void checkDenseMatrixEqual(M1 const& m1, M2 const& m2){
BOOST_REQUIRE_EQUAL(m1.size1(),m2.size1());
BOOST_REQUIRE_EQUAL(m1.size2(),m2.size2());
//indexed access
for(std::size_t i = 0; i != m2.size1(); ++i){
for(std::size_t j = 0; j != m2.size2(); ++j){
BOOST_CHECK_EQUAL(m1(i,j),m2(i,j));
}
}
//iterator access rows
for(std::size_t i = 0; i != m2.size1(); ++i){
typedef typename M1::const_row_iterator Iter;
BOOST_REQUIRE_EQUAL(m1.row_end(i)-m1.row_begin(i), m1.size2());
std::size_t k = 0;
for(Iter it = m1.row_begin(i); it != m1.row_end(i); ++it,++k){
BOOST_CHECK_EQUAL(k,it.index());
BOOST_CHECK_EQUAL(*it,m2(i,k));
}
//test that the actual iterated length equals the number of elements
BOOST_CHECK_EQUAL(k, m1.size2());
}
//iterator access columns
for(std::size_t i = 0; i != m2.size2(); ++i){
typedef typename M1::const_column_iterator Iter;
BOOST_REQUIRE_EQUAL(m1.column_end(i)-m1.column_begin(i), m1.size1());
std::size_t k = 0;
for(Iter it = m1.column_begin(i); it != m1.column_end(i); ++it,++k){
BOOST_CHECK_EQUAL(k,it.index());
BOOST_CHECK_EQUAL(*it,m2(k,i));
}
//test that the actual iterated length equals the number of elements
BOOST_CHECK_EQUAL(k, m1.size1());
}
}
void bi::cov(const M1 X, const V1 mu, M2 Sigma) {
/* pre-conditions */
BI_ASSERT(X.size2() == mu.size());
BI_ASSERT(Sigma.size1() == mu.size() && Sigma.size2() == mu.size());
const int N = X.size1();
typename sim_temp_matrix<M2>::type Y(X.size1(), X.size2());
Y = X;
sub_rows(Y, mu);
syrk(1.0/(N - 1.0), Y, 0.0, Sigma, 'U', 'T');
}
void bi::var(const M1 X, const V1 mu, V2 sigma) {
/* pre-conditions */
BI_ASSERT(X.size2() == mu.size());
BI_ASSERT(sigma.size() == mu.size());
const int N = X.size1();
typename sim_temp_matrix<M1>::type Z(X.size2(), X.size1());
Z = X;
sub_rows(Z, mu);
dot_columns(Z, sigma);
scal(1.0/(N - 1.0), sigma);
}
void bi::cross(const M1 X, const M2 Y, const V1 muX, const V2 muY,
M3 SigmaXY) {
/* pre-conditions */
BI_ASSERT(X.size2() == muX.size());
BI_ASSERT(Y.size2() == muY.size());
BI_ASSERT(X.size1() == Y.size1());
BI_ASSERT(SigmaXY.size1() == muX.size() && SigmaXY.size2() == muY.size());
const int N = X.size1();
gemm(1.0/(N - 1.0), X, Y, 0.0, SigmaXY, 'T', 'N');
ger(-N/(N - 1.0), muX, muY, SigmaXY);
}
typename viennacl::enable_if< viennacl::is_any_dense_nonstructured_matrix<M1>::value
&& viennacl::is_any_dense_nonstructured_vector<V1>::value
>::type
inplace_solve(const M1 & mat,
V1 & vec,
SOLVERTAG)
{
assert( (mat.size1() == vec.size()) && bool("Size check failed in inplace_solve(): size1(A) != size(b)"));
assert( (mat.size2() == vec.size()) && bool("Size check failed in inplace_solve(): size2(A) != size(b)"));
switch (viennacl::traits::handle(mat).get_active_handle_id())
{
case viennacl::MAIN_MEMORY:
viennacl::linalg::host_based::inplace_solve(mat, vec, SOLVERTAG());
break;
#ifdef VIENNACL_WITH_OPENCL
case viennacl::OPENCL_MEMORY:
viennacl::linalg::opencl::inplace_solve(mat, vec, SOLVERTAG());
break;
#endif
#ifdef VIENNACL_WITH_CUDA
case viennacl::CUDA_MEMORY:
viennacl::linalg::cuda::inplace_solve(mat, vec, SOLVERTAG());
break;
#endif
default:
throw "not implemented";
}
}
void checkMatrixEqual(M1 const& m1, M2 const& m2){
BOOST_REQUIRE_EQUAL(m1.size1(),m2.size1());
BOOST_REQUIRE_EQUAL(m1.size2(),m2.size2());
for(std::size_t i = 0; i != m2.size1(); ++i){
for(std::size_t j = 0; j != m2.size2(); ++j){
BOOST_CHECK_EQUAL(m1(i,j),m2(i,j));
}
}
}
void bi::mean(const M1 X, V1 mu) {
/* pre-condition */
BI_ASSERT(X.size2() == mu.size());
const int N = X.size1();
typename sim_temp_vector<V1>::type w(N);
set_elements(w, 1.0);
gemv(1.0/N, X, w, 0.0, mu, 'T');
}
void bi::cov(const M1 X, const V1 w, const V2 mu, M2 Sigma) {
/* pre-conditions */
BI_ASSERT(X.size2() == mu.size());
BI_ASSERT(X.size1() == w.size());
BI_ASSERT(Sigma.size1() == mu.size() && Sigma.size2() == mu.size());
typedef typename V1::value_type T;
typename sim_temp_matrix<M2>::type Y(X.size1(), X.size2());
typename sim_temp_matrix<M2>::type Z(X.size1(), X.size2());
typename sim_temp_vector<V2>::type v(w.size());
T Wt = sum_reduce(w);
Y = X;
sub_rows(Y, mu);
sqrt_elements(w, v);
gdmm(1.0, v, Y, 0.0, Z);
syrk(1.0/Wt, Z, 0.0, Sigma, 'U', 'T');
// alternative weight: 1.0/(Wt - W2t/Wt)
}
void bi::mean(const M1 X, const V1 w, V2 mu) {
/* pre-conditions */
BI_ASSERT(X.size2() == mu.size());
BI_ASSERT(X.size1() == w.size());
typedef typename V1::value_type T;
T Wt = sum_reduce(w);
gemv(1.0/Wt, X, w, 0.0, mu, 'T');
}
void bi::var(const M1 X, const V1 w, const V2 mu, V3 sigma) {
/* pre-conditions */
BI_ASSERT(X.size2() == mu.size());
BI_ASSERT(X.size1() == w.size());
BI_ASSERT(sigma.size() == mu.size());
typedef typename V1::value_type T1;
typename sim_temp_matrix<M1>::type Z(X.size1(), X.size2());
typename sim_temp_matrix<M1>::type Y(X.size1(), X.size2());
typename sim_temp_vector<V2>::type v(w.size());
T1 Wt = sum_reduce(w);
Z = X;
sub_rows(Z, mu);
sqrt_elements(w, v);
gdmm(1.0, v, Z, 0.0, Y);
dot_columns(Y, sigma);
divscal_elements(sigma, Wt, sigma);
// alternative weight: 1.0/(Wt - W2t/Wt)
}
void bi::cov(const GammaPdf& q, M1 Sigma) {
/* pre-condition */
BI_ASSERT(Sigma.size1() == q.size());
BI_ASSERT(Sigma.size2() == q.size());
real alpha = q.shape();
real beta = q.scale();
real sigma = alpha*std::pow(beta, 2);
Sigma.clear();
set_elements(diagonal(Sigma), sigma);
}
void bi::cross(const M1 X, const M2 Y, const V1 w, const V2 muX,
const V3 muY, M3 SigmaXY) {
/* pre-conditions */
BI_ASSERT(X.size2() == muX.size());
BI_ASSERT(Y.size2() == muY.size());
BI_ASSERT(X.size1() == Y.size1());
BI_ASSERT(X.size1() == w.size());
BI_ASSERT(Y.size1() == w.size());
BI_ASSERT(SigmaXY.size1() == muX.size() && SigmaXY.size2() == muY.size());
typedef typename V1::value_type T;
typename sim_temp_matrix<M3>::type Z(X.size1(), X.size2());
T Wt = sum_reduce(w);
T Wt2 = std::pow(Wt, 2);
T W2t = sumsq_reduce(w);
gdmm(1.0, w, X, 0.0, Z);
gemm(1.0/Wt, Z, Y, 0.0, SigmaXY, 'T', 'N');
ger(-1.0, muX, muY, SigmaXY);
matrix_scal(1.0/(1.0 - W2t/Wt2), SigmaXY);
}
void bi::cov(const InverseGammaPdf& q, M1 Sigma) {
/* pre-condition */
BI_ASSERT(Sigma.size1() == q.size());
BI_ASSERT(Sigma.size2() == q.size());
BI_ASSERT(q.shape() > 2.0);
real alpha = q.shape();
real beta = q.scale();
real sigma = std::pow(beta, 2)/(std::pow(alpha - 1.0, 2)*(alpha - 2.0));
Sigma.clear();
set_elements(diagonal(Sigma), sigma);
}
void bi::cov(const UniformPdf<V1>& q, M1 Sigma) {
/* pre-condition */
BI_ASSERT(Sigma.size1() == q.size());
BI_ASSERT(Sigma.size2() == q.size());
temp_host_vector<real>::type diff(q.size());
diff = q.upper();
sub_elements(diff, q.lower(), diff);
sq_elements(diff, diff);
Sigma.clear();
axpy(1.0/12.0, diff, diagonal(Sigma));
}
void bi::inverse_gamma_log_densities(const M1 Z, const T1 alpha, const T1 beta,
V1 p, const bool clear) {
/* pre-condition */
BI_ASSERT(Z.size1() == p.size());
op_elements(vec(Z), vec(Z), inverse_gamma_log_density_functor<T1>(alpha, beta));
if (clear) {
sum_columns(Z, p);
} else {
typename sim_temp_vector<V1>::type p1(p.size());
sum_columns(Z, p1);
add_elements(p, p1, p);
}
}
void bi::gaussian_log_densities(const M1 Z, const T1 logZ, V1 p,
const bool clear) {
/* pre-condition */
BI_ASSERT(Z.size1() == p.size());
typedef typename V1::value_type T2;
if (clear) {
dot_rows(Z, p);
op_elements(p, p, gaussian_log_density_functor<T2>(logZ));
} else {
typename sim_temp_vector<V1>::type p1(p.size());
dot_rows(Z, p1);
op_elements(p1, p, p, gaussian_log_density_update_functor<T2>(logZ));
}
}
void bi::distance(const M1 X, const real h, M2 D) {
/* pre-conditions */
BI_ASSERT(D.size1() == D.size2());
BI_ASSERT(D.size1() == X.size1());
BI_ASSERT(!M2::on_device);
typedef typename M1::value_type T1;
FastGaussianKernel K(X.size2(), h);
typename temp_host_vector<T1>::type d(X.size2());
int i, j;
for (j = 0; j < D.size2(); ++j) {
for (i = 0; i <= j; ++i) {
d = row(X, i);
axpy(-1.0, row(X, j), d);
D(i, j) = K(dot(d));
}
}
}
