sample_cublasLt_LtSgemmSimpleAutoTuning.h

/*
 * SPDX-FileCopyrightText: Copyright (c) 2020 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
 * SPDX-License-Identifier: Apache-2.0
 *
 * Licensed under the Apache License, Version 2.0 (the "License");
 * you may not use this file except in compliance with the License.
 * You may obtain a copy of the License at
 *
 * http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */

#include <cublasLt.h>

/// Sample wrapper executing single precision gemm algorithm auto tuning by querying cublasLt heuristics for best
/// algorithms, iterate over the results and pick the algorithm that have the best performance for the given problem
///
/// pointer mode is always host, to change it configure the appropriate matmul descriptor attribute
/// matmul is not using cublas handle's configuration of math mode, here tensor ops are implicitly allowed; to change
/// this configure appropriate attribute in the preference handle
void LtSgemmSimpleAutoTuning(cublasLtHandle_t ltHandle,
                             cublasOperation_t transa,
                             cublasOperation_t transb,
                             int m,
                             int n,
                             int k,
                             const float *alpha, /* host pointer */
                             const float *A,
                             int lda,
                             const float *B,
                             int ldb,
                             const float *beta, /* host pointer */
                             float *C,
                             int ldc,
                             void *workspace,
                             size_t workspaceSize,
                             cublasLtMatmulAlgo_t &algo);