From cea7060684ae6c33fc8e16affc1c7998d17815ae Mon Sep 17 00:00:00 2001 From: Pablo Marquez Tello Date: Thu, 17 Aug 2023 16:18:17 +0100 Subject: NEFuseBatchNormalizationKernel rework * Enable fp16 in armv8a multi_isa builds * Code guarded with __ARM_FEATURE_FP16_VECTOR_ARITHMETIC needs to be moved to an fp16.cpp file to allow compilation with -march=armv8.2-a+fp16 * fp16.cpp needs to use the template add_same_neon() so it had to be moved from impl.cpp to impl.h * Partially resolves MLCE-1102 Change-Id: Ia51007f5e663b708071958bb94bfab4535e4b2f8 Signed-off-by: Pablo Marquez Tello Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/10191 Benchmark: Arm Jenkins Tested-by: Arm Jenkins Reviewed-by: Viet-Hoa Do Comments-Addressed: Arm Jenkins --- Android.bp | 1 - 1 file changed, 1 deletion(-) (limited to 'Android.bp') diff --git a/Android.bp b/Android.bp index 14290b9e1c..487c818185 100644 --- a/Android.bp +++ b/Android.bp @@ -515,7 +515,6 @@ cc_library_static { "src/cpu/kernels/floor/neon/fp32.cpp", "src/cpu/kernels/fuse_batch_normalization/generic/fp16.cpp", "src/cpu/kernels/fuse_batch_normalization/generic/fp32.cpp", - "src/cpu/kernels/fuse_batch_normalization/generic/impl.cpp", "src/cpu/kernels/fuse_batch_normalization/nchw/all.cpp", "src/cpu/kernels/fuse_batch_normalization/nhwc/neon/fp16.cpp", "src/cpu/kernels/fuse_batch_normalization/nhwc/neon/fp32.cpp", -- cgit v1.2.1