1 /* Copyright 2017 The TensorFlow Authors. All Rights Reserved. 2 3 Licensed under the Apache License, Version 2.0 (the "License"); 4 you may not use this file except in compliance with the License. 5 You may obtain a copy of the License at 6 7 http://www.apache.org/licenses/LICENSE-2.0 8 9 Unless required by applicable law or agreed to in writing, software 10 distributed under the License is distributed on an "AS IS" BASIS, 11 WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 See the License for the specific language governing permissions and 13 limitations under the License. 14 ==============================================================================*/ 15 16 #ifndef TENSORFLOW_COMPILER_XLA_SERVICE_CPU_RUNTIME_MATVEC_H_ 17 #define TENSORFLOW_COMPILER_XLA_SERVICE_CPU_RUNTIME_MATVEC_H_ 18 19 #include "tensorflow/core/platform/types.h" 20 21 namespace xla { 22 23 // Performs a matrix-vector multiplication using Eigen. 'lhs' and 'rhs' are 24 // pointers to buffers containing input matrices in column-major order. 'out' is 25 // a pointer to a buffer sufficiently large to hold the result of the 26 // operation. Following standard nomenclature: lhs is m x k, rhs is k x n, and 27 // out is m x n. 28 // 29 // This requires that m = 1 or n = 1. 30 // 31 // TODO(b/64684907): Compare runtime performance of these functions with dot 32 // simplification. 33 void EigenMatVecF32(float* out, float* lhs, float* rhs, tensorflow::int64 m, 34 tensorflow::int64 n, tensorflow::int64 k, 35 tensorflow::int32 transpose_lhs, 36 tensorflow::int32 transpose_rhs); 37 38 void EigenMatVecF64(double* out, double* lhs, double* rhs, tensorflow::int64 m, 39 tensorflow::int64 n, tensorflow::int64 k, 40 tensorflow::int32 transpose_lhs, 41 tensorflow::int32 transpose_rhs); 42 43 } // namespace xla 44 45 #endif // TENSORFLOW_COMPILER_XLA_SERVICE_CPU_RUNTIME_MATVEC_H_ 46
