BE-513: HashQL: Rework dynamic aggregate size estimation
#8697Comparing
bm/be-513-hashql-size-estimation-aggregate-cardinality-is-wrong-for
(393f316
) withbm/be-512-hashql-switchint-allow-cross-backend-transitions
(a18ae88
)-11%
- Regression
- 4
- Untouched
- 20
- Skipped
- 56
No successful run was found on bm/be-512-hashql-switchint-allow-cross-backend-transitions ( 43c449a) during the generation of this report, so main ( a18ae88) was used instead as the comparison base. There might be some changes unrelated to this pull request in this report.
Different runtime environments detected
Some benchmarks with significant performance changes were compared across different runtime environments, which may affect the accuracy of the results. Learn more about regression causes.Benchmarks
80 total
entity_projections
libs/@local/hashql/mir/benches/execution.rs::benches::execution_analysis::execution_analysis-11%
64.9 µs73.2 µs
fibonacci_recursive[24]
libs/@local/hashql/mir/benches/interpret.rs::benches::fibonacci_recursive-11%
85.9 ms96.4 ms
fibonacci_recursive[16]
libs/@local/hashql/mir/benches/interpret.rs::benches::fibonacci_recursive-11%
1.8 ms2.1 ms
diamond
libs/@local/hashql/mir/benches/transform.rs::benches::forward_substitution::forward_substitution-10%
16.2 µs18 µs
diamond
libs/@local/hashql/mir/benches/transform.rs::benches::cfg_simplify::cfg_simplify+3%
7.8 µs7.6 µs
linear
libs/@local/hashql/mir/benches/transform.rs::benches::cfg_simplify::cfg_simplify+2%
16.9 µs16.5 µs
diamond
libs/@local/hashql/mir/benches/transform.rs::benches::inst_simplify::inst_simplify+2%
12.4 µs12.2 µs
complex
libs/@local/hashql/mir/benches/transform.rs::benches::cfg_simplify::cfg_simplify+1%
11.2 µs11.1 µs
complex
libs/@local/hashql/mir/benches/transform.rs::benches::inst_simplify::inst_simplify+1%
18.1 µs18 µs
dead stores
libs/@local/hashql/mir/benches/transform.rs::benches::dse::dse0%
9.9 µs9.9 µs
linear
libs/@local/hashql/mir/benches/transform.rs::benches::inst_simplify::inst_simplify0%
10.2 µs10.2 µs
complex
libs/@local/hashql/mir/benches/transform.rs::benches::dse::dse0%
7.1 µs7.1 µs
foldable
libs/@local/hashql/mir/benches/transform.rs::benches::inst_simplify::inst_simplify0%
9.5 µs9.5 µs
diamond
libs/@local/hashql/mir/benches/transform.rs::benches::dse::dse-1%
5.5 µs5.5 µs
inline
libs/@local/hashql/mir/benches/transform.rs::benches::pipeline::pipeline-1%
232.7 µs235.8 µs
linear
libs/@local/hashql/mir/benches/transform.rs::benches::dse::dse-2%
5.1 µs5.2 µs
linear
libs/@local/hashql/mir/benches/transform.rs::benches::pipeline::pipeline-2%
48.8 µs49.6 µs
linear
libs/@local/hashql/mir/benches/transform.rs::benches::forward_substitution::forward_substitution-2%
7.5 µs7.7 µs
diamond
libs/@local/hashql/mir/benches/transform.rs::benches::pipeline::pipeline-4%
82.2 µs85.3 µs
complex
libs/@local/hashql/mir/benches/transform.rs::benches::pipeline::pipeline-4%
116.4 µs120.9 µs
diamond_cfg
libs/@local/hashql/mir/benches/execution.rs::benches::execution_analysis::execution_analysis-7%
89.2 µs95.7 µs
simple
libs/@local/hashql/mir/benches/execution.rs::benches::execution_analysis::execution_analysis-10%
55.9 µs61.8 µs
complex
libs/@local/hashql/mir/benches/transform.rs::benches::forward_substitution::forward_substitution-10%
21.6 µs23.9 µs
fibonacci_recursive[8]
libs/@local/hashql/mir/benches/interpret.rs::benches::fibonacci_recursive-10%
46.6 µs51.8 µs
The benchmarks below were skipped, so their baseline results are used instead. If they were deleted in your codebase, archive them to remove them from the performance reports.
Learn more about archiving benchmarks
Learn more about archiving benchmarks
runtime_equal
libs/@local/hashql/core/benches/symbol.rs::benches::equality::equalitySkipped
< 1 ns*
Commits
Click on a commit to change the comparison rangeBase
main
a18ae88
-11.34%
chore: truncate instead of resize on mul
393f316
8 days ago
by indietyp