NVIDIA / NVIDIA/cudf

[FEA] Improve readability of thread id based branching

Open
#6,241 6 comments 2 reactions 0 assignees View on GitHub
cuIO feature request good first issue libcudf
Dominant language
C++
Stars
9.8k
Forks
1.1k
Avg merge
3d 6m
Merged PRs (30d)
278

Description

Improve readability of thread id based branches by giving them more descriptive names.

#### e.g.
```c++
if (!t) // is actually a t == 0
```
#### and
https://github.com/rapidsai/cudf/blob/57ef76927373d7260b6a0eda781e59a4c563d36e/cpp/src/io/statistics/column_stats.cu#L285
Is actually a `lane_id == 0`
As demonstrated in https://github.com/rapidsai/cudf/issues/6241#issuecomment-693125331, prefer cooperative groups for this.

#### and
https://github.com/rapidsai/cudf/blob/85cd56dfb3449140f18c7cef3a3be01ac976fd14/cpp/src/io/parquet/page_enc.cu#L1256
is actually ~`t < 32`~ `lane_id == 31`. (~I think this might be an oversight,~ ignore as it might be fixed in #6238 ).

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.