perf: optimize count distinct fast path and sliding count distinct

[lyne7-sc]

Which issue does this PR close?

• Closes #.

Rationale for this change

This PR improves two hot paths for count distinct.

For the primitive non-sliding path, it adds a fast path to avoid per-row null handling when the input batch contains no nulls.

For the sliding path, it adds a primitive accumulator and keeps other types on the generic path for now.

What changes are included in this PR?

This pr adds a null-free fast path for primitive COUNT(DISTINCT) and a primitive sliding distinct accumulator for integer types.

Benchmarks

group                                                     optimized                                 main
-----                                                     -----------------                      --------------------
count_distinct i16 bitmap                                 1.00      4.4±0.01µs        ? ?/sec    1.01      4.4±0.06µs        ? ?/sec
count_distinct i32 80% distinct                           1.00     18.9±0.29µs        ? ?/sec    2.79     52.7±0.12µs        ? ?/sec
count_distinct i32 99% distinct                           1.00     18.9±0.20µs        ? ?/sec    2.78     52.5±0.23µs        ? ?/sec
count_distinct i64 80% distinct                           1.00     18.5±0.22µs        ? ?/sec    2.89     53.5±0.27µs        ? ?/sec
count_distinct i64 99% distinct                           1.00     18.8±0.39µs        ? ?/sec    2.85     53.6±0.23µs        ? ?/sec
count_distinct i8 bitmap                                  1.00   1250.0±3.33ns        ? ?/sec    1.00   1251.0±1.82ns        ? ?/sec
count_distinct u16 bitmap                                 1.00      4.4±0.01µs        ? ?/sec    1.00      4.4±0.01µs        ? ?/sec
count_distinct u32 80% distinct                           1.00     18.9±0.35µs        ? ?/sec    2.80     52.9±0.22µs        ? ?/sec
count_distinct u32 99% distinct                           1.00     19.2±0.26µs        ? ?/sec    2.72     52.4±0.14µs        ? ?/sec
count_distinct u8 bitmap                                  1.01   1254.1±3.38ns        ? ?/sec    1.00   1246.5±3.27ns        ? ?/sec
count_distinct_sliding i64 high window_1024               1.00    503.8±1.41µs        ? ?/sec    1.64    827.2±3.43µs        ? ?/sec
count_distinct_sliding i64 high window_256                1.00    487.3±1.17µs        ? ?/sec    1.69    823.4±2.38µs        ? ?/sec
count_distinct_sliding i64 low window_1024                1.00    525.0±1.29µs        ? ?/sec    1.59    833.4±6.13µs        ? ?/sec
count_distinct_sliding i64 low window_256                 1.00    471.2±1.25µs        ? ?/sec    1.70    802.3±3.48µs        ? ?/sec
count_distinct_sliding i64 mid window_1024                1.00    513.3±1.23µs        ? ?/sec    1.63    838.0±4.07µs        ? ?/sec
count_distinct_sliding i64 mid window_256                 1.00    479.1±0.77µs        ? ?/sec    1.72    825.8±3.68µs        ? ?/sec

Are these changes tested?

yes

Are there any user-facing changes?

no

[Dandandan]

run benchmarks

[adriangbot]

🤖 Benchmark running (GKE) | trigger
Instance: c4a-highmem-16 (12 vCPU / 65 GiB) | Linux bench-c4297664227-1752-8r9pr 6.12.55+ #1 SMP Sun Feb 1 08:59:41 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 perf-count-distinct-clean (d71d55b) to 4bff17e (merge-base) diff using: clickbench_partitioned
Results will be posted here when complete

---

File an issue against this benchmark runner

[adriangbot]

🤖 Benchmark running (GKE) | trigger
Instance: c4a-highmem-16 (12 vCPU / 65 GiB) | Linux bench-c4297664227-1753-m4tp6 6.12.55+ #1 SMP Sun Feb 1 08:59:41 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 perf-count-distinct-clean (d71d55b) to 4bff17e (merge-base) diff using: tpcds
Results will be posted here when complete

---

File an issue against this benchmark runner

[adriangbot]

🤖 Benchmark running (GKE) | trigger
Instance: c4a-highmem-16 (12 vCPU / 65 GiB) | Linux bench-c4297664227-1754-frjpc 6.12.55+ #1 SMP Sun Feb 1 08:59:41 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 perf-count-distinct-clean (d71d55b) to 4bff17e (merge-base) diff using: tpch
Results will be posted here when complete

---

File an issue against this benchmark runner

[adriangbot]

🤖 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 perf-count-distinct-clean
--------------------
Benchmark tpch_sf1.json
--------------------
┏━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━┓
┃ Query     ┃                           HEAD ┃      perf-count-distinct-clean ┃    Change ┃
┡━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━┩
│ QQuery 1  │ 40.85 / 42.01 ±1.03 / 43.54 ms │ 41.09 / 41.88 ±1.14 / 44.08 ms │ no change │
│ QQuery 2  │ 21.04 / 21.32 ±0.27 / 21.70 ms │ 21.34 / 21.59 ±0.32 / 22.20 ms │ no change │
│ QQuery 3  │ 38.65 / 40.82 ±1.74 / 42.47 ms │ 39.07 / 41.06 ±1.20 / 42.51 ms │ no change │
│ QQuery 4  │ 18.35 / 18.69 ±0.23 / 19.07 ms │ 18.69 / 19.53 ±0.69 / 20.17 ms │ no change │
│ QQuery 5  │ 48.50 / 51.14 ±1.52 / 52.92 ms │ 50.03 / 51.24 ±0.74 / 52.09 ms │ no change │
│ QQuery 6  │ 17.42 / 17.65 ±0.38 / 18.40 ms │ 17.47 / 17.56 ±0.08 / 17.67 ms │ no change │
│ QQuery 7  │ 54.76 / 56.46 ±1.10 / 57.98 ms │ 53.90 / 55.57 ±1.13 / 56.77 ms │ no change │
│ QQuery 8  │ 48.48 / 48.90 ±0.51 / 49.88 ms │ 48.15 / 48.66 ±0.52 / 49.62 ms │ no change │
│ QQuery 9  │ 53.66 / 54.89 ±0.85 / 56.31 ms │ 54.17 / 54.91 ±0.82 / 56.49 ms │ no change │
│ QQuery 10 │ 66.11 / 67.93 ±1.94 / 71.23 ms │ 66.32 / 67.05 ±1.19 / 69.42 ms │ no change │
│ QQuery 11 │ 14.31 / 14.66 ±0.21 / 14.95 ms │ 14.34 / 14.59 ±0.18 / 14.86 ms │ no change │
│ QQuery 12 │ 27.64 / 28.15 ±0.67 / 29.45 ms │ 27.49 / 28.24 ±0.55 / 29.20 ms │ no change │
│ QQuery 13 │ 38.40 / 39.05 ±0.75 / 40.18 ms │ 37.89 / 38.75 ±0.45 / 39.18 ms │ no change │
│ QQuery 14 │ 28.35 / 28.64 ±0.26 / 29.05 ms │ 28.28 / 28.66 ±0.57 / 29.80 ms │ no change │
│ QQuery 15 │ 33.99 / 34.67 ±0.54 / 35.25 ms │ 34.24 / 34.61 ±0.62 / 35.84 ms │ no change │
│ QQuery 16 │ 15.56 / 15.75 ±0.25 / 16.24 ms │ 15.51 / 15.67 ±0.26 / 16.18 ms │ no change │
│ QQuery 17 │ 80.38 / 81.04 ±0.59 / 82.10 ms │ 78.56 / 80.73 ±1.41 / 82.74 ms │ no change │
│ QQuery 18 │ 76.88 / 78.13 ±0.75 / 79.11 ms │ 75.70 / 77.01 ±1.02 / 78.39 ms │ no change │
│ QQuery 19 │ 37.73 / 38.12 ±0.25 / 38.42 ms │ 38.08 / 38.19 ±0.09 / 38.35 ms │ no change │
│ QQuery 20 │ 39.79 / 40.36 ±0.37 / 40.85 ms │ 40.13 / 41.87 ±1.63 / 44.26 ms │ no change │
│ QQuery 21 │ 64.93 / 66.00 ±1.06 / 67.96 ms │ 65.61 / 66.12 ±0.29 / 66.46 ms │ no change │
│ QQuery 22 │ 17.27 / 17.38 ±0.06 / 17.43 ms │ 17.27 / 17.46 ±0.13 / 17.66 ms │ no change │
└───────────┴────────────────────────────────┴────────────────────────────────┴───────────┘
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━┓
┃ Benchmark Summary                        ┃          ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━┩
│ Total Time (HEAD)                        │ 901.75ms │
│ Total Time (perf-count-distinct-clean)   │ 900.94ms │
│ Average Time (HEAD)                      │  40.99ms │
│ Average Time (perf-count-distinct-clean) │  40.95ms │
│ Queries Faster                           │        0 │
│ Queries Slower                           │        0 │
│ Queries with No Change                   │       22 │
│ Queries with Failure                     │        0 │
└──────────────────────────────────────────┴──────────┘

Resource Usage

tpch — base (merge-base)

Metric	Value
Wall time	5.0s
Peak memory	5.4 GiB
Avg memory	4.8 GiB
CPU user	34.2s
CPU sys	2.5s
Peak spill	0 B

tpch — branch

Metric	Value
Wall time	5.0s
Peak memory	5.4 GiB
Avg memory	4.8 GiB
CPU user	34.0s
CPU sys	2.5s
Peak spill	0 B

---

File an issue against this benchmark runner

[adriangbot]

🤖 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 perf-count-distinct-clean
--------------------
Benchmark clickbench_partitioned.json
--------------------
┏━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━┓
┃ Query     ┃                                  HEAD ┃             perf-count-distinct-clean ┃       Change ┃
┡━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━┩
│ QQuery 0  │          1.18 / 4.61 ±6.73 / 18.08 ms │          1.18 / 4.55 ±6.69 / 17.93 ms │    no change │
│ QQuery 1  │        12.99 / 13.46 ±0.29 / 13.84 ms │        12.66 / 12.98 ±0.23 / 13.38 ms │    no change │
│ QQuery 2  │        37.42 / 37.59 ±0.16 / 37.85 ms │        36.96 / 37.17 ±0.18 / 37.44 ms │    no change │
│ QQuery 3  │        32.16 / 33.05 ±0.79 / 34.05 ms │        31.58 / 31.95 ±0.28 / 32.23 ms │    no change │
│ QQuery 4  │     247.55 / 250.36 ±1.43 / 251.37 ms │     245.19 / 249.20 ±6.36 / 261.83 ms │    no change │
│ QQuery 5  │     289.26 / 291.66 ±1.56 / 294.14 ms │     287.09 / 288.92 ±2.05 / 292.58 ms │    no change │
│ QQuery 6  │           6.42 / 7.53 ±0.85 / 9.01 ms │          6.11 / 7.51 ±1.63 / 10.66 ms │    no change │
│ QQuery 7  │        14.30 / 14.37 ±0.05 / 14.46 ms │        14.28 / 14.46 ±0.10 / 14.59 ms │    no change │
│ QQuery 8  │     334.43 / 339.03 ±5.44 / 348.80 ms │     330.16 / 334.11 ±3.78 / 340.39 ms │    no change │
│ QQuery 9  │     458.32 / 466.64 ±6.02 / 476.73 ms │    449.26 / 461.36 ±11.01 / 475.29 ms │    no change │
│ QQuery 10 │        74.87 / 75.85 ±0.69 / 76.92 ms │        75.48 / 76.27 ±0.81 / 77.43 ms │    no change │
│ QQuery 11 │        86.52 / 87.36 ±0.73 / 88.57 ms │        86.89 / 88.22 ±1.01 / 89.31 ms │    no change │
│ QQuery 12 │     281.81 / 284.70 ±3.25 / 290.32 ms │     274.94 / 279.00 ±3.43 / 284.56 ms │    no change │
│ QQuery 13 │     405.19 / 417.76 ±8.91 / 433.01 ms │     390.58 / 401.28 ±6.32 / 408.67 ms │    no change │
│ QQuery 14 │     289.53 / 293.20 ±3.88 / 300.21 ms │     287.80 / 294.46 ±4.43 / 301.75 ms │    no change │
│ QQuery 15 │     291.73 / 295.30 ±3.22 / 300.51 ms │     283.99 / 289.92 ±4.68 / 296.79 ms │    no change │
│ QQuery 16 │     634.08 / 640.51 ±4.72 / 645.59 ms │     620.51 / 633.39 ±6.92 / 641.38 ms │    no change │
│ QQuery 17 │     631.20 / 638.16 ±5.30 / 647.22 ms │     629.08 / 635.52 ±6.25 / 646.06 ms │    no change │
│ QQuery 18 │  1268.92 / 1276.86 ±4.96 / 1282.22 ms │ 1269.65 / 1298.28 ±16.32 / 1319.17 ms │    no change │
│ QQuery 19 │        28.95 / 29.42 ±0.33 / 29.89 ms │        29.37 / 29.61 ±0.28 / 30.13 ms │    no change │
│ QQuery 20 │     519.97 / 533.30 ±9.98 / 550.56 ms │     532.91 / 540.37 ±7.99 / 555.10 ms │    no change │
│ QQuery 21 │     598.83 / 603.75 ±5.25 / 612.55 ms │     606.21 / 612.42 ±4.67 / 618.44 ms │    no change │
│ QQuery 22 │  1072.96 / 1079.95 ±4.13 / 1084.62 ms │  1071.10 / 1076.59 ±6.40 / 1088.96 ms │    no change │
│ QQuery 23 │ 3386.74 / 3410.86 ±22.66 / 3450.31 ms │ 3389.90 / 3411.78 ±21.12 / 3443.47 ms │    no change │
│ QQuery 24 │        42.26 / 46.30 ±5.12 / 56.03 ms │       42.17 / 49.01 ±13.20 / 75.41 ms │ 1.06x slower │
│ QQuery 25 │     115.39 / 119.77 ±4.56 / 127.34 ms │     113.98 / 114.70 ±0.69 / 115.91 ms │    no change │
│ QQuery 26 │        42.90 / 44.01 ±1.25 / 46.42 ms │        42.61 / 44.82 ±3.08 / 50.71 ms │    no change │
│ QQuery 27 │     678.17 / 681.62 ±2.72 / 685.73 ms │     676.06 / 684.72 ±6.91 / 696.57 ms │    no change │
│ QQuery 28 │ 3024.44 / 3047.64 ±21.53 / 3074.34 ms │ 3012.96 / 3029.03 ±19.99 / 3067.44 ms │    no change │
│ QQuery 29 │        42.62 / 43.19 ±0.54 / 43.94 ms │        42.56 / 46.30 ±4.63 / 53.96 ms │ 1.07x slower │
│ QQuery 30 │     313.51 / 320.90 ±6.26 / 329.76 ms │     316.70 / 321.64 ±4.13 / 326.97 ms │    no change │
│ QQuery 31 │     307.16 / 321.02 ±9.24 / 330.54 ms │     310.19 / 321.12 ±9.02 / 331.28 ms │    no change │
│ QQuery 32 │ 1024.64 / 1051.96 ±33.36 / 1116.98 ms │ 1027.92 / 1048.72 ±29.49 / 1106.22 ms │    no change │
│ QQuery 33 │ 1434.61 / 1477.99 ±46.31 / 1564.22 ms │ 1451.74 / 1494.46 ±44.29 / 1577.85 ms │    no change │
│ QQuery 34 │ 1450.92 / 1482.58 ±33.14 / 1533.11 ms │ 1441.60 / 1469.16 ±26.18 / 1509.58 ms │    no change │
│ QQuery 35 │    292.27 / 313.92 ±28.57 / 368.91 ms │    291.49 / 307.50 ±24.75 / 356.48 ms │    no change │
│ QQuery 36 │        61.81 / 67.34 ±3.62 / 71.33 ms │        61.52 / 68.23 ±4.36 / 75.21 ms │    no change │
│ QQuery 37 │        35.28 / 35.55 ±0.24 / 35.94 ms │        35.14 / 35.78 ±0.36 / 36.13 ms │    no change │
│ QQuery 38 │        42.07 / 45.74 ±4.18 / 53.45 ms │        39.66 / 47.66 ±6.00 / 58.21 ms │    no change │
│ QQuery 39 │     126.78 / 133.69 ±3.93 / 137.29 ms │     121.19 / 133.91 ±7.35 / 143.63 ms │    no change │
│ QQuery 40 │        14.48 / 14.79 ±0.27 / 15.22 ms │        14.33 / 14.54 ±0.18 / 14.85 ms │    no change │
│ QQuery 41 │        13.86 / 14.00 ±0.10 / 14.13 ms │        13.90 / 15.41 ±2.06 / 19.34 ms │ 1.10x slower │
│ QQuery 42 │        13.61 / 13.74 ±0.12 / 13.91 ms │        13.24 / 13.55 ±0.18 / 13.80 ms │    no change │
└───────────┴───────────────────────────────────────┴───────────────────────────────────────┴──────────────┘
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━┓
┃ Benchmark Summary                        ┃            ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━┩
│ Total Time (HEAD)                        │ 20401.03ms │
│ Total Time (perf-count-distinct-clean)   │ 20369.60ms │
│ Average Time (HEAD)                      │   474.44ms │
│ Average Time (perf-count-distinct-clean) │   473.71ms │
│ Queries Faster                           │          0 │
│ Queries Slower                           │          3 │
│ Queries with No Change                   │         40 │
│ Queries with Failure                     │          0 │
└──────────────────────────────────────────┴────────────┘

Resource Usage

clickbench_partitioned — base (merge-base)

Metric	Value
Wall time	105.0s
Peak memory	30.2 GiB
Avg memory	22.7 GiB
CPU user	1075.4s
CPU sys	67.5s
Peak spill	0 B

clickbench_partitioned — branch

Metric	Value
Wall time	105.0s
Peak memory	30.0 GiB
Avg memory	22.8 GiB
CPU user	1072.3s
CPU sys	68.2s
Peak spill	0 B

---

File an issue against this benchmark runner

[adriangbot]

🤖 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 perf-count-distinct-clean
--------------------
Benchmark tpcds_sf1.json
--------------------
┏━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
┃ Query     ┃                                     HEAD ┃                perf-count-distinct-clean ┃        Change ┃
┡━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
│ QQuery 1  │              6.74 / 7.24 ±0.90 / 9.03 ms │              6.74 / 7.26 ±0.83 / 8.92 ms │     no change │
│ QQuery 2  │        144.97 / 145.67 ±0.43 / 146.20 ms │        144.55 / 145.55 ±0.99 / 147.17 ms │     no change │
│ QQuery 3  │        112.57 / 113.76 ±0.71 / 114.70 ms │        114.86 / 115.98 ±1.60 / 119.09 ms │     no change │
│ QQuery 4  │    1348.13 / 1430.83 ±45.10 / 1476.55 ms │    1230.58 / 1397.72 ±93.92 / 1474.08 ms │     no change │
│ QQuery 5  │        174.16 / 175.95 ±2.73 / 181.32 ms │        171.85 / 173.64 ±2.40 / 178.33 ms │     no change │
│ QQuery 6  │       804.87 / 841.97 ±25.25 / 880.25 ms │       803.49 / 844.11 ±32.07 / 889.24 ms │     no change │
│ QQuery 7  │        342.13 / 347.38 ±3.18 / 351.45 ms │        333.73 / 335.57 ±1.05 / 336.64 ms │     no change │
│ QQuery 8  │        116.25 / 116.90 ±1.00 / 118.89 ms │        112.39 / 113.98 ±1.42 / 116.48 ms │     no change │
│ QQuery 9  │        102.31 / 108.28 ±4.73 / 116.71 ms │        101.16 / 104.95 ±1.95 / 106.40 ms │     no change │
│ QQuery 10 │        104.71 / 106.30 ±0.82 / 107.10 ms │        102.58 / 103.07 ±0.48 / 103.68 ms │     no change │
│ QQuery 11 │      859.53 / 964.83 ±62.37 / 1049.05 ms │        863.44 / 869.61 ±4.25 / 876.20 ms │ +1.11x faster │
│ QQuery 12 │           42.71 / 43.05 ±0.22 / 43.25 ms │           43.41 / 43.85 ±0.23 / 44.04 ms │     no change │
│ QQuery 13 │        385.92 / 389.64 ±2.31 / 392.63 ms │        390.82 / 400.42 ±7.61 / 409.40 ms │     no change │
│ QQuery 14 │       977.05 / 991.31 ±9.70 / 1006.19 ms │      977.82 / 998.04 ±10.26 / 1005.02 ms │     no change │
│ QQuery 15 │           15.71 / 15.96 ±0.22 / 16.35 ms │           15.72 / 15.86 ±0.14 / 16.08 ms │     no change │
│ QQuery 16 │              7.89 / 8.04 ±0.17 / 8.33 ms │              7.93 / 8.07 ±0.11 / 8.25 ms │     no change │
│ QQuery 17 │        221.36 / 229.63 ±6.38 / 238.16 ms │        223.61 / 228.73 ±3.16 / 233.57 ms │     no change │
│ QQuery 18 │        125.83 / 127.92 ±2.06 / 131.02 ms │        124.98 / 126.07 ±0.89 / 127.54 ms │     no change │
│ QQuery 19 │        151.80 / 152.80 ±0.87 / 154.33 ms │        151.92 / 153.10 ±1.09 / 154.91 ms │     no change │
│ QQuery 20 │           12.51 / 12.80 ±0.25 / 13.22 ms │           12.64 / 12.88 ±0.22 / 13.23 ms │     no change │
│ QQuery 21 │           18.34 / 18.53 ±0.10 / 18.61 ms │           18.64 / 18.86 ±0.28 / 19.36 ms │     no change │
│ QQuery 22 │        473.37 / 475.36 ±2.45 / 479.90 ms │        471.23 / 474.98 ±3.41 / 479.63 ms │     no change │
│ QQuery 23 │        800.44 / 807.99 ±6.00 / 815.63 ms │       883.82 / 898.12 ±12.28 / 919.82 ms │  1.11x slower │
│ QQuery 24 │        369.39 / 372.02 ±2.01 / 374.46 ms │        394.35 / 395.37 ±1.01 / 397.25 ms │  1.06x slower │
│ QQuery 25 │        330.58 / 336.98 ±6.19 / 347.35 ms │        339.61 / 346.29 ±4.58 / 351.33 ms │     no change │
│ QQuery 26 │           79.72 / 81.49 ±3.15 / 87.78 ms │           79.43 / 79.88 ±0.41 / 80.61 ms │     no change │
│ QQuery 27 │              7.33 / 7.46 ±0.10 / 7.61 ms │             7.58 / 8.92 ±1.80 / 12.17 ms │  1.20x slower │
│ QQuery 28 │        152.90 / 153.72 ±0.75 / 155.05 ms │        147.65 / 150.64 ±2.02 / 153.43 ms │     no change │
│ QQuery 29 │        285.10 / 289.44 ±3.68 / 294.97 ms │        271.41 / 273.25 ±2.23 / 277.50 ms │ +1.06x faster │
│ QQuery 30 │           43.39 / 43.66 ±0.27 / 44.13 ms │           41.09 / 41.65 ±0.37 / 42.18 ms │     no change │
│ QQuery 31 │        170.67 / 173.10 ±1.50 / 174.70 ms │        163.04 / 165.53 ±3.00 / 171.43 ms │     no change │
│ QQuery 32 │           14.38 / 14.72 ±0.27 / 15.05 ms │           13.20 / 13.37 ±0.14 / 13.62 ms │ +1.10x faster │
│ QQuery 33 │        143.95 / 145.66 ±2.32 / 150.22 ms │        138.07 / 138.92 ±0.49 / 139.32 ms │     no change │
│ QQuery 34 │              7.40 / 7.54 ±0.11 / 7.67 ms │              6.88 / 7.04 ±0.19 / 7.40 ms │ +1.07x faster │
│ QQuery 35 │        103.91 / 105.14 ±0.75 / 106.06 ms │        100.44 / 101.23 ±0.81 / 102.75 ms │     no change │
│ QQuery 36 │              6.94 / 7.06 ±0.10 / 7.23 ms │              6.66 / 6.83 ±0.10 / 6.96 ms │     no change │
│ QQuery 37 │              8.63 / 8.67 ±0.03 / 8.72 ms │              8.13 / 8.28 ±0.13 / 8.53 ms │     no change │
│ QQuery 38 │           87.27 / 90.86 ±4.77 / 99.94 ms │           86.30 / 88.73 ±1.97 / 91.36 ms │     no change │
│ QQuery 39 │        114.72 / 116.37 ±1.07 / 117.54 ms │        122.91 / 128.97 ±3.32 / 133.03 ms │  1.11x slower │
│ QQuery 40 │        103.75 / 108.17 ±3.89 / 113.76 ms │        106.27 / 111.92 ±5.14 / 120.82 ms │     no change │
│ QQuery 41 │           13.79 / 14.00 ±0.25 / 14.49 ms │           14.97 / 15.12 ±0.18 / 15.45 ms │  1.08x slower │
│ QQuery 42 │        105.19 / 107.72 ±3.46 / 114.54 ms │        109.40 / 111.04 ±2.89 / 116.82 ms │     no change │
│ QQuery 43 │              5.46 / 6.37 ±1.50 / 9.36 ms │              6.26 / 6.32 ±0.07 / 6.45 ms │     no change │
│ QQuery 44 │           11.29 / 11.49 ±0.14 / 11.64 ms │           12.44 / 12.66 ±0.14 / 12.86 ms │  1.10x slower │
│ QQuery 45 │           48.18 / 48.37 ±0.14 / 48.54 ms │           50.35 / 51.10 ±0.91 / 52.85 ms │  1.06x slower │
│ QQuery 46 │              8.37 / 8.50 ±0.14 / 8.77 ms │              8.91 / 9.10 ±0.15 / 9.36 ms │  1.07x slower │
│ QQuery 47 │        665.31 / 672.41 ±6.17 / 683.45 ms │       664.86 / 749.80 ±79.27 / 846.85 ms │  1.12x slower │
│ QQuery 48 │        274.01 / 276.59 ±2.65 / 280.23 ms │        272.61 / 276.79 ±4.11 / 284.13 ms │     no change │
│ QQuery 49 │        248.36 / 249.37 ±0.91 / 251.03 ms │        248.08 / 249.45 ±0.70 / 250.09 ms │     no change │
│ QQuery 50 │        202.14 / 209.49 ±6.46 / 221.17 ms │        199.78 / 203.74 ±4.29 / 210.93 ms │     no change │
│ QQuery 51 │        175.95 / 178.03 ±1.11 / 179.19 ms │        172.63 / 177.02 ±3.39 / 182.81 ms │     no change │
│ QQuery 52 │        106.38 / 107.13 ±0.43 / 107.67 ms │        105.57 / 107.01 ±0.99 / 108.45 ms │     no change │
│ QQuery 53 │        101.94 / 103.04 ±1.68 / 106.31 ms │        101.00 / 101.82 ±0.77 / 103.09 ms │     no change │
│ QQuery 54 │        143.40 / 144.99 ±1.27 / 147.19 ms │        142.03 / 143.45 ±0.88 / 144.25 ms │     no change │
│ QQuery 55 │        105.77 / 106.13 ±0.27 / 106.56 ms │        105.12 / 105.85 ±0.45 / 106.41 ms │     no change │
│ QQuery 56 │        138.66 / 139.59 ±0.85 / 141.00 ms │        142.12 / 145.08 ±2.13 / 147.91 ms │     no change │
│ QQuery 57 │        163.46 / 165.20 ±1.69 / 168.42 ms │        170.28 / 172.03 ±2.33 / 176.60 ms │     no change │
│ QQuery 58 │        311.04 / 314.29 ±2.43 / 317.87 ms │        315.40 / 316.61 ±0.71 / 317.53 ms │     no change │
│ QQuery 59 │        201.64 / 203.22 ±1.33 / 204.98 ms │        204.00 / 204.61 ±0.61 / 205.53 ms │     no change │
│ QQuery 60 │        145.74 / 146.35 ±0.87 / 148.01 ms │        145.58 / 148.11 ±1.43 / 149.95 ms │     no change │
│ QQuery 61 │           14.11 / 14.21 ±0.08 / 14.31 ms │           14.12 / 14.24 ±0.13 / 14.46 ms │     no change │
│ QQuery 62 │       904.07 / 929.19 ±20.65 / 959.71 ms │       846.01 / 878.40 ±37.86 / 951.35 ms │ +1.06x faster │
│ QQuery 63 │        101.41 / 105.24 ±3.76 / 110.35 ms │        100.37 / 103.15 ±3.85 / 110.71 ms │     no change │
│ QQuery 64 │        652.77 / 654.83 ±2.07 / 658.23 ms │        654.26 / 657.44 ±1.98 / 659.86 ms │     no change │
│ QQuery 65 │        239.66 / 242.56 ±1.99 / 244.78 ms │        242.53 / 244.83 ±2.88 / 250.51 ms │     no change │
│ QQuery 66 │       223.02 / 239.28 ±12.82 / 258.59 ms │        210.54 / 218.40 ±7.86 / 229.35 ms │ +1.10x faster │
│ QQuery 67 │        314.13 / 317.33 ±1.89 / 319.24 ms │       289.55 / 300.91 ±14.20 / 325.83 ms │ +1.05x faster │
│ QQuery 68 │            9.28 / 11.50 ±4.21 / 19.92 ms │              8.49 / 8.71 ±0.21 / 9.09 ms │ +1.32x faster │
│ QQuery 69 │        100.25 / 102.21 ±2.45 / 106.88 ms │           97.30 / 98.27 ±0.56 / 98.81 ms │     no change │
│ QQuery 70 │        326.68 / 336.37 ±7.39 / 346.83 ms │       308.36 / 322.55 ±11.75 / 335.38 ms │     no change │
│ QQuery 71 │        136.65 / 139.08 ±3.21 / 145.34 ms │        132.72 / 132.98 ±0.19 / 133.18 ms │     no change │
│ QQuery 72 │       592.97 / 614.11 ±15.10 / 633.85 ms │       583.85 / 602.24 ±17.16 / 626.52 ms │     no change │
│ QQuery 73 │              6.49 / 6.63 ±0.21 / 7.04 ms │             7.23 / 8.40 ±2.06 / 12.51 ms │  1.27x slower │
│ QQuery 74 │        537.90 / 543.48 ±4.21 / 548.68 ms │        655.42 / 669.41 ±8.39 / 680.07 ms │  1.23x slower │
│ QQuery 75 │        264.32 / 267.41 ±3.28 / 273.75 ms │        274.68 / 276.45 ±1.08 / 277.55 ms │     no change │
│ QQuery 76 │        134.49 / 135.99 ±1.15 / 137.76 ms │        133.20 / 135.30 ±1.98 / 138.08 ms │     no change │
│ QQuery 77 │        190.74 / 191.58 ±0.98 / 193.26 ms │        187.06 / 189.65 ±1.73 / 191.74 ms │     no change │
│ QQuery 78 │        346.91 / 350.37 ±2.06 / 353.29 ms │        324.33 / 327.38 ±1.70 / 329.39 ms │ +1.07x faster │
│ QQuery 79 │       224.18 / 241.21 ±13.02 / 254.93 ms │        224.99 / 228.47 ±2.81 / 233.41 ms │ +1.06x faster │
│ QQuery 80 │        316.71 / 319.31 ±2.69 / 323.80 ms │        317.99 / 321.46 ±3.10 / 325.38 ms │     no change │
│ QQuery 81 │           25.40 / 26.16 ±1.00 / 28.15 ms │           26.92 / 27.54 ±0.52 / 28.24 ms │  1.05x slower │
│ QQuery 82 │           38.19 / 38.86 ±0.36 / 39.26 ms │           40.16 / 40.70 ±0.28 / 40.93 ms │     no change │
│ QQuery 83 │           35.86 / 36.28 ±0.30 / 36.74 ms │           38.26 / 38.57 ±0.22 / 38.91 ms │  1.06x slower │
│ QQuery 84 │           45.51 / 46.02 ±0.49 / 46.67 ms │           47.24 / 47.99 ±0.83 / 49.57 ms │     no change │
│ QQuery 85 │        140.65 / 141.46 ±1.22 / 143.87 ms │        144.36 / 145.53 ±1.54 / 148.41 ms │     no change │
│ QQuery 86 │           36.79 / 37.12 ±0.27 / 37.60 ms │           38.31 / 38.84 ±0.53 / 39.73 ms │     no change │
│ QQuery 87 │              3.44 / 3.51 ±0.12 / 3.74 ms │              3.67 / 3.78 ±0.13 / 4.03 ms │  1.08x slower │
│ QQuery 88 │         98.96 / 106.40 ±8.02 / 120.51 ms │        102.12 / 103.04 ±0.65 / 104.03 ms │     no change │
│ QQuery 89 │        115.80 / 116.62 ±0.59 / 117.49 ms │        118.46 / 119.91 ±1.78 / 123.36 ms │     no change │
│ QQuery 90 │           21.82 / 22.28 ±0.34 / 22.78 ms │           23.03 / 23.66 ±0.46 / 24.45 ms │  1.06x slower │
│ QQuery 91 │           58.43 / 59.15 ±0.77 / 60.60 ms │           60.60 / 61.03 ±0.62 / 62.26 ms │     no change │
│ QQuery 92 │           54.95 / 55.72 ±0.69 / 56.63 ms │           57.77 / 59.06 ±1.53 / 62.07 ms │  1.06x slower │
│ QQuery 93 │        179.15 / 179.87 ±0.59 / 180.91 ms │        188.30 / 190.57 ±1.85 / 193.89 ms │  1.06x slower │
│ QQuery 94 │           59.88 / 60.55 ±0.69 / 61.82 ms │           62.92 / 63.55 ±0.46 / 64.08 ms │     no change │
│ QQuery 95 │        124.26 / 125.50 ±1.09 / 127.21 ms │        128.76 / 129.73 ±0.50 / 130.12 ms │     no change │
│ QQuery 96 │           67.44 / 68.96 ±1.59 / 71.40 ms │           69.22 / 70.04 ±0.51 / 70.77 ms │     no change │
│ QQuery 97 │        114.92 / 117.11 ±1.37 / 118.73 ms │        123.59 / 124.97 ±1.71 / 128.26 ms │  1.07x slower │
│ QQuery 98 │        148.94 / 152.55 ±3.73 / 158.54 ms │        152.92 / 156.28 ±2.08 / 158.78 ms │     no change │
│ QQuery 99 │ 10885.36 / 10976.42 ±66.16 / 11052.19 ms │ 10836.31 / 10940.63 ±86.30 / 11086.76 ms │     no change │
└───────────┴──────────────────────────────────────────┴──────────────────────────────────────────┴───────────────┘
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━┓
┃ Benchmark Summary                        ┃            ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━┩
│ Total Time (HEAD)                        │ 31038.91ms │
│ Total Time (perf-count-distinct-clean)   │ 31088.00ms │
│ Average Time (HEAD)                      │   313.52ms │
│ Average Time (perf-count-distinct-clean) │   314.02ms │
│ Queries Faster                           │         10 │
│ Queries Slower                           │         18 │
│ Queries with No Change                   │         71 │
│ Queries with Failure                     │          0 │
└──────────────────────────────────────────┴────────────┘

Resource Usage

tpcds — base (merge-base)

Metric	Value
Wall time	160.0s
Peak memory	6.2 GiB
Avg memory	5.5 GiB
CPU user	258.3s
CPU sys	8.4s
Peak spill	0 B

tpcds — branch

Metric	Value
Wall time	160.0s
Peak memory	6.3 GiB
Avg memory	5.6 GiB
CPU user	261.0s
CPU sys	8.3s
Peak spill	0 B

---

File an issue against this benchmark runner

[lyne7-sc]

synced with main during development and accidentally pulled in some unrelated optimizations into the description. cleaned up now, sorry for the noise.