[Mlir-commits] [mlir] [MLIR] Enable scalable vectorization for linalg.batch_matmul (PR #172333)

[Andrzej Warzyński]

================
@@ -1725,3 +1725,87 @@ module attributes {transform.with_named_sequence} {
     transform.yield
   }
 }
+
+// -----
+
+func.func @batch_matmul(%A: memref<?x?x?xf32>, %B: memref<?x?x?xf32>, %C: memref<?x?x?xf32>) {
+  linalg.batch_matmul ins(%A, %B: memref<?x?x?xf32>, memref<?x?x?xf32>)
+                      outs(%C: memref<?x?x?xf32>)
+  return
+}
+
+// CHECK-LABEL: func.func @batch_matmul(
+// CHECK-SAME:  %[[A:.*]]: memref<?x?x?xf32>, %[[B:.*]]: memref<?x?x?xf32>, %[[C:.*]]: memref<?x?x?xf32>
+// CHECK:       %[[c0:.*]] = arith.constant 0 : index
----------------
banach-space wrote:

Let's use CAPS for all LIT variables
```suggestion
// CHECK:       %[[C0:.*]] = arith.constant 0 : index
```

https://github.com/llvm/llvm-project/pull/172333