[Mlir-commits] [mlir] [mlir][linalg] Extend `FuseElementwiseOps` pattern to work with named ops (PR #144922)
Renato Golin
llvmlistbot at llvm.org
Fri Jun 20 13:15:15 PDT 2025
================
@@ -59,3 +59,57 @@ func.func @handle_unused_operands(%arg0: tensor<8xf32>, %arg1: tensor<8xf32>) ->
// CHECK: %[[FUSED_OP:.+]] = linalg.generic
// CHECK-SAME: outs(%[[EMPTY]] :
// CHECK-NOT: linalg.generic
+
+// -----
+
+func.func @map_ops(%in1: tensor<8xf32>, %in2: tensor<8xf32>) -> tensor<8xf32> {
+ %fill = tensor.empty() : tensor<8xf32>
+ %add = linalg.map {arith.addf} ins(%in1, %in2: tensor<8xf32>, tensor<8xf32>) outs(%fill: tensor<8xf32>)
+ %mapped_65 = linalg.map { math.sqrt } ins(%add : tensor<8xf32>) outs(%fill : tensor<8xf32>)
+ return %mapped_65 : tensor<8xf32>
+}
+
+// CHECK-LABEL: func @map_ops
+// CHECK-SAME: %[[ARG0:[a-zA-Z0-9]+]]: tensor<8xf32>
+// CHECK-SAME: %[[ARG1:[a-zA-Z0-9]+]]: tensor<8xf32>
+// CHECK: %[[EMPTY:.+]] = tensor.empty() : tensor<8xf32>
+// CHECK: %[[FUSED_OP:.+]] = linalg.generic
----------------
rengolin wrote:
> Also that wouldn't help with elementwise+elementwise -> map anyway
Right, the idea is that `ew` + `ew` -> `map` is still better than to `generic`. So we only _walk up_ the tree when needed (assuming `generic` -> `map` -> `ew` is the branch we're walking).
https://github.com/llvm/llvm-project/pull/144922
More information about the Mlir-commits
mailing list