From 03b2971ac69a86f10a1566938d1a25afee15746c Mon Sep 17 00:00:00 2001 From: Viet-Hoa Do Date: Wed, 1 Jun 2022 11:47:14 +0100 Subject: Integrate SME2 kernels * Add SME/SME2 detection. * Integrate SME2 implementation for: - Normal convolution - Winograd - Depthwise convolution - Pooling Resolves: COMPMID-5700 Signed-off-by: Viet-Hoa Do Change-Id: I2f1ca1d05f8cfeee9309ed1c0a36096a4a6aad5c Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/8692 Reviewed-by: Gunes Bayir Tested-by: Arm Jenkins Comments-Addressed: Arm Jenkins --- .../NEON/kernels/arm_gemm/transforms/list-sve.hpp | 20 +++++++++++++++++++- 1 file changed, 19 insertions(+), 1 deletion(-) (limited to 'src/core/NEON/kernels/arm_gemm/transforms/list-sve.hpp') diff --git a/src/core/NEON/kernels/arm_gemm/transforms/list-sve.hpp b/src/core/NEON/kernels/arm_gemm/transforms/list-sve.hpp index 895177b6cc..c066c01bab 100644 --- a/src/core/NEON/kernels/arm_gemm/transforms/list-sve.hpp +++ b/src/core/NEON/kernels/arm_gemm/transforms/list-sve.hpp @@ -1,5 +1,5 @@ /* - * Copyright (c) 2021 Arm Limited. + * Copyright (c) 2021-2022 Arm Limited. * * SPDX-License-Identifier: MIT * @@ -21,6 +21,24 @@ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE * SOFTWARE. */ +#ifdef ARM_COMPUTE_ENABLE_SME +#include "sme_transpose_interleave_16VL_1x4.hpp" +#include "sme_transpose_interleave_16VL_2x2_fp32bf16.hpp" +#include "sme_transpose_interleave_16VL_2x2.hpp" +#include "sme_transpose_interleave_16VL.hpp" +#include "sme_transpose_interleave_1VL_1x4.hpp" +#include "sme_transpose_interleave_1VL_2x2_fp32bf16.hpp" +#include "sme_transpose_interleave_1VL_2x2.hpp" +#include "sme_transpose_interleave_1VL.hpp" +#include "sme_transpose_interleave_2VL_1x4.hpp" +#include "sme_transpose_interleave_2VL_2x2.hpp" +#include "sme_transpose_interleave_2VL_2x2_fp32bf16.hpp" +#include "sme_transpose_interleave_2VL.hpp" +#include "sme_transpose_interleave_4VL_1x4.hpp" +#include "sme_transpose_interleave_4VL_2x2.hpp" +#include "sme_transpose_interleave_4VL_2x2_fp32bf16.hpp" +#include "sme_transpose_interleave_4VL.hpp" +#endif // ARM_COMPUTE_ENABLE_SME #include "sve_transpose_interleave_12VL_2x4_fp32bf16.hpp" #include "sve_transpose_interleave_1VL_1x4.hpp" #include "sve_transpose_interleave_1VL.hpp" -- cgit v1.2.1