Andy Grove
Andy Grove
### What is the problem the feature request solves? DataFusion has a fast path for aggregates that implement group accumulators. See https://github.com/apache/datafusion-comet/issues/1275#issuecomment-2787795808 for one example where we saw a 4x...
### What is the problem the feature request solves? Spark 4 will soon be available, so we should coordinate the work to add support. We already have partial support for...
### What is the problem the feature request solves? DataFusion just added support for SMJ with RightSemi join in https://github.com/apache/datafusion/pull/15972, so we should be able to support this in Comet...
### Describe the bug There are more than 100 failures in `core2` suite that seem to have the same root cause: ``` - Spark vectorized reader - without partition data...
### Describe the bug This error can happen with DPP queries. There are Spark SQL tests in `DynamicPartitionPruningSuite` that fail with this error when they are not ignored: - SPARK-35568:...
### What is the problem the feature request solves? The follow Spark SQL tests should now pass because we fall back to Spark for DPP, so we should stop ignoring...
## Which issue does this PR close? Closes https://github.com/apache/datafusion-comet/issues/1254 ## Rationale for this change The config `COMET_SHUFFLE_FALLBACK_TO_COLUMNAR` was added as a workaround for Spark SQL test failures and we need...
## Which issue does this PR close? Closes https://github.com/apache/datafusion-comet/issues/1709 ## Rationale for this change ## What changes are included in this PR? ## How are these changes tested?
### What is the problem the feature request solves? `CometFuzzTestSuite` currently has tests for structs and arrays, but not maps. This issue is for adding maps. ### Describe the potential...
### What is the problem the feature request solves? During the upgrade to DataFusion 47.0.0 () it was necessary to disable some tests that use FIRST and LAST because the...