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_MATMUL_H_ 17 #define TENSORFLOW_COMPILER_XLA_SERVICE_CPU_RUNTIME_MATMUL_H_ 18 19 #include "third_party/eigen3/Eigen/Core" 20 #include "tensorflow/core/platform/types.h" 21 22 extern "C" { 23 24 // Performs a multi-threaded matrix multiplication using Eigen. 'lhs' and 'rhs' 25 // are pointers to buffers containing input matrices in column-major 26 // order. 'out' is a pointer to a buffer sufficiently large to hold the result 27 // of the operation. Following standard nomenclature: lhs is m x k, 28 // rhs is k x n, and out is m x n. 29 extern void __xla_cpu_runtime_EigenMatMulF16( 30 const void* /* xla::ExecutableRunOptions* */ run_options_ptr, 31 Eigen::half* out, Eigen::half* lhs, Eigen::half* rhs, tensorflow::int64 m, 32 tensorflow::int64 n, tensorflow::int64 k, tensorflow::int32 transpose_lhs, 33 tensorflow::int32 transpose_rhs); 34 35 extern void __xla_cpu_runtime_EigenMatMulF32( 36 const void* /* xla::ExecutableRunOptions* */ run_options_ptr, float* out, 37 float* lhs, float* rhs, tensorflow::int64 m, tensorflow::int64 n, 38 tensorflow::int64 k, tensorflow::int32 transpose_lhs, 39 tensorflow::int32 transpose_rhs); 40 41 extern void __xla_cpu_runtime_EigenMatMulF64( 42 const void* /* xla::ExecutableRunOptions* */ run_options_ptr, double* out, 43 double* lhs, double* rhs, tensorflow::int64 m, tensorflow::int64 n, 44 tensorflow::int64 k, tensorflow::int32 transpose_lhs, 45 tensorflow::int32 transpose_rhs); 46 47 } // extern "C" 48 49 #endif // TENSORFLOW_COMPILER_XLA_SERVICE_CPU_RUNTIME_MATMUL_H_ 50