From 40b441905760846e9fdaca283a4a4de038a6ef0d Mon Sep 17 00:00:00 2001 From: Viet-Hoa Do Date: Thu, 22 Sep 2022 10:24:23 +0100 Subject: 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 Change-Id: I221d2d3801ecaae4fe0b7cf6ae8ef00ca3743665 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/8317 Tested-by: Arm Jenkins Reviewed-by: Gunes Bayir Comments-Addressed: Arm Jenkins Benchmark: Arm Jenkins --- src/core/NEON/wrapper/intrinsics/intrinsics.h | 1 + 1 file changed, 1 insertion(+) (limited to '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 0256e0a8c8..97975ebe7c 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" -- cgit v1.2.1