[Mlir-commits] [mlir] [mlir] [linalg] fix side effect of linalg op (PR #114045)

Kunwar Grover llvmlistbot at llvm.org
Tue Oct 29 07:20:36 PDT 2024


================
@@ -1232,3 +1232,21 @@ func.func @transpose_buffer(%input: memref<?xf32>,
 //  CHECK-SAME:            %[[VAL_1:.*]]: memref<?xf32>) {
 //       CHECK:     linalg.transpose ins(%[[VAL_0]] : memref<?xf32>)
 //  CHECK-SAME:       outs(%[[VAL_1]] : memref<?xf32>) permutation = [0]
+
+// -----
+
+// This test checks linalg op has a recursive memory effect. Otherwise
+// linalg.map without user would not be deleted in canonicalize.
----------------
Groverkss wrote:

Otherwise linalg.map.... -> Otherwise linalg.map without a user would be DCEd

https://github.com/llvm/llvm-project/pull/114045


More information about the Mlir-commits mailing list