Enable quantized data types for CpuElementwiseUnary on Armv7a
- Adding fallback functions neon_qasymm8_signed_elementwise_unary() and
neon_qasymm8_elementwise_unary()
- They would be called in case target is not aarch64
Resolves: COMPMID-5994
Change-Id: Id0db1e7cb0fe92f1eaef0b3a9ed2bea01b3f2a15
Signed-off-by: Ramy Elgammal <ramy.elgammal@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9416
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Viet-Hoa Do <viet-hoa.do@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Benchmark: Arm Jenkins <bsgcomp@arm.com>
diff --git a/tests/validation/NEON/ElementwiseRound.cpp b/tests/validation/NEON/ElementwiseRound.cpp
index a6ff47c..620618c 100644
--- a/tests/validation/NEON/ElementwiseRound.cpp
+++ b/tests/validation/NEON/ElementwiseRound.cpp
@@ -114,8 +114,8 @@
validate(Accessor(_target), _reference, tolerance_qasymm8_signed);
}
TEST_SUITE_END() // QASYMM8_SIGNED
-
TEST_SUITE_END() // Quantized
+
TEST_SUITE_END() // RoundLayer
TEST_SUITE_END() // Neon
} // namespace validation