void OverwriteCols(DenseMatrix<T>& A,
const DenseMatrix<T>& B,
const std::vector<unsigned int>& col_indices,
const unsigned int num_cols)
{
const unsigned int height = A.Height();
// Overwrite columns of A with B.
if (B.Height() != A.Height())
throw std::logic_error("OverwriteCols: height mismatch");
if (num_cols > static_cast<unsigned int>(A.Width()))
throw std::logic_error("OverwriteCols: col indices out of bounds");
T* buf_a = A.Buffer();
const unsigned int ldim_a = A.LDim();
const T* buf_b = B.LockedBuffer();
const unsigned int ldim_b = B.LDim();
for (unsigned int c=0; c<num_cols; ++c)
{
unsigned int col_a = col_indices[c];
unsigned int offset_a = col_a*ldim_a;
unsigned int offset_b = c*ldim_b;
memcpy(&buf_a[offset_a], &buf_b[offset_b], height * sizeof(T));
}
}
void Overwrite(DenseMatrix<T>& A,
const DenseMatrix<T>& B,
const std::vector<unsigned int>& row_indices,
const std::vector<unsigned int>& col_indices,
const unsigned int num_rows,
const unsigned int num_cols)
{
// Overwrite entries in A with entries in B. The row and column
// index arrays contain the destination indices to be overwritten.
// Matrix B has size num_rows x num_cols.
if (num_rows > static_cast<unsigned int>(A.Height()))
throw std::logic_error("Overwrite: row indices out of bounds");
if (num_cols > static_cast<unsigned int>(A.Width()))
throw std::logic_error("Overwrite: col indices out of bounds");
const T* buf_b = B.LockedBuffer();
const unsigned int ldim_b = B.LDim();
T* buf_a = A.Buffer();
const unsigned int ldim_a = A.LDim();
for (unsigned int c=0; c<num_cols; ++c)
{
unsigned int col_a = col_indices[c];
unsigned int offset_a = ldim_a * col_a;
unsigned int offset_b = ldim_b * c;
for (unsigned int r=0; r<num_rows; ++r)
{
unsigned int row_a = row_indices[r];
//T val = B.Get(r, c);
//A.Set(row_a, col_a, val);
buf_a[offset_a + row_a] = buf_b[offset_b + r];
}
}
}
void ZeroizeSmallValues(DenseMatrix<T>& A, const T tol)
{
// set Aij to zero if |Aij| < tol
T* buf = A.Buffer();
const unsigned int ldim = A.LDim();
const unsigned int height = A.Height();
const unsigned int width = A.Width();
OPENMP_PRAGMA(omp parallel for)
for (unsigned int c=0; c<width; ++c)
{
unsigned int col_offset = c*ldim;
for (unsigned int r=0; r<height; ++r)
{
T val = buf[col_offset + r];
if (std::abs(val) < tol)
{
buf[col_offset + r] = T(0);
}
}
}
}
void BppUpdateSets(BitMatrix& nonopt_set,
BitMatrix& infeas_set,
const BitMatrix& not_opt_mask,
const DenseMatrix<T>& X,
const DenseMatrix<T>& Y,
const BitMatrix& passive_set)
{
// This function performs the equivalent of these operations:
//
// nonopt_set = not_opt_mask & (Y < T(0)) & ~passive_set;
// infeas_set = not_opt_mask & (X < T(0)) & passive_set;
const unsigned int height = not_opt_mask.Height();
const unsigned int width = not_opt_mask.Width();
if ( (static_cast<unsigned int>(X.Height()) != height) ||
(static_cast<unsigned int>(Y.Height()) != height) ||
(passive_set.Height() != height))
throw std::logic_error("BppUpdateSets: height mismatch");
if ( (static_cast<unsigned int>(X.Width()) != width) ||
(static_cast<unsigned int>(Y.Width()) != width) ||
(passive_set.Width() != width))
throw std::logic_error("BppUpdateSets: width mismatch");
nonopt_set.Resize(height, width);
infeas_set.Resize(height, width);
const unsigned int BITS = BitMatrix::BITS_PER_WORD;
const unsigned int MASK = nonopt_set.Mask();
assert(infeas_set.Mask() == MASK);
unsigned int* buf_r = nonopt_set.Buffer();
const unsigned int ldim_r = nonopt_set.LDim();
unsigned int* buf_i = infeas_set.Buffer();
const unsigned int ldim_i = infeas_set.LDim();
const unsigned int* buf_m = not_opt_mask.LockedBuffer();
const unsigned int ldim_m = not_opt_mask.LDim();
const T* buf_x = X.LockedBuffer();
const unsigned int ldim_x = X.LDim();
const T* buf_y = Y.LockedBuffer();
const unsigned int ldim_y = Y.LDim();
const unsigned int* buf_p = passive_set.LockedBuffer();
const unsigned int ldim_p = passive_set.LDim();
const unsigned int full_wds = height / BITS;
const unsigned int extra = height - BITS*full_wds;
assert(ldim_r >= ldim_m);
assert(ldim_r >= ldim_p);
OPENMP_PRAGMA(omp parallel for)
for (unsigned int c=0; c<width; ++c)
{
unsigned int offset_r = c*ldim_r;
unsigned int offset_i = c*ldim_i;
unsigned int offset_m = c*ldim_m;
unsigned int offset_x = c*ldim_x;
unsigned int offset_y = c*ldim_y;
unsigned int offset_p = c*ldim_p;
unsigned int r_wd = 0, r=0;
for (; r_wd<full_wds; ++r_wd)
{
unsigned int x_wd = 0, y_wd = 0;
for (unsigned int q=0; q<BITS; ++q, ++r)
{
if (buf_x[offset_x + r] < T(0))
x_wd |= (1 << q);
if (buf_y[offset_y + r] < T(0))
y_wd |= (1 << q);
}
buf_r[offset_r + r_wd] = buf_m[offset_m + r_wd] & y_wd & ~buf_p[offset_p + r_wd];
buf_i[offset_i + r_wd] = buf_m[offset_m + r_wd] & x_wd & buf_p[offset_p + r_wd];
}
if (extra > 0)
{
unsigned int x_wd = 0, y_wd = 0;
for (unsigned int q=0; q<extra; ++q, ++r)
{
if (buf_x[offset_x + r] < T(0))
x_wd |= (1 << q);
if (buf_y[offset_y + r] < T(0))
y_wd |= (1 << q);
}
buf_r[offset_r + r_wd] = MASK & buf_m[offset_m + r_wd] & y_wd & ~buf_p[offset_p + r_wd];
buf_i[offset_i + r_wd] = MASK & buf_m[offset_m + r_wd] & x_wd & buf_p[offset_p + r_wd];
}
}
}