[PATCH] D28782: [AMDGPU] Do not allow register coalescer to create big superregs

[Matt Arsenault via Phabricator via llvm-commits]

arsenm added inline comments.


================
Comment at: test/CodeGen/AMDGPU/limit-coalesce.mir:3-4
+
+# Check that coalescer does not create 96 bit register tuple
+# CHECK-NOT: vreg_96
+
----------------
This should use positive checks


Repository:
  rL LLVM

https://reviews.llvm.org/D28782