Remzi Yang

Add `Nan` handling in `GpuArrayMin`

1

Signed-off-by: remzi Close #6317 Close #6330 Close #6332 # Changes in this PR 1. remove the `hasNan` configuration on `GpuArrayMin` 2. Add `Nan` handling in `GpuArrayMin` - Just as `GpuMax`...

[BUG] `array_min` does not fall back to CPU when `hasNan = true`

1

**Describe the bug** A clear and concise description of what the bug is. **Steps/Code to reproduce bug** ```scala scala> spark.conf.set("spark.rapids.sql.hasNans","true") scala> val df = Seq((Seq(1.0, 2.0, 3.0)), (Seq(1.1, 2.1, Double.NaN))).toDF("a")...

[FEA] Add `Nan` handling in `GpuArrayMin`

2

**Is your feature request related to a problem? Please describe.** This is a subtask of #5320 **Describe the solution you'd like** A clear and concise description of what you want...

Add `GpuMapConcat` support for nested type keys.

2

Signed-off-by: remzi This is a subtask of #5559. The `GpuMaxConcat` could support array typed keys and struct typed keys.

[FEA] Add `GpuMapConcat` support for nested (array, struct, map) types.

2

**Is your feature request related to a problem? Please describe.** This is a follow on issue of https://github.com/NVIDIA/spark-rapids/pull/5533. **Describe the solution you'd like** `GpuMapConcat` should support arbitrary nested types for...

[FEA] Add `Nan` handling in the `GpuMin`

4

**Is your feature request related to a problem? Please describe.** Currently, the `min` kernel will fall back to CPU if `hasNan = true`. We should let the `GpuMin` support the...

Signed-off-by: remzi Close #6164.

`StringConcat` gives inconsistent result with `concat` when containing `null`

1

**Describe the bug** A clear and concise description of what the bug is. **To Reproduce** Steps to reproduce the behavior: ``` ❯ select concat('a', null) from t; +------------------------+ | concat(Utf8("a"),NULL)...

**Describe the bug** ``` remziy@remziy-mlt:scheduler$ yarn start yarn run v1.22.19 $ react-scripts start node:internal/modules/cjs/loader:498 throw e; ^ Error [ERR_PACKAGE_PATH_NOT_EXPORTED]: Package subpath './lib/tokenize' is not defined by "exports" in /Users/remziy/FangcloudV2/personal_space.localized/working/Ballista/ballista/ui/scheduler/node_modules/postcss-safe-parser/node_modules/postcss/package.json at...

**Is your feature request related to a problem? Please describe.** https://github.com/apache/spark/commit/8e853933ba64bb43e02af78198bc36d471efaa18 refactored the File Data Source Options. For example, it moves the `BASE_PATH_PARAM` from `PartitioningAwareFileIndex` to `FileIndexOptions`. We should move...