Decouple fuseBatchNormalizationKernel

- Decouple data type for CPU implementation
    supported data types are: fp32, fp16

Resolves COMPMID-4613
Signed-off-by: Yair Schwarzbaum <yair.schwarzbaum@arm.com>
Change-Id: I8aff3ba2d446f64e4d182a866e3a3debc9ef613b
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7175
Reviewed-by: Giorgio Arena <giorgio.arena@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>

1 files changed, 40 insertions, 0 deletions

diff --git a/src/cpu/kernels/fuse_batch_normalization/nhwc/neon/impl.h b/src/cpu/kernels/fuse_batch_normalization/nhwc/neon/impl.h
new file mode 100644
index 0000000000..3b813132b1
--- /dev/null
+++ b/src/cpu/kernels/fuse_batch_normalization/nhwc/neon/impl.h
@@ -0,0 +1,40 @@
+/*
+ * Copyright (c) 2021-2022 Arm Limited.
+ *
+ * SPDX-License-Identifier: MIT
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to
+ * deal in the Software without restriction, including without limitation the
+ * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
+ * sell copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in all
+ * copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+#ifndef SRC_CORE_NEON_KERNELS_FUSE_BATCH_NORMALIZATION_IMPL_H
+#define SRC_CORE_NEON_KERNELS_FUSE_BATCH_NORMALIZATION_IMPL_H
+
+#include "arm_compute/core/Helpers.h"
+#include "src/core/NEON/wrapper/wrapper.h"
+
+namespace arm_compute
+{
+namespace cpu
+{
+template <typename T>
+void fused_batch_normalization_dwc_nhwc(const ITensor *dwc_weights, const ITensor *dwc_bias, ITensor *fused_weights, ITensor *fused_bias,
+                                        const ITensor *bn_mean, const ITensor *bn_var, const ITensor *bn_beta, const ITensor *bn_gamma, float epsilon, const Window &window);
+
+} // namespace cpu
+} // namespace arm_compute
+#endif //SRC_CORE_NEON_KERNELS_FUSE_BATCH_NORMALIZATION_IMPL_H