[PATCH] D60015: [NVPTX] Added intrinsics/instructions for MMA ops on (sub-)integers

[Tim Shen via Phabricator via llvm-commits]

timshen accepted this revision.
timshen added a comment.
This revision is now accepted and ready to land.

Discussed with Art offline. The tablegen code is still not readable, but it's considerably better than the past, and inventing new tools (e.g. Cartesian product) may be hard.



================
Comment at: llvm/include/llvm/IR/IntrinsicsNVVM.td:155
+//   TypeN: PTX type of the corresponding fragment's element.
+//   TypeB and TypeD may be empty if it must match that of TypeA or TypeC.
+class MMA_OPS<list<string> Geom, list<string> TypeA, list<string> TypeB,
----------------
Can you add a few examples of the generated regs?


================
Comment at: llvm/include/llvm/IR/IntrinsicsNVVM.td:155
+//   TypeN: PTX type of the corresponding fragment's element.
+//   TypeB and TypeD may be empty if it must match that of TypeA or TypeC.
+class MMA_OPS<list<string> Geom, list<string> TypeA, list<string> TypeB,
----------------
timshen wrote:
> Can you add a few examples of the generated regs?
Can you document Type{A,B,C,D} for their meanings?


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D60015/new/

https://reviews.llvm.org/D60015