diff options
| author | Ramy Elgammal <ramy.elgammal@arm.com> | 2024-05-13 11:12:11 +0100 |
|---|---|---|
| committer | Pablo Marquez Tello <pablo.tello@arm.com> | 2024-05-13 19:10:40 +0000 |
| commit | 21fb2ad16a30a5ff29929515abe28c14b2c6b5a1 (patch) | |
| tree | d9dfebf7619237d021009997aa8198e738e48bc4 /Android.bp | |
| parent | 4c3f716371da92977d4a998fe5c89dee04ddbced (diff) | |
| download | ComputeLibrary-21fb2ad16a30a5ff29929515abe28c14b2c6b5a1.tar.gz | |
Fix ReductionLayer FP16 for armv8a multi_isa builds
- Enable FP16 code when building multi_isa for armv8a architecture in
order to run on higher architectures e.g. 8.2, 8.6.
- When running this build on v8 the validation will stop it flagging
that the arch does not support FP16.
Resolves: COMPMID-7013
Signed-off-by: Ramy Elgammal <ramy.elgammal@arm.com>
Change-Id: I0d445e2fade31c1156d7a6e142edf2a7f84d3622
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/11544
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Pablo Marquez Tello <pablo.tello@arm.com>
Benchmark: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'Android.bp')
| -rw-r--r-- | Android.bp | 5 |
1 files changed, 5 insertions, 0 deletions
diff --git a/Android.bp b/Android.bp index ab554a8ca2..c6e89b02c4 100644 --- a/Android.bp +++ b/Android.bp @@ -557,6 +557,11 @@ cc_library_static { "src/cpu/kernels/range/generic/neon/fp16.cpp", "src/cpu/kernels/range/generic/neon/fp32.cpp", "src/cpu/kernels/range/generic/neon/integer.cpp", + "src/cpu/kernels/reduction_layer/generic/neon/fp16.cpp", + "src/cpu/kernels/reduction_layer/generic/neon/fp32.cpp", + "src/cpu/kernels/reduction_layer/generic/neon/integer.cpp", + "src/cpu/kernels/reduction_layer/generic/neon/qasymm8.cpp", + "src/cpu/kernels/reduction_layer/generic/neon/qasymm8_signed.cpp", "src/cpu/kernels/roialign/generic/neon/fp16.cpp", "src/cpu/kernels/roialign/generic/neon/fp32.cpp", "src/cpu/kernels/roialign/generic/neon/qasymm8.cpp", |