[PATCH] D100026: [X86] Support AMX fast register allocation

[Pengfei Wang via Phabricator via llvm-commits]

pengfei added inline comments.


================
Comment at: llvm/lib/Target/X86/X86LowerAMXType.cpp:131
+      // Row = Row / 4
+      Row = getRowFromCol(II, Row, 4);
       Col = II->getArgOperand(1);
----------------
Can we always get the shape by the def of a AMX. Then we can avoid to add calculation for it.
We can add assert here to make sure of it.


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D100026/new/

https://reviews.llvm.org/D100026