///////////////////////////////////////////////////////////////////////
// File:        intsindmatrixsse.cpp
// Description: SSE implementation of 8-bit int SIMD matrix multiply.
// Author:      Ray Smith
// Created:     Tue Aug 23 13:58:49 PST 2017
//
// (C) Copyright 2017, Google Inc.
// 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 "intsimdmatrixsse.h"

#include <stdint.h>
#include <vector>
#include "dotproductsse.h"

namespace tesseract {

#ifdef __SSE4_1__
// Computes part of matrix.vector v = Wu. Computes 1 result.
static void PartialMatrixDotVector1(const int8_t* wi, const double* scales,
                                    const int8_t* u, int num_in, int num_out,
                                    double* v) {
  int total = IntDotProductSSE(u, wi, num_in);
  // Add in the bias and correct for integer values.
  *v = (static_cast<double>(total) / MAX_INT8 + wi[num_in]) * *scales;
}
#endif  // __SSE4_1__

IntSimdMatrixSSE::IntSimdMatrixSSE() {
#ifdef __SSE4_1__
  partial_funcs_ = {PartialMatrixDotVector1};
#endif  // __SSE4_1__
}

}  // namespace tesseract.