From 8d4cdd43a74574e0f99f83f1adb1d391c0c85abe Mon Sep 17 00:00:00 2001 From: Pablo Marquez Tello Date: Tue, 21 Nov 2023 10:10:01 +0000 Subject: BatchNorm changes to enable fp16 in armv8a multi_isa builds * Moved NCHW kernels fp16 and fp32 to their corresponding files src/cpu/kernels/fuse_batch_normalization/nchw/neon/fp16.cpp and src/cpu/kernels/fuse_batch_normalization/nchw/neon/fp32.cpp * Changes in filelist.json to include the new fp16 and fp32 files * Moved the template batch_normalization_nchw to impl.h as we need to instantiate it from fp16.cpp and fp32.cpp * Pooling layer: removed the guard __ARM_FEATURE_FP16_VECTOR_ARITHMETIC that prevented the FP16 kernel execution. * Partially resolves MLCE-1102 Change-Id: Ia8c85e9ffb76c9e387f9ae2685e5df5e52c8dc27 Signed-off-by: Pablo Marquez Tello Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/10777 Reviewed-by: Viet-Hoa Do Comments-Addressed: Arm Jenkins Tested-by: Arm Jenkins Benchmark: Arm Jenkins --- filelist.json | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'filelist.json') diff --git a/filelist.json b/filelist.json index a84db7188d..c34eff2ff9 100644 --- a/filelist.json +++ b/filelist.json @@ -982,12 +982,15 @@ "fp16": [ "src/cpu/kernels/fuse_batch_normalization/generic/fp16.cpp", "src/core/NEON/kernels/batchnormalization/impl/NEON/fp16.cpp", - "src/cpu/kernels/fuse_batch_normalization/nhwc/neon/fp16.cpp" + "src/cpu/kernels/fuse_batch_normalization/nhwc/neon/fp16.cpp", + "src/cpu/kernels/fuse_batch_normalization/nchw/neon/fp16.cpp" + ], "fp32": [ "src/cpu/kernels/fuse_batch_normalization/generic/fp32.cpp", "src/core/NEON/kernels/batchnormalization/impl/NEON/fp32.cpp", - "src/cpu/kernels/fuse_batch_normalization/nhwc/neon/fp32.cpp" + "src/cpu/kernels/fuse_batch_normalization/nhwc/neon/fp32.cpp", + "src/cpu/kernels/fuse_batch_normalization/nchw/neon/fp32.cpp" ] }, "sve": { -- cgit v1.2.1