Optimize add layer by considering the input tensors as 1D array
Resolves: COMPMID-5108
Change-Id: I544f8160fbe5b4ffbef348d1fbd3dd626a6e1bdb
Signed-off-by: Gunes Bayir <gunes.bayir@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/8002
Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Benchmark: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
diff --git a/src/cpu/kernels/add/generic/neon/impl.h b/src/cpu/kernels/add/generic/neon/impl.h
index 07afdda..f8f0f51 100644
--- a/src/cpu/kernels/add/generic/neon/impl.h
+++ b/src/cpu/kernels/add/generic/neon/impl.h
@@ -1,5 +1,5 @@
/*
- * Copyright (c) 2021 Arm Limited.
+ * Copyright (c) 2021-2022 Arm Limited.
*
* SPDX-License-Identifier: MIT
*
@@ -32,6 +32,9 @@
{
template <typename ScalarType>
void add_same_neon(const ITensor *src0, const ITensor *src1, ITensor *dst, const ConvertPolicy &policy, const Window &window);
+
+template <typename ScalarType>
+void add_same_neon_as_1d_array(const ITensor *src0, const ITensor *src1, ITensor *dst, const ConvertPolicy &policy, const Window &window);
} // namespace cpu
} // namespace arm_compute
#endif // SRC_CORE_NEON_KERNELS_ADD_IMPL_H
\ No newline at end of file