Remove dependency on fp16 definitions from some core include files

This significantly improves the compilation times for parts of the core library that just need
a definition of float16_t rather than access to all of the fp16 intrinsics.

Signed-off-by: Matthew Bentham <Matthew.Bentham@arm.com>
Change-Id: I5da1c6b0df0dd87d1d17948cd2e9b7375874f455
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/c/VisualCompute/ComputeLibrary/+/529385
Tested-by: bsgcomp <bsgcomp@arm.com>
Reviewed-by: Pablo Tello <pablo.tello@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9781
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>

5 files changed, 57 insertions, 62 deletions

diff --git a/arm_compute/core/QuantizationInfo.h b/arm_compute/core/QuantizationInfo.h
index f760d7512c..8fa513eee1 100644
--- a/arm_compute/core/QuantizationInfo.h
+++ b/arm_compute/core/QuantizationInfo.h
@@ -24,13 +24,10 @@
 #ifndef ARM_COMPUTE_QUANTIZATION_INFO_H
 #define ARM_COMPUTE_QUANTIZATION_INFO_H
 
-#include "arm_compute/core/Error.h"
 #include "arm_compute/core/Rounding.h"
+#include "arm_compute/core/utils/misc/Utility.h"
 #include "support/ToolchainSupport.h"
-#include "utils/misc/Utility.h"
 
-#include <cstddef>
-#include <type_traits>
 #include <vector>
 
 namespace arm_compute
diff --git a/arm_compute/core/Utils.h b/arm_compute/core/Utils.h
index edeae21c6f..188ae8cf5b 100644
--- a/arm_compute/core/Utils.h
+++ b/arm_compute/core/Utils.h
@@ -593,59 +593,6 @@ inline std::tuple<PixelValue, PixelValue> get_min_max(DataType dt)
     return std::make_tuple(min, max);
 }
 
-/** Return true if the given format has horizontal subsampling.
- *
- * @param[in] format Format to determine subsampling.
- *
- * @return True if the format can be subsampled horizontaly.
- */
-inline bool has_format_horizontal_subsampling(Format format)
-{
-    return (format == Format::YUYV422 || format == Format::UYVY422 || format == Format::NV12 || format == Format::NV21 || format == Format::IYUV || format == Format::UV88) ? true : false;
-}
-
-/** Return true if the given format has vertical subsampling.
- *
- * @param[in] format Format to determine subsampling.
- *
- * @return True if the format can be subsampled verticaly.
- */
-inline bool has_format_vertical_subsampling(Format format)
-{
-    return (format == Format::NV12 || format == Format::NV21 || format == Format::IYUV || format == Format::UV88) ? true : false;
-}
-
-/** Calculate subsampled shape for a given format and channel
- *
- * @param[in] shape   Shape of the tensor to calculate the extracted channel.
- * @param[in] format  Format of the tensor.
- * @param[in] channel Channel to create tensor shape to be extracted.
- *
- * @return The subsampled tensor shape.
- */
-inline TensorShape calculate_subsampled_shape(const TensorShape &shape, Format format, Channel channel = Channel::UNKNOWN)
-{
-    TensorShape output{ shape };
-
-    // Subsample shape only for U or V channel
-    if(Channel::U == channel || Channel::V == channel || Channel::UNKNOWN == channel)
-    {
-        // Subsample width for the tensor shape when channel is U or V
-        if(has_format_horizontal_subsampling(format))
-        {
-            output.set(0, output.x() / 2U);
-        }
-
-        // Subsample height for the tensor shape when channel is U or V
-        if(has_format_vertical_subsampling(format))
-        {
-            output.set(1, output.y() / 2U);
-        }
-    }
-
-    return output;
-}
-
 /** Permutes the given dimensions according the permutation vector
  *
  * @param[in,out] dimensions Dimensions to be permuted.
diff --git a/arm_compute/core/Validate.h b/arm_compute/core/Validate.h
index 7e387c9cc1..ff4540cd8a 100644
--- a/arm_compute/core/Validate.h
+++ b/arm_compute/core/Validate.h
@@ -27,6 +27,7 @@
 #include "arm_compute/core/Error.h"
 #include "arm_compute/core/IKernel.h"
 #include "arm_compute/core/ITensor.h"
+#include "arm_compute/core/QuantizationInfo.h"
 #include "arm_compute/core/Utils.h"
 #include "arm_compute/core/Window.h"
 
@@ -285,6 +286,28 @@ arm_compute::Status error_on_mismatching_dimensions(const char *function, const
 #define ARM_COMPUTE_RETURN_ERROR_ON_MISMATCHING_DIMENSIONS(...) \
     ARM_COMPUTE_RETURN_ON_ERROR(::arm_compute::error_on_mismatching_dimensions(__func__, __FILE__, __LINE__, __VA_ARGS__))
 
+/** Return true if the given format has horizontal subsampling.
+ *
+ * @param[in] format Format to determine subsampling.
+ *
+ * @return True if the format can be subsampled horizontaly.
+ */
+inline bool has_format_horizontal_subsampling(Format format)
+{
+    return (format == Format::YUYV422 || format == Format::UYVY422 || format == Format::NV12 || format == Format::NV21 || format == Format::IYUV || format == Format::UV88) ? true : false;
+}
+
+/** Return true if the given format has vertical subsampling.
+ *
+ * @param[in] format Format to determine subsampling.
+ *
+ * @return True if the format can be subsampled verticaly.
+ */
+inline bool has_format_vertical_subsampling(Format format)
+{
+    return (format == Format::NV12 || format == Format::NV21 || format == Format::IYUV || format == Format::UV88) ? true : false;
+}
+
 /** Adjust tensor shape size if width or height are odd for a given multi-planar format. No modification is done for other formats.
  *
  * @note Adding here a few links discussing the issue of odd size and sharing the same solution:
@@ -349,6 +372,37 @@ arm_compute::Status error_on_tensors_not_even(const char *function, const char *
 #define ARM_COMPUTE_RETURN_ERROR_ON_TENSORS_NOT_EVEN(...) \
     ARM_COMPUTE_RETURN_ON_ERROR(::arm_compute::error_on_tensors_not_even(__func__, __FILE__, __LINE__, __VA_ARGS__))
 
+/** Calculate subsampled shape for a given format and channel
+ *
+ * @param[in] shape   Shape of the tensor to calculate the extracted channel.
+ * @param[in] format  Format of the tensor.
+ * @param[in] channel Channel to create tensor shape to be extracted.
+ *
+ * @return The subsampled tensor shape.
+ */
+inline TensorShape calculate_subsampled_shape(const TensorShape &shape, Format format, Channel channel = Channel::UNKNOWN)
+{
+    TensorShape output{ shape };
+
+    // Subsample shape only for U or V channel
+    if(Channel::U == channel || Channel::V == channel || Channel::UNKNOWN == channel)
+    {
+        // Subsample width for the tensor shape when channel is U or V
+        if(has_format_horizontal_subsampling(format))
+        {
+            output.set(0, output.x() / 2U);
+        }
+
+        // Subsample height for the tensor shape when channel is U or V
+        if(has_format_vertical_subsampling(format))
+        {
+            output.set(1, output.y() / 2U);
+        }
+    }
+
+    return output;
+}
+
 /** Return an error if the passed tensor objects are not sub-sampled.
  *
  * @param[in] function Function in which the error occurred.
diff --git a/arm_compute/graph/Graph.h b/arm_compute/graph/Graph.h
index d8d3feb1f7..806d84c3fd 100644
--- a/arm_compute/graph/Graph.h
+++ b/arm_compute/graph/Graph.h
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2018-2020 Arm Limited.
+ * Copyright (c) 2018-2020,2023 Arm Limited.
  *
  * SPDX-License-Identifier: MIT
  *
@@ -30,7 +30,6 @@
 #include "arm_compute/graph/Types.h"
 
 #include "support/Mutex.h"
-#include "support/ToolchainSupport.h"
 
 #include <map>
 #include <memory>
diff --git a/arm_compute/runtime/CPP/functions/CPPSplit.h b/arm_compute/runtime/CPP/functions/CPPSplit.h
index e2e5add264..56aad2db4b 100644
--- a/arm_compute/runtime/CPP/functions/CPPSplit.h
+++ b/arm_compute/runtime/CPP/functions/CPPSplit.h
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2020-2021 Arm Limited.
+ * Copyright (c) 2020-2021,2023 Arm Limited.
  *
  * SPDX-License-Identifier: MIT
  *
@@ -30,8 +30,6 @@
 #include "arm_compute/core/Types.h"
 #include "arm_compute/core/utils/misc/ShapeCalculator.h"
 
-#include "support/ToolchainSupport.h"
-
 #include "arm_compute/runtime/IFunction.h"
 
 namespace arm_compute