[ONCPUML-1451] Add matmul kernel to enable bf16 to bf16 operations via PyTorch® autocast() function

The full range of tests must be added with [MLINFSW-482] epic due to the lack of reordering kernels implemented in Acl.

Co-Authored-By: David Mansell <David.Mansell@arm.com>
Change-Id: I820d316295a1ec94fdc89c37e4144a268f914c36
Signed-off-by: Renato Arantes <renato.arantes@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/11169
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Gunes Bayir <gunes.bayir@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Benchmark: Arm Jenkins <bsgcomp@arm.com>
diff --git a/tests/validation/reference/ReshapeLayer.cpp b/tests/validation/reference/ReshapeLayer.cpp
index daea001..30a58dd 100644
--- a/tests/validation/reference/ReshapeLayer.cpp
+++ b/tests/validation/reference/ReshapeLayer.cpp
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2017 Arm Limited.
+ * Copyright (c) 2017,2024 Arm Limited.
  *
  * SPDX-License-Identifier: MIT
  *
@@ -44,14 +44,15 @@
     return dst;
 }
 
-template SimpleTensor<uint8_t> reshape_layer(const SimpleTensor<uint8_t> &src, const TensorShape &output_shape);
-template SimpleTensor<int8_t> reshape_layer(const SimpleTensor<int8_t> &src, const TensorShape &output_shape);
+template SimpleTensor<uint8_t>  reshape_layer(const SimpleTensor<uint8_t> &src, const TensorShape &output_shape);
+template SimpleTensor<int8_t>   reshape_layer(const SimpleTensor<int8_t> &src, const TensorShape &output_shape);
 template SimpleTensor<uint16_t> reshape_layer(const SimpleTensor<uint16_t> &src, const TensorShape &output_shape);
-template SimpleTensor<int16_t> reshape_layer(const SimpleTensor<int16_t> &src, const TensorShape &output_shape);
+template SimpleTensor<int16_t>  reshape_layer(const SimpleTensor<int16_t> &src, const TensorShape &output_shape);
 template SimpleTensor<uint32_t> reshape_layer(const SimpleTensor<uint32_t> &src, const TensorShape &output_shape);
-template SimpleTensor<int32_t> reshape_layer(const SimpleTensor<int32_t> &src, const TensorShape &output_shape);
-template SimpleTensor<half> reshape_layer(const SimpleTensor<half> &src, const TensorShape &output_shape);
-template SimpleTensor<float> reshape_layer(const SimpleTensor<float> &src, const TensorShape &output_shape);
+template SimpleTensor<int32_t>  reshape_layer(const SimpleTensor<int32_t> &src, const TensorShape &output_shape);
+template SimpleTensor<half>     reshape_layer(const SimpleTensor<half> &src, const TensorShape &output_shape);
+template SimpleTensor<float>    reshape_layer(const SimpleTensor<float> &src, const TensorShape &output_shape);
+template SimpleTensor<bfloat16> reshape_layer(const SimpleTensor<bfloat16> &src, const TensorShape &output_shape);
 /** [ReshapeLayer] **/
 } // namespace reference
 } // namespace validation