[llvm] [AMDGPU] Optimize block count calculations to the new ABI (PR #174112)

[Joseph Huber via llvm-commits]

================
@@ -1,4 +1,5 @@
-//===-- AMDGPULowerKernelAttributes.cpp ------------------------------------------===//
+//===-- AMDGPULowerKernelAttributes.cpp
+//------------------------------------------===//
----------------
jhuber6 wrote:

Did it in the first commit so you can view it separately

https://github.com/llvm/llvm-project/pull/174112