You are viewing a plain text version of this content. The canonical link for it is here.
Posted to github@datafusion.apache.org by "adriangb (via GitHub)" <gi...@apache.org> on 2026/09/09 21:09:24 UTC

[PR] [benchmark only] GroupsAccumulatorAdapter: walk only the groups a batch has rows for [datafusion]

adriangb opened a new pull request, #25132:
URL: https://github.com/apache/datafusion/pull/25132

   **Do not review or merge β€” this PR exists only so the benchmark bot can reach the ref.**
   
   It measures option 1 of https://github.com/apache/datafusion/issues/25116 (record the groups a batch has rows for, keep the per-group scratch vectors) as the counterfactual for https://github.com/apache/datafusion/pull/25123, which additionally replaces those vectors with a counting sort.
   
   #25123 is a reproducible +19% on `clickbench_extended` Q14 and +6.5% on Q5, but a reproducible βˆ’10% on Q2, which groups by a 110-value column with four `COUNT(DISTINCT)` adapters. This branch is the half of that change that has the same sign at every cardinality, and the question is how much of the win it keeps.
   
   Will be closed once the numbers are in.
   
   πŸ€– Generated with [Claude Code](https://claude.com/claude-code)
   


-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: github-unsubscribe@datafusion.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org


---------------------------------------------------------------------
To unsubscribe, e-mail: github-unsubscribe@datafusion.apache.org
For additional commands, e-mail: github-help@datafusion.apache.org


Re: [PR] [benchmark only] GroupsAccumulatorAdapter: walk only the groups a batch has rows for [datafusion]

Posted by "adriangbot (via GitHub)" <gi...@apache.org>.
adriangbot commented on PR #25132:
URL: https://github.com/apache/datafusion/pull/25132#issuecomment-5608818528

   πŸ€– Benchmark running (GKE) | [trigger](https://github.com/apache/datafusion/pull/25132#issuecomment-5608785809)
   **Instance:** `c4a-highmem-16` (12 vCPU / 65 GiB) | `Linux bench-c5608785809-2286-jrdws 6.12.94+ #1 SMP Fri Jul 17 09:42:57 UTC 2026 aarch64 GNU/Linux`
   <details><summary>CPU Details (lscpu)</summary>
   
   ```
   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 claude/adapter-option1-bench (3e27f79fa3b1b90a14512e28009ef89b0f99ac38) to 4048898 (merge-base) [diff](https://github.com/apache/datafusion/compare/40488988ad596c9b093ad60e1453430d803ce33c..3e27f79fa3b1b90a14512e28009ef89b0f99ac38)
   
   <details><summary>Run configuration</summary>
   
   ```yaml
   run benchmark clickbench_extended
   ```
   
   </details>
   
   Results will be posted here when complete
   
   ---
   [File an issue](https://github.com/adriangb/datafusion-benchmarking/issues) against this benchmark runner


-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: github-unsubscribe@datafusion.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org


---------------------------------------------------------------------
To unsubscribe, e-mail: github-unsubscribe@datafusion.apache.org
For additional commands, e-mail: github-help@datafusion.apache.org


Re: [PR] [benchmark only] GroupsAccumulatorAdapter: walk only the groups a batch has rows for [datafusion]

Posted by "adriangb (via GitHub)" <gi...@apache.org>.
adriangb commented on PR #25132:
URL: https://github.com/apache/datafusion/pull/25132#issuecomment-5608786764

   run benchmark clickbench_extended
   


-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: github-unsubscribe@datafusion.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org


---------------------------------------------------------------------
To unsubscribe, e-mail: github-unsubscribe@datafusion.apache.org
For additional commands, e-mail: github-help@datafusion.apache.org


Re: [PR] [benchmark only] GroupsAccumulatorAdapter: walk only the groups a batch has rows for [datafusion]

Posted by "adriangb (via GitHub)" <gi...@apache.org>.
adriangb commented on PR #25132:
URL: https://github.com/apache/datafusion/pull/25132#issuecomment-5611152224

   Numbers are in and captured in https://github.com/apache/datafusion/pull/25123. Closing.
   
   This branch (option 1 of https://github.com/apache/datafusion/issues/25116) is what #25123 now ships. The counting-sort variant it was measured against is faster where the groups are many, but 10% slower on `clickbench_extended` Q2, which groups by a 110-value column with four `COUNT(DISTINCT)` adapters. #25123 carries the full comparison.


-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: github-unsubscribe@datafusion.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org


---------------------------------------------------------------------
To unsubscribe, e-mail: github-unsubscribe@datafusion.apache.org
For additional commands, e-mail: github-help@datafusion.apache.org


Re: [PR] [benchmark only] GroupsAccumulatorAdapter: walk only the groups a batch has rows for [datafusion]

Posted by "adriangbot (via GitHub)" <gi...@apache.org>.
adriangbot commented on PR #25132:
URL: https://github.com/apache/datafusion/pull/25132#issuecomment-5609081208

   πŸ€– Benchmark completed (GKE) | [trigger](https://github.com/apache/datafusion/pull/25132#issuecomment-5608785809)
   
   **Instance:** `c4a-highmem-16` (12 vCPU / 65 GiB)
   
   Comparing claude/adapter-option1-bench (3e27f79fa3b1b90a14512e28009ef89b0f99ac38) to 4048898 (merge-base) [diff](https://github.com/apache/datafusion/compare/40488988ad596c9b093ad60e1453430d803ce33c..3e27f79fa3b1b90a14512e28009ef89b0f99ac38)
   
   <details><summary>Run configuration</summary>
   
   ```yaml
   run benchmark clickbench_extended
   ```
   
   </details>
   
   <details><summary>CPU Details (lscpu)</summary>
   
   ```
   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>
   
   <details><summary>Details</summary>
   <p>
   
   ```
   Comparing HEAD and claude_adapter-option1-bench
   --------------------
   Benchmark clickbench_extended.json
   --------------------
   ┏━━━━━━━━━━━┳━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
   ┃ Query     ┃        HEAD ┃ claude_adapter-option1-bench ┃        Change ┃
   ┑━━━━━━━━━━━╇━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
   β”‚ QQuery 0  β”‚   778.86 ms β”‚                    780.05 ms β”‚     no change β”‚
   β”‚ QQuery 1  β”‚   194.35 ms β”‚                    193.63 ms β”‚     no change β”‚
   β”‚ QQuery 2  β”‚   459.82 ms β”‚                    463.53 ms β”‚     no change β”‚
   β”‚ QQuery 3  β”‚   313.91 ms β”‚                    314.32 ms β”‚     no change β”‚
   β”‚ QQuery 4  β”‚  1167.98 ms β”‚                   1158.60 ms β”‚     no change β”‚
   β”‚ QQuery 5  β”‚ 10805.71 ms β”‚                  10625.13 ms β”‚     no change β”‚
   β”‚ QQuery 6  β”‚     2.56 ms β”‚                      2.56 ms β”‚     no change β”‚
   β”‚ QQuery 7  β”‚   662.49 ms β”‚                    705.45 ms β”‚  1.06x slower β”‚
   β”‚ QQuery 8  β”‚   409.10 ms β”‚                    409.07 ms β”‚     no change β”‚
   β”‚ QQuery 9  β”‚  2873.73 ms β”‚                   2927.81 ms β”‚     no change β”‚
   β”‚ QQuery 10 β”‚   626.41 ms β”‚                    651.39 ms β”‚     no change β”‚
   β”‚ QQuery 11 β”‚  2194.48 ms β”‚                   2182.68 ms β”‚     no change β”‚
   β”‚ QQuery 12 β”‚   187.22 ms β”‚                    188.65 ms β”‚     no change β”‚
   β”‚ QQuery 13 β”‚   543.05 ms β”‚                    547.66 ms β”‚     no change β”‚
   β”‚ QQuery 14 β”‚  2752.34 ms β”‚                   2403.54 ms β”‚ +1.15x faster β”‚
   β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”΄β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”΄β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”΄β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜
   ┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━┓
   ┃ Benchmark Summary                           ┃            ┃
   ┑━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━┩
   β”‚ Total Time (HEAD)                           β”‚ 23972.00ms β”‚
   β”‚ Total Time (claude_adapter-option1-bench)   β”‚ 23554.06ms β”‚
   β”‚ Average Time (HEAD)                         β”‚  1598.13ms β”‚
   β”‚ Average Time (claude_adapter-option1-bench) β”‚  1570.27ms β”‚
   β”‚ Queries Faster                              β”‚          1 β”‚
   β”‚ Queries Slower                              β”‚          1 β”‚
   β”‚ Queries with No Change                      β”‚         13 β”‚
   β”‚ Queries with Failure                        β”‚          0 β”‚
   β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”΄β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜
   
   Distribution per query (min / mean Β±stddev / max):
   
   Comparing HEAD and claude_adapter-option1-bench
   --------------------
   Benchmark clickbench_extended.json
   --------------------
   ┏━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
   ┃ Query     ┃                                      HEAD ┃              claude_adapter-option1-bench ┃        Change ┃
   ┑━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
   β”‚ QQuery 0  β”‚         778.86 / 791.34 Β±9.55 / 808.33 ms β”‚         780.05 / 789.79 Β±8.27 / 802.65 ms β”‚     no change β”‚
   β”‚ QQuery 1  β”‚         194.35 / 198.20 Β±4.86 / 207.41 ms β”‚         193.63 / 197.24 Β±6.40 / 210.03 ms β”‚     no change β”‚
   β”‚ QQuery 2  β”‚         459.82 / 462.07 Β±2.14 / 465.13 ms β”‚         463.53 / 468.96 Β±3.60 / 472.53 ms β”‚     no change β”‚
   β”‚ QQuery 3  β”‚         313.91 / 315.36 Β±1.06 / 316.85 ms β”‚         314.32 / 315.30 Β±1.14 / 317.44 ms β”‚     no change β”‚
   β”‚ QQuery 4  β”‚     1167.98 / 1185.64 Β±10.16 / 1195.70 ms β”‚      1158.60 / 1172.29 Β±8.04 / 1183.46 ms β”‚     no change β”‚
   β”‚ QQuery 5  β”‚ 10805.71 / 11288.34 Β±431.55 / 12011.81 ms β”‚ 10625.13 / 10873.19 Β±148.88 / 11078.80 ms β”‚     no change β”‚
   β”‚ QQuery 6  β”‚               2.56 / 2.83 Β±0.30 / 3.41 ms β”‚               2.56 / 2.83 Β±0.34 / 3.50 ms β”‚     no change β”‚
   β”‚ QQuery 7  β”‚        662.49 / 689.80 Β±14.18 / 701.76 ms β”‚        705.45 / 747.98 Β±33.19 / 806.04 ms β”‚  1.08x slower β”‚
   β”‚ QQuery 8  β”‚        409.10 / 423.08 Β±18.09 / 458.78 ms β”‚         409.07 / 414.41 Β±3.06 / 418.57 ms β”‚     no change β”‚
   β”‚ QQuery 9  β”‚    2873.73 / 3023.74 Β±104.34 / 3170.51 ms β”‚     2927.81 / 2974.29 Β±32.96 / 3028.97 ms β”‚     no change β”‚
   β”‚ QQuery 10 β”‚        626.41 / 669.43 Β±46.19 / 753.88 ms β”‚        651.39 / 690.09 Β±41.84 / 770.74 ms β”‚     no change β”‚
   β”‚ QQuery 11 β”‚     2194.48 / 2260.77 Β±52.90 / 2354.37 ms β”‚     2182.68 / 2221.67 Β±29.05 / 2262.72 ms β”‚     no change β”‚
   β”‚ QQuery 12 β”‚        187.22 / 229.88 Β±79.76 / 389.34 ms β”‚        188.65 / 228.64 Β±76.25 / 381.08 ms β”‚     no change β”‚
   β”‚ QQuery 13 β”‚        543.05 / 558.54 Β±21.73 / 601.62 ms β”‚         547.66 / 556.05 Β±9.45 / 571.63 ms β”‚     no change β”‚
   β”‚ QQuery 14 β”‚     2752.34 / 2847.40 Β±71.83 / 2950.86 ms β”‚     2403.54 / 2462.89 Β±40.46 / 2511.87 ms β”‚ +1.16x faster β”‚
   β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”΄β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”΄β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”΄β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜
   ┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━┓
   ┃ Benchmark Summary                           ┃            ┃
   ┑━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━┩
   β”‚ Total Time (HEAD)                           β”‚ 24946.42ms β”‚
   β”‚ Total Time (claude_adapter-option1-bench)   β”‚ 24115.62ms β”‚
   β”‚ Average Time (HEAD)                         β”‚  1663.09ms β”‚
   β”‚ Average Time (claude_adapter-option1-bench) β”‚  1607.71ms β”‚
   β”‚ Queries Faster                              β”‚          1 β”‚
   β”‚ Queries Slower                              β”‚          1 β”‚
   β”‚ Queries with No Change                      β”‚         13 β”‚
   β”‚ Queries with Failure                        β”‚          0 β”‚
   β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”΄β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜
   ```
   
   </p>
   </details>
   
   <details><summary>Resource Usage</summary>
   
   **clickbench_extended β€” base (merge-base)**
   | Metric | Value |
   |--------|-------|
   | Wall time | 130.0s |
   | Peak memory | 11.1 GiB |
   | Avg memory | 5.0 GiB |
   | CPU user | 1120.9s |
   | CPU sys | 56.2s |
   | Peak spill | 0 B |
   
   **clickbench_extended β€” branch**
   | Metric | Value |
   |--------|-------|
   | Wall time | 125.0s |
   | Peak memory | 11.7 GiB |
   | Avg memory | 5.0 GiB |
   | CPU user | 1092.1s |
   | CPU sys | 56.9s |
   | Peak spill | 0 B |
   
   </details>
   
   
   ---
   [File an issue](https://github.com/adriangb/datafusion-benchmarking/issues) against this benchmark runner


-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: github-unsubscribe@datafusion.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org


---------------------------------------------------------------------
To unsubscribe, e-mail: github-unsubscribe@datafusion.apache.org
For additional commands, e-mail: github-help@datafusion.apache.org


Re: [PR] [benchmark only] GroupsAccumulatorAdapter: walk only the groups a batch has rows for [datafusion]

Posted by "adriangbot (via GitHub)" <gi...@apache.org>.
adriangbot commented on PR #25132:
URL: https://github.com/apache/datafusion/pull/25132#issuecomment-5608819085

   πŸ€– Benchmark running (GKE) | [trigger](https://github.com/apache/datafusion/pull/25132#issuecomment-5608786764)
   **Instance:** `c4a-highmem-16` (12 vCPU / 65 GiB) | `Linux bench-c5608786764-2287-pxflk 6.12.94+ #1 SMP Fri Jul 17 09:42:57 UTC 2026 aarch64 GNU/Linux`
   <details><summary>CPU Details (lscpu)</summary>
   
   ```
   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 claude/adapter-option1-bench (3e27f79fa3b1b90a14512e28009ef89b0f99ac38) to 4048898 (merge-base) [diff](https://github.com/apache/datafusion/compare/40488988ad596c9b093ad60e1453430d803ce33c..3e27f79fa3b1b90a14512e28009ef89b0f99ac38)
   
   <details><summary>Run configuration</summary>
   
   ```yaml
   run benchmark clickbench_extended
   ```
   
   </details>
   
   Results will be posted here when complete
   
   ---
   [File an issue](https://github.com/adriangb/datafusion-benchmarking/issues) against this benchmark runner


-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: github-unsubscribe@datafusion.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org


---------------------------------------------------------------------
To unsubscribe, e-mail: github-unsubscribe@datafusion.apache.org
For additional commands, e-mail: github-help@datafusion.apache.org


Re: [PR] [benchmark only] GroupsAccumulatorAdapter: walk only the groups a batch has rows for [datafusion]

Posted by "adriangbot (via GitHub)" <gi...@apache.org>.
adriangbot commented on PR #25132:
URL: https://github.com/apache/datafusion/pull/25132#issuecomment-5609088373

   πŸ€– Benchmark completed (GKE) | [trigger](https://github.com/apache/datafusion/pull/25132#issuecomment-5608786764)
   
   **Instance:** `c4a-highmem-16` (12 vCPU / 65 GiB)
   
   Comparing claude/adapter-option1-bench (3e27f79fa3b1b90a14512e28009ef89b0f99ac38) to 4048898 (merge-base) [diff](https://github.com/apache/datafusion/compare/40488988ad596c9b093ad60e1453430d803ce33c..3e27f79fa3b1b90a14512e28009ef89b0f99ac38)
   
   <details><summary>Run configuration</summary>
   
   ```yaml
   run benchmark clickbench_extended
   ```
   
   </details>
   
   <details><summary>CPU Details (lscpu)</summary>
   
   ```
   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>
   
   <details><summary>Details</summary>
   <p>
   
   ```
   Comparing HEAD and claude_adapter-option1-bench
   --------------------
   Benchmark clickbench_extended.json
   --------------------
   ┏━━━━━━━━━━━┳━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
   ┃ Query     ┃        HEAD ┃ claude_adapter-option1-bench ┃        Change ┃
   ┑━━━━━━━━━━━╇━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
   β”‚ QQuery 0  β”‚   815.64 ms β”‚                    823.58 ms β”‚     no change β”‚
   β”‚ QQuery 1  β”‚   194.40 ms β”‚                    193.73 ms β”‚     no change β”‚
   β”‚ QQuery 2  β”‚   462.84 ms β”‚                    465.46 ms β”‚     no change β”‚
   β”‚ QQuery 3  β”‚   314.37 ms β”‚                    319.27 ms β”‚     no change β”‚
   β”‚ QQuery 4  β”‚  1152.04 ms β”‚                   1161.96 ms β”‚     no change β”‚
   β”‚ QQuery 5  β”‚ 11430.56 ms β”‚                  10566.64 ms β”‚ +1.08x faster β”‚
   β”‚ QQuery 6  β”‚     2.60 ms β”‚                      2.92 ms β”‚  1.12x slower β”‚
   β”‚ QQuery 7  β”‚   714.64 ms β”‚                    707.26 ms β”‚     no change β”‚
   β”‚ QQuery 8  β”‚   421.50 ms β”‚                    419.38 ms β”‚     no change β”‚
   β”‚ QQuery 9  β”‚  3004.50 ms β”‚                   3061.48 ms β”‚     no change β”‚
   β”‚ QQuery 10 β”‚   656.43 ms β”‚                    635.36 ms β”‚     no change β”‚
   β”‚ QQuery 11 β”‚  2305.77 ms β”‚                   2293.01 ms β”‚     no change β”‚
   β”‚ QQuery 12 β”‚   201.40 ms β”‚                    191.71 ms β”‚     no change β”‚
   β”‚ QQuery 13 β”‚   539.59 ms β”‚                    550.24 ms β”‚     no change β”‚
   β”‚ QQuery 14 β”‚  2864.99 ms β”‚                   2347.29 ms β”‚ +1.22x faster β”‚
   β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”΄β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”΄β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”΄β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜
   ┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━┓
   ┃ Benchmark Summary                           ┃            ┃
   ┑━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━┩
   β”‚ Total Time (HEAD)                           β”‚ 25081.27ms β”‚
   β”‚ Total Time (claude_adapter-option1-bench)   β”‚ 23739.27ms β”‚
   β”‚ Average Time (HEAD)                         β”‚  1672.08ms β”‚
   β”‚ Average Time (claude_adapter-option1-bench) β”‚  1582.62ms β”‚
   β”‚ Queries Faster                              β”‚          2 β”‚
   β”‚ Queries Slower                              β”‚          1 β”‚
   β”‚ Queries with No Change                      β”‚         12 β”‚
   β”‚ Queries with Failure                        β”‚          0 β”‚
   β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”΄β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜
   
   Distribution per query (min / mean Β±stddev / max):
   
   Comparing HEAD and claude_adapter-option1-bench
   --------------------
   Benchmark clickbench_extended.json
   --------------------
   ┏━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
   ┃ Query     ┃                                      HEAD ┃              claude_adapter-option1-bench ┃        Change ┃
   ┑━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
   β”‚ QQuery 0  β”‚       815.64 / 892.04 Β±71.57 / 1021.57 ms β”‚        823.58 / 851.69 Β±18.36 / 871.66 ms β”‚     no change β”‚
   β”‚ QQuery 1  β”‚         194.40 / 197.69 Β±3.69 / 204.55 ms β”‚         193.73 / 194.95 Β±0.83 / 196.24 ms β”‚     no change β”‚
   β”‚ QQuery 2  β”‚         462.84 / 465.93 Β±2.26 / 468.44 ms β”‚         465.46 / 471.29 Β±4.12 / 477.77 ms β”‚     no change β”‚
   β”‚ QQuery 3  β”‚         314.37 / 316.81 Β±1.61 / 319.14 ms β”‚         319.27 / 321.30 Β±1.34 / 322.86 ms β”‚     no change β”‚
   β”‚ QQuery 4  β”‚     1152.04 / 1183.31 Β±27.45 / 1232.31 ms β”‚     1161.96 / 1180.47 Β±25.70 / 1228.73 ms β”‚     no change β”‚
   β”‚ QQuery 5  β”‚ 11430.56 / 11700.45 Β±209.15 / 11938.37 ms β”‚ 10566.64 / 10827.72 Β±237.65 / 11202.71 ms β”‚ +1.08x faster β”‚
   β”‚ QQuery 6  β”‚               2.60 / 2.93 Β±0.37 / 3.64 ms β”‚               2.92 / 3.10 Β±0.18 / 3.43 ms β”‚  1.06x slower β”‚
   β”‚ QQuery 7  β”‚        714.64 / 745.06 Β±28.72 / 792.09 ms β”‚        707.26 / 730.70 Β±13.07 / 746.19 ms β”‚     no change β”‚
   β”‚ QQuery 8  β”‚        421.50 / 448.93 Β±33.04 / 497.60 ms β”‚        419.38 / 437.39 Β±31.01 / 499.23 ms β”‚     no change β”‚
   β”‚ QQuery 9  β”‚     3004.50 / 3057.46 Β±61.18 / 3170.98 ms β”‚    3061.48 / 3176.04 Β±101.28 / 3312.19 ms β”‚     no change β”‚
   β”‚ QQuery 10 β”‚      656.43 / 734.28 Β±136.00 / 1005.97 ms β”‚        635.36 / 687.96 Β±66.01 / 816.49 ms β”‚ +1.07x faster β”‚
   β”‚ QQuery 11 β”‚     2305.77 / 2324.05 Β±16.77 / 2352.37 ms β”‚     2293.01 / 2349.65 Β±54.17 / 2447.48 ms β”‚     no change β”‚
   β”‚ QQuery 12 β”‚        201.40 / 221.53 Β±32.27 / 285.87 ms β”‚        191.71 / 202.25 Β±12.93 / 221.14 ms β”‚ +1.10x faster β”‚
   β”‚ QQuery 13 β”‚        539.59 / 570.46 Β±24.02 / 612.41 ms β”‚        550.24 / 565.22 Β±23.49 / 611.97 ms β”‚     no change β”‚
   β”‚ QQuery 14 β”‚     2864.99 / 2907.12 Β±38.45 / 2954.91 ms β”‚    2347.29 / 2550.52 Β±129.75 / 2729.80 ms β”‚ +1.14x faster β”‚
   β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”΄β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”΄β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”΄β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜
   ┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━┓
   ┃ Benchmark Summary                           ┃            ┃
   ┑━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━┩
   β”‚ Total Time (HEAD)                           β”‚ 25768.04ms β”‚
   β”‚ Total Time (claude_adapter-option1-bench)   β”‚ 24550.24ms β”‚
   β”‚ Average Time (HEAD)                         β”‚  1717.87ms β”‚
   β”‚ Average Time (claude_adapter-option1-bench) β”‚  1636.68ms β”‚
   β”‚ Queries Faster                              β”‚          4 β”‚
   β”‚ Queries Slower                              β”‚          1 β”‚
   β”‚ Queries with No Change                      β”‚         10 β”‚
   β”‚ Queries with Failure                        β”‚          0 β”‚
   β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”΄β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜
   ```
   
   </p>
   </details>
   
   <details><summary>Resource Usage</summary>
   
   **clickbench_extended β€” base (merge-base)**
   | Metric | Value |
   |--------|-------|
   | Wall time | 130.0s |
   | Peak memory | 11.6 GiB |
   | Avg memory | 5.2 GiB |
   | CPU user | 1149.4s |
   | CPU sys | 59.9s |
   | Peak spill | 0 B |
   
   **clickbench_extended β€” branch**
   | Metric | Value |
   |--------|-------|
   | Wall time | 125.0s |
   | Peak memory | 11.5 GiB |
   | Avg memory | 5.2 GiB |
   | CPU user | 1104.8s |
   | CPU sys | 60.4s |
   | Peak spill | 0 B |
   
   </details>
   
   
   ---
   [File an issue](https://github.com/adriangb/datafusion-benchmarking/issues) against this benchmark runner


-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: github-unsubscribe@datafusion.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org


---------------------------------------------------------------------
To unsubscribe, e-mail: github-unsubscribe@datafusion.apache.org
For additional commands, e-mail: github-help@datafusion.apache.org


Re: [PR] [benchmark only] GroupsAccumulatorAdapter: walk only the groups a batch has rows for [datafusion]

Posted by "adriangb (via GitHub)" <gi...@apache.org>.
adriangb commented on PR #25132:
URL: https://github.com/apache/datafusion/pull/25132#issuecomment-5608786400

   run benchmark clickbench_extended
   


-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: github-unsubscribe@datafusion.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org


---------------------------------------------------------------------
To unsubscribe, e-mail: github-unsubscribe@datafusion.apache.org
For additional commands, e-mail: github-help@datafusion.apache.org


Re: [PR] [benchmark only] GroupsAccumulatorAdapter: walk only the groups a batch has rows for [datafusion]

Posted by "codecov-commenter (via GitHub)" <gi...@apache.org>.
codecov-commenter commented on PR #25132:
URL: https://github.com/apache/datafusion/pull/25132#issuecomment-5610318074

   ## [Codecov](https://app.codecov.io/gh/apache/datafusion/pull/25132?dropdown=coverage&src=pr&el=h1&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=apache) Report
   :white_check_mark: All modified and coverable lines are covered by tests.
   :white_check_mark: Project coverage is 81.80%. Comparing base ([`4048898`](https://app.codecov.io/gh/apache/datafusion/commit/40488988ad596c9b093ad60e1453430d803ce33c?dropdown=coverage&el=desc&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=apache)) to head ([`3e27f79`](https://app.codecov.io/gh/apache/datafusion/commit/3e27f79fa3b1b90a14512e28009ef89b0f99ac38?dropdown=coverage&el=desc&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=apache)).
   
   <details><summary>Additional details and impacted files</summary>
   
   
   
   ```diff
   @@            Coverage Diff             @@
   ##             main   #25132      +/-   ##
   ==========================================
   - Coverage   81.80%   81.80%   -0.01%     
   ==========================================
     Files        1130     1130              
     Lines      417754   417755       +1     
     Branches   417754   417755       +1     
   ==========================================
   - Hits       341754   341747       -7     
   - Misses      55875    55880       +5     
   - Partials    20125    20128       +3     
   ```
   </details>
   
   [:umbrella: View full report in Codecov by Harness](https://app.codecov.io/gh/apache/datafusion/pull/25132?dropdown=coverage&src=pr&el=continue&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=apache).   
   :loudspeaker: Have feedback on the report? [Share it here](https://about.codecov.io/codecov-pr-comment-feedback/?utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=apache).
   <details><summary> :rocket: New features to boost your workflow: </summary>
   
   - :snowflake: [Test Analytics](https://docs.codecov.com/docs/test-analytics): Detect flaky tests, report on failures, and find test suite problems.
   - :package: [JS Bundle Analysis](https://docs.codecov.com/docs/javascript-bundle-analysis): Save yourself from yourself by tracking and limiting bundle sizes in JS merges.
   </details>


-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: github-unsubscribe@datafusion.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org


---------------------------------------------------------------------
To unsubscribe, e-mail: github-unsubscribe@datafusion.apache.org
For additional commands, e-mail: github-help@datafusion.apache.org


Re: [PR] [benchmark only] GroupsAccumulatorAdapter: walk only the groups a batch has rows for [datafusion]

Posted by "adriangbot (via GitHub)" <gi...@apache.org>.
adriangbot commented on PR #25132:
URL: https://github.com/apache/datafusion/pull/25132#issuecomment-5608822813

   πŸ€– Benchmark running (GKE) | [trigger](https://github.com/apache/datafusion/pull/25132#issuecomment-5608786400)
   **Instance:** `c4a-highmem-16` (12 vCPU / 65 GiB) | `Linux bench-c5608786400-2288-65sj7 6.12.94+ #1 SMP Fri Jul 17 09:42:57 UTC 2026 aarch64 GNU/Linux`
   <details><summary>CPU Details (lscpu)</summary>
   
   ```
   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 claude/adapter-option1-bench (3e27f79fa3b1b90a14512e28009ef89b0f99ac38) to 4048898 (merge-base) [diff](https://github.com/apache/datafusion/compare/40488988ad596c9b093ad60e1453430d803ce33c..3e27f79fa3b1b90a14512e28009ef89b0f99ac38)
   
   <details><summary>Run configuration</summary>
   
   ```yaml
   run benchmark clickbench_extended
   ```
   
   </details>
   
   Results will be posted here when complete
   
   ---
   [File an issue](https://github.com/adriangb/datafusion-benchmarking/issues) against this benchmark runner


-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: github-unsubscribe@datafusion.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org


---------------------------------------------------------------------
To unsubscribe, e-mail: github-unsubscribe@datafusion.apache.org
For additional commands, e-mail: github-help@datafusion.apache.org


Re: [PR] [benchmark only] GroupsAccumulatorAdapter: walk only the groups a batch has rows for [datafusion]

Posted by "adriangb (via GitHub)" <gi...@apache.org>.
adriangb closed pull request #25132: [benchmark only] GroupsAccumulatorAdapter: walk only the groups a batch has rows for
URL: https://github.com/apache/datafusion/pull/25132


-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: github-unsubscribe@datafusion.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org


---------------------------------------------------------------------
To unsubscribe, e-mail: github-unsubscribe@datafusion.apache.org
For additional commands, e-mail: github-help@datafusion.apache.org


Re: [PR] [benchmark only] GroupsAccumulatorAdapter: walk only the groups a batch has rows for [datafusion]

Posted by "adriangb (via GitHub)" <gi...@apache.org>.
adriangb commented on PR #25132:
URL: https://github.com/apache/datafusion/pull/25132#issuecomment-5608785809

   run benchmark clickbench_extended
   


-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: github-unsubscribe@datafusion.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org


---------------------------------------------------------------------
To unsubscribe, e-mail: github-unsubscribe@datafusion.apache.org
For additional commands, e-mail: github-help@datafusion.apache.org


Re: [PR] [benchmark only] GroupsAccumulatorAdapter: walk only the groups a batch has rows for [datafusion]

Posted by "adriangbot (via GitHub)" <gi...@apache.org>.
adriangbot commented on PR #25132:
URL: https://github.com/apache/datafusion/pull/25132#issuecomment-5609084615

   πŸ€– Benchmark completed (GKE) | [trigger](https://github.com/apache/datafusion/pull/25132#issuecomment-5608786400)
   
   **Instance:** `c4a-highmem-16` (12 vCPU / 65 GiB)
   
   Comparing claude/adapter-option1-bench (3e27f79fa3b1b90a14512e28009ef89b0f99ac38) to 4048898 (merge-base) [diff](https://github.com/apache/datafusion/compare/40488988ad596c9b093ad60e1453430d803ce33c..3e27f79fa3b1b90a14512e28009ef89b0f99ac38)
   
   <details><summary>Run configuration</summary>
   
   ```yaml
   run benchmark clickbench_extended
   ```
   
   </details>
   
   <details><summary>CPU Details (lscpu)</summary>
   
   ```
   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>
   
   <details><summary>Details</summary>
   <p>
   
   ```
   Comparing HEAD and claude_adapter-option1-bench
   --------------------
   Benchmark clickbench_extended.json
   --------------------
   ┏━━━━━━━━━━━┳━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
   ┃ Query     ┃        HEAD ┃ claude_adapter-option1-bench ┃        Change ┃
   ┑━━━━━━━━━━━╇━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
   β”‚ QQuery 0  β”‚   795.68 ms β”‚                    792.57 ms β”‚     no change β”‚
   β”‚ QQuery 1  β”‚   193.95 ms β”‚                    193.57 ms β”‚     no change β”‚
   β”‚ QQuery 2  β”‚   461.23 ms β”‚                    466.61 ms β”‚     no change β”‚
   β”‚ QQuery 3  β”‚   315.47 ms β”‚                    314.85 ms β”‚     no change β”‚
   β”‚ QQuery 4  β”‚  1156.58 ms β”‚                   1147.96 ms β”‚     no change β”‚
   β”‚ QQuery 5  β”‚ 10823.48 ms β”‚                  10166.33 ms β”‚ +1.06x faster β”‚
   β”‚ QQuery 6  β”‚     2.58 ms β”‚                      2.70 ms β”‚     no change β”‚
   β”‚ QQuery 7  β”‚   675.88 ms β”‚                    674.74 ms β”‚     no change β”‚
   β”‚ QQuery 8  β”‚   413.11 ms β”‚                    415.41 ms β”‚     no change β”‚
   β”‚ QQuery 9  β”‚  2954.54 ms β”‚                   2911.08 ms β”‚     no change β”‚
   β”‚ QQuery 10 β”‚   621.77 ms β”‚                    632.10 ms β”‚     no change β”‚
   β”‚ QQuery 11 β”‚  2126.95 ms β”‚                   2261.95 ms β”‚  1.06x slower β”‚
   β”‚ QQuery 12 β”‚   188.93 ms β”‚                    189.36 ms β”‚     no change β”‚
   β”‚ QQuery 13 β”‚   539.33 ms β”‚                    545.76 ms β”‚     no change β”‚
   β”‚ QQuery 14 β”‚  2727.00 ms β”‚                   2358.37 ms β”‚ +1.16x faster β”‚
   β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”΄β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”΄β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”΄β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜
   ┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━┓
   ┃ Benchmark Summary                           ┃            ┃
   ┑━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━┩
   β”‚ Total Time (HEAD)                           β”‚ 23996.48ms β”‚
   β”‚ Total Time (claude_adapter-option1-bench)   β”‚ 23073.35ms β”‚
   β”‚ Average Time (HEAD)                         β”‚  1599.77ms β”‚
   β”‚ Average Time (claude_adapter-option1-bench) β”‚  1538.22ms β”‚
   β”‚ Queries Faster                              β”‚          2 β”‚
   β”‚ Queries Slower                              β”‚          1 β”‚
   β”‚ Queries with No Change                      β”‚         12 β”‚
   β”‚ Queries with Failure                        β”‚          0 β”‚
   β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”΄β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜
   
   Distribution per query (min / mean Β±stddev / max):
   
   Comparing HEAD and claude_adapter-option1-bench
   --------------------
   Benchmark clickbench_extended.json
   --------------------
   ┏━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓
   ┃ Query     ┃                                      HEAD ┃              claude_adapter-option1-bench ┃        Change ┃
   ┑━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩
   β”‚ QQuery 0  β”‚        795.68 / 821.43 Β±17.00 / 840.48 ms β”‚         792.57 / 802.07 Β±7.30 / 811.95 ms β”‚     no change β”‚
   β”‚ QQuery 1  β”‚         193.95 / 197.55 Β±5.08 / 207.62 ms β”‚         193.57 / 194.12 Β±0.45 / 194.78 ms β”‚     no change β”‚
   β”‚ QQuery 2  β”‚         461.23 / 464.20 Β±2.68 / 468.84 ms β”‚         466.61 / 469.27 Β±2.81 / 474.51 ms β”‚     no change β”‚
   β”‚ QQuery 3  β”‚         315.47 / 317.27 Β±1.33 / 319.25 ms β”‚         314.85 / 315.92 Β±1.18 / 318.12 ms β”‚     no change β”‚
   β”‚ QQuery 4  β”‚     1156.58 / 1172.38 Β±13.64 / 1195.43 ms β”‚     1147.96 / 1197.85 Β±44.36 / 1279.28 ms β”‚     no change β”‚
   β”‚ QQuery 5  β”‚ 10823.48 / 11333.36 Β±354.84 / 11889.33 ms β”‚ 10166.33 / 10645.17 Β±412.93 / 11387.93 ms β”‚ +1.06x faster β”‚
   β”‚ QQuery 6  β”‚               2.58 / 2.82 Β±0.30 / 3.40 ms β”‚             2.70 / 9.60 Β±13.34 / 36.26 ms β”‚  3.40x slower β”‚
   β”‚ QQuery 7  β”‚        675.88 / 716.21 Β±45.00 / 798.67 ms β”‚        674.74 / 708.18 Β±22.28 / 744.03 ms β”‚     no change β”‚
   β”‚ QQuery 8  β”‚        413.11 / 430.52 Β±18.90 / 463.05 ms β”‚        415.41 / 442.96 Β±37.20 / 515.71 ms β”‚     no change β”‚
   β”‚ QQuery 9  β”‚     2954.54 / 3046.96 Β±83.97 / 3186.23 ms β”‚     2911.08 / 3014.89 Β±66.42 / 3109.65 ms β”‚     no change β”‚
   β”‚ QQuery 10 β”‚       621.77 / 712.64 Β±121.98 / 952.87 ms β”‚        632.10 / 655.60 Β±21.63 / 696.29 ms β”‚ +1.09x faster β”‚
   β”‚ QQuery 11 β”‚     2126.95 / 2232.49 Β±58.52 / 2297.30 ms β”‚     2261.95 / 2284.40 Β±17.30 / 2305.96 ms β”‚     no change β”‚
   β”‚ QQuery 12 β”‚        188.93 / 207.87 Β±32.72 / 272.90 ms β”‚        189.36 / 229.74 Β±64.07 / 356.71 ms β”‚  1.11x slower β”‚
   β”‚ QQuery 13 β”‚         539.33 / 547.25 Β±7.41 / 559.22 ms β”‚         545.76 / 549.69 Β±4.77 / 558.67 ms β”‚     no change β”‚
   β”‚ QQuery 14 β”‚     2727.00 / 2767.01 Β±34.71 / 2815.40 ms β”‚     2358.37 / 2424.45 Β±50.72 / 2482.04 ms β”‚ +1.14x faster β”‚
   β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”΄β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”΄β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”΄β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜
   ┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━┓
   ┃ Benchmark Summary                           ┃            ┃
   ┑━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━┩
   β”‚ Total Time (HEAD)                           β”‚ 24969.97ms β”‚
   β”‚ Total Time (claude_adapter-option1-bench)   β”‚ 23943.92ms β”‚
   β”‚ Average Time (HEAD)                         β”‚  1664.66ms β”‚
   β”‚ Average Time (claude_adapter-option1-bench) β”‚  1596.26ms β”‚
   β”‚ Queries Faster                              β”‚          3 β”‚
   β”‚ Queries Slower                              β”‚          2 β”‚
   β”‚ Queries with No Change                      β”‚         10 β”‚
   β”‚ Queries with Failure                        β”‚          0 β”‚
   β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”΄β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜
   ```
   
   </p>
   </details>
   
   <details><summary>Resource Usage</summary>
   
   **clickbench_extended β€” base (merge-base)**
   | Metric | Value |
   |--------|-------|
   | Wall time | 130.0s |
   | Peak memory | 13.3 GiB |
   | Avg memory | 5.2 GiB |
   | CPU user | 1137.6s |
   | CPU sys | 55.2s |
   | Peak spill | 0 B |
   
   **clickbench_extended β€” branch**
   | Metric | Value |
   |--------|-------|
   | Wall time | 125.0s |
   | Peak memory | 11.4 GiB |
   | Avg memory | 4.9 GiB |
   | CPU user | 1085.8s |
   | CPU sys | 55.9s |
   | Peak spill | 0 B |
   
   </details>
   
   
   ---
   [File an issue](https://github.com/adriangb/datafusion-benchmarking/issues) against this benchmark runner


-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: github-unsubscribe@datafusion.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org


---------------------------------------------------------------------
To unsubscribe, e-mail: github-unsubscribe@datafusion.apache.org
For additional commands, e-mail: github-help@datafusion.apache.org