[llvm] [AMDGPU][NPM] Port AMDGPUMarkLastScratchLoad to NPM (PR #131738)

[Matt Arsenault via llvm-commits]

================
@@ -1,5 +1,6 @@
 # NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py UTC_ARGS: --version 3
 # RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1200 -o - %s -run-pass=greedy -run-pass=amdgpu-mark-last-scratch-load -verify-machineinstrs | FileCheck -check-prefix=CHECK %s
+# RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1200 -o - %s -passes=greedy,amdgpu-mark-last-scratch-load | FileCheck -check-prefix=CHECK %s
----------------
arsenm wrote:

Technically this isn't running the right greedy, but the other line is doing the same 

https://github.com/llvm/llvm-project/pull/131738