From 4ee8b1599dbaf7634d25607fa5ac96ba3dc6b0f2 Mon Sep 17 00:00:00 2001 From: Georgios Pinitas Date: Fri, 16 Jul 2021 16:16:43 +0100 Subject: Update GEMM assembly kernels - Introduce Fp32 kernels with internal calculations in Bfloat16 when fast_mode is enabled - Improve kernel selection heuristics Signed-off-by: Georgios Pinitas Change-Id: I68a9e7e862b6fd2721b46e0d7cc791091c4ab279 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5965 Tested-by: Arm Jenkins Comments-Addressed: Arm Jenkins --- .../NEON/kernels/arm_gemm/transforms/transpose_interleave_common.hpp | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'src/core/NEON/kernels/arm_gemm/transforms/transpose_interleave_common.hpp') diff --git a/src/core/NEON/kernels/arm_gemm/transforms/transpose_interleave_common.hpp b/src/core/NEON/kernels/arm_gemm/transforms/transpose_interleave_common.hpp index a3216c494f..02367bd7e7 100644 --- a/src/core/NEON/kernels/arm_gemm/transforms/transpose_interleave_common.hpp +++ b/src/core/NEON/kernels/arm_gemm/transforms/transpose_interleave_common.hpp @@ -1,5 +1,5 @@ /* - * Copyright (c) 2017-2018 Arm Limited. + * Copyright (c) 2017-2021 Arm Limited. * * SPDX-License-Identifier: MIT * @@ -58,7 +58,7 @@ struct TransposeInterleaveCommon { } } - static inline void Transform(TOut *out, const TIn *in, const int stride, const int x0, const int xmax, const int k0, const int kmax) { + static void Transform(TOut *out, const TIn *in, const int stride, const int x0, const int xmax, const int k0, const int kmax) { const auto ldin = stride; TOut *outarray = out; -- cgit v1.2.1