[Mlir-commits] [mlir] [MLIR][Linalg] Add pass to convert linalg.generic back to named ops (PR #95656)

[Renato Golin]

================
@@ -0,0 +1,148 @@
+// RUN: mlir-opt --transform-interpreter --split-input-file --verify-diagnostics %s | FileCheck %s
+
+#map = affine_map<(d0, d1, d2) -> (d0, d2)>
+#map1 = affine_map<(d0, d1, d2) -> (d2, d1)>
+#map2 = affine_map<(d0, d1, d2) -> (d0, d1)>
+func.func @specialize_matmul(%arg0: tensor<?x?xf32>, %arg1: tensor<?x?xf32>, %arg2: tensor<?x?xf32>) -> tensor<?x?xf32> {
----------------
rengolin wrote:

Can you add element wise for transforms, too?

https://github.com/llvm/llvm-project/pull/95656