COMPMID-3460: Refactor NEElementwiseUnaryKernel
Removed most of the templates and refactored the code.
Performance is the same but the libary size dropped by
52Kb.
Change-Id: I41ff0c0853c923d925cdaeb05f4a58c9086fff94
Signed-off-by: Michalis Spyrou <michalis.spyrou@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/3190
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
diff --git a/arm_compute/core/NEON/wrapper/intrinsics/log.h b/arm_compute/core/NEON/wrapper/intrinsics/log.h
index bb4181e..682830c 100644
--- a/arm_compute/core/NEON/wrapper/intrinsics/log.h
+++ b/arm_compute/core/NEON/wrapper/intrinsics/log.h
@@ -1,5 +1,5 @@
/*
- * Copyright (c) 2018-2019 ARM Limited.
+ * Copyright (c) 2018-2020 ARM Limited.
*
* SPDX-License-Identifier: MIT
*
@@ -37,10 +37,19 @@
return prefix##_##postfix(a); \
}
+#define VLOG_IMPL_INT(vtype, prefix, postfix) \
+ inline vtype vlog(const vtype &a) \
+ { \
+ ARM_COMPUTE_UNUSED(a); \
+ ARM_COMPUTE_ERROR("Not supported"); \
+ }
+
VLOG_IMPL(float32x4_t, vlogq, f32)
#ifdef __ARM_FEATURE_FP16_VECTOR_ARITHMETIC
VLOG_IMPL(float16x8_t, vlogq, f16)
#endif // __ARM_FEATURE_FP16_VECTOR_ARITHMETIC
+VLOG_IMPL_INT(int32x4_t, vlogq, s32)
+
#undef VLOG_IMPL
} // namespace wrapper
} // namespace arm_compute