[Mlir-commits] [mlir] [mlir][linalg] Add pattern to clean unused results after fusion (PR #158627)

[llvmlistbot at llvm.org]

================
@@ -1079,4 +1079,49 @@ module {
 // CHECK-NOT:     linalg.generic
 // CHECK:         tensor.expand_shape
 // CHECK:         linalg.generic {{.*}}, iterator_types = ["parallel", "parallel", "parallel", "parallel", "parallel", "parallel", "reduction"]}
-// CHECK-SAME:     ins(%[[ARG0]], %[[FUSED]]#1 : tensor<1x1x2x1xf32>, tensor<4x1x1x1xf32>)
\ No newline at end of file
+// CHECK-SAME:     ins(%[[ARG0]], %[[FUSED]]#1 : tensor<1x1x2x1xf32>, tensor<4x1x1x1xf32>)
+
+// -----
+
+// CHECK-LABEL: @drop_unused_results
+// CHECK-SAME:   [[ARG0:%[a-zA-Z0-9]+]]: tensor<64xf32>, [[ARG1:%[a-zA-Z0-9]+]]: tensor<1x56x56x64xf32>
+func.func @drop_unused_results(%arg0: tensor<64xf32>, %arg1: tensor<1x56x56x64xf32>) -> tensor<1x56x56x64xf32> {
+  %cst = arith.constant 3.40282347E+38 : f32
+  %cst_0 = arith.constant 0.000000e+00 : f32
+  // CHECK: [[OUT:%[a-zA-Z0-9]+]] = tensor.empty() : tensor<1x56x56x64xf32>
+  %0 = tensor.empty() : tensor<1x56x56x64xf32>
+  // CHECK: [[RES:%[0-9]+]] = linalg.generic {{.*}} ins([[ARG0]], [[ARG1]] : tensor<64xf32>, tensor<1x56x56x64xf32>) outs([[OUT]] : tensor<1x56x56x64xf32>)
+  %1:2 = linalg.generic {indexing_maps = [affine_map<(d0, d1, d2, d3) -> (d3)>, affine_map<(d0, d1, d2, d3) -> (d0, d1, d2, d3)>, affine_map<(d0, d1, d2, d3) -> (d0, d1, d2, d3)>], iterator_types = ["parallel", "parallel", "parallel", "parallel"]} ins(%arg0 : tensor<64xf32>) outs(%arg1, %0 : tensor<1x56x56x64xf32>, tensor<1x56x56x64xf32>) {
----------------
MaheshRavishankar wrote:

Well having said that, there is a pattern [`populateMoveInitOperandsToInput`](https://github.com/llvm/llvm-project/blob/90d03a0386a6b9640e50513f6948cd2549937208/mlir/include/mlir/Dialect/Linalg/Transforms/Transforms.h#L1979`) that already seems to do some of this. Maybe if you run that "before" your pass it will fix the issue for you. I think that pattern was added explicitly to fix such "ill-defined" operations.

https://github.com/llvm/llvm-project/pull/158627