Andy Grove
Andy Grove
## Which issue does this PR close? N/A ## Rationale for this change `AQEShuffleRead` will never have a native version so we should stop warning that we cannot run it...
## Which issue does this PR close? Closes #. ## Rationale for this change Fix a performance regression and simplify configs for enabling operators and expressions  We now fall...
## Which issue does this PR close? N/A ## Rationale for this change Our current TPS-DS microbenchmarks are not really microbencmarks because they run Spark and invoke Java and Rust...
### What is the problem the feature request solves? Query: ```sql select ss_sold_date_sk, ss_sold_time_sk, ss_quantity, d_year, d_moy, d_dom from date_dim join store_sales on d_date_sk = ss_sold_date_sk where d_year = 2000;...
## Which issue does this PR close? Closes https://github.com/apache/datafusion-comet/issues/837 ## Rationale for this change This is in preparation for implementing an optimized C2R in Comet. ## What changes are included...
### What is the problem the feature request solves? I am creating this epic to track performance issues that the community is working on for the 0.2.0 release. - [x]...
### What is the problem the feature request solves? Spark's `ColumnarToRowExec` can be very slow in some cases. This plan shows that C2R took 8 minutes even though the underlying...
### What is the problem the feature request solves? We would like to implement a custom version of ColumnarToRowExec to allow for more efficient use of JNI interactions. I would...
## Which issue does this PR close? Closes https://github.com/apache/datafusion-comet/issues/631 ## Rationale for this change This is part of our effort to support more operations on complex types. Performance seems ok....
### What is the problem the feature request solves? The native planner currently injects a `CopyExec` around the left and right inputs to joins. `CopyExec` is also injected around the...