Open
Conversation
AdamGS
force-pushed
the
adamg/aggregate-fn-array-uncompressed
branch
from
1c091b1 to
c8699a6
Compare
Merging this PR will degrade performance by 10.6%
|
| Mode | Benchmark | BASE |
HEAD |
Efficiency | |
|---|---|---|---|---|---|
| ⚡ | Simulation | take_search_chunked[(0.1, 0.5)] |
2.4 ms | 2.1 ms | +14.49% |
| ⚡ | Simulation | take_search_chunked[(0.01, 0.5)] |
2 ms | 1.7 ms | +18.64% |
| ⚡ | Simulation | take_search[(0.01, 1.0)] |
3.3 ms | 2.5 ms | +28.78% |
| ⚡ | Simulation | take_search_chunked[(0.005, 1.0)] |
3.7 ms | 3.1 ms | +20.18% |
| ⚡ | Simulation | take_search_chunked[(0.1, 1.0)] |
4.9 ms | 4.2 ms | +14.61% |
| ⚡ | Simulation | take_search[(0.1, 0.1)] |
458.5 µs | 385.2 µs | +19.01% |
| ⚡ | Simulation | take_search[(0.1, 0.5)] |
2.2 ms | 1.8 ms | +20.41% |
| ⚡ | Simulation | take_search_chunked[(0.005, 0.5)] |
1.9 ms | 1.5 ms | +20.07% |
| ⚡ | Simulation | take_search[(0.005, 0.5)] |
1.5 ms | 1.2 ms | +31.06% |
| ⚡ | Simulation | take_search_chunked[(0.01, 0.1)] |
408.4 µs | 346.2 µs | +17.97% |
| ⚡ | Simulation | take_search[(0.1, 1.0)] |
4.3 ms | 3.5 ms | +20.64% |
| ⚡ | Simulation | take_search_chunked[(0.005, 0.05)] |
200.4 µs | 169.1 µs | +18.5% |
| ⚡ | Simulation | take_search_chunked[(0.005, 0.1)] |
383.8 µs | 321.6 µs | +19.35% |
| ⚡ | Simulation | take_search_chunked[(0.1, 0.05)] |
279 µs | 247.7 µs | +12.62% |
| ⚡ | Simulation | take_search[(0.005, 0.05)] |
167.9 µs | 131.2 µs | +28.04% |
| ⚡ | Simulation | take_search[(0.01, 0.5)] |
1.6 ms | 1.3 ms | +28.6% |
| ⚡ | Simulation | take_search[(0.1, 0.05)] |
248.8 µs | 212.1 µs | +17.33% |
| ⚡ | Simulation | take_search_chunked[(0.01, 0.05)] |
213.1 µs | 181.8 µs | +17.19% |
| ⚡ | Simulation | take_search[(0.005, 1.0)] |
3.1 ms | 2.3 ms | +31.27% |
| ⚡ | Simulation | take_search[(0.005, 0.1)] |
320.1 µs | 246.9 µs | +29.64% |
| ... | ... | ... | ... | ... | ... |
ℹ️ Only the first 20 benchmarks are displayed. Go to the app to view all benchmarks.
Comparing adamg/aggregate-fn-array-uncompressed (2ac1bd9) with develop (903ee6c)
Footnotes
-
138 benchmarks were skipped, so the baseline results were used instead. If they were deleted from the codebase, click here and archive them to remove them from the performance reports. ↩
AdamGS
added
changelog/feature
github-actions
Bot
removed
the
action/benchmark
Contributor
Polar Signals Profiling ResultsLatest Run
Previous Runs (1)
Powered by Polar Signals Cloud |
Contributor
Benchmarks: PolarSignals ProfilingVortex (geomean): 1.091x ➖ datafusion / vortex-file-compressed (1.091x ➖, 0↑ 4↓)
|
Contributor
File Sizes: PolarSignals ProfilingNo file size changes detected. |
Contributor
Benchmarks: FineWeb NVMeVerdict: No clear signal (low confidence) datafusion / vortex-file-compressed (0.962x ➖, 2↑ 0↓)
datafusion / vortex-compact (0.971x ➖, 0↑ 0↓)
datafusion / parquet (0.969x ➖, 0↑ 0↓)
duckdb / vortex-file-compressed (0.979x ➖, 0↑ 0↓)
duckdb / vortex-compact (1.012x ➖, 0↑ 2↓)
duckdb / parquet (0.953x ➖, 1↑ 0↓)
Full attributed analysis
|
Contributor
File Sizes: FineWeb NVMeNo file size changes detected. |
Contributor
Benchmarks: TPC-H SF=1 on NVMEVerdict: No clear signal (low confidence) datafusion / vortex-file-compressed (1.000x ➖, 0↑ 0↓)
datafusion / vortex-compact (1.000x ➖, 0↑ 0↓)
datafusion / parquet (1.000x ➖, 1↑ 1↓)
datafusion / arrow (0.984x ➖, 1↑ 0↓)
duckdb / vortex-file-compressed (1.005x ➖, 0↑ 0↓)
duckdb / vortex-compact (1.003x ➖, 0↑ 0↓)
duckdb / parquet (1.016x ➖, 0↑ 1↓)
duckdb / duckdb (1.005x ➖, 0↑ 0↓)
Full attributed analysis
|
Contributor
File Sizes: TPC-H SF=1 on NVMENo file size changes detected. |
Contributor
Benchmarks: TPC-DS SF=1 on NVMEVerdict: No clear signal (low confidence) datafusion / vortex-file-compressed (1.078x ➖, 0↑ 26↓)
datafusion / vortex-compact (1.060x ➖, 1↑ 10↓)
datafusion / parquet (1.066x ➖, 0↑ 16↓)
duckdb / vortex-file-compressed (1.064x ➖, 0↑ 21↓)
duckdb / vortex-compact (1.047x ➖, 0↑ 8↓)
duckdb / parquet (1.041x ➖, 0↑ 6↓)
duckdb / duckdb (1.064x ➖, 0↑ 19↓)
Full attributed analysis
|
Contributor
File Sizes: TPC-DS SF=1 on NVMENo file size changes detected. |
Contributor
Benchmarks: FineWeb S3Verdict: No clear signal (low confidence) datafusion / vortex-file-compressed (1.024x ➖, 0↑ 0↓)
datafusion / vortex-compact (0.704x ➖, 4↑ 0↓)
datafusion / parquet (1.085x ➖, 0↑ 0↓)
duckdb / vortex-file-compressed (1.113x ➖, 0↑ 1↓)
duckdb / vortex-compact (1.124x ➖, 0↑ 1↓)
duckdb / parquet (1.018x ➖, 0↑ 0↓)
Full attributed analysis
|
Contributor
Benchmarks: Random AccessVortex (geomean): 0.967x ➖ unknown / unknown (0.990x ➖, 3↑ 0↓)
|
Contributor
Benchmarks: Statistical and Population GeneticsVerdict: No clear signal (low confidence) duckdb / vortex-file-compressed (0.991x ➖, 1↑ 0↓)
duckdb / vortex-compact (1.024x ➖, 0↑ 0↓)
duckdb / parquet (1.017x ➖, 0↑ 0↓)
Full attributed analysis
|
Contributor
File Sizes: Statistical and Population GeneticsNo file size changes detected. |
Contributor
Benchmarks: Clickbench on NVMEVerdict: No clear signal (low confidence) datafusion / vortex-file-compressed (1.024x ➖, 0↑ 2↓)
datafusion / parquet (1.015x ➖, 0↑ 0↓)
duckdb / vortex-file-compressed (1.014x ➖, 0↑ 2↓)
duckdb / parquet (0.990x ➖, 1↑ 0↓)
duckdb / duckdb (1.020x ➖, 0↑ 1↓)
Full attributed analysis
|
Contributor
File Sizes: Clickbench on NVMEFile Size Changes (1 files changed, -0.0% overall, 0↑ 1↓)
Totals:
|
Contributor
Benchmarks: TPC-H SF=1 on S3Verdict: No clear signal (environment too noisy confidence) datafusion / vortex-file-compressed (1.119x ➖, 0↑ 1↓)
datafusion / vortex-compact (1.091x ➖, 0↑ 2↓)
datafusion / parquet (0.977x ➖, 1↑ 0↓)
duckdb / vortex-file-compressed (0.921x ➖, 0↑ 0↓)
duckdb / vortex-compact (0.924x ➖, 0↑ 0↓)
duckdb / parquet (0.959x ➖, 0↑ 0↓)
Full attributed analysis
|
Contributor
Benchmarks: CompressionVortex (geomean): 1.002x ➖ unknown / unknown (0.982x ➖, 10↑ 3↓)
|
Contributor
Benchmarks: TPC-H SF=10 on S3Verdict: No clear signal (environment too noisy confidence) datafusion / vortex-file-compressed (1.030x ➖, 0↑ 0↓)
datafusion / vortex-compact (0.980x ➖, 1↑ 0↓)
datafusion / parquet (1.121x ➖, 0↑ 4↓)
duckdb / vortex-file-compressed (1.055x ➖, 0↑ 0↓)
duckdb / vortex-compact (1.035x ➖, 0↑ 0↓)
duckdb / parquet (1.046x ➖, 0↑ 0↓)
Full attributed analysis
|
Contributor
Benchmarks: TPC-H SF=10 on NVMEVerdict: No clear signal (low confidence) datafusion / vortex-file-compressed (1.043x ➖, 0↑ 0↓)
datafusion / vortex-compact (1.037x ➖, 0↑ 0↓)
datafusion / parquet (1.041x ➖, 0↑ 1↓)
datafusion / arrow (1.069x ➖, 0↑ 2↓)
duckdb / vortex-file-compressed (1.031x ➖, 0↑ 0↓)
duckdb / vortex-compact (1.025x ➖, 0↑ 0↓)
duckdb / parquet (1.021x ➖, 0↑ 1↓)
duckdb / duckdb (1.021x ➖, 0↑ 0↓)
Full attributed analysis
|
Contributor
File Sizes: TPC-H SF=10 on NVMENo file size changes detected. |
robert3005
reviewed
Apr 29, 2026
| 0 | ||
| } else { | ||
| let rebuilt = array.rebuild(ListViewRebuildMode::MakeExact)?; | ||
| super::uncompressed_size_in_bytes_u64(rebuilt.elements(), ctx)? |
Contributor
There was a problem hiding this comment.
Can we import all those super:: methods
| /// Applies to all types and returns a non-null `u64`. Encoding kernels can return this aggregate | ||
| /// directly from metadata to avoid decoding arrays whose uncompressed size is known. | ||
| #[derive(Clone, Debug)] | ||
| pub struct UncompressedSizeInBytes; |
Contributor
There was a problem hiding this comment.
So this is only buffers of the array and all children.
Are we sure we should not include metadata?
Maybe just justify why?
Contributor
Author
There was a problem hiding this comment.
I don't think we do now, and it should really be a rounding error right?
It also seems to be more of an implementation details and not the number execution engines care about.
Signed-off-by: Adam Gutglick <adam@spiraldb.com>
Signed-off-by: Adam Gutglick <adam@spiraldb.com>
AdamGS
force-pushed
the
adamg/aggregate-fn-array-uncompressed
branch
from
0e19932 to
2ac1bd9
Compare
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
This stat turns out to be very useful for helping execution engines plan joins better, but its currently requires a full-decompression. This PR includes the basic structure for a new AggregateFn, including implementation for all canonical types.