diff options
| author | Michael Tyler <michael.tyler@arm.com> | 2023-04-12 17:43:17 +0100 |
|---|---|---|
| committer | michael.tyler <michael.tyler@arm.com> | 2023-06-05 15:57:58 +0000 |
| commit | 74921eee924625426429044decefe3673561b174 (patch) | |
| tree | 654da1a95e3d42d6af8ad1ff27bb40d77b1fd8c5 /src/core/NEON/kernels/convolution/winograd/output_transforms_fp32.cpp | |
| parent | df5d9878008be9b60586df97ebfff197abb5195e (diff) | |
| download | ComputeLibrary-74921eee924625426429044decefe3673561b174.tar.gz | |
Update CPU kernel implementations and guard directives
Resolves COMPMID-6023
Change-Id: I868975d14c4f98af6716726feda22405a6a4c891
Signed-off-by: Michael Tyler <michael.tyler@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9686
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>
Diffstat (limited to 'src/core/NEON/kernels/convolution/winograd/output_transforms_fp32.cpp')
| -rw-r--r-- | src/core/NEON/kernels/convolution/winograd/output_transforms_fp32.cpp | 10 |
1 files changed, 5 insertions, 5 deletions
diff --git a/src/core/NEON/kernels/convolution/winograd/output_transforms_fp32.cpp b/src/core/NEON/kernels/convolution/winograd/output_transforms_fp32.cpp index a221aee5d8..0a7030324e 100644 --- a/src/core/NEON/kernels/convolution/winograd/output_transforms_fp32.cpp +++ b/src/core/NEON/kernels/convolution/winograd/output_transforms_fp32.cpp @@ -1,5 +1,5 @@ /* - * Copyright (c) 2022 Arm Limited. + * Copyright (c) 2022-2023 Arm Limited. * * SPDX-License-Identifier: MIT * @@ -30,9 +30,9 @@ namespace winograd { namespace output_transform { #if defined(__aarch64__) -#if defined(ARM_COMPUTE_ENABLE_SVE) && defined(ARM_COMPUTE_ENABLE_SME) +#if defined(ARM_COMPUTE_ENABLE_SME) void sme_fp32_mopa_4x4_3x3(unsigned int, const float *, size_t, const float *, float *, size_t, size_t, float, float); -#endif // defined(ARM_COMPUTE_ENABLE_SVE) && defined(ARM_COMPUTE_ENABLE_SME) +#endif // defined(ARM_COMPUTE_ENABLE_SME) #endif // defined(__aarch64__) void arm_fp32_4x4_3x3(unsigned int, const float *, size_t, const float *, float *, size_t, size_t, float, float); void arm_fp32_2x2_3x3(unsigned int, const float *, size_t, const float *, float *, size_t, size_t, float, float); @@ -49,9 +49,9 @@ void arm_fp32_1x2_1x7(unsigned int, const float *, size_t, const float *, float static const TransformImplementation<float> transforms_fp32[] = { #if defined(__aarch64__) -#if defined(ARM_COMPUTE_ENABLE_SVE) && defined(ARM_COMPUTE_ENABLE_SME) +#if defined(ARM_COMPUTE_ENABLE_SME) { IMPL(4, 4, 3, 3, sme_fp32_mopa_4x4_3x3, Unpadded), MethodConstraints::RequiresSME }, -#endif // defined(ARM_COMPUTE_ENABLE_SVE) && defined(ARM_COMPUTE_ENABLE_SME) +#endif // defined(ARM_COMPUTE_ENABLE_SME) #endif // defined(__aarch64__) { IMPL(4, 4, 3, 3, arm_fp32_4x4_3x3, Unpadded), MethodConstraints::LargerShape }, { IMPL(2, 2, 3, 3, arm_fp32_2x2_3x3, Unpadded) }, |