[llvm] [mlir] [mlir] Lower math dialect later in gpu-lower-to-nvvm-pipeline (PR #78556)

[Adam Paszke via llvm-commits]

================
@@ -0,0 +1,1267 @@
+// -----// IR Dump After ConvertNVGPUToNVVMPass (convert-nvgpu-to-nvvm) //----- //
----------------
apaszke wrote:

I assume this is an accidental inclusion to this PR?

https://github.com/llvm/llvm-project/pull/78556