From ba93371f2316218a09a24403076ab3fdf967b168 Mon Sep 17 00:00:00 2001 From: Pablo Marquez Tello Date: Mon, 13 Nov 2023 15:57:54 +0000 Subject: 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 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/10739 Tested-by: Arm Jenkins Reviewed-by: Viet-Hoa Do Comments-Addressed: Arm Jenkins Benchmark: Arm Jenkins --- filelist.json | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'filelist.json') diff --git a/filelist.json b/filelist.json index d8c1692e80..ca8b18c0a5 100644 --- a/filelist.json +++ b/filelist.json @@ -1913,7 +1913,11 @@ "common": [ "src/core/NEON/kernels/NENormalizationLayerKernel.cpp", "src/runtime/NEON/functions/NENormalizationLayer.cpp" - ] + ], + "neon":{ + "fp16":["src/cpu/kernels/norm_layer/generic/neon/fp16.cpp"], + "fp32":["src/cpu/kernels/norm_layer/generic/neon/fp32.cpp"] + } } }, "Pad": { -- cgit v1.2.1