commit 40b441905760846e9fdaca283a4a4de038a6ef0d
author Viet-Hoa Do <viet-hoa.do@arm.com> Thu Sep 22 10:24:23 2022 +0100
committer Viet-Hoa Do <viet-hoa.do@arm.com> Mon Oct 03 08:57:23 2022 +0000
tree 38a4f6b5122bfaf44a2a33e90b331a2e1a30b113
parent ff81de5a9a0f6b9331c3b112cc2aed552f0482a9

Optimize CPU add layer on quantized data

* Use fixed-point arithmetic where possible.
* Various optimization for the FP32-based implementation.
  This implementation is kept as the fall-back solution
  in case of unrealistic quantization parameters that exceed
  the range of fixed-point solution.

Resolves: COMPMID-5458
Signed-off-by: Viet-Hoa Do <viet-hoa.do@arm.com>
Change-Id: I221d2d3801ecaae4fe0b7cf6ae8ef00ca3743665
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/8317
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>

src/core/NEON/wrapper/intrinsics/intrinsics.h

diff --git a/src/core/NEON/wrapper/intrinsics/intrinsics.h b/src/core/NEON/wrapper/intrinsics/intrinsics.h
index 0256e0a..97975eb 100644
--- a/src/core/NEON/wrapper/intrinsics/intrinsics.h
+++ b/src/core/NEON/wrapper/intrinsics/intrinsics.h
@@ -67,6 +67,7 @@
 #include "src/core/NEON/wrapper/intrinsics/rev64.h"
 #include "src/core/NEON/wrapper/intrinsics/round.h"
 #include "src/core/NEON/wrapper/intrinsics/setlane.h"
+#include "src/core/NEON/wrapper/intrinsics/shr.h"
 #include "src/core/NEON/wrapper/intrinsics/sin.h"
 #include "src/core/NEON/wrapper/intrinsics/sqrt.h"
 #include "src/core/NEON/wrapper/intrinsics/store.h"