[Mlir-commits] [mlir] [mlir][linalg] Preserve cast semantics during generic to matmul (PR #174757)

[Andrzej Warzyński]

================
@@ -58,8 +62,118 @@ func.func @op_matmul(%A: tensor<?x?xf32>, %B: tensor<?x?xf32>, %Out: tensor<?x?x
 // CHECK-NOT: linalg.generic
 // CHECK: linalg.matmul ins(%[[A]], %[[B]] : tensor<?x?xf32>, tensor<?x?xf32>) outs(%[[Out]] : tensor<?x?xf32>) -> tensor<?x?xf32>
 
+// Cast-auditing tests: ensure we only specialize when the cast semantics can
+// be expressed by linalg.matmul, and use the cast attribute when needed.
+
+// Check matmul with unsigned cast is correctly raised back to named op.
+func.func @op_matmul_unsigned_cast(%A: tensor<16x8xi16>, %B: tensor<8x32xi64>,
+                                   %Out: tensor<16x32xi32>) -> tensor<16x32xi32> {
+  %0 = linalg.generic
+         {indexing_maps = [#map, #map1, #map2], iterator_types = ["parallel", "parallel", "reduction"]}
+         ins(%A, %B : tensor<16x8xi16>, tensor<8x32xi64>) outs(%Out : tensor<16x32xi32>) {
+   ^bb0(%in: i16, %in_0: i64, %out: i32):
+     %1 = arith.extui %in : i16 to i32
+     %2 = arith.trunci %in_0 : i64 to i32
----------------
banach-space wrote:

>  I'd prefer handling it separately as it is not a bug introduced by this change

That's fine with me, but could you create a GitHub issue and link it in the code? Thanks!

https://github.com/llvm/llvm-project/pull/174757