[Mlir-commits] [mlir] [mlir][gpu] Support `minimumnumf` and `maximumnumf` in GPU dialect (PR #226903)

[Lewis Crawford]

================
@@ -0,0 +1,21 @@
+// RUN: mlir-opt --convert-gpu-to-nvvm %s | FileCheck %s
----------------
LewisCrawford wrote:

I notice that the corresponding `mlir/test/Dialect/GPU/all-reduce-maxf.mlir` test is completely different, and is auto-generated using `-test-gpu-rewrite` instead of `--convert-gpu-to-nvvm` . I also notice that there is not a corresponding test for `minimum` / `maximum` .

Would it be worth making consistent tests for all 3 min/max variants?

https://github.com/llvm/llvm-project/pull/226903