flagm2 frint svei8mm svebf16 i8mm bf16 dgh rng bti
L1d cache:                               1 MiB (16 instances)
L1i cache:                               1 MiB (16 instances)
L2 cache:                                32 MiB (16 instances)
L3 cache:                                80 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; __user pointer sanitization
Vulnerability Spectre v2:                Mitigation; CSV2, BHB
Vulnerability Srbds:                     Not affected
Vulnerability Tsa:                       Not affected
Vulnerability Tsx async abort:           Not affected
Vulnerability Vmscape:                   Not affected
Details

Comparing HEAD and final-aggr-with-lazily-materialize-poc
--------------------
Benchmark clickbench_partitioned.json
--------------------
┏━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Query     ┃                                  HEAD ┃ final-aggr-with-lazily-materialize-poc ┃        Change ┃
┡━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ QQuery 0  │          1.24 / 4.05 ±5.49 / 15.03 ms │           1.21 / 4.01 ±5.46 / 14.92 ms │     no change │
│ QQuery 1  │        13.01 / 13.28 ±0.24 / 13.70 ms │         12.73 / 12.96 ±0.15 / 13.10 ms │     no change │
│ QQuery 2  │        36.20 / 36.39 ±0.21 / 36.75 ms │         35.51 / 35.72 ±0.25 / 36.21 ms │     no change │
│ QQuery 3  │        31.69 / 32.39 ±0.72 / 33.71 ms │         30.44 / 30.73 ±0.32 / 31.32 ms │ +1.05x faster │
│ QQuery 4  │     223.87 / 226.44 ±1.52 / 228.10 ms │      193.56 / 196.31 ±1.82 / 199.14 ms │ +1.15x faster │
│ QQuery 5  │     271.13 / 273.83 ±1.88 / 276.40 ms │      286.36 / 290.80 ±3.85 / 297.23 ms │  1.06x slower │
│ QQuery 6  │           1.28 / 1.43 ±0.23 / 1.87 ms │            1.26 / 1.41 ±0.23 / 1.87 ms │     no change │
│ QQuery 7  │        14.44 / 14.54 ±0.06 / 14.63 ms │         13.97 / 14.03 ±0.05 / 14.09 ms │     no change │
│ QQuery 8  │     320.72 / 323.17 ±1.70 / 325.19 ms │      299.67 / 306.51 ±6.53 / 314.63 ms │ +1.05x faster │
│ QQuery 9  │     455.35 / 461.37 ±7.62 / 475.28 ms │      418.06 / 424.94 ±9.09 / 441.27 ms │ +1.09x faster │
│ QQuery 10 │        72.09 / 73.21 ±0.90 / 74.24 ms │         71.75 / 72.71 ±0.59 / 73.37 ms │     no change │
│ QQuery 11 │        83.35 / 86.32 ±4.54 / 95.32 ms │         83.63 / 84.77 ±0.81 / 86.11 ms │     no change │
│ QQuery 12 │     267.95 / 272.98 ±4.34 / 280.26 ms │      280.15 / 288.46 ±5.08 / 296.16 ms │  1.06x slower │
│ QQuery 13 │     378.56 / 388.11 ±8.79 / 400.78 ms │      381.68 / 390.18 ±6.50 / 400.68 ms │     no change │
│ QQuery 14 │     283.02 / 285.39 ±1.68 / 287.67 ms │      287.78 / 291.90 ±2.89 / 296.76 ms │     no change │
│ QQuery 15 │     272.95 / 280.39 ±9.87 / 299.69 ms │     250.76 / 265.36 ±16.14 / 289.61 ms │ +1.06x faster │
│ QQuery 16 │     613.87 / 621.20 ±5.98 / 628.95 ms │     606.30 / 621.54 ±19.88 / 659.87 ms │     no change │
│ QQuery 17 │     622.34 / 627.36 ±4.23 / 633.34 ms │     507.97 / 523.99 ±13.03 / 546.14 ms │ +1.20x faster │
│ QQuery 18 │ 1260.31 / 1273.00 ±10.46 / 1286.09 ms │  1214.03 / 1279.59 ±50.36 / 1360.37 ms │     no change │
│ QQuery 19 │       28.48 / 37.17 ±15.60 / 68.36 ms │        27.74 / 36.70 ±16.15 / 68.98 ms │     no change │
│ QQuery 20 │    514.39 / 524.61 ±11.15 / 545.94 ms │      530.83 / 540.40 ±8.55 / 550.68 ms │     no change │
│ QQuery 21 │     519.52 / 522.42 ±3.37 / 528.43 ms │      522.10 / 528.46 ±3.83 / 533.49 ms │     no change │
│ QQuery 22 │  983.15 / 1001.66 ±10.80 / 1013.95 ms │   997.20 / 1043.47 ±30.35 / 1082.39 ms │     no change │
│ QQuery 23 │ 3075.18 / 3094.07 ±16.66 / 3125.15 ms │  3159.35 / 3180.12 ±19.52 / 3212.54 ms │     no change │
│ QQuery 24 │        41.90 / 45.45 ±5.40 / 56.06 ms │         42.41 / 45.73 ±5.04 / 55.70 ms │     no change │
│ QQuery 25 │     113.24 / 115.51 ±1.98 / 118.99 ms │      112.52 / 118.65 ±6.38 / 129.76 ms │     no change │
│ QQuery 26 │        42.34 / 43.66 ±1.35 / 46.21 ms │         41.97 / 47.28 ±8.04 / 63.11 ms │  1.08x slower │
│ QQuery 27 │     669.99 / 677.75 ±8.82 / 694.55 ms │      675.83 / 678.96 ±2.89 / 684.24 ms │     no change │
│ QQuery 28 │ 3014.38 / 3034.17 ±22.72 / 3073.34 ms │  3084.30 / 3098.63 ±10.30 / 3114.28 ms │     no change │
│ QQuery 29 │        40.77 / 40.90 ±0.11 / 41.07 ms │        40.41 / 50.90 ±20.40 / 91.70 ms │  1.24x slower │
│ QQuery 30 │    300.91 / 312.14 ±13.81 / 338.71 ms │      287.59 / 296.67 ±7.23 / 307.28 ms │     no change │
│ QQuery 31 │     286.06 / 294.90 ±7.06 / 306.19 ms │      263.21 / 272.59 ±6.64 / 280.71 ms │ +1.08x faster │
│ QQuery 32 │    925.79 / 965.99 ±23.58 / 996.50 ms │     763.20 / 817.59 ±40.27 / 870.74 ms │ +1.18x faster │
│ QQuery 33 │ 1450.00 / 1480.46 ±18.74 / 1507.48 ms │  1698.91 / 1754.55 ±76.98 / 1906.13 ms │  1.19x slower │
│ QQuery 34 │  1486.91 / 1496.43 ±9.89 / 1514.10 ms │  1700.67 / 1742.37 ±37.79 / 1809.49 ms │  1.16x slower │
│ QQuery 35 │    277.94 / 298.85 ±20.66 / 335.87 ms │     266.26 / 311.33 ±65.51 / 437.10 ms │     no change │
│ QQuery 36 │        65.19 / 78.58 ±9.55 / 90.02 ms │        66.25 / 79.03 ±11.94 / 97.02 ms │     no change │
│ QQuery 37 │        35.47 / 36.14 ±0.54 / 36.99 ms │         36.11 / 43.84 ±6.70 / 55.05 ms │  1.21x slower │
│ QQuery 38 │        42.93 / 46.63 ±3.38 / 51.95 ms │         40.42 / 43.33 ±3.79 / 50.00 ms │ +1.08x faster │
│ QQuery 39 │     138.62 / 149.55 ±7.74 / 162.00 ms │     141.20 / 162.59 ±12.65 / 179.48 ms │  1.09x slower │
│ QQuery 40 │        14.36 / 15.73 ±2.02 / 19.73 ms │         14.96 / 18.27 ±5.05 / 28.31 ms │  1.16x slower │
│ QQuery 41 │        13.64 / 14.14 ±0.45 / 14.90 ms │         14.23 / 14.54 ±0.31 / 14.99 ms │     no change │
│ QQuery 42 │        13.39 / 15.51 ±4.00 / 23.51 ms │         13.49 / 13.71 ±0.19 / 13.93 ms │ +1.13x faster │
└───────────┴───────────────────────────────────────┴────────────────────────────────────────┴───────────────┘
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━┓
┃ Benchmark Summary                                     ┃            ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━┩
│ Total Time (HEAD)                                     │ 19637.28ms │
│ Total Time (final-aggr-with-lazily-materialize-poc)   │ 20075.62ms │
│ Average Time (HEAD)                                   │   456.68ms │
│ Average Time (final-aggr-with-lazily-materialize-poc) │   466.87ms │
│ Queries Faster                                        │         10 │
│ Queries Slower                                        │          9 │
│ Queries with No Change                                │         24 │
│ Queries with Failure                                  │          0 │
└───────────────────────────────────────────────────────┴────────────┘

Resource Usage

clickbench_partitioned — base (merge-base)

Metric Value
Wall time 100.0s
Peak memory 11.1 GiB
Avg memory 4.5 GiB
CPU user 1010.1s
CPU sys 70.1s
Peak spill 0 B

clickbench_partitioned — branch

Metric Value
Wall time 105.0s
Peak memory 11.7 GiB
Avg memory 4.2 GiB
CPU user 974.6s
CPU sys 88.3s
Peak spill 0 B

File an issue against this benchmark runner

@Rachelint

Copy link
Copy Markdown
Contributor Author

run benchmarks clickbench_partitioned

@adriangbot

Copy link
Copy Markdown

🤖 Benchmark running (GKE) | trigger
Instance: c4a-highmem-16 (12 vCPU / 65 GiB) | Linux bench-c4862903506-796-7h5wm 6.12.85+ #1 SMP Mon May 11 08:17:35 UTC 2026 aarch64 GNU/Linux

CPU Details (lscpu)
Architecture:                            aarch64
CPU op-mode(s):                          64-bit
Byte Order:                              Little Endian
CPU(s):                                  16
On-line CPU(s) list:                     0-15
Vendor ID:                               ARM
Model name:                              Neoverse-V2
Model:                                   1
Thread(s) per core:                      1
Core(s) per cluster:                     16
Socket(s):                               -
Cluster(s):                              1
Stepping:                                r0p1
BogoMIPS:                                2000.00
Flags:                                   fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm jscvt fcma lrcpc dcpop sha3 sm3 sm4 asimddp sha512 sve asimdfhm dit uscat ilrcpc flagm sb paca pacg dcpodp sve2 sveaes svepmull svebitperm svesha3 svesm4 flagm2 frint svei8mm svebf16 i8mm bf16 dgh rng bti
L1d cache:                               1 MiB (16 instances)
L1i cache:                               1 MiB (16 instances)
L2 cache:                                32 MiB (16 instances)
L3 cache:                                80 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; __user pointer sanitization
Vulnerability Spectre v2:                Mitigation; CSV2, BHB
Vulnerability Srbds:                     Not affected
Vulnerability Tsa:                       Not affected
Vulnerability Tsx async abort:           Not affected
Vulnerability Vmscape:                   Not affected

Comparing final-aggr-with-lazily-materialize-poc (a8d2b6c) to eaafba4 (merge-base) diff using: clickbench_partitioned
Results will be posted here when complete


File an issue against this benchmark runner

@adriangbot

Copy link
Copy Markdown

🤖 Benchmark completed (GKE) | trigger

Instance: c4a-highmem-16 (12 vCPU / 65 GiB)

CPU Details (lscpu)
Architecture:                            aarch64
CPU op-mode(s):                          64-bit
Byte Order:                              Little Endian
CPU(s):                                  16
On-line CPU(s) list:                     0-15
Vendor ID:                               ARM
Model name:                              Neoverse-V2
Model:                                   1
Thread(s) per core:                      1
Core(s) per cluster:                     16
Socket(s):                               -
Cluster(s):                              1
Stepping:                                r0p1
BogoMIPS:                                2000.00
Flags:                                   fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm jscvt fcma lrcpc dcpop sha3 sm3 sm4 asimddp sha512 sve asimdfhm dit uscat ilrcpc flagm sb paca pacg dcpodp sve2 sveaes svepmull svebitperm svesha3 svesm4 flagm2 frint svei8mm svebf16 i8mm bf16 dgh rng bti
L1d cache:                               1 MiB (16 instances)
L1i cache:                               1 MiB (16 instances)
L2 cache:                                32 MiB (16 instances)
L3 cache:                                80 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; __user pointer sanitization
Vulnerability Spectre v2:                Mitigation; CSV2, BHB
Vulnerability Srbds:                     Not affected
Vulnerability Tsa:                       Not affected
Vulnerability Tsx async abort:           Not affected
Vulnerability Vmscape:                   Not affected
Details

Comparing HEAD and final-aggr-with-lazily-materialize-poc
--------------------
Benchmark clickbench_partitioned.json
--------------------
┏━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Query     ┃                                  HEAD ┃ final-aggr-with-lazily-materialize-poc ┃        Change ┃
┡━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ QQuery 0  │          1.22 / 3.97 ±5.41 / 14.78 ms │           1.23 / 3.92 ±5.30 / 14.53 ms │     no change │
│ QQuery 1  │        12.65 / 13.06 ±0.23 / 13.32 ms │         12.69 / 12.85 ±0.17 / 13.13 ms │     no change │
│ QQuery 2  │        36.49 / 36.76 ±0.25 / 37.19 ms │         35.74 / 36.05 ±0.22 / 36.29 ms │     no change │
│ QQuery 3  │        31.27 / 31.84 ±0.64 / 33.08 ms │         30.42 / 30.76 ±0.20 / 31.02 ms │     no change │
│ QQuery 4  │     220.07 / 223.69 ±2.54 / 226.94 ms │      194.30 / 198.44 ±4.45 / 207.08 ms │ +1.13x faster │
│ QQuery 5  │     270.09 / 271.65 ±1.20 / 273.46 ms │      285.42 / 288.64 ±3.17 / 293.73 ms │  1.06x slower │
│ QQuery 6  │           1.29 / 1.44 ±0.23 / 1.89 ms │            1.26 / 1.42 ±0.24 / 1.88 ms │     no change │
│ QQuery 7  │        13.85 / 13.93 ±0.04 / 13.97 ms │         14.03 / 14.24 ±0.17 / 14.52 ms │     no change │
│ QQuery 8  │     316.03 / 321.64 ±3.58 / 326.28 ms │      298.91 / 303.26 ±4.30 / 309.99 ms │ +1.06x faster │
│ QQuery 9  │     450.95 / 454.45 ±3.29 / 460.70 ms │      408.99 / 409.68 ±0.76 / 411.12 ms │ +1.11x faster │
│ QQuery 10 │        71.84 / 74.19 ±2.71 / 79.38 ms │        73.47 / 79.39 ±10.03 / 99.42 ms │  1.07x slower │
│ QQuery 11 │        83.75 / 84.45 ±0.71 / 85.66 ms │         85.64 / 86.56 ±0.99 / 88.47 ms │     no change │
│ QQuery 12 │     266.14 / 269.10 ±3.11 / 274.70 ms │      284.89 / 291.73 ±5.47 / 298.10 ms │  1.08x slower │
│ QQuery 13 │     360.77 / 371.31 ±7.63 / 384.00 ms │     378.37 / 394.94 ±11.90 / 409.26 ms │  1.06x slower │
│ QQuery 14 │     281.62 / 285.96 ±4.05 / 292.03 ms │      288.02 / 294.44 ±7.44 / 308.51 ms │     no change │
│ QQuery 15 │     270.86 / 275.05 ±2.44 / 278.39 ms │     244.18 / 256.55 ±11.28 / 275.45 ms │ +1.07x faster │
│ QQuery 16 │     607.26 / 614.73 ±4.57 / 620.75 ms │      614.28 / 621.95 ±7.24 / 634.75 ms │     no change │
│ QQuery 17 │     614.86 / 621.60 ±7.34 / 630.73 ms │      504.13 / 517.70 ±9.54 / 531.34 ms │ +1.20x faster │
│ QQuery 18 │ 1258.69 / 1270.12 ±10.36 / 1288.12 ms │  1210.05 / 1260.49 ±45.36 / 1328.35 ms │     no change │
│ QQuery 19 │        28.18 / 31.21 ±5.62 / 42.46 ms │        28.02 / 34.49 ±12.39 / 59.27 ms │  1.11x slower │
│ QQuery 20 │    513.54 / 524.51 ±17.41 / 559.11 ms │     520.37 / 543.77 ±42.25 / 628.22 ms │     no change │
│ QQuery 21 │     508.81 / 514.22 ±3.54 / 517.76 ms │      515.76 / 525.42 ±7.29 / 537.13 ms │     no change │
│ QQuery 22 │     976.32 / 985.74 ±7.19 / 998.44 ms │      991.56 / 993.99 ±2.77 / 997.95 ms │     no change │
│ QQuery 23 │ 3060.69 / 3082.10 ±20.29 / 3117.72 ms │  3111.60 / 3158.37 ±32.13 / 3198.69 ms │     no change │
│ QQuery 24 │        41.09 / 41.55 ±0.32 / 41.91 ms │         41.33 / 43.53 ±2.86 / 48.83 ms │     no change │
│ QQuery 25 │     112.67 / 114.51 ±2.29 / 118.98 ms │      112.36 / 113.68 ±1.41 / 115.46 ms │     no change │
│ QQuery 26 │        41.61 / 43.24 ±1.94 / 47.01 ms │         41.75 / 44.04 ±2.16 / 46.72 ms │     no change │
│ QQuery 27 │     665.84 / 673.80 ±7.37 / 687.76 ms │      664.02 / 673.72 ±6.62 / 683.50 ms │     no change │
│ QQuery 28 │ 2998.34 / 3043.16 ±23.07 / 3062.14 ms │  3058.75 / 3082.56 ±25.11 / 3123.25 ms │     no change │
│ QQuery 29 │        40.74 / 40.94 ±0.28 / 41.48 ms │         40.34 / 41.09 ±1.26 / 43.59 ms │     no change │
│ QQuery 30 │     299.56 / 308.74 ±6.82 / 316.42 ms │     285.90 / 296.34 ±10.53 / 316.29 ms │     no change │
│ QQuery 31 │     282.48 / 291.51 ±6.47 / 299.15 ms │      261.97 / 267.28 ±4.88 / 274.95 ms │ +1.09x faster │
│ QQuery 32 │    913.72 / 933.14 ±13.90 / 955.17 ms │     748.02 / 816.63 ±88.29 / 979.98 ms │ +1.14x faster │
│ QQuery 33 │ 1449.56 / 1484.70 ±35.25 / 1549.06 ms │  1646.52 / 1680.11 ±21.92 / 1710.87 ms │  1.13x slower │
│ QQuery 34 │ 1466.33 / 1481.75 ±15.56 / 1501.78 ms │  1707.45 / 1801.50 ±93.97 / 1927.95 ms │  1.22x slower │
│ QQuery 35 │    280.68 / 301.95 ±20.75 / 336.46 ms │     256.01 / 341.54 ±96.21 / 472.14 ms │  1.13x slower │
│ QQuery 36 │        66.25 / 71.39 ±4.14 / 78.34 ms │         73.20 / 78.38 ±7.07 / 92.31 ms │  1.10x slower │
│ QQuery 37 │        35.88 / 37.89 ±2.91 / 43.62 ms │         36.14 / 36.49 ±0.21 / 36.78 ms │     no change │
│ QQuery 38 │        43.01 / 48.48 ±6.49 / 58.74 ms │        40.46 / 47.64 ±11.23 / 69.93 ms │     no change │
│ QQuery 39 │     140.12 / 151.05 ±6.26 / 159.04 ms │     138.74 / 159.95 ±11.95 / 170.37 ms │  1.06x slower │
│ QQuery 40 │        13.69 / 14.44 ±0.52 / 15.25 ms │         14.25 / 15.00 ±0.61 / 15.78 ms │     no change │
│ QQuery 41 │        13.58 / 19.60 ±8.30 / 35.37 ms │         13.68 / 17.21 ±6.65 / 30.50 ms │ +1.14x faster │
│ QQuery 42 │        13.02 / 15.66 ±2.98 / 19.34 ms │         13.05 / 17.07 ±4.59 / 24.45 ms │  1.09x slower │
└───────────┴───────────────────────────────────────┴────────────────────────────────────────┴───────────────┘
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━┓
┃ Benchmark Summary                                     ┃            ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━┩
│ Total Time (HEAD)                                     │ 19494.18ms │
│ Total Time (final-aggr-with-lazily-materialize-poc)   │ 19932.82ms │
│ Average Time (HEAD)                                   │   453.35ms │
│ Average Time (final-aggr-with-lazily-materialize-poc) │   463.55ms │
│ Queries Faster                                        │          8 │
│ Queries Slower                                        │         11 │
│ Queries with No Change                                │         24 │
│ Queries with Failure                                  │          0 │
└───────────────────────────────────────────────────────┴────────────┘

Resource Usage

clickbench_partitioned — base (merge-base)

Metric Value
Wall time 100.0s
Peak memory 12.1 GiB
Avg memory 4.5 GiB
CPU user 1007.0s
CPU sys 65.9s
Peak spill 0 B

clickbench_partitioned — branch

Metric Value
Wall time 100.0s
Peak memory 12.1 GiB
Avg memory 4.4 GiB
CPU user 968.7s
CPU sys 82.3s
Peak spill 0 B

File an issue against this benchmark runner

@Rachelint

Copy link
Copy Markdown
Contributor Author

run benchmarks clickbench_partitioned

@adriangbot

Copy link
Copy Markdown

🤖 Benchmark running (GKE) | trigger
Instance: c4a-highmem-16 (12 vCPU / 65 GiB) | Linux bench-c4914553964-905-ht6kt 6.12.85+ #1 SMP Mon May 11 08:17:35 UTC 2026 aarch64 GNU/Linux

CPU Details (lscpu)
Architecture:                            aarch64
CPU op-mode(s):                          64-bit
Byte Order:                              Little Endian
CPU(s):                                  16
On-line CPU(s) list:                     0-15
Vendor ID:                               ARM
Model name:                              Neoverse-V2
Model:                                   1
Thread(s) per core:                      1
Core(s) per cluster:                     16
Socket(s):                               -
Cluster(s):                              1
Stepping:                                r0p1
BogoMIPS:                                2000.00
Flags:                                   fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm jscvt fcma lrcpc dcpop sha3 sm3 sm4 asimddp sha512 sve asimdfhm dit uscat ilrcpc flagm sb paca pacg dcpodp sve2 sveaes svepmull svebitperm svesha3 svesm4 flagm2 frint svei8mm svebf16 i8mm bf16 dgh rng bti
L1d cache:                               1 MiB (16 instances)
L1i cache:                               1 MiB (16 instances)
L2 cache:                                32 MiB (16 instances)
L3 cache:                                80 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; __user pointer sanitization
Vulnerability Spectre v2:                Mitigation; CSV2, BHB
Vulnerability Srbds:                     Not affected
Vulnerability Tsa:                       Not affected
Vulnerability Tsx async abort:           Not affected
Vulnerability Vmscape:                   Not affected

Comparing final-aggr-with-lazily-materialize-poc (62ea9e8) to eaafba4 (merge-base) diff using: clickbench_partitioned
Results will be posted here when complete


File an issue against this benchmark runner

@adriangbot

Copy link
Copy Markdown

🤖 Benchmark completed (GKE) | trigger

Instance: c4a-highmem-16 (12 vCPU / 65 GiB)

CPU Details (lscpu)
Architecture:                            aarch64
CPU op-mode(s):                          64-bit
Byte Order:                              Little Endian
CPU(s):                                  16
On-line CPU(s) list:                     0-15
Vendor ID:                               ARM
Model name:                              Neoverse-V2
Model:                                   1
Thread(s) per core:                      1
Core(s) per cluster:                     16
Socket(s):                               -
Cluster(s):                              1
Stepping:                                r0p1
BogoMIPS:                                2000.00
Flags:                                   fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm jscvt fcma lrcpc dcpop sha3 sm3 sm4 asimddp sha512 sve asimdfhm dit uscat ilrcpc flagm sb paca pacg dcpodp sve2 sveaes svepmull svebitperm svesha3 svesm4 flagm2 frint svei8mm svebf16 i8mm bf16 dgh rng bti
L1d cache:                               1 MiB (16 instances)
L1i cache:                               1 MiB (16 instances)
L2 cache:                                32 MiB (16 instances)
L3 cache:                                80 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; __user pointer sanitization
Vulnerability Spectre v2:                Mitigation; CSV2, BHB
Vulnerability Srbds:                     Not affected
Vulnerability Tsa:                       Not affected
Vulnerability Tsx async abort:           Not affected
Vulnerability Vmscape:                   Not affected
Details

Comparing HEAD and final-aggr-with-lazily-materialize-poc
--------------------
Benchmark clickbench_partitioned.json
--------------------
┏━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Query     ┃                                  HEAD ┃ final-aggr-with-lazily-materialize-poc ┃        Change ┃
┡━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ QQuery 0  │          1.23 / 3.93 ±5.34 / 14.62 ms │           1.24 / 4.05 ±5.50 / 15.05 ms │     no change │
│ QQuery 1  │        12.54 / 12.70 ±0.11 / 12.85 ms │         12.53 / 13.02 ±0.34 / 13.58 ms │     no change │
│ QQuery 2  │        35.70 / 36.03 ±0.33 / 36.54 ms │         36.11 / 36.40 ±0.28 / 36.89 ms │     no change │
│ QQuery 3  │        30.88 / 31.30 ±0.63 / 32.54 ms │         31.41 / 31.69 ±0.36 / 32.35 ms │     no change │
│ QQuery 4  │     216.70 / 224.23 ±4.88 / 229.81 ms │      198.06 / 201.47 ±2.40 / 205.37 ms │ +1.11x faster │
│ QQuery 5  │     267.62 / 270.27 ±1.62 / 272.50 ms │      270.31 / 271.44 ±1.43 / 273.75 ms │     no change │
│ QQuery 6  │           1.25 / 1.41 ±0.23 / 1.85 ms │            1.25 / 1.40 ±0.24 / 1.87 ms │     no change │
│ QQuery 7  │        13.61 / 13.74 ±0.10 / 13.91 ms │         13.96 / 14.20 ±0.14 / 14.34 ms │     no change │
│ QQuery 8  │     315.36 / 320.26 ±3.06 / 324.76 ms │      292.54 / 300.36 ±6.12 / 311.16 ms │ +1.07x faster │
│ QQuery 9  │     445.41 / 451.47 ±4.56 / 459.15 ms │     430.86 / 473.10 ±28.06 / 519.03 ms │     no change │
│ QQuery 10 │        70.59 / 72.69 ±1.62 / 74.76 ms │         74.06 / 76.27 ±2.24 / 80.60 ms │     no change │
│ QQuery 11 │        83.30 / 84.28 ±1.12 / 85.84 ms │         85.25 / 88.56 ±3.04 / 94.30 ms │  1.05x slower │
│ QQuery 12 │     266.58 / 270.31 ±4.62 / 278.77 ms │     255.72 / 264.78 ±12.65 / 289.47 ms │     no change │
│ QQuery 13 │     356.63 / 368.01 ±9.38 / 383.67 ms │     362.57 / 374.81 ±11.40 / 391.22 ms │     no change │
│ QQuery 14 │     279.54 / 283.98 ±3.05 / 287.79 ms │      291.74 / 297.12 ±5.95 / 307.79 ms │     no change │
│ QQuery 15 │     268.03 / 274.46 ±7.05 / 283.83 ms │     244.09 / 258.85 ±12.39 / 278.03 ms │ +1.06x faster │
│ QQuery 16 │     605.60 / 613.73 ±5.77 / 619.80 ms │     659.11 / 682.40 ±18.98 / 717.17 ms │  1.11x slower │
│ QQuery 17 │     611.41 / 618.41 ±5.15 / 623.76 ms │      673.38 / 677.40 ±4.21 / 683.79 ms │  1.10x slower │
│ QQuery 18 │ 1237.32 / 1260.96 ±12.81 / 1271.57 ms │  1339.08 / 1389.65 ±40.52 / 1450.19 ms │  1.10x slower │
│ QQuery 19 │        27.56 / 29.03 ±2.44 / 33.88 ms │         27.90 / 28.29 ±0.34 / 28.84 ms │     no change │
│ QQuery 20 │     512.88 / 521.00 ±9.60 / 538.80 ms │     517.25 / 537.92 ±26.98 / 590.45 ms │     no change │
│ QQuery 21 │     511.22 / 516.43 ±3.91 / 521.46 ms │      521.73 / 527.59 ±5.87 / 538.19 ms │     no change │
│ QQuery 22 │    983.69 / 992.80 ±5.86 / 1000.36 ms │    995.20 / 1002.87 ±7.76 / 1014.74 ms │     no change │
│ QQuery 23 │ 3040.54 / 3060.45 ±15.65 / 3087.93 ms │  3081.15 / 3129.55 ±33.77 / 3164.17 ms │     no change │
│ QQuery 24 │        40.94 / 42.32 ±2.19 / 46.62 ms │         40.97 / 43.13 ±2.22 / 47.04 ms │     no change │
│ QQuery 25 │     112.14 / 114.26 ±1.54 / 116.47 ms │      110.37 / 111.72 ±1.26 / 113.79 ms │     no change │
│ QQuery 26 │        41.38 / 41.68 ±0.39 / 42.42 ms │         41.18 / 41.96 ±1.38 / 44.71 ms │     no change │
│ QQuery 27 │     664.28 / 671.71 ±7.38 / 685.04 ms │      663.29 / 672.51 ±5.49 / 680.44 ms │     no change │
│ QQuery 28 │ 3046.18 / 3057.87 ±10.01 / 3072.26 ms │  3100.23 / 3168.17 ±49.62 / 3239.05 ms │     no change │
│ QQuery 29 │        40.16 / 40.77 ±0.72 / 42.13 ms │         42.01 / 46.15 ±7.94 / 62.02 ms │  1.13x slower │
│ QQuery 30 │     297.00 / 303.11 ±4.75 / 311.18 ms │      308.44 / 317.01 ±7.29 / 327.09 ms │     no change │
│ QQuery 31 │    280.83 / 302.41 ±23.54 / 348.17 ms │      272.38 / 280.18 ±8.78 / 294.02 ms │ +1.08x faster │
│ QQuery 32 │   922.86 / 972.13 ±38.65 / 1026.64 ms │     760.48 / 809.41 ±47.24 / 899.59 ms │ +1.20x faster │
│ QQuery 33 │ 1420.61 / 1463.66 ±29.89 / 1511.14 ms │  1589.19 / 1680.21 ±73.18 / 1807.92 ms │  1.15x slower │
│ QQuery 34 │ 1514.71 / 1567.66 ±56.69 / 1670.30 ms │  1575.86 / 1676.09 ±57.06 / 1736.34 ms │  1.07x slower │
│ QQuery 35 │    294.00 / 314.66 ±19.17 / 343.90 ms │     255.45 / 289.83 ±66.10 / 422.02 ms │ +1.09x faster │
│ QQuery 36 │        73.76 / 78.80 ±4.61 / 85.89 ms │         65.57 / 68.62 ±2.96 / 74.12 ms │ +1.15x faster │
│ QQuery 37 │        36.46 / 40.49 ±6.20 / 52.85 ms │         35.03 / 41.63 ±7.72 / 55.38 ms │     no change │
│ QQuery 38 │        42.17 / 44.63 ±3.66 / 51.88 ms │         39.77 / 43.72 ±2.71 / 47.38 ms │     no change │
│ QQuery 39 │     155.15 / 159.08 ±4.41 / 166.13 ms │     146.42 / 157.69 ±12.47 / 179.31 ms │     no change │
│ QQuery 40 │        14.60 / 17.46 ±4.79 / 27.02 ms │         13.97 / 14.37 ±0.41 / 15.14 ms │ +1.22x faster │
│ QQuery 41 │        14.54 / 14.82 ±0.23 / 15.21 ms │         13.42 / 15.81 ±4.52 / 24.84 ms │  1.07x slower │
│ QQuery 42 │        13.68 / 14.84 ±1.84 / 18.48 ms │         13.21 / 14.47 ±2.24 / 18.94 ms │     no change │
└───────────┴───────────────────────────────────────┴────────────────────────────────────────┴───────────────┘
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━┓
┃ Benchmark Summary                                     ┃            ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━┩
│ Total Time (HEAD)                                     │ 19594.24ms │
│ Total Time (final-aggr-with-lazily-materialize-poc)   │ 20175.87ms │
│ Average Time (HEAD)                                   │   455.68ms │
│ Average Time (final-aggr-with-lazily-materialize-poc) │   469.21ms │
│ Queries Faster                                        │          8 │
│ Queries Slower                                        │          8 │
│ Queries with No Change                                │         27 │
│ Queries with Failure                                  │          0 │
└───────────────────────────────────────────────────────┴────────────┘

Resource Usage

clickbench_partitioned — base (merge-base)

Metric Value
Wall time 100.0s
Peak memory 12.4 GiB
Avg memory 4.5 GiB
CPU user 1007.0s
CPU sys 69.8s
Peak spill 0 B

clickbench_partitioned — branch

Metric Value
Wall time 105.0s
Peak memory 10.5 GiB
Avg memory 4.0 GiB
CPU user 1002.7s
CPU sys 76.7s
Peak spill 0 B

File an issue against this benchmark runner

@Rachelint

Copy link
Copy Markdown
Contributor Author

run benchmarks clickbench_partitioned

@adriangbot

Copy link
Copy Markdown

🤖 Benchmark running (GKE) | trigger
Instance: c4a-highmem-16 (12 vCPU / 65 GiB) | Linux bench-c4914751153-906-dprdp 6.12.85+ #1 SMP Mon May 11 08:17:35 UTC 2026 aarch64 GNU/Linux

CPU Details (lscpu)
Architecture:                            aarch64
CPU op-mode(s):                          64-bit
Byte Order:                              Little Endian
CPU(s):                                  16
On-line CPU(s) list:                     0-15
Vendor ID:                               ARM
Model name:                              Neoverse-V2
Model:                                   1
Thread(s) per core:                      1
Core(s) per cluster:                     16
Socket(s):                               -
Cluster(s):                              1
Stepping:                                r0p1
BogoMIPS:                                2000.00
Flags:                                   fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm jscvt fcma lrcpc dcpop sha3 sm3 sm4 asimddp sha512 sve asimdfhm dit uscat ilrcpc flagm sb paca pacg dcpodp sve2 sveaes svepmull svebitperm svesha3 svesm4 flagm2 frint svei8mm svebf16 i8mm bf16 dgh rng bti
L1d cache:                               1 MiB (16 instances)
L1i cache:                               1 MiB (16 instances)
L2 cache:                                32 MiB (16 instances)
L3 cache:                                80 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; __user pointer sanitization
Vulnerability Spectre v2:                Mitigation; CSV2, BHB
Vulnerability Srbds:                     Not affected
Vulnerability Tsa:                       Not affected
Vulnerability Tsx async abort:           Not affected
Vulnerability Vmscape:                   Not affected

Comparing final-aggr-with-lazily-materialize-poc (62ea9e8) to eaafba4 (merge-base) diff using: clickbench_partitioned
Results will be posted here when complete


File an issue against this benchmark runner

@adriangbot

Copy link
Copy Markdown

🤖 Benchmark completed (GKE) | trigger

Instance: c4a-highmem-16 (12 vCPU / 65 GiB)

CPU Details (lscpu)
Architecture:                            aarch64
CPU op-mode(s):                          64-bit
Byte Order:                              Little Endian
CPU(s):                                  16
On-line CPU(s) list:                     0-15
Vendor ID:                               ARM
Model name:                              Neoverse-V2
Model:                                   1
Thread(s) per core:                      1
Core(s) per cluster:                     16
Socket(s):                               -
Cluster(s):                              1
Stepping:                                r0p1
BogoMIPS:                                2000.00
Flags:                                   fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm jscvt fcma lrcpc dcpop sha3 sm3 sm4 asimddp sha512 sve asimdfhm dit uscat ilrcpc flagm sb paca pacg dcpodp sve2 sveaes svepmull svebitperm svesha3 svesm4 flagm2 frint svei8mm svebf16 i8mm bf16 dgh rng bti
L1d cache:                               1 MiB (16 instances)
L1i cache:                               1 MiB (16 instances)
L2 cache:                                32 MiB (16 instances)
L3 cache:                                80 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; __user pointer sanitization
Vulnerability Spectre v2:                Mitigation; CSV2, BHB
Vulnerability Srbds:                     Not affected
Vulnerability Tsa:                       Not affected
Vulnerability Tsx async abort:           Not affected
Vulnerability Vmscape:                   Not affected
Details

Comparing HEAD and final-aggr-with-lazily-materialize-poc
--------------------
Benchmark clickbench_partitioned.json
--------------------
┏━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Query     ┃                                  HEAD ┃ final-aggr-with-lazily-materialize-poc ┃        Change ┃
┡━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ QQuery 0  │          1.22 / 4.02 ±5.47 / 14.96 ms │           1.20 / 3.91 ±5.33 / 14.57 ms │     no change │
│ QQuery 1  │        12.70 / 12.78 ±0.07 / 12.91 ms │         12.62 / 12.89 ±0.23 / 13.19 ms │     no change │
│ QQuery 2  │        35.61 / 35.99 ±0.26 / 36.30 ms │         35.97 / 36.31 ±0.38 / 36.96 ms │     no change │
│ QQuery 3  │        30.82 / 31.56 ±0.92 / 33.24 ms │         30.77 / 30.98 ±0.16 / 31.16 ms │     no change │
│ QQuery 4  │     222.61 / 226.67 ±2.32 / 228.72 ms │      185.23 / 190.32 ±2.96 / 194.11 ms │ +1.19x faster │
│ QQuery 5  │     271.02 / 272.41 ±1.79 / 275.93 ms │      255.12 / 258.68 ±3.01 / 262.98 ms │ +1.05x faster │
│ QQuery 6  │           1.28 / 1.42 ±0.23 / 1.87 ms │            1.27 / 1.43 ±0.23 / 1.89 ms │     no change │
│ QQuery 7  │        13.64 / 13.74 ±0.11 / 13.95 ms │         13.84 / 13.98 ±0.13 / 14.20 ms │     no change │
│ QQuery 8  │     319.55 / 323.64 ±3.25 / 327.81 ms │      288.13 / 291.15 ±2.25 / 295.05 ms │ +1.11x faster │
│ QQuery 9  │     452.95 / 460.98 ±5.60 / 468.28 ms │      405.14 / 414.01 ±8.34 / 427.31 ms │ +1.11x faster │
│ QQuery 10 │        70.82 / 71.67 ±1.07 / 73.74 ms │         70.39 / 71.68 ±1.09 / 73.61 ms │     no change │
│ QQuery 11 │        81.72 / 82.78 ±0.84 / 83.79 ms │         81.57 / 82.06 ±0.25 / 82.24 ms │     no change │
│ QQuery 12 │     263.78 / 272.17 ±8.43 / 287.19 ms │      256.81 / 260.05 ±2.75 / 264.93 ms │     no change │
│ QQuery 13 │     375.52 / 390.65 ±7.71 / 397.22 ms │     365.48 / 373.65 ±10.75 / 393.31 ms │     no change │
│ QQuery 14 │     281.09 / 286.26 ±4.29 / 293.94 ms │      289.68 / 296.78 ±9.33 / 315.03 ms │     no change │
│ QQuery 15 │     273.68 / 281.75 ±9.96 / 300.70 ms │      226.06 / 233.05 ±4.87 / 241.27 ms │ +1.21x faster │
│ QQuery 16 │     608.15 / 615.57 ±5.06 / 622.83 ms │      625.27 / 634.37 ±8.40 / 645.98 ms │     no change │
│ QQuery 17 │    613.95 / 623.68 ±11.55 / 645.62 ms │     621.21 / 636.40 ±11.63 / 656.31 ms │     no change │
│ QQuery 18 │ 1241.13 / 1271.84 ±19.16 / 1297.44 ms │  1271.55 / 1293.07 ±15.87 / 1318.69 ms │     no change │
│ QQuery 19 │        27.48 / 28.31 ±0.71 / 29.35 ms │         27.71 / 27.99 ±0.46 / 28.92 ms │     no change │
│ QQuery 20 │     515.38 / 529.01 ±7.21 / 536.31 ms │      514.77 / 522.71 ±4.15 / 526.52 ms │     no change │
│ QQuery 21 │     515.95 / 520.67 ±4.51 / 527.91 ms │      512.25 / 519.03 ±4.93 / 526.81 ms │     no change │
│ QQuery 22 │     982.02 / 987.51 ±3.15 / 991.80 ms │     983.00 / 988.10 ±6.78 / 1000.58 ms │     no change │
│ QQuery 23 │ 3067.83 / 3099.47 ±26.38 / 3127.43 ms │  3049.00 / 3093.01 ±25.46 / 3123.27 ms │     no change │
│ QQuery 24 │        42.67 / 48.88 ±5.61 / 57.70 ms │        44.29 / 55.60 ±12.51 / 78.77 ms │  1.14x slower │
│ QQuery 25 │     111.12 / 112.41 ±0.78 / 113.30 ms │      112.79 / 114.02 ±1.05 / 115.95 ms │     no change │
│ QQuery 26 │        41.65 / 43.42 ±2.46 / 48.24 ms │         42.01 / 42.87 ±0.63 / 43.67 ms │     no change │
│ QQuery 27 │     671.66 / 678.79 ±5.51 / 687.14 ms │      673.42 / 674.63 ±1.45 / 677.46 ms │     no change │
│ QQuery 28 │ 3047.71 / 3063.24 ±11.55 / 3082.44 ms │   3064.58 / 3074.84 ±7.70 / 3083.61 ms │     no change │
│ QQuery 29 │        40.55 / 45.93 ±6.26 / 54.15 ms │        40.83 / 54.89 ±20.20 / 92.85 ms │  1.20x slower │
│ QQuery 30 │     297.54 / 306.93 ±5.31 / 312.43 ms │     286.38 / 299.05 ±12.88 / 321.04 ms │     no change │
│ QQuery 31 │     276.99 / 289.38 ±7.22 / 295.84 ms │     256.41 / 266.23 ±14.33 / 294.44 ms │ +1.09x faster │
│ QQuery 32 │    922.78 / 946.96 ±15.34 / 970.03 ms │     681.13 / 740.49 ±83.00 / 903.08 ms │ +1.28x faster │
│ QQuery 33 │ 1454.06 / 1499.59 ±48.61 / 1574.64 ms │  1418.66 / 1499.47 ±52.59 / 1582.99 ms │     no change │
│ QQuery 34 │ 1487.30 / 1500.83 ±10.37 / 1514.01 ms │  1483.45 / 1533.12 ±31.47 / 1572.67 ms │     no change │
│ QQuery 35 │    279.02 / 293.15 ±11.22 / 312.34 ms │     250.55 / 292.76 ±72.17 / 436.85 ms │     no change │
│ QQuery 36 │        66.47 / 72.74 ±4.42 / 78.49 ms │         66.58 / 69.68 ±2.91 / 74.10 ms │     no change │
│ QQuery 37 │        35.92 / 36.87 ±0.92 / 38.53 ms │        35.64 / 42.99 ±14.08 / 71.14 ms │  1.17x slower │
│ QQuery 38 │        40.80 / 45.60 ±4.75 / 54.58 ms │         40.70 / 42.95 ±1.53 / 44.79 ms │ +1.06x faster │
│ QQuery 39 │     136.52 / 153.29 ±9.96 / 164.00 ms │      137.86 / 143.35 ±4.59 / 151.38 ms │ +1.07x faster │
│ QQuery 40 │        13.99 / 15.58 ±2.77 / 21.11 ms │        14.58 / 22.37 ±14.08 / 50.52 ms │  1.44x slower │
│ QQuery 41 │        13.56 / 14.04 ±0.55 / 15.12 ms │         14.12 / 14.86 ±1.25 / 17.36 ms │  1.06x slower │
│ QQuery 42 │        13.11 / 15.71 ±4.91 / 25.53 ms │         13.39 / 13.64 ±0.24 / 14.08 ms │ +1.15x faster │
└───────────┴───────────────────────────────────────┴────────────────────────────────────────┴───────────────┘
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━┓
┃ Benchmark Summary                                     ┃            ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━┩
│ Total Time (HEAD)                                     │ 19627.89ms │
│ Total Time (final-aggr-with-lazily-materialize-poc)   │ 19283.46ms │
│ Average Time (HEAD)                                   │   456.46ms │
│ Average Time (final-aggr-with-lazily-materialize-poc) │   448.45ms │
│ Queries Faster                                        │         10 │
│ Queries Slower                                        │          5 │
│ Queries with No Change                                │         28 │
│ Queries with Failure                                  │          0 │
└───────────────────────────────────────────────────────┴────────────┘

Resource Usage

clickbench_partitioned — base (merge-base)

Metric Value
Wall time 100.0s
Peak memory 11.8 GiB
Avg memory 4.4 GiB
CPU user 1007.5s
CPU sys 68.7s
Peak spill 0 B

clickbench_partitioned — branch

Metric Value
Wall time 100.0s
Peak memory 10.2 GiB
Avg memory 4.1 GiB
CPU user 965.0s
CPU sys 69.5s
Peak spill 0 B

File an issue against this benchmark runner

@Rachelint Rachelint force-pushed the final-aggr-with-lazily-materialize-poc branch from 62ea9e8 to 611e4ff Compare July 12, 2026 10:51
@Rachelint

Copy link
Copy Markdown
Contributor Author

run benchmarks clickbench_partitioned

@adriangbot

Copy link
Copy Markdown

🤖 Benchmark running (GKE) | trigger
Instance: c4a-highmem-16 (12 vCPU / 65 GiB) | Linux bench-c4950907445-999-6szmm 6.12.85+ #1 SMP Mon May 11 08:17:35 UTC 2026 aarch64 GNU/Linux

CPU Details (lscpu)
Architecture:                            aarch64
CPU op-mode(s):                          64-bit
Byte Order:                              Little Endian
CPU(s):                                  16
On-line CPU(s) list:                     0-15
Vendor ID:                               ARM
Model name:                              Neoverse-V2
Model:                                   1
Thread(s) per core:                      1
Core(s) per cluster:                     16
Socket(s):                               -
Cluster(s):                              1
Stepping:                                r0p1
BogoMIPS:                                2000.00
Flags:                                   fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm jscvt fcma lrcpc dcpop sha3 sm3 sm4 asimddp sha512 sve asimdfhm dit uscat ilrcpc flagm sb paca pacg dcpodp sve2 sveaes svepmull svebitperm svesha3 svesm4 flagm2 frint svei8mm svebf16 i8mm bf16 dgh rng bti
L1d cache:                               1 MiB (16 instances)
L1i cache:                               1 MiB (16 instances)
L2 cache:                                32 MiB (16 instances)
L3 cache:                                80 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; __user pointer sanitization
Vulnerability Spectre v2:                Mitigation; CSV2, BHB
Vulnerability Srbds:                     Not affected
Vulnerability Tsa:                       Not affected
Vulnerability Tsx async abort:           Not affected
Vulnerability Vmscape:                   Not affected

Comparing final-aggr-with-lazily-materialize-poc (611e4ff) to eaafba4 (merge-base) diff using: clickbench_partitioned
Results will be posted here when complete


File an issue against this benchmark runner

@adriangbot

Copy link
Copy Markdown

🤖 Benchmark completed (GKE) | trigger

Instance: c4a-highmem-16 (12 vCPU / 65 GiB)

CPU Details (lscpu)
Architecture:                            aarch64
CPU op-mode(s):                          64-bit
Byte Order:                              Little Endian
CPU(s):                                  16
On-line CPU(s) list:                     0-15
Vendor ID:                               ARM
Model name:                              Neoverse-V2
Model:                                   1
Thread(s) per core:                      1
Core(s) per cluster:                     16
Socket(s):                               -
Cluster(s):                              1
Stepping:                                r0p1
BogoMIPS:                                2000.00
Flags:                                   fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm jscvt fcma lrcpc dcpop sha3 sm3 sm4 asimddp sha512 sve asimdfhm dit uscat ilrcpc flagm sb paca pacg dcpodp sve2 sveaes svepmull svebitperm svesha3 svesm4 flagm2 frint svei8mm svebf16 i8mm bf16 dgh rng bti
L1d cache:                               1 MiB (16 instances)
L1i cache:                               1 MiB (16 instances)
L2 cache:                                32 MiB (16 instances)
L3 cache:                                80 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; __user pointer sanitization
Vulnerability Spectre v2:                Mitigation; CSV2, BHB
Vulnerability Srbds:                     Not affected
Vulnerability Tsa:                       Not affected
Vulnerability Tsx async abort:           Not affected
Vulnerability Vmscape:                   Not affected
Details

Comparing HEAD and final-aggr-with-lazily-materialize-poc
--------------------
Benchmark clickbench_partitioned.json
--------------------
┏━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Query     ┃                                  HEAD ┃ final-aggr-with-lazily-materialize-poc ┃        Change ┃
┡━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ QQuery 0  │          1.24 / 3.99 ±5.41 / 14.82 ms │           1.21 / 3.99 ±5.48 / 14.94 ms │     no change │
│ QQuery 1  │        12.62 / 12.77 ±0.12 / 12.97 ms │         12.61 / 12.71 ±0.07 / 12.83 ms │     no change │
│ QQuery 2  │        35.52 / 35.85 ±0.28 / 36.25 ms │         35.35 / 35.54 ±0.24 / 35.99 ms │     no change │
│ QQuery 3  │        30.79 / 31.66 ±0.80 / 32.86 ms │         30.58 / 30.91 ±0.30 / 31.35 ms │     no change │
│ QQuery 4  │     225.67 / 227.74 ±1.55 / 229.68 ms │      188.67 / 191.68 ±2.14 / 194.14 ms │ +1.19x faster │
│ QQuery 5  │     271.73 / 273.90 ±1.67 / 275.72 ms │      269.61 / 273.50 ±3.30 / 279.26 ms │     no change │
│ QQuery 6  │           1.26 / 1.42 ±0.25 / 1.91 ms │            1.26 / 1.40 ±0.23 / 1.85 ms │     no change │
│ QQuery 7  │        13.71 / 13.91 ±0.12 / 14.09 ms │         13.68 / 13.84 ±0.10 / 13.95 ms │     no change │
│ QQuery 8  │     322.83 / 325.30 ±2.13 / 329.17 ms │      289.95 / 294.87 ±3.18 / 299.15 ms │ +1.10x faster │
│ QQuery 9  │    434.24 / 454.13 ±10.90 / 463.53 ms │     406.73 / 422.03 ±13.28 / 444.03 ms │ +1.08x faster │
│ QQuery 10 │        69.76 / 73.30 ±5.68 / 84.63 ms │         70.54 / 71.88 ±1.13 / 73.77 ms │     no change │
│ QQuery 11 │        81.81 / 83.14 ±1.15 / 84.70 ms │         81.19 / 83.05 ±1.48 / 85.70 ms │     no change │
│ QQuery 12 │     268.08 / 271.74 ±2.94 / 275.90 ms │      265.73 / 271.61 ±6.24 / 282.99 ms │     no change │
│ QQuery 13 │    368.85 / 380.96 ±12.65 / 398.50 ms │     344.62 / 372.83 ±14.84 / 384.01 ms │     no change │
│ QQuery 14 │     286.30 / 289.85 ±3.96 / 297.56 ms │      282.62 / 287.40 ±3.43 / 291.34 ms │     no change │
│ QQuery 15 │     269.89 / 280.44 ±7.25 / 287.83 ms │      234.39 / 240.81 ±4.86 / 247.54 ms │ +1.16x faster │
│ QQuery 16 │     611.91 / 617.42 ±3.55 / 621.56 ms │     591.76 / 606.20 ±11.82 / 618.88 ms │     no change │
│ QQuery 17 │     619.65 / 626.85 ±8.53 / 642.99 ms │     497.19 / 520.08 ±18.16 / 536.94 ms │ +1.21x faster │
│ QQuery 18 │  1277.07 / 1286.65 ±9.25 / 1302.07 ms │  1181.32 / 1229.51 ±51.84 / 1326.86 ms │     no change │
│ QQuery 19 │        27.60 / 30.18 ±4.35 / 38.87 ms │         27.83 / 27.92 ±0.11 / 28.13 ms │ +1.08x faster │
│ QQuery 20 │    517.73 / 525.90 ±11.14 / 547.42 ms │      519.75 / 533.17 ±9.20 / 547.65 ms │     no change │
│ QQuery 21 │     514.86 / 522.74 ±8.81 / 539.92 ms │      527.99 / 533.13 ±3.57 / 536.48 ms │     no change │
│ QQuery 22 │    989.78 / 994.54 ±4.01 / 1001.08 ms │    987.93 / 996.26 ±11.02 / 1017.92 ms │     no change │
│ QQuery 23 │ 3053.28 / 3074.51 ±21.03 / 3114.03 ms │  3052.14 / 3109.47 ±37.74 / 3161.02 ms │     no change │
│ QQuery 24 │       42.40 / 50.03 ±13.89 / 77.81 ms │         41.66 / 42.62 ±1.01 / 44.05 ms │ +1.17x faster │
│ QQuery 25 │     112.09 / 114.69 ±2.78 / 119.98 ms │      110.55 / 111.90 ±1.23 / 114.19 ms │     no change │
│ QQuery 26 │        42.11 / 42.76 ±0.74 / 44.11 ms │         42.07 / 42.80 ±0.90 / 44.44 ms │     no change │
│ QQuery 27 │     672.88 / 678.35 ±5.05 / 685.46 ms │     672.55 / 688.79 ±25.81 / 739.95 ms │     no change │
│ QQuery 28 │ 3016.52 / 3039.02 ±22.05 / 3081.08 ms │   3066.69 / 3075.62 ±8.96 / 3092.34 ms │     no change │
│ QQuery 29 │        40.34 / 40.56 ±0.15 / 40.70 ms │         40.41 / 42.55 ±4.08 / 50.71 ms │     no change │
│ QQuery 30 │    297.10 / 311.64 ±16.01 / 342.52 ms │     282.38 / 297.69 ±10.96 / 315.26 ms │     no change │
│ QQuery 31 │     278.13 / 289.13 ±5.68 / 294.45 ms │      253.64 / 259.08 ±5.13 / 266.97 ms │ +1.12x faster │
│ QQuery 32 │    899.22 / 922.18 ±13.91 / 942.91 ms │     703.75 / 730.84 ±26.52 / 769.01 ms │ +1.26x faster │
│ QQuery 33 │ 1447.29 / 1477.71 ±24.08 / 1521.36 ms │  1492.66 / 1544.97 ±57.25 / 1652.38 ms │     no change │
│ QQuery 34 │ 1490.42 / 1523.09 ±22.65 / 1553.16 ms │  1550.99 / 1641.24 ±89.91 / 1756.85 ms │  1.08x slower │
│ QQuery 35 │    273.98 / 299.97 ±36.81 / 372.97 ms │     249.99 / 277.18 ±24.86 / 311.38 ms │ +1.08x faster │
│ QQuery 36 │        65.26 / 73.40 ±8.34 / 88.20 ms │         67.31 / 75.60 ±6.42 / 84.14 ms │     no change │
│ QQuery 37 │        35.69 / 40.09 ±5.30 / 49.51 ms │         36.55 / 41.48 ±4.01 / 45.18 ms │     no change │
│ QQuery 38 │        41.76 / 45.32 ±2.38 / 48.33 ms │         43.16 / 48.04 ±5.21 / 57.69 ms │  1.06x slower │
│ QQuery 39 │     137.91 / 147.91 ±6.88 / 158.08 ms │      145.98 / 157.24 ±9.56 / 169.71 ms │  1.06x slower │
│ QQuery 40 │        13.67 / 15.61 ±2.85 / 21.29 ms │         14.75 / 17.46 ±4.59 / 26.62 ms │  1.12x slower │
│ QQuery 41 │        13.82 / 16.73 ±3.17 / 21.45 ms │         13.80 / 16.58 ±5.29 / 27.17 ms │     no change │
│ QQuery 42 │        13.11 / 15.24 ±3.99 / 23.22 ms │         13.06 / 15.09 ±3.56 / 22.19 ms │     no change │
└───────────┴───────────────────────────────────────┴────────────────────────────────────────┴───────────────┘
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━┓
┃ Benchmark Summary                                     ┃            ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━┩
│ Total Time (HEAD)                                     │ 19582.30ms │
│ Total Time (final-aggr-with-lazily-materialize-poc)   │ 19290.56ms │
│ Average Time (HEAD)                                   │   455.40ms │
│ Average Time (final-aggr-with-lazily-materialize-poc) │   448.62ms │
│ Queries Faster                                        │         10 │
│ Queries Slower                                        │          4 │
│ Queries with No Change                                │         29 │
│ Queries with Failure                                  │          0 │
└───────────────────────────────────────────────────────┴────────────┘

Resource Usage

clickbench_partitioned — base (merge-base)

Metric Value
Wall time 100.0s
Peak memory 11.7 GiB
Avg memory 4.2 GiB
CPU user 1009.6s
CPU sys 69.2s
Peak spill 0 B

clickbench_partitioned — branch

Metric Value
Wall time 100.0s
Peak memory 12.3 GiB
Avg memory 4.1 GiB
CPU user 950.5s
CPU sys 73.4s
Peak spill 0 B

File an issue against this benchmark runner

@Rachelint

Copy link
Copy Markdown
Contributor Author

run benchmarks clickbench_partitioned

@adriangbot

Copy link
Copy Markdown

🤖 Benchmark running (GKE) | trigger
Instance: c4a-highmem-16 (12 vCPU / 65 GiB) | Linux bench-c4950987650-1000-qwkgr 6.12.85+ #1 SMP Mon May 11 08:17:35 UTC 2026 aarch64 GNU/Linux

CPU Details (lscpu)
Architecture:                            aarch64
CPU op-mode(s):                          64-bit
Byte Order:                              Little Endian
CPU(s):                                  16
On-line CPU(s) list:                     0-15
Vendor ID:                               ARM
Model name:                              Neoverse-V2
Model:                                   1
Thread(s) per core:                      1
Core(s) per cluster:                     16
Socket(s):                               -
Cluster(s):                              1
Stepping:                                r0p1
BogoMIPS:                                2000.00
Flags:                                   fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm jscvt fcma lrcpc dcpop sha3 sm3 sm4 asimddp sha512 sve asimdfhm dit uscat ilrcpc flagm sb paca pacg dcpodp sve2 sveaes svepmull svebitperm svesha3 svesm4 flagm2 frint svei8mm svebf16 i8mm bf16 dgh rng bti
L1d cache:                               1 MiB (16 instances)
L1i cache:                               1 MiB (16 instances)
L2 cache:                                32 MiB (16 instances)
L3 cache:                                80 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; __user pointer sanitization
Vulnerability Spectre v2:                Mitigation; CSV2, BHB
Vulnerability Srbds:                     Not affected
Vulnerability Tsa:                       Not affected
Vulnerability Tsx async abort:           Not affected
Vulnerability Vmscape:                   Not affected

Comparing final-aggr-with-lazily-materialize-poc (611e4ff) to eaafba4 (merge-base) diff using: clickbench_partitioned
Results will be posted here when complete


File an issue against this benchmark runner

@adriangbot

Copy link
Copy Markdown

🤖 Benchmark completed (GKE) | trigger

Instance: c4a-highmem-16 (12 vCPU / 65 GiB)

CPU Details (lscpu)
Architecture:                            aarch64
CPU op-mode(s):                          64-bit
Byte Order:                              Little Endian
CPU(s):                                  16
On-line CPU(s) list:                     0-15
Vendor ID:                               ARM
Model name:                              Neoverse-V2
Model:                                   1
Thread(s) per core:                      1
Core(s) per cluster:                     16
Socket(s):                               -
Cluster(s):                              1
Stepping:                                r0p1
BogoMIPS:                                2000.00
Flags:                                   fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm jscvt fcma lrcpc dcpop sha3 sm3 sm4 asimddp sha512 sve asimdfhm dit uscat ilrcpc flagm sb paca pacg dcpodp sve2 sveaes svepmull svebitperm svesha3 svesm4 flagm2 frint svei8mm svebf16 i8mm bf16 dgh rng bti
L1d cache:                               1 MiB (16 instances)
L1i cache:                               1 MiB (16 instances)
L2 cache:                                32 MiB (16 instances)
L3 cache:                                80 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; __user pointer sanitization
Vulnerability Spectre v2:                Mitigation; CSV2, BHB
Vulnerability Srbds:                     Not affected
Vulnerability Tsa:                       Not affected
Vulnerability Tsx async abort:           Not affected
Vulnerability Vmscape:                   Not affected
Details

Comparing HEAD and final-aggr-with-lazily-materialize-poc
--------------------
Benchmark clickbench_partitioned.json
--------------------
┏━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Query     ┃                                   HEAD ┃ final-aggr-with-lazily-materialize-poc ┃        Change ┃
┡━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ QQuery 0  │           1.79 / 4.97 ±6.00 / 16.96 ms │           1.24 / 3.97 ±5.37 / 14.72 ms │ +1.25x faster │
│ QQuery 1  │         13.37 / 13.62 ±0.17 / 13.82 ms │         12.87 / 13.07 ±0.18 / 13.33 ms │     no change │
│ QQuery 2  │         37.14 / 37.41 ±0.33 / 38.04 ms │         36.41 / 36.56 ±0.19 / 36.93 ms │     no change │
│ QQuery 3  │         33.37 / 33.98 ±0.64 / 35.15 ms │         32.26 / 32.71 ±0.39 / 33.38 ms │     no change │
│ QQuery 4  │     231.03 / 266.51 ±24.40 / 303.73 ms │      213.52 / 220.64 ±4.30 / 226.02 ms │ +1.21x faster │
│ QQuery 5  │      274.21 / 278.89 ±4.01 / 283.83 ms │      302.00 / 307.38 ±4.10 / 311.49 ms │  1.10x slower │
│ QQuery 6  │            1.29 / 1.45 ±0.24 / 1.92 ms │            1.36 / 1.61 ±0.25 / 2.08 ms │  1.11x slower │
│ QQuery 7  │         13.63 / 13.78 ±0.11 / 13.91 ms │         15.02 / 17.24 ±4.00 / 25.23 ms │  1.25x slower │
│ QQuery 8  │      325.60 / 329.07 ±2.51 / 332.83 ms │      306.88 / 312.59 ±4.22 / 319.97 ms │ +1.05x faster │
│ QQuery 9  │      454.93 / 464.18 ±8.46 / 479.37 ms │     409.22 / 421.09 ±11.21 / 440.48 ms │ +1.10x faster │
│ QQuery 10 │         71.90 / 72.85 ±1.06 / 74.90 ms │         70.20 / 73.03 ±3.81 / 80.55 ms │     no change │
│ QQuery 11 │         82.58 / 83.21 ±0.92 / 85.02 ms │         82.21 / 83.08 ±0.69 / 83.78 ms │     no change │
│ QQuery 12 │     285.44 / 307.90 ±18.19 / 332.55 ms │      262.38 / 270.07 ±5.62 / 279.09 ms │ +1.14x faster │
│ QQuery 13 │     369.34 / 386.92 ±11.46 / 404.74 ms │      358.33 / 370.06 ±8.22 / 380.84 ms │     no change │
│ QQuery 14 │      282.89 / 286.61 ±2.64 / 290.45 ms │      288.66 / 291.67 ±3.10 / 296.64 ms │     no change │
│ QQuery 15 │      268.38 / 274.01 ±4.87 / 282.13 ms │     226.01 / 250.41 ±19.35 / 275.27 ms │ +1.09x faster │
│ QQuery 16 │     610.73 / 679.16 ±49.57 / 732.10 ms │     633.01 / 681.53 ±35.12 / 723.15 ms │     no change │
│ QQuery 17 │     627.36 / 651.61 ±20.83 / 683.50 ms │     501.34 / 527.36 ±17.28 / 546.64 ms │ +1.24x faster │
│ QQuery 18 │  1251.57 / 1275.95 ±19.16 / 1300.20 ms │  1189.98 / 1227.94 ±30.34 / 1272.01 ms │     no change │
│ QQuery 19 │         27.52 / 27.73 ±0.18 / 27.97 ms │         28.89 / 28.98 ±0.07 / 29.06 ms │     no change │
│ QQuery 20 │      534.43 / 548.01 ±9.81 / 559.14 ms │      519.55 / 529.60 ±5.88 / 537.14 ms │     no change │
│ QQuery 21 │      513.19 / 517.81 ±3.89 / 522.28 ms │      519.86 / 527.80 ±5.81 / 536.53 ms │     no change │
│ QQuery 22 │     991.62 / 996.43 ±3.78 / 1000.99 ms │   989.97 / 1030.62 ±27.81 / 1069.58 ms │     no change │
│ QQuery 23 │  3044.79 / 3146.22 ±77.38 / 3264.30 ms │  3032.39 / 3105.48 ±65.15 / 3207.39 ms │     no change │
│ QQuery 24 │         40.93 / 45.97 ±7.79 / 61.51 ms │         41.10 / 44.06 ±5.21 / 54.46 ms │     no change │
│ QQuery 25 │      111.49 / 116.38 ±5.77 / 127.37 ms │      111.01 / 115.53 ±4.38 / 123.82 ms │     no change │
│ QQuery 26 │         41.70 / 42.97 ±1.33 / 45.35 ms │         42.47 / 44.47 ±1.74 / 46.57 ms │     no change │
│ QQuery 27 │      666.54 / 677.85 ±9.43 / 690.49 ms │      672.06 / 681.03 ±7.09 / 690.06 ms │     no change │
│ QQuery 28 │  3051.74 / 3119.70 ±47.83 / 3190.22 ms │  3070.42 / 3148.03 ±86.97 / 3308.09 ms │     no change │
│ QQuery 29 │         40.44 / 41.40 ±0.83 / 42.77 ms │         40.49 / 48.24 ±8.31 / 58.56 ms │  1.17x slower │
│ QQuery 30 │      297.68 / 307.77 ±9.43 / 323.83 ms │     290.30 / 315.48 ±12.69 / 323.86 ms │     no change │
│ QQuery 31 │      316.06 / 328.35 ±9.69 / 340.89 ms │      284.45 / 289.10 ±3.57 / 295.36 ms │ +1.14x faster │
│ QQuery 32 │   944.73 / 1015.38 ±59.08 / 1104.21 ms │     699.61 / 722.23 ±19.19 / 751.80 ms │ +1.41x faster │
│ QQuery 33 │ 1445.52 / 1543.41 ±119.19 / 1763.13 ms │  1520.89 / 1600.21 ±84.92 / 1741.38 ms │     no change │
│ QQuery 34 │  1463.14 / 1503.65 ±33.44 / 1559.28 ms │  1597.30 / 1715.11 ±83.39 / 1816.28 ms │  1.14x slower │
│ QQuery 35 │     278.46 / 327.38 ±72.38 / 469.45 ms │     245.01 / 274.47 ±28.83 / 327.03 ms │ +1.19x faster │
│ QQuery 36 │         65.59 / 66.83 ±1.32 / 69.38 ms │         73.63 / 78.59 ±4.09 / 85.96 ms │  1.18x slower │
│ QQuery 37 │         35.22 / 36.23 ±1.81 / 39.84 ms │         35.57 / 40.91 ±3.14 / 44.88 ms │  1.13x slower │
│ QQuery 38 │         41.10 / 46.03 ±5.05 / 54.44 ms │         40.52 / 43.13 ±1.36 / 44.45 ms │ +1.07x faster │
│ QQuery 39 │     131.53 / 152.97 ±11.18 / 162.03 ms │      147.19 / 161.33 ±9.83 / 177.62 ms │  1.05x slower │
│ QQuery 40 │         13.90 / 14.15 ±0.25 / 14.60 ms │         14.49 / 15.01 ±0.49 / 15.81 ms │  1.06x slower │
│ QQuery 41 │         13.51 / 15.35 ±3.07 / 21.48 ms │         13.56 / 15.38 ±3.21 / 21.77 ms │     no change │
│ QQuery 42 │         12.84 / 15.36 ±3.02 / 20.57 ms │         13.20 / 13.52 ±0.18 / 13.70 ms │ +1.14x faster │
└───────────┴────────────────────────────────────────┴────────────────────────────────────────┴───────────────┘
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━┓
┃ Benchmark Summary                                     ┃            ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━┩
│ Total Time (HEAD)                                     │ 20115.38ms │
│ Total Time (final-aggr-with-lazily-materialize-poc)   │ 19730.32ms │
│ Average Time (HEAD)                                   │   467.80ms │
│ Average Time (final-aggr-with-lazily-materialize-poc) │   458.84ms │
│ Queries Faster                                        │         12 │
│ Queries Slower                                        │          9 │
│ Queries with No Change                                │         22 │
│ Queries with Failure                                  │          0 │
└───────────────────────────────────────────────────────┴────────────┘

Resource Usage

clickbench_partitioned — base (merge-base)

Metric Value
Wall time 105.0s
Peak memory 10.8 GiB
Avg memory 4.3 GiB
CPU user 1033.0s
CPU sys 71.0s
Peak spill 0 B

clickbench_partitioned — branch

Metric Value
Wall time 100.0s
Peak memory 12.3 GiB
Avg memory 4.1 GiB
CPU user 972.9s
CPU sys 77.1s
Peak spill 0 B

File an issue against this benchmark runner

@Rachelint Rachelint force-pushed the final-aggr-with-lazily-materialize-poc branch from e3ae29e to f800afb Compare July 12, 2026 14:43
@Rachelint

Copy link
Copy Markdown
Contributor Author

run benchmarks clickbench_partitioned

@adriangbot

Copy link
Copy Markdown

🤖 Benchmark running (GKE) | trigger
Instance: c4a-highmem-16 (12 vCPU / 65 GiB) | Linux bench-c4951637745-1011-tzp6z 6.12.85+ #1 SMP Mon May 11 08:17:35 UTC 2026 aarch64 GNU/Linux

CPU Details (lscpu)
Architecture:                            aarch64
CPU op-mode(s):                          64-bit
Byte Order:                              Little Endian
CPU(s):                                  16
On-line CPU(s) list:                     0-15
Vendor ID:                               ARM
Model name:                              Neoverse-V2
Model:                                   1
Thread(s) per core:                      1
Core(s) per cluster:                     16
Socket(s):                               -
Cluster(s):                              1
Stepping:                                r0p1
BogoMIPS:                                2000.00
Flags:                                   fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm jscvt fcma lrcpc dcpop sha3 sm3 sm4 asimddp sha512 sve asimdfhm dit uscat ilrcpc flagm sb paca pacg dcpodp sve2 sveaes svepmull svebitperm svesha3 svesm4 flagm2 frint svei8mm svebf16 i8mm bf16 dgh rng bti
L1d cache:                               1 MiB (16 instances)
L1i cache:                               1 MiB (16 instances)
L2 cache:                                32 MiB (16 instances)
L3 cache:                                80 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; __user pointer sanitization
Vulnerability Spectre v2:                Mitigation; CSV2, BHB
Vulnerability Srbds:                     Not affected
Vulnerability Tsa:                       Not affected
Vulnerability Tsx async abort:           Not affected
Vulnerability Vmscape:                   Not affected

Comparing final-aggr-with-lazily-materialize-poc (8a09547) to eaafba4 (merge-base) diff using: clickbench_partitioned
Results will be posted here when complete


File an issue against this benchmark runner

@adriangbot

Copy link
Copy Markdown

🤖 Benchmark completed (GKE) | trigger

Instance: c4a-highmem-16 (12 vCPU / 65 GiB)

CPU Details (lscpu)
Architecture:                            aarch64
CPU op-mode(s):                          64-bit
Byte Order:                              Little Endian
CPU(s):                                  16
On-line CPU(s) list:                     0-15
Vendor ID:                               ARM
Model name:                              Neoverse-V2
Model:                                   1
Thread(s) per core:                      1
Core(s) per cluster:                     16
Socket(s):                               -
Cluster(s):                              1
Stepping:                                r0p1
BogoMIPS:                                2000.00
Flags:                                   fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm jscvt fcma lrcpc dcpop sha3 sm3 sm4 asimddp sha512 sve asimdfhm dit uscat ilrcpc flagm sb paca pacg dcpodp sve2 sveaes svepmull svebitperm svesha3 svesm4 flagm2 frint svei8mm svebf16 i8mm bf16 dgh rng bti
L1d cache:                               1 MiB (16 instances)
L1i cache:                               1 MiB (16 instances)
L2 cache:                                32 MiB (16 instances)
L3 cache:                                80 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; __user pointer sanitization
Vulnerability Spectre v2:                Mitigation; CSV2, BHB
Vulnerability Srbds:                     Not affected
Vulnerability Tsa:                       Not affected
Vulnerability Tsx async abort:           Not affected
Vulnerability Vmscape:                   Not affected
Details

Comparing HEAD and final-aggr-with-lazily-materialize-poc
--------------------
Benchmark clickbench_partitioned.json
--------------------
┏━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Query     ┃                                  HEAD ┃ final-aggr-with-lazily-materialize-poc ┃        Change ┃
┡━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ QQuery 0  │          1.21 / 3.90 ±5.32 / 14.53 ms │           1.23 / 3.93 ±5.35 / 14.62 ms │     no change │
│ QQuery 1  │        12.47 / 12.78 ±0.18 / 13.01 ms │         12.60 / 12.73 ±0.11 / 12.85 ms │     no change │
│ QQuery 2  │        35.74 / 36.06 ±0.27 / 36.39 ms │         35.54 / 35.85 ±0.22 / 36.14 ms │     no change │
│ QQuery 3  │        31.63 / 31.88 ±0.38 / 32.63 ms │         30.23 / 30.72 ±0.38 / 31.34 ms │     no change │
│ QQuery 4  │     220.69 / 223.48 ±3.18 / 229.24 ms │      189.05 / 191.33 ±1.84 / 194.35 ms │ +1.17x faster │
│ QQuery 5  │     270.44 / 272.54 ±1.89 / 274.84 ms │      264.25 / 269.43 ±3.30 / 273.85 ms │     no change │
│ QQuery 6  │           1.28 / 1.42 ±0.22 / 1.84 ms │            1.28 / 1.43 ±0.22 / 1.86 ms │     no change │
│ QQuery 7  │        13.81 / 13.89 ±0.05 / 13.95 ms │         13.58 / 13.75 ±0.12 / 13.92 ms │     no change │
│ QQuery 8  │     314.31 / 320.38 ±3.28 / 323.12 ms │      289.78 / 293.90 ±4.39 / 302.00 ms │ +1.09x faster │
│ QQuery 9  │     448.53 / 456.68 ±6.89 / 467.91 ms │     404.94 / 418.76 ±13.20 / 438.50 ms │ +1.09x faster │
│ QQuery 10 │        72.35 / 73.41 ±0.66 / 74.30 ms │         73.26 / 75.61 ±2.04 / 78.75 ms │     no change │
│ QQuery 11 │        81.84 / 83.01 ±0.86 / 84.17 ms │         85.94 / 86.28 ±0.27 / 86.67 ms │     no change │
│ QQuery 12 │     264.74 / 272.44 ±4.90 / 279.64 ms │      261.76 / 269.49 ±8.05 / 284.19 ms │     no change │
│ QQuery 13 │    362.97 / 379.78 ±21.57 / 421.41 ms │      345.96 / 355.24 ±5.38 / 361.89 ms │ +1.07x faster │
│ QQuery 14 │     280.03 / 285.50 ±6.36 / 297.33 ms │      286.79 / 289.93 ±3.53 / 294.94 ms │     no change │
│ QQuery 15 │     271.29 / 274.72 ±4.21 / 282.69 ms │     226.52 / 252.30 ±28.36 / 305.25 ms │ +1.09x faster │
│ QQuery 16 │     606.58 / 617.34 ±9.90 / 631.76 ms │     580.42 / 596.88 ±11.52 / 612.29 ms │     no change │
│ QQuery 17 │     605.68 / 615.53 ±7.03 / 625.18 ms │     491.52 / 507.56 ±10.70 / 520.28 ms │ +1.21x faster │
│ QQuery 18 │ 1229.94 / 1262.96 ±20.85 / 1287.52 ms │  1162.45 / 1183.71 ±13.50 / 1202.13 ms │ +1.07x faster │
│ QQuery 19 │        27.69 / 27.98 ±0.18 / 28.22 ms │       27.64 / 52.22 ±34.20 / 115.32 ms │  1.87x slower │
│ QQuery 20 │     513.72 / 520.11 ±8.97 / 537.69 ms │      516.29 / 523.21 ±7.02 / 535.32 ms │     no change │
│ QQuery 21 │     510.78 / 514.25 ±3.42 / 518.39 ms │      511.49 / 526.63 ±9.15 / 537.77 ms │     no change │
│ QQuery 22 │     974.85 / 981.51 ±8.28 / 997.46 ms │     985.06 / 993.76 ±6.08 / 1001.99 ms │     no change │
│ QQuery 23 │ 3011.12 / 3068.04 ±33.60 / 3116.30 ms │  3049.36 / 3072.58 ±27.92 / 3127.21 ms │     no change │
│ QQuery 24 │        41.76 / 42.15 ±0.41 / 42.89 ms │         41.46 / 42.41 ±0.61 / 43.03 ms │     no change │
│ QQuery 25 │     112.91 / 118.93 ±9.60 / 137.95 ms │      112.64 / 115.67 ±2.57 / 120.27 ms │     no change │
│ QQuery 26 │        42.08 / 44.22 ±3.82 / 51.85 ms │         42.03 / 44.12 ±2.46 / 48.90 ms │     no change │
│ QQuery 27 │     667.71 / 674.58 ±4.69 / 680.61 ms │      665.22 / 677.51 ±9.83 / 690.12 ms │     no change │
│ QQuery 28 │ 3019.36 / 3041.35 ±11.83 / 3053.22 ms │  3061.11 / 3080.64 ±26.96 / 3133.77 ms │     no change │
│ QQuery 29 │        40.25 / 40.65 ±0.27 / 41.07 ms │         40.41 / 42.23 ±3.39 / 49.01 ms │     no change │
│ QQuery 30 │     297.55 / 306.57 ±9.52 / 323.91 ms │      283.67 / 290.26 ±8.39 / 306.72 ms │ +1.06x faster │
│ QQuery 31 │    277.88 / 305.46 ±30.83 / 364.49 ms │      258.78 / 261.49 ±2.95 / 266.73 ms │ +1.17x faster │
│ QQuery 32 │    921.64 / 943.11 ±22.67 / 976.60 ms │     677.11 / 714.90 ±30.98 / 758.56 ms │ +1.32x faster │
│ QQuery 33 │ 1444.15 / 1460.71 ±24.56 / 1508.85 ms │  1526.76 / 1539.96 ±11.50 / 1553.57 ms │  1.05x slower │
│ QQuery 34 │ 1452.19 / 1480.14 ±14.71 / 1493.15 ms │  1559.22 / 1583.34 ±31.72 / 1645.63 ms │  1.07x slower │
│ QQuery 35 │    269.54 / 311.75 ±48.10 / 372.88 ms │     243.58 / 284.18 ±42.56 / 343.92 ms │ +1.10x faster │
│ QQuery 36 │        63.25 / 69.82 ±5.53 / 76.18 ms │         68.45 / 76.86 ±7.07 / 88.68 ms │  1.10x slower │
│ QQuery 37 │        35.27 / 36.90 ±1.73 / 39.92 ms │         35.16 / 38.14 ±2.60 / 42.58 ms │     no change │
│ QQuery 38 │        40.06 / 42.86 ±2.05 / 46.14 ms │         41.07 / 43.67 ±3.13 / 49.75 ms │     no change │
│ QQuery 39 │    134.98 / 151.99 ±13.05 / 173.57 ms │     146.88 / 163.93 ±11.36 / 178.93 ms │  1.08x slower │
│ QQuery 40 │        13.86 / 14.40 ±0.59 / 15.33 ms │         14.42 / 15.38 ±0.94 / 16.89 ms │  1.07x slower │
│ QQuery 41 │        13.40 / 13.73 ±0.39 / 14.49 ms │         13.47 / 13.58 ±0.08 / 13.69 ms │     no change │
│ QQuery 42 │        12.84 / 13.02 ±0.12 / 13.14 ms │         12.81 / 15.60 ±5.36 / 26.32 ms │  1.20x slower │
└───────────┴───────────────────────────────────────┴────────────────────────────────────────┴───────────────┘
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━┓
┃ Benchmark Summary                                     ┃            ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━┩
│ Total Time (HEAD)                                     │ 19461.93ms │
│ Total Time (final-aggr-with-lazily-materialize-poc)   │ 19101.13ms │
│ Average Time (HEAD)                                   │   452.60ms │
│ Average Time (final-aggr-with-lazily-materialize-poc) │   444.21ms │
│ Queries Faster                                        │         11 │
│ Queries Slower                                        │          7 │
│ Queries with No Change                                │         25 │
│ Queries with Failure                                  │          0 │
└───────────────────────────────────────────────────────┴────────────┘

Resource Usage

clickbench_partitioned — base (merge-base)

Metric Value
Wall time 100.0s
Peak memory 10.9 GiB
Avg memory 4.4 GiB
CPU user 1002.3s
CPU sys 66.1s
Peak spill 0 B

clickbench_partitioned — branch

Metric Value
Wall time 100.0s
Peak memory 12.7 GiB
Avg memory 4.3 GiB
CPU user 945.3s
CPU sys 70.1s
Peak spill 0 B

File an issue against this benchmark runner

@Rachelint

Copy link
Copy Markdown
Contributor Author

run benchmarks clickbench_partitioned

@adriangbot

Copy link
Copy Markdown

🤖 Benchmark running (GKE) | trigger
Instance: c4a-highmem-16 (12 vCPU / 65 GiB) | Linux bench-c4951748836-1012-xdp26 6.12.85+ #1 SMP Mon May 11 08:17:35 UTC 2026 aarch64 GNU/Linux

CPU Details (lscpu)
Architecture:                            aarch64
CPU op-mode(s):                          64-bit
Byte Order:                              Little Endian
CPU(s):                                  16
On-line CPU(s) list:                     0-15
Vendor ID:                               ARM
Model name:                              Neoverse-V2
Model:                                   1
Thread(s) per core:                      1
Core(s) per cluster:                     16
Socket(s):                               -
Cluster(s):                              1
Stepping:                                r0p1
BogoMIPS:                                2000.00
Flags:                                   fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm jscvt fcma lrcpc dcpop sha3 sm3 sm4 asimddp sha512 sve asimdfhm dit uscat ilrcpc flagm sb paca pacg dcpodp sve2 sveaes svepmull svebitperm svesha3 svesm4 flagm2 frint svei8mm svebf16 i8mm bf16 dgh rng bti
L1d cache:                               1 MiB (16 instances)
L1i cache:                               1 MiB (16 instances)
L2 cache:                                32 MiB (16 instances)
L3 cache:                                80 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; __user pointer sanitization
Vulnerability Spectre v2:                Mitigation; CSV2, BHB
Vulnerability Srbds:                     Not affected
Vulnerability Tsa:                       Not affected
Vulnerability Tsx async abort:           Not affected
Vulnerability Vmscape:                   Not affected

Comparing final-aggr-with-lazily-materialize-poc (8a09547) to eaafba4 (merge-base) diff using: clickbench_partitioned
Results will be posted here when complete


File an issue against this benchmark runner

@adriangbot

Copy link
Copy Markdown

🤖 Benchmark completed (GKE) | trigger

Instance: c4a-highmem-16 (12 vCPU / 65 GiB)

CPU Details (lscpu)
Architecture:                            aarch64
CPU op-mode(s):                          64-bit
Byte Order:                              Little Endian
CPU(s):                                  16
On-line CPU(s) list:                     0-15
Vendor ID:                               ARM
Model name:                              Neoverse-V2
Model:                                   1
Thread(s) per core:                      1
Core(s) per cluster:                     16
Socket(s):                               -
Cluster(s):                              1
Stepping:                                r0p1
BogoMIPS:                                2000.00
Flags:                                   fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm jscvt fcma lrcpc dcpop sha3 sm3 sm4 asimddp sha512 sve asimdfhm dit uscat ilrcpc flagm sb paca pacg dcpodp sve2 sveaes svepmull svebitperm svesha3 svesm4 flagm2 frint svei8mm svebf16 i8mm bf16 dgh rng bti
L1d cache:                               1 MiB (16 instances)
L1i cache:                               1 MiB (16 instances)
L2 cache:                                32 MiB (16 instances)
L3 cache:                                80 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; __user pointer sanitization
Vulnerability Spectre v2:                Mitigation; CSV2, BHB
Vulnerability Srbds:                     Not affected
Vulnerability Tsa:                       Not affected
Vulnerability Tsx async abort:           Not affected
Vulnerability Vmscape:                   Not affected
Details

Comparing HEAD and final-aggr-with-lazily-materialize-poc
--------------------
Benchmark clickbench_partitioned.json
--------------------
┏━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Query     ┃                                  HEAD ┃ final-aggr-with-lazily-materialize-poc ┃        Change ┃
┡━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ QQuery 0  │          1.25 / 4.17 ±5.69 / 15.55 ms │           1.33 / 4.34 ±5.81 / 15.95 ms │     no change │
│ QQuery 1  │        12.60 / 13.04 ±0.24 / 13.30 ms │         13.18 / 13.55 ±0.21 / 13.77 ms │     no change │
│ QQuery 2  │        36.02 / 36.52 ±0.40 / 37.05 ms │         36.57 / 36.79 ±0.33 / 37.44 ms │     no change │
│ QQuery 3  │        30.82 / 31.50 ±0.65 / 32.61 ms │         32.14 / 32.45 ±0.28 / 32.91 ms │     no change │
│ QQuery 4  │     222.01 / 230.76 ±6.34 / 240.11 ms │      220.43 / 224.13 ±2.48 / 227.26 ms │     no change │
│ QQuery 5  │     268.47 / 270.84 ±1.67 / 273.65 ms │      276.83 / 289.00 ±8.91 / 304.12 ms │  1.07x slower │
│ QQuery 6  │           1.25 / 1.41 ±0.23 / 1.86 ms │            1.29 / 1.45 ±0.24 / 1.91 ms │     no change │
│ QQuery 7  │        13.35 / 13.72 ±0.21 / 14.01 ms │         14.51 / 14.75 ±0.30 / 15.33 ms │  1.08x slower │
│ QQuery 8  │     316.14 / 320.37 ±2.27 / 322.33 ms │      294.41 / 296.40 ±2.89 / 302.03 ms │ +1.08x faster │
│ QQuery 9  │     446.85 / 454.95 ±6.20 / 463.84 ms │     406.65 / 421.25 ±10.81 / 433.52 ms │ +1.08x faster │
│ QQuery 10 │        71.92 / 72.27 ±0.21 / 72.58 ms │         73.68 / 74.91 ±1.18 / 77.16 ms │     no change │
│ QQuery 11 │        82.84 / 83.81 ±0.71 / 84.63 ms │         84.09 / 85.20 ±0.92 / 86.87 ms │     no change │
│ QQuery 12 │     266.19 / 272.23 ±4.27 / 277.81 ms │      263.19 / 269.50 ±4.50 / 275.11 ms │     no change │
│ QQuery 13 │     408.14 / 419.52 ±9.26 / 431.89 ms │     353.90 / 377.75 ±15.06 / 397.42 ms │ +1.11x faster │
│ QQuery 14 │    294.79 / 311.67 ±12.00 / 324.91 ms │     287.20 / 295.00 ±11.56 / 317.57 ms │ +1.06x faster │
│ QQuery 15 │     267.78 / 279.29 ±7.47 / 286.13 ms │      227.46 / 235.44 ±5.77 / 243.38 ms │ +1.19x faster │
│ QQuery 16 │     606.30 / 614.12 ±5.92 / 623.50 ms │     598.45 / 607.51 ±12.47 / 632.23 ms │     no change │
│ QQuery 17 │     612.42 / 619.71 ±6.47 / 629.85 ms │     551.97 / 570.30 ±15.55 / 592.75 ms │ +1.09x faster │
│ QQuery 18 │ 1253.83 / 1278.16 ±22.76 / 1318.01 ms │   1218.87 / 1227.28 ±7.26 / 1238.23 ms │     no change │
│ QQuery 19 │        27.75 / 31.11 ±4.49 / 39.74 ms │         27.81 / 28.06 ±0.25 / 28.48 ms │ +1.11x faster │
│ QQuery 20 │    523.73 / 541.44 ±10.45 / 556.53 ms │      518.01 / 526.72 ±6.95 / 536.84 ms │     no change │
│ QQuery 21 │    515.42 / 526.90 ±13.31 / 552.32 ms │      523.16 / 533.38 ±7.56 / 543.66 ms │     no change │
│ QQuery 22 │    985.51 / 994.68 ±6.22 / 1002.03 ms │   997.85 / 1043.22 ±28.95 / 1088.44 ms │     no change │
│ QQuery 23 │ 3054.74 / 3126.54 ±95.74 / 3315.32 ms │  3086.09 / 3178.35 ±73.33 / 3289.04 ms │     no change │
│ QQuery 24 │        41.41 / 45.72 ±7.86 / 61.42 ms │         41.10 / 41.75 ±0.61 / 42.85 ms │ +1.10x faster │
│ QQuery 25 │     112.56 / 116.54 ±7.01 / 130.49 ms │      113.17 / 115.92 ±2.41 / 120.12 ms │     no change │
│ QQuery 26 │        41.56 / 42.84 ±1.69 / 45.82 ms │         42.06 / 44.26 ±2.60 / 49.18 ms │     no change │
│ QQuery 27 │    668.42 / 682.13 ±12.50 / 701.06 ms │     668.98 / 684.22 ±15.39 / 711.52 ms │     no change │
│ QQuery 28 │ 3016.56 / 3080.58 ±64.20 / 3166.81 ms │  3067.85 / 3116.86 ±52.73 / 3214.43 ms │     no change │
│ QQuery 29 │        42.07 / 44.98 ±4.89 / 54.69 ms │         40.54 / 45.39 ±7.84 / 60.81 ms │     no change │
│ QQuery 30 │    299.60 / 321.20 ±16.16 / 349.08 ms │      285.09 / 292.65 ±3.96 / 295.95 ms │ +1.10x faster │
│ QQuery 31 │     291.99 / 297.89 ±5.25 / 305.77 ms │      261.52 / 269.05 ±4.94 / 276.64 ms │ +1.11x faster │
│ QQuery 32 │   917.72 / 967.81 ±30.10 / 1010.57 ms │     722.39 / 795.25 ±49.30 / 850.86 ms │ +1.22x faster │
│ QQuery 33 │ 1410.39 / 1515.10 ±90.91 / 1666.74 ms │  1544.68 / 1629.75 ±65.40 / 1741.82 ms │  1.08x slower │
│ QQuery 34 │ 1469.37 / 1551.52 ±78.85 / 1698.51 ms │ 1566.35 / 1691.67 ±120.78 / 1885.04 ms │  1.09x slower │
│ QQuery 35 │    271.06 / 322.82 ±79.19 / 479.95 ms │     251.48 / 299.91 ±54.92 / 392.76 ms │ +1.08x faster │
│ QQuery 36 │        67.89 / 75.96 ±7.04 / 87.33 ms │         68.30 / 74.05 ±4.23 / 79.82 ms │     no change │
│ QQuery 37 │       35.56 / 43.28 ±11.12 / 65.08 ms │         35.59 / 38.56 ±3.00 / 42.91 ms │ +1.12x faster │
│ QQuery 38 │        40.41 / 43.48 ±3.23 / 49.55 ms │         40.77 / 45.89 ±4.95 / 51.94 ms │  1.06x slower │
│ QQuery 39 │     141.89 / 148.42 ±4.31 / 154.51 ms │      144.63 / 154.21 ±8.74 / 169.63 ms │     no change │
│ QQuery 40 │        13.97 / 14.79 ±1.05 / 16.69 ms │         14.35 / 19.75 ±8.08 / 35.46 ms │  1.34x slower │
│ QQuery 41 │        13.27 / 13.60 ±0.24 / 13.91 ms │         14.34 / 16.29 ±3.11 / 22.49 ms │  1.20x slower │
│ QQuery 42 │        13.05 / 15.10 ±3.74 / 22.58 ms │         13.23 / 13.45 ±0.12 / 13.59 ms │ +1.12x faster │
└───────────┴───────────────────────────────────────┴────────────────────────────────────────┴───────────────┘
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━┓
┃ Benchmark Summary                                     ┃            ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━┩
│ Total Time (HEAD)                                     │ 19892.46ms │
│ Total Time (final-aggr-with-lazily-materialize-poc)   │ 19775.65ms │
│ Average Time (HEAD)                                   │   462.62ms │
│ Average Time (final-aggr-with-lazily-materialize-poc) │   459.90ms │
│ Queries Faster                                        │         14 │
│ Queries Slower                                        │          7 │
│ Queries with No Change                                │         22 │
│ Queries with Failure                                  │          0 │
└───────────────────────────────────────────────────────┴────────────┘

Resource Usage

clickbench_partitioned — base (merge-base)

Metric Value
Wall time 100.0s
Peak memory 11.8 GiB
Avg memory 4.4 GiB
CPU user 1023.0s
CPU sys 69.3s
Peak spill 0 B

clickbench_partitioned — branch

Metric Value
Wall time 100.0s
Peak memory 12.4 GiB
Avg memory 4.6 GiB
CPU user 972.6s
CPU sys 77.9s
Peak spill 0 B

File an issue against this benchmark runner

@Rachelint

Copy link
Copy Markdown
Contributor Author

run benchmarks clickbench_partitioned

@adriangbot

Copy link
Copy Markdown

🤖 Benchmark running (GKE) | trigger
Instance: c4a-highmem-16 (12 vCPU / 65 GiB) | Linux bench-c4951838757-1016-wcfb9 6.12.85+ #1 SMP Mon May 11 08:17:35 UTC 2026 aarch64 GNU/Linux

CPU Details (lscpu)
Architecture:                            aarch64
CPU op-mode(s):                          64-bit
Byte Order:                              Little Endian
CPU(s):                                  16
On-line CPU(s) list:                     0-15
Vendor ID:                               ARM
Model name:                              Neoverse-V2
Model:                                   1
Thread(s) per core:                      1
Core(s) per cluster:                     16
Socket(s):                               -
Cluster(s):                              1
Stepping:                                r0p1
BogoMIPS:                                2000.00
Flags:                                   fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm jscvt fcma lrcpc dcpop sha3 sm3 sm4 asimddp sha512 sve asimdfhm dit uscat ilrcpc flagm sb paca pacg dcpodp sve2 sveaes svepmull svebitperm svesha3 svesm4 flagm2 frint svei8mm svebf16 i8mm bf16 dgh rng bti
L1d cache:                               1 MiB (16 instances)
L1i cache:                               1 MiB (16 instances)
L2 cache:                                32 MiB (16 instances)
L3 cache:                                80 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; __user pointer sanitization
Vulnerability Spectre v2:                Mitigation; CSV2, BHB
Vulnerability Srbds:                     Not affected
Vulnerability Tsa:                       Not affected
Vulnerability Tsx async abort:           Not affected
Vulnerability Vmscape:                   Not affected

Comparing final-aggr-with-lazily-materialize-poc (8a09547) to eaafba4 (merge-base) diff using: clickbench_partitioned
Results will be posted here when complete


File an issue against this benchmark runner

@adriangbot

Copy link
Copy Markdown

🤖 Benchmark completed (GKE) | trigger

Instance: c4a-highmem-16 (12 vCPU / 65 GiB)

CPU Details (lscpu)
Architecture:                            aarch64
CPU op-mode(s):                          64-bit
Byte Order:                              Little Endian
CPU(s):                                  16
On-line CPU(s) list:                     0-15
Vendor ID:                               ARM
Model name:                              Neoverse-V2
Model:                                   1
Thread(s) per core:                      1
Core(s) per cluster:                     16
Socket(s):                               -
Cluster(s):                              1
Stepping:                                r0p1
BogoMIPS:                                2000.00
Flags:                                   fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm jscvt fcma lrcpc dcpop sha3 sm3 sm4 asimddp sha512 sve asimdfhm dit uscat ilrcpc flagm sb paca pacg dcpodp sve2 sveaes svepmull svebitperm svesha3 svesm4 flagm2 frint svei8mm svebf16 i8mm bf16 dgh rng bti
L1d cache:                               1 MiB (16 instances)
L1i cache:                               1 MiB (16 instances)
L2 cache:                                32 MiB (16 instances)
L3 cache:                                80 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; __user pointer sanitization
Vulnerability Spectre v2:                Mitigation; CSV2, BHB
Vulnerability Srbds:                     Not affected
Vulnerability Tsa:                       Not affected
Vulnerability Tsx async abort:           Not affected
Vulnerability Vmscape:                   Not affected
Details

Comparing HEAD and final-aggr-with-lazily-materialize-poc
--------------------
Benchmark clickbench_partitioned.json
--------------------
┏━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Query     ┃                                  HEAD ┃ final-aggr-with-lazily-materialize-poc ┃        Change ┃
┡━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ QQuery 0  │          1.23 / 3.98 ±5.40 / 14.79 ms │           1.23 / 3.94 ±5.36 / 14.66 ms │     no change │
│ QQuery 1  │        12.48 / 12.79 ±0.17 / 12.98 ms │         12.45 / 12.83 ±0.27 / 13.11 ms │     no change │
│ QQuery 2  │        35.29 / 35.70 ±0.34 / 36.14 ms │         35.84 / 36.27 ±0.32 / 36.71 ms │     no change │
│ QQuery 3  │        30.24 / 31.00 ±0.71 / 32.29 ms │         30.98 / 31.42 ±0.28 / 31.71 ms │     no change │
│ QQuery 4  │     219.78 / 223.04 ±1.80 / 224.88 ms │      188.34 / 190.52 ±2.25 / 194.56 ms │ +1.17x faster │
│ QQuery 5  │     269.73 / 273.34 ±3.03 / 278.92 ms │      268.62 / 272.59 ±3.39 / 277.54 ms │     no change │
│ QQuery 6  │           1.26 / 1.41 ±0.23 / 1.86 ms │            1.27 / 1.42 ±0.23 / 1.88 ms │     no change │
│ QQuery 7  │        13.54 / 13.63 ±0.09 / 13.79 ms │         13.81 / 14.01 ±0.17 / 14.32 ms │     no change │
│ QQuery 8  │     318.26 / 322.25 ±2.08 / 324.07 ms │      289.04 / 292.52 ±2.41 / 295.34 ms │ +1.10x faster │
│ QQuery 9  │     449.55 / 460.53 ±7.79 / 470.90 ms │     456.68 / 478.69 ±14.34 / 499.05 ms │     no change │
│ QQuery 10 │        70.03 / 71.37 ±0.90 / 72.83 ms │         74.55 / 75.26 ±0.66 / 76.08 ms │  1.05x slower │
│ QQuery 11 │        81.68 / 84.77 ±3.52 / 90.08 ms │        86.58 / 94.57 ±9.49 / 110.89 ms │  1.12x slower │
│ QQuery 12 │     305.88 / 308.75 ±2.41 / 313.18 ms │      265.38 / 270.60 ±3.97 / 277.66 ms │ +1.14x faster │
│ QQuery 13 │    414.87 / 424.76 ±14.27 / 453.06 ms │     351.02 / 364.37 ±12.55 / 379.90 ms │ +1.17x faster │
│ QQuery 14 │     319.13 / 322.67 ±2.28 / 324.99 ms │      284.16 / 289.41 ±4.17 / 294.36 ms │ +1.11x faster │
│ QQuery 15 │     321.48 / 329.92 ±7.47 / 341.25 ms │      233.84 / 238.62 ±2.80 / 241.43 ms │ +1.38x faster │
│ QQuery 16 │    618.79 / 649.14 ±30.32 / 700.92 ms │      592.92 / 601.97 ±9.35 / 618.89 ms │ +1.08x faster │
│ QQuery 17 │     608.12 / 618.69 ±6.62 / 625.90 ms │     497.59 / 510.80 ±11.00 / 527.50 ms │ +1.21x faster │
│ QQuery 18 │ 1293.33 / 1324.47 ±35.01 / 1382.69 ms │  1177.01 / 1275.03 ±98.87 / 1419.72 ms │     no change │
│ QQuery 19 │       27.68 / 35.42 ±14.94 / 65.31 ms │         30.54 / 30.68 ±0.16 / 30.98 ms │ +1.15x faster │
│ QQuery 20 │     518.40 / 523.78 ±7.14 / 537.72 ms │      535.58 / 544.56 ±8.55 / 560.82 ms │     no change │
│ QQuery 21 │     514.32 / 519.75 ±4.73 / 528.11 ms │     547.34 / 557.47 ±12.27 / 580.85 ms │  1.07x slower │
│ QQuery 22 │  997.30 / 1029.44 ±20.11 / 1050.70 ms │   997.46 / 1015.10 ±14.57 / 1040.88 ms │     no change │
│ QQuery 23 │ 3053.73 / 3125.80 ±47.10 / 3189.18 ms │  3090.70 / 3133.43 ±44.77 / 3209.59 ms │     no change │
│ QQuery 24 │        41.54 / 41.93 ±0.41 / 42.70 ms │         43.11 / 49.36 ±8.68 / 66.01 ms │  1.18x slower │
│ QQuery 25 │     111.78 / 117.82 ±9.17 / 136.06 ms │      112.87 / 113.97 ±0.72 / 115.10 ms │     no change │
│ QQuery 26 │        41.82 / 42.69 ±1.01 / 44.64 ms │         43.55 / 46.90 ±3.09 / 51.73 ms │  1.10x slower │
│ QQuery 27 │     666.84 / 675.00 ±7.51 / 688.08 ms │     675.56 / 699.50 ±15.26 / 722.98 ms │     no change │
│ QQuery 28 │ 3014.06 / 3100.98 ±85.18 / 3208.14 ms │  3075.02 / 3119.05 ±48.07 / 3200.16 ms │     no change │
│ QQuery 29 │       42.45 / 52.29 ±16.26 / 84.68 ms │         40.39 / 49.00 ±9.76 / 62.85 ms │ +1.07x faster │
│ QQuery 30 │     338.02 / 344.85 ±6.18 / 353.14 ms │      283.94 / 296.38 ±9.58 / 309.87 ms │ +1.16x faster │
│ QQuery 31 │    278.58 / 301.28 ±12.20 / 312.08 ms │     258.82 / 270.61 ±10.02 / 288.01 ms │ +1.11x faster │
│ QQuery 32 │  952.65 / 1003.84 ±55.27 / 1093.05 ms │     683.31 / 749.89 ±91.96 / 929.27 ms │ +1.34x faster │
│ QQuery 33 │ 1441.48 / 1477.75 ±36.41 / 1544.07 ms │ 1518.62 / 1714.01 ±154.76 / 1908.83 ms │  1.16x slower │
│ QQuery 34 │ 1474.67 / 1519.48 ±34.66 / 1567.33 ms │ 1653.34 / 1805.79 ±169.82 / 2117.45 ms │  1.19x slower │
│ QQuery 35 │    304.83 / 342.21 ±28.95 / 390.29 ms │     257.00 / 287.04 ±25.38 / 325.97 ms │ +1.19x faster │
│ QQuery 36 │        82.00 / 88.16 ±6.08 / 96.04 ms │         69.52 / 80.96 ±7.26 / 88.88 ms │ +1.09x faster │
│ QQuery 37 │        35.50 / 40.14 ±3.15 / 45.39 ms │         36.75 / 39.01 ±3.23 / 45.42 ms │     no change │
│ QQuery 38 │        41.83 / 47.07 ±3.02 / 50.65 ms │         42.12 / 48.27 ±3.72 / 52.91 ms │     no change │
│ QQuery 39 │     158.15 / 160.02 ±1.37 / 161.77 ms │      145.49 / 152.08 ±4.24 / 157.15 ms │     no change │
│ QQuery 40 │        13.90 / 15.16 ±1.63 / 18.26 ms │         14.06 / 16.43 ±2.78 / 21.83 ms │  1.08x slower │
│ QQuery 41 │        13.51 / 15.95 ±4.35 / 24.64 ms │         13.88 / 17.17 ±3.77 / 22.03 ms │  1.08x slower │
│ QQuery 42 │        12.85 / 13.16 ±0.23 / 13.51 ms │         13.18 / 15.26 ±3.52 / 22.29 ms │  1.16x slower │
└───────────┴───────────────────────────────────────┴────────────────────────────────────────┴───────────────┘
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━┓
┃ Benchmark Summary                                     ┃            ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━┩
│ Total Time (HEAD)                                     │ 20146.17ms │
│ Total Time (final-aggr-with-lazily-materialize-poc)   │ 19906.76ms │
│ Average Time (HEAD)                                   │   468.52ms │
│ Average Time (final-aggr-with-lazily-materialize-poc) │   462.95ms │
│ Queries Faster                                        │         15 │
│ Queries Slower                                        │         10 │
│ Queries with No Change                                │         18 │
│ Queries with Failure                                  │          0 │
└───────────────────────────────────────────────────────┴────────────┘

Resource Usage

clickbench_partitioned — base (merge-base)

Metric Value
Wall time 105.0s
Peak memory 11.2 GiB
Avg memory 4.4 GiB
CPU user 1036.6s
CPU sys 72.1s
Peak spill 0 B

clickbench_partitioned — branch

Metric Value
Wall time 100.0s
Peak memory 11.9 GiB
Avg memory 4.4 GiB
CPU user 974.6s
CPU sys 79.6s
Peak spill 0 B

File an issue against this benchmark runner

@Rachelint

Copy link
Copy Markdown
Contributor Author

run benchmarks clickbench_partitioned

@adriangbot

Copy link
Copy Markdown

🤖 Benchmark running (GKE) | trigger
Instance: c4a-highmem-16 (12 vCPU / 65 GiB) | Linux bench-c4951931520-1017-mjrbc 6.12.85+ #1 SMP Mon May 11 08:17:35 UTC 2026 aarch64 GNU/Linux

CPU Details (lscpu)
Architecture:                            aarch64
CPU op-mode(s):                          64-bit
Byte Order:                              Little Endian
CPU(s):                                  16
On-line CPU(s) list:                     0-15
Vendor ID:                               ARM
Model name:                              Neoverse-V2
Model:                                   1
Thread(s) per core:                      1
Core(s) per cluster:                     16
Socket(s):                               -
Cluster(s):                              1
Stepping:                                r0p1
BogoMIPS:                                2000.00
Flags:                                   fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm jscvt fcma lrcpc dcpop sha3 sm3 sm4 asimddp sha512 sve asimdfhm dit uscat ilrcpc flagm sb paca pacg dcpodp sve2 sveaes svepmull svebitperm svesha3 svesm4 flagm2 frint svei8mm svebf16 i8mm bf16 dgh rng bti
L1d cache:                               1 MiB (16 instances)
L1i cache:                               1 MiB (16 instances)
L2 cache:                                32 MiB (16 instances)
L3 cache:                                80 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; __user pointer sanitization
Vulnerability Spectre v2:                Mitigation; CSV2, BHB
Vulnerability Srbds:                     Not affected
Vulnerability Tsa:                       Not affected
Vulnerability Tsx async abort:           Not affected
Vulnerability Vmscape:                   Not affected

Comparing final-aggr-with-lazily-materialize-poc (8a09547) to eaafba4 (merge-base) diff using: clickbench_partitioned
Results will be posted here when complete


File an issue against this benchmark runner

@adriangbot

Copy link
Copy Markdown

🤖 Benchmark completed (GKE) | trigger

Instance: c4a-highmem-16 (12 vCPU / 65 GiB)

CPU Details (lscpu)
Architecture:                            aarch64
CPU op-mode(s):                          64-bit
Byte Order:                              Little Endian
CPU(s):                                  16
On-line CPU(s) list:                     0-15
Vendor ID:                               ARM
Model name:                              Neoverse-V2
Model:                                   1
Thread(s) per core:                      1
Core(s) per cluster:                     16
Socket(s):                               -
Cluster(s):                              1
Stepping:                                r0p1
BogoMIPS:                                2000.00
Flags:                                   fp asimd evtstrm aes pmull sha1 sha2 crc32 atomics fphp asimdhp cpuid asimdrdm jscvt fcma lrcpc dcpop sha3 sm3 sm4 asimddp sha512 sve asimdfhm dit uscat ilrcpc flagm sb paca pacg dcpodp sve2 sveaes svepmull svebitperm svesha3 svesm4 flagm2 frint svei8mm svebf16 i8mm bf16 dgh rng bti
L1d cache:                               1 MiB (16 instances)
L1i cache:                               1 MiB (16 instances)
L2 cache:                                32 MiB (16 instances)
L3 cache:                                80 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; __user pointer sanitization
Vulnerability Spectre v2:                Mitigation; CSV2, BHB
Vulnerability Srbds:                     Not affected
Vulnerability Tsa:                       Not affected
Vulnerability Tsx async abort:           Not affected
Vulnerability Vmscape:                   Not affected
Details

Comparing HEAD and final-aggr-with-lazily-materialize-poc
--------------------
Benchmark clickbench_partitioned.json
--------------------
┏━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Query     ┃                                  HEAD ┃ final-aggr-with-lazily-materialize-poc ┃        Change ┃
┡━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ QQuery 0  │          1.25 / 3.94 ±5.32 / 14.58 ms │           1.23 / 3.91 ±5.31 / 14.54 ms │     no change │
│ QQuery 1  │        12.53 / 12.80 ±0.24 / 13.17 ms │         12.96 / 13.13 ±0.14 / 13.34 ms │     no change │
│ QQuery 2  │        35.64 / 35.98 ±0.28 / 36.38 ms │         37.26 / 37.76 ±0.36 / 38.33 ms │     no change │
│ QQuery 3  │        30.40 / 31.09 ±0.58 / 32.16 ms │         31.55 / 31.85 ±0.30 / 32.36 ms │     no change │
│ QQuery 4  │     223.01 / 227.23 ±2.56 / 230.58 ms │      188.51 / 191.54 ±2.66 / 195.55 ms │ +1.19x faster │
│ QQuery 5  │     272.62 / 274.92 ±1.41 / 276.65 ms │      267.04 / 270.72 ±3.01 / 275.59 ms │     no change │
│ QQuery 6  │           1.27 / 1.41 ±0.22 / 1.84 ms │            1.29 / 1.44 ±0.24 / 1.90 ms │     no change │
│ QQuery 7  │        13.55 / 13.64 ±0.05 / 13.72 ms │         14.23 / 14.49 ±0.18 / 14.67 ms │  1.06x slower │
│ QQuery 8  │     313.73 / 321.46 ±4.37 / 327.28 ms │      287.87 / 293.53 ±4.78 / 298.83 ms │ +1.10x faster │
│ QQuery 9  │     446.20 / 449.32 ±2.41 / 453.66 ms │      405.16 / 414.02 ±5.17 / 418.30 ms │ +1.09x faster │
│ QQuery 10 │        71.74 / 72.05 ±0.34 / 72.57 ms │         74.27 / 76.39 ±2.30 / 80.83 ms │  1.06x slower │
│ QQuery 11 │        82.30 / 85.07 ±5.04 / 95.11 ms │         85.24 / 88.30 ±5.24 / 98.73 ms │     no change │
│ QQuery 12 │     263.86 / 271.91 ±4.76 / 277.67 ms │      263.62 / 269.89 ±4.97 / 277.43 ms │     no change │
│ QQuery 13 │     365.53 / 372.47 ±6.71 / 385.26 ms │     350.26 / 367.07 ±22.24 / 410.87 ms │     no change │
│ QQuery 14 │     278.01 / 283.16 ±3.71 / 289.31 ms │     285.87 / 295.55 ±11.94 / 318.74 ms │     no change │
│ QQuery 15 │     266.78 / 271.02 ±2.27 / 272.99 ms │      234.20 / 242.79 ±8.00 / 255.37 ms │ +1.12x faster │
│ QQuery 16 │     612.68 / 616.93 ±4.51 / 624.83 ms │     578.66 / 610.38 ±25.56 / 647.10 ms │     no change │
│ QQuery 17 │     617.24 / 622.50 ±4.26 / 629.63 ms │     499.78 / 514.92 ±16.28 / 545.55 ms │ +1.21x faster │
│ QQuery 18 │ 1236.31 / 1266.74 ±25.45 / 1305.87 ms │  1146.09 / 1197.46 ±38.82 / 1249.80 ms │ +1.06x faster │
│ QQuery 19 │        27.53 / 28.93 ±1.61 / 32.02 ms │         28.53 / 35.60 ±8.30 / 46.68 ms │  1.23x slower │
│ QQuery 20 │    518.26 / 529.96 ±10.17 / 547.07 ms │     514.55 / 528.70 ±10.16 / 542.45 ms │     no change │
│ QQuery 21 │     514.00 / 523.15 ±5.58 / 528.29 ms │      518.19 / 524.13 ±7.04 / 537.05 ms │     no change │
│ QQuery 22 │    986.83 / 996.47 ±8.16 / 1008.18 ms │     984.34 / 994.82 ±6.37 / 1002.43 ms │     no change │
│ QQuery 23 │ 3061.92 / 3106.57 ±35.30 / 3148.90 ms │  3070.44 / 3123.73 ±42.21 / 3198.61 ms │     no change │
│ QQuery 24 │        41.78 / 51.29 ±7.50 / 62.21 ms │         41.61 / 45.05 ±2.41 / 49.11 ms │ +1.14x faster │
│ QQuery 25 │     112.21 / 113.26 ±0.61 / 113.89 ms │      113.57 / 115.01 ±2.06 / 119.04 ms │     no change │
│ QQuery 26 │       41.92 / 48.97 ±11.88 / 72.65 ms │         43.02 / 45.68 ±2.18 / 49.50 ms │ +1.07x faster │
│ QQuery 27 │     669.93 / 676.44 ±5.56 / 683.69 ms │      669.10 / 678.57 ±7.38 / 689.93 ms │     no change │
│ QQuery 28 │ 2998.71 / 3024.62 ±27.63 / 3074.48 ms │  3043.66 / 3065.38 ±13.10 / 3083.70 ms │     no change │
│ QQuery 29 │        40.42 / 40.91 ±0.79 / 42.47 ms │        40.76 / 57.68 ±17.91 / 79.47 ms │  1.41x slower │
│ QQuery 30 │    297.95 / 322.25 ±29.69 / 380.43 ms │     287.58 / 300.35 ±10.11 / 311.24 ms │ +1.07x faster │
│ QQuery 31 │    280.88 / 290.74 ±11.75 / 313.48 ms │      255.98 / 264.55 ±5.00 / 269.07 ms │ +1.10x faster │
│ QQuery 32 │   925.59 / 952.53 ±27.29 / 1003.14 ms │     677.97 / 712.16 ±27.76 / 746.92 ms │ +1.34x faster │
│ QQuery 33 │ 1426.47 / 1471.92 ±29.22 / 1506.34 ms │  1496.46 / 1557.34 ±33.16 / 1593.60 ms │  1.06x slower │
│ QQuery 34 │ 1474.78 / 1505.10 ±25.13 / 1542.56 ms │  1554.30 / 1601.39 ±39.79 / 1650.03 ms │  1.06x slower │
│ QQuery 35 │    272.79 / 299.06 ±44.41 / 387.56 ms │     247.36 / 281.67 ±41.61 / 362.17 ms │ +1.06x faster │
│ QQuery 36 │       65.77 / 80.26 ±11.39 / 93.46 ms │         66.11 / 74.63 ±8.78 / 91.05 ms │ +1.08x faster │
│ QQuery 37 │        35.57 / 38.54 ±3.96 / 46.39 ms │         35.05 / 41.90 ±5.28 / 46.81 ms │  1.09x slower │
│ QQuery 38 │        39.78 / 45.60 ±4.50 / 52.35 ms │         41.12 / 45.89 ±4.21 / 51.35 ms │     no change │
│ QQuery 39 │     142.93 / 152.93 ±9.06 / 169.08 ms │      149.95 / 158.83 ±6.86 / 168.05 ms │     no change │
│ QQuery 40 │        13.84 / 16.29 ±3.33 / 22.67 ms │         14.15 / 16.48 ±3.11 / 22.37 ms │     no change │
│ QQuery 41 │        13.37 / 17.07 ±4.20 / 24.89 ms │         14.35 / 20.55 ±8.66 / 37.33 ms │  1.20x slower │
│ QQuery 42 │        12.84 / 13.12 ±0.19 / 13.40 ms │         13.47 / 15.34 ±3.35 / 22.04 ms │  1.17x slower │
└───────────┴───────────────────────────────────────┴────────────────────────────────────────┴───────────────┘
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━┓
┃ Benchmark Summary                                     ┃            ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━┩
│ Total Time (HEAD)                                     │ 19579.61ms │
│ Total Time (final-aggr-with-lazily-materialize-poc)   │ 19240.59ms │
│ Average Time (HEAD)                                   │   455.34ms │
│ Average Time (final-aggr-with-lazily-materialize-poc) │   447.46ms │
│ Queries Faster                                        │         13 │
│ Queries Slower                                        │          9 │
│ Queries with No Change                                │         21 │
│ Queries with Failure                                  │          0 │
└───────────────────────────────────────────────────────┴────────────┘

Resource Usage

clickbench_partitioned — base (merge-base)

Metric Value
Wall time 100.0s
Peak memory 11.6 GiB
Avg memory 4.7 GiB
CPU user 1005.4s
CPU sys 68.7s
Peak spill 0 B

clickbench_partitioned — branch

Metric Value
Wall time 100.0s
Peak memory 12.6 GiB
Avg memory 3.9 GiB
CPU user 950.4s
CPU sys 73.4s
Peak spill 0 B

File an issue against this benchmark runner

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

common Related to common crate core Core DataFusion crate documentation Improvements or additions to documentation optimizer Optimizer rules physical-expr Changes to the physical-expr crates physical-plan Changes to the physical-plan crate

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants