Comments (6)
r3stl355
commented on May 28, 2024
2
A quick experiment replacing value_fn with pre-computed arrays shows about 50% improvement for benchmarks using columns but about 20% regression for scalar only benchmark (I think I should be able to get that scalar version back to baseline). If you think this is significant I can carry on working on it
from arrow-datafusion.
vojtechtoman
commented on May 28, 2024
1
@alamb I was looking at this out of interest and I just noticed that this issue has been closed in the meantime. I introduced some further improvements in #9600 which lead to about 10% performance gain for the cases involving arrays and about 20% for the scalars-only case.
from arrow-datafusion.
alamb
commented on May 28, 2024
Sounds pretty great to me -- thanks @r3stl355
from arrow-datafusion.
Omega359
commented on May 28, 2024
I think with #9112 this issue could be closed @alamb ?
from arrow-datafusion.
alamb
commented on May 28, 2024
I agree -- thank you for the ping
from arrow-datafusion.
alamb
commented on May 28, 2024
Thank you @vojtechtoman -- very exciting
from arrow-datafusion.
Related Issues (20)
- `LogFunc` simplifier swaps the order of arguments
- Standardize the separator in name HOT 1
- Onyl recompute schema in `TypeCoercion` when necessary
- Better timezone functionalities HOT 3
- Auto-update mechanism for dataframe test HOT 1
- Remove `Expr::GetIndexedField` and `GetFieldAccess` and always use function `get_field` for indexing HOT 6
- Support user defined display for UDF HOT 2
- Remove DataPtr trait and use Arc::ptr_eq directly
- Sort Merge Join. LeftSemi issues
- Sort Merge Join. LeftAnti issues
- Port aggregate test to sqllogictest
- Move `Covariance` (Population) `covar_pop` to be a UDAF HOT 1
- For DML plans, `LogicalPlan::schema` returns the input schema instead of output schema
- DataFusion weekly project plan (Andrew Lamb) - May 6, 2024 HOT 3
- Reduce repetition in datafusion::functions using macros HOT 1
- Support custom SchemaAdapter on ParquetExec HOT 2
- Use `min_value` and `max_value` on statistics to avoid `ExecutionPlan.execute` HOT 3
- Make ASF public press release HOT 1
- Substrait integration doesn't recognize typed functions HOT 2
- Incorrect results with expression resolution HOT 4
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from arrow-datafusion.