[Mlir-commits] [mlir] [mlir][tosa] Remove FullyConnectedOp from TOSA Dialect (PR #126152)

[Suraj Sudhir]

================
@@ -1,164 +0,0 @@
-//===- TosaDecomposeConv2D.cpp --------------------------------------------===//
----------------
sjarus wrote:

It is my understanding that the argument is not whether conv2d 1x1s are relevant, but whether they should be converted to the nearest replacement for FC , which is a matmul. The matmul op is missing a bias addition component that conv2d has. Is it truly the decomposition desired here ? 

https://github.com/llvm/llvm-project/pull/126152