diff options
| author | ramelg01 <ramy.elgammal@arm.com> | 2022-04-07 02:42:52 +0100 |
|---|---|---|
| committer | Ramy Elgammal <ramy.elgammal@arm.com> | 2022-04-26 15:51:22 +0000 |
| commit | 8a164884dddf769643cf3b9f7f94e43cb4f3c20b (patch) | |
| tree | 35958dd48b6df1a851c880dad2b2ce285671b611 /src/core/NEON/kernels/arm_conv/depthwise/kernels/a64_fp16_nhwc_generic_output9_mla_depthfirst/generic.cpp | |
| parent | c827e99fc46521f43719b0c2d1b6f05d66abf68c (diff) | |
| download | ComputeLibrary-8a164884dddf769643cf3b9f7f94e43cb4f3c20b.tar.gz | |
Update Neon™ depthwise kernel
- Reduce duplication and simplify overall structure.
- Improve multi-threaded performance by sharing more data
in lower-level caches.
Partially Resolves: COMPMID-5054
Signed-off-by: Ramy Elgammal <ramy.elgammal@arm.com>
Change-Id: Iac747f39b21c540122fa75218762631c4d787911
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7449
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Andrew Mundy
Reviewed-by: Sheri Zhang <sheri.zhang@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'src/core/NEON/kernels/arm_conv/depthwise/kernels/a64_fp16_nhwc_generic_output9_mla_depthfirst/generic.cpp')
| -rw-r--r-- | src/core/NEON/kernels/arm_conv/depthwise/kernels/a64_fp16_nhwc_generic_output9_mla_depthfirst/generic.cpp | 6 |
1 files changed, 3 insertions, 3 deletions
diff --git a/src/core/NEON/kernels/arm_conv/depthwise/kernels/a64_fp16_nhwc_generic_output9_mla_depthfirst/generic.cpp b/src/core/NEON/kernels/arm_conv/depthwise/kernels/a64_fp16_nhwc_generic_output9_mla_depthfirst/generic.cpp index 8ac79f82fa..423ee4190c 100644 --- a/src/core/NEON/kernels/arm_conv/depthwise/kernels/a64_fp16_nhwc_generic_output9_mla_depthfirst/generic.cpp +++ b/src/core/NEON/kernels/arm_conv/depthwise/kernels/a64_fp16_nhwc_generic_output9_mla_depthfirst/generic.cpp @@ -1,5 +1,5 @@ /* - * Copyright (c) 2021 Arm Limited. + * Copyright (c) 2021-2022 Arm Limited. * * SPDX-License-Identifier: MIT * @@ -25,7 +25,7 @@ #include <cstddef> #include <cstdint> -#if defined(__ARM_FP16_ARGS) && defined(__ARM_FEATURE_FP16_VECTOR_ARITHMETIC) +#if defined(__aarch64__) && defined(__ARM_FP16_ARGS) && defined(__ARM_FEATURE_FP16_VECTOR_ARITHMETIC) namespace arm_conv { namespace depthwise { @@ -524,4 +524,4 @@ void a64_fp16_nhwc_generic_output9_mla_depthfirst_impl( } // namespace depthwise } // namespace arm_conv -#endif // defined(__ARM_FP16_ARGS) && defined(__ARM_FEATURE_FP16_VECTOR_ARITHMETIC) +#endif // defined(__aarch64__) && defined(__ARM_FP16_ARGS) && defined(__ARM_FEATURE_FP16_VECTOR_ARITHMETIC) |