[PATCH] D76897: [mlir][Linalg] Extend fusion to support WAW atm on buffers.

[Nicolas Vasilache via Phabricator via llvm-commits]

nicolasvasilache accepted this revision.
nicolasvasilache added inline comments.


================
Comment at: mlir/include/mlir/Dialect/Linalg/IR/LinalgStructuredOpsInterface.td:105
+      "Return the input or output buffer at the given index.",
+      "Value", "getInputsAndOutputsBuffer", (ins "unsigned":$i)
+    >,
----------------
mravishankar wrote:
> Nit : rename to getInputAndOutputBuffers
This should be either `getInputOrOutputBuffer` or just `getBuffer`.
It returns one single buffer at position `$i`. 


================
Comment at: mlir/test/Dialect/Linalg/fusion.mlir:336
 // CHECK:  (%[[A:.*]]:{{.*}}, %[[B:.*]]:{{.*}}, %[[C:.*]]:{{.*}}, %[[D:.*]]:{{.*}}, %[[E:.*]]:{{.*}})
-// Cannot fuse C due to interleaved read of C that would be bypassed.
-// Cannot fuse E (WAW).
-// CHECK:  linalg.matmul
-// CHECK:  linalg.matmul
+// Fuse B and C, then fuse with A.
 // CHECK:  loop.for
----------------
This comment does not make sense to me.
The original comment used `C` and `E` as a shortcut for `the producer of C` and `the producer of E`.

How about:
`fuse the producer of E (WAW) then the producer of C (WAR)` ?

Also the resulting fusion is most likely a bug.
It's not your fault and independent from this CL.
I'll fix in a followup.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D76897/new/

https://reviews.llvm.org/D76897