commit ba93371f2316218a09a24403076ab3fdf967b168
author Pablo Marquez Tello <pablo.tello@arm.com> Mon Nov 13 15:57:54 2023 +0000
committer Pablo Marquez Tello <pablo.tello@arm.com> Thu Nov 16 10:07:38 2023 +0000
tree 6e1ff3b974c3893cb50ccb6226e580e4553ab5a7
parent d4650e9e98c8f854776ae78fb6d3e46e7fe4ba20

NormalizationLayer changes to enable fp16 in armv8a multi_isa builds

    * Moved the template arm_compute::normalize_float to impl.h because
      we need to instantiate it from both NENormalizationLayerKernel.cpp
      and src/cpu/kernels/norm_layer/generic/neon/fp16.cpp

    * Changes in filelist.json: added a new fp16.cpp file for the float16_t kernels

    * Replaced the guard __ARM_FEATURE_FP16_VECTOR_ARITHMETIC in
      NENormalizationLayerKernel by ARM_COMPUTE_ENABLE_FP16 so that
      the fp16 kernels can be compiled in for multi_isa builds

    * Moved fp32 kernels to the corresponding file
      src/cpu/kernels/norm_layer/generic/neon/fp32.cpp

    * Partially resolves MLCE-1102

Change-Id: I3f2eb2ed0b6c7f68092b17872b85082fbb5f39e2
Signed-off-by: Pablo Marquez Tello <pablo.tello@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/10739
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Viet-Hoa Do <viet-hoa.do@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Benchmark: Arm Jenkins <bsgcomp@arm.com>

src/core/NEON/kernels/NENormalizationLayerKernel.h

diff --git a/src/core/NEON/kernels/NENormalizationLayerKernel.h b/src/core/NEON/kernels/NENormalizationLayerKernel.h
index 2d8d9f3..5ba4c3e 100644
--- a/src/core/NEON/kernels/NENormalizationLayerKernel.h
+++ b/src/core/NEON/kernels/NENormalizationLayerKernel.h
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2017-2020 Arm Limited.
+ * Copyright (c) 2017-2020, 2023 Arm Limited.
  *
  * SPDX-License-Identifier: MIT
  *
@@ -21,8 +21,8 @@
  * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
  * SOFTWARE.
  */
-#ifndef ARM_COMPUTE_NENORMALIZATIONLAYERKERNEL_H
-#define ARM_COMPUTE_NENORMALIZATIONLAYERKERNEL_H
+#ifndef ACL_SRC_CORE_NEON_KERNELS_NENORMALIZATIONLAYERKERNEL_H
+#define ACL_SRC_CORE_NEON_KERNELS_NENORMALIZATIONLAYERKERNEL_H
 
 #include "src/core/NEON/INEKernel.h"
 
@@ -82,24 +82,12 @@
     void run(const Window &window, const ThreadInfo &info) override;
 
 private:
-    /** Function to perform normalization depending on the given template
-     *  dimension. The second template parameter specifies whether the
-     *  normalization has to be 1D or 2D.
-     *
-     * @note Only supported normalizations are:
-     *  - 1D over X or Z
-     *  - 2D over X and Y
-     *
-     * @param[in] window Region on which to execute the kernel.
-     */
-    template <typename T, unsigned int S, unsigned int dim, bool do_2D_norm>
-    void normalize_float(const Window &window);
-
     /** Common signature for all the specialised normalization functions
      *
      * @param[in] window Region on which to execute the kernel.
      */
-    using NormalizationFunction = void (NENormalizationLayerKernel::*)(const Window &window);
+    using NormalizationFunction = void (*)(
+        const Window &window, const ITensor *in, const ITensor *in_squared, ITensor *out, NormalizationLayerInfo ninfo);
 
 private:
     NormalizationFunction  _func;
@@ -109,4 +97,4 @@
     NormalizationLayerInfo _norm_info;
 };
 } // namespace arm_compute
-#endif /*ARM_COMPUTE_NENORMALIZATIONLAYERKERNEL_H */
+#endif // ACL_SRC_CORE_NEON_KERNELS_NENORMALIZATIONLAYERKERNEL_H