float support for smat
This commit is contained in:
jiri committed
1 parent
ee8c6279e1
commit
5266767a4c
2 files changed
+657
-25
No files matched your search
@@ -387,6 +387,22 @@ inline NRSMat<double> & NRSMat<double>::operator*=(const double &a) {
|
||||
return *this;
|
||||
}
|
||||
|
||||
template<>
|
||||
inline NRSMat<float> & NRSMat<float>::operator*=(const float &a) {
|
||||
copyonwrite();
|
||||
#ifdef CUDALA
|
||||
if(location == cpu){
|
||||
#endif
|
||||
cblas_sscal(NN2, a, v, 1);
|
||||
#ifdef CUDALA
|
||||
}else{
|
||||
cublasSscal(NN2, a, v, 1);
|
||||
TEST_CUBLAS("cublasSscal");//"NRSMat<float>& NRSMat<float>::operator*=(const float &)"
|
||||
}
|
||||
#endif
|
||||
return *this;
|
||||
}
|
||||
|
||||
/***************************************************************************//**
|
||||
* multiply this complex symmetric matrix with complex scalar value
|
||||
* @param[in] a complex multiplicative factor
|
||||
@@ -410,6 +426,24 @@ NRSMat<std::complex<double> >::operator*=(const std::complex<double> &a) {
|
||||
return *this;
|
||||
}
|
||||
|
||||
template<>
|
||||
inline NRSMat<std::complex<float> > &
|
||||
NRSMat<std::complex<float> >::operator*=(const std::complex<float> &a) {
|
||||
copyonwrite();
|
||||
#ifdef CUDALA
|
||||
if(location == cpu){
|
||||
#endif
|
||||
cblas_cscal(NN2, &a, v, 1);
|
||||
#ifdef CUDALA
|
||||
}else{
|
||||
const cuComplex _a = make_cuComplex(a.real(), a.imag());
|
||||
cublasCscal(NN2, _a, (cuComplex*)v, 1);
|
||||
TEST_CUBLAS("cublasCscal");//"NRSMat<std::complex<float> >& NRSMat<std::complex<float> >::operator*=(const std::complex<float> &)"
|
||||
}
|
||||
#endif
|
||||
return *this;
|
||||
}
|
||||
|
||||
|
||||
/***************************************************************************//**
|
||||
* multiply this symmetric matrix of general type <code>T</code> stored in packed form
|
||||
@@ -508,6 +542,27 @@ inline NRSMat<double>& NRSMat<double>::operator+=(const NRSMat<double> & rhs) {
|
||||
return *this;
|
||||
}
|
||||
|
||||
template<>
|
||||
inline NRSMat<float>& NRSMat<float>::operator+=(const NRSMat<float> & rhs) {
|
||||
#ifdef DEBUG
|
||||
if(nn != rhs.nn) laerror("incompatible dimensions in NRSMat<float>& NRSMat<float>::operator+=(const NRSMat<float> &)");
|
||||
#endif
|
||||
SAME_LOC(*this, rhs);
|
||||
copyonwrite();
|
||||
|
||||
#ifdef CUDALA
|
||||
if(location == cpu){
|
||||
#endif
|
||||
cblas_saxpy(NN2, 1.0, rhs.v, 1, v, 1);
|
||||
#ifdef CUDALA
|
||||
}else{
|
||||
cublasSaxpy(NN2, 1.0, rhs.v, 1, v, 1);
|
||||
TEST_CUBLAS("cublasSaxpy");//" NRSMat<float>& NRSMat<float>::operator+=(const NRSMat<float> &)"
|
||||
}
|
||||
#endif
|
||||
return *this;
|
||||
}
|
||||
|
||||
/***************************************************************************//**
|
||||
* add up this complex symmetric matrix with given symmetric matrix
|
||||
* @param[in] rhs complex symmetric matrix to be added
|
||||
@@ -534,6 +589,27 @@ inline NRSMat<std::complex<double> >& NRSMat<std::complex<double> >::operator+=(
|
||||
return *this;
|
||||
}
|
||||
|
||||
template<>
|
||||
inline NRSMat<std::complex<float> >& NRSMat<std::complex<float> >::operator+=(const NRSMat<std::complex<float> > & rhs) {
|
||||
#ifdef DEBUG
|
||||
if(nn != rhs.nn) laerror("incompatible dimensions in NRSMat<std::complex<float> >& NRSMat<std::complex<float> >::operator+=(const NRSMat<std::complex<float> > &)");
|
||||
#endif
|
||||
SAME_LOC(*this, rhs);
|
||||
copyonwrite();
|
||||
|
||||
#ifdef CUDALA
|
||||
if(location == cpu){
|
||||
#endif
|
||||
cblas_caxpy(NN2, &CONEF, rhs.v, 1, v, 1);
|
||||
#ifdef CUDALA
|
||||
}else{
|
||||
cublasCaxpy(NN2, CUONE, (cuComplex*)(rhs.v), 1, (cuComplex*)v, 1);
|
||||
TEST_CUBLAS("cublasCaxpy");//"NRSMat<std::complex<float> >& NRSMat<std::complex<float> >::operator+=(const NRSMat<std::complex<float> > &)"
|
||||
}
|
||||
#endif
|
||||
return *this;
|
||||
}
|
||||
|
||||
/***************************************************************************//**
|
||||
* add up this symmetric matrix of general type <code>T</code> with given symmetric matrix
|
||||
* @param[in] rhs complex matrix of general type <code>T</code> to be added
|
||||
@@ -578,6 +654,27 @@ inline NRSMat<double>& NRSMat<double>::operator-=(const NRSMat<double>& rhs) {
|
||||
return *this;
|
||||
}
|
||||
|
||||
template<>
|
||||
inline NRSMat<float>& NRSMat<float>::operator-=(const NRSMat<float>& rhs) {
|
||||
#ifdef DEBUG
|
||||
if(nn != rhs.nn) laerror("incompatible dimensions in NRSMat<float>& NRSMat<float>::operator-=(const NRSMat<float> &)");
|
||||
#endif
|
||||
SAME_LOC(*this, rhs);
|
||||
copyonwrite();
|
||||
|
||||
#ifdef CUDALA
|
||||
if(location == cpu){
|
||||
#endif
|
||||
cblas_saxpy(NN2, -1.0, rhs.v, 1, v, 1);
|
||||
#ifdef CUDALA
|
||||
}else{
|
||||
cublasSaxpy(NN2, -1.0, rhs.v, 1, v, 1);
|
||||
TEST_CUBLAS("cublasSaxpy");//" NRSMat<float>& NRSMat<float>::operator-=(const NRSMat<float> &)"
|
||||
}
|
||||
#endif
|
||||
return *this;
|
||||
}
|
||||
|
||||
/***************************************************************************//**
|
||||
* subtracts given complex symmetric matrix from this complex symmetric matrix
|
||||
* @param[in] rhs complex symmetric matrix to be subtracted
|
||||
@@ -604,6 +701,27 @@ inline NRSMat<std::complex<double> >& NRSMat<std::complex<double> >::operator-=(
|
||||
return *this;
|
||||
}
|
||||
|
||||
template<>
|
||||
inline NRSMat<std::complex<float> >& NRSMat<std::complex<float> >::operator-=(const NRSMat<std::complex<float> >& rhs) {
|
||||
#ifdef DEBUG
|
||||
if(nn != rhs.nn) laerror("incompatible dimensions in NRSMat<std::complex<float> >& NRSMat<std::complex<float> >::operator-=(const NRSMat<std::complex<float> > &)");
|
||||
#endif
|
||||
SAME_LOC(*this, rhs);
|
||||
copyonwrite();
|
||||
|
||||
#ifdef CUDALA
|
||||
if(location == cpu){
|
||||
#endif
|
||||
cblas_caxpy(NN2, &CMONEF, rhs.v, 1, v, 1);
|
||||
#ifdef CUDALA
|
||||
}else{
|
||||
cublasCaxpy(NN2, CUMONE, (cuComplex*)(rhs.v), 1, (cuComplex*)v, 1);
|
||||
TEST_CUBLAS("cublasCaxpy");//"NRSMat<std::complex<float> >& NRSMat<std::complex<float> >::operator-=(const NRSMat<std::complex<float> > &)"
|
||||
}
|
||||
#endif
|
||||
return *this;
|
||||
}
|
||||
|
||||
/***************************************************************************//**
|
||||
* subtracts given symmetric matrix of general type <code>T</code> from this symmetric matrix of type <code>T</code>
|
||||
* @param[in] rhs symmetric matrix of general type <code>T</code> to be subtracted
|
||||
@@ -871,6 +989,24 @@ inline const double NRSMat<double>::amax() const {
|
||||
return ret;
|
||||
}
|
||||
|
||||
template<>
|
||||
inline const float NRSMat<float>::amax() const {
|
||||
float ret(0.0);
|
||||
#ifdef CUDALA
|
||||
if(location == cpu){
|
||||
#endif
|
||||
ret = v[cblas_isamax(NN2, v, 1)];
|
||||
#ifdef CUDALA
|
||||
}else{
|
||||
const int pozice = cublasIsamax(NN2, v, 1) ;
|
||||
TEST_CUBLAS("cublasIsamax");//"float NRSMat<float>::amax()"
|
||||
|
||||
gpuget(1, sizeof(float), v + pozice, &ret);
|
||||
}
|
||||
#endif
|
||||
return ret;
|
||||
}
|
||||
|
||||
/***************************************************************************//**
|
||||
* for this real symmetric matrix \f$A\f$, determine the
|
||||
* first element with smallest absolute value
|
||||
@@ -901,6 +1037,31 @@ inline const double NRSMat<double>::amin() const {
|
||||
return ret;
|
||||
}
|
||||
|
||||
template<>
|
||||
inline const float NRSMat<float>::amin() const {
|
||||
float ret(0.0);
|
||||
#ifdef CUDALA
|
||||
if(location == cpu){
|
||||
#endif
|
||||
// idamin seems not to be supported
|
||||
float val(0.0);
|
||||
int index(-1);
|
||||
ret = std::numeric_limits<float>::max();
|
||||
for(register size_t i = 0; i < NN2; i++){
|
||||
val = std::abs(v[i]);
|
||||
if(val < ret){ index = i; ret = val; }
|
||||
}
|
||||
ret = v[index];
|
||||
#ifdef CUDALA
|
||||
}else{
|
||||
const int pozice = cublasIsamin(nn, v, 1);
|
||||
TEST_CUBLAS("cublasIsamin");//"float NRSMat<float>::amin()"
|
||||
gpuget(1, sizeof(float), v + pozice, &ret);
|
||||
}
|
||||
#endif
|
||||
return ret;
|
||||
}
|
||||
|
||||
/***************************************************************************//**
|
||||
* for this complex symmetric matrix \f$A\f$, determine the
|
||||
* first element with largest "absolute value"
|
||||
@@ -923,6 +1084,23 @@ inline const std::complex<double> NRSMat< std::complex<double> >::amax() const{
|
||||
return ret;
|
||||
}
|
||||
|
||||
template<>
|
||||
inline const std::complex<float> NRSMat< std::complex<float> >::amax() const{
|
||||
std::complex<float> ret(0., 0.);
|
||||
#ifdef CUDALA
|
||||
if(location == cpu){
|
||||
#endif
|
||||
ret = v[cblas_icamax(NN2, v, 1)];
|
||||
#ifdef CUDALA
|
||||
}else{
|
||||
const int pozice = cublasIcamax(NN2, (cuComplex*)v, 1);
|
||||
TEST_CUBLAS("cublasIcamax");//"std::complex<float> NRSMat<std::complex<float> >::amax()"
|
||||
gpuget(1, sizeof(std::complex<float>), v + pozice, &ret);
|
||||
}
|
||||
#endif
|
||||
return ret;
|
||||
}
|
||||
|
||||
/***************************************************************************//**
|
||||
* for this complex symmetric matrix \f$A\f$, determine the
|
||||
* first element with smallest "absolute value"
|
||||
@@ -956,6 +1134,34 @@ inline const std::complex<double> NRSMat<std::complex<double> >::amin() const{
|
||||
return ret;
|
||||
}
|
||||
|
||||
template<>
|
||||
inline const std::complex<float> NRSMat<std::complex<float> >::amin() const{
|
||||
std::complex<float> ret(0., 0.);
|
||||
#ifdef CUDALA
|
||||
if(location == cpu){
|
||||
#endif
|
||||
// izamin seems not to be supported
|
||||
int index(0);
|
||||
float val(0.0), min_val(0.0);
|
||||
std::complex<float> z_val(0.0, 0.0);
|
||||
|
||||
min_val = std::numeric_limits<float>::max();
|
||||
for(register size_t i = 0; i < NN2; i++){
|
||||
z_val = v[i];
|
||||
val = std::abs(z_val.real()) + std::abs(z_val.imag());
|
||||
if(val < min_val){ index = i; min_val = val; }
|
||||
}
|
||||
ret = v[index];
|
||||
#ifdef CUDALA
|
||||
}else{
|
||||
const int pozice = cublasIcamin(nn, (cuComplex*)v, 1);
|
||||
TEST_CUBLAS("cublasIcamin");//"std::complex<float> NRSMat<std::complex<float> >::amin()"
|
||||
gpuget(1, sizeof(std::complex<float>), v + pozice, &ret);
|
||||
}
|
||||
#endif
|
||||
return ret;
|
||||
}
|
||||
|
||||
/***************************************************************************//**
|
||||
* @return pointer of general type T to the underlying data structure
|
||||
******************************************************************************/
|
||||
@@ -1215,28 +1421,9 @@ NRSMat<std::complex<T> > complexify(const NRSMat<T> &rhs) {
|
||||
}
|
||||
|
||||
|
||||
/***************************************************************************//**
|
||||
* complexify a given double-precision real matrix \f$A\f$
|
||||
* @param[in] rhs matrix \f$A\f$ intended for this operation
|
||||
* @return matrix \f$B\f$ where \f$\Re B=A\f$ and \f$\Im B = 0\f$
|
||||
******************************************************************************/
|
||||
/*
|
||||
template<>
|
||||
NRSMat<std::complex<double> > complexify(const NRSMat<double> &rhs) {
|
||||
NRSMat<std::complex<double> > r(rhs.nrows(), rhs.getlocation());
|
||||
#ifdef CUDALA
|
||||
if(rhs.getlocation() == cpu){
|
||||
#endif
|
||||
cblas_dcopy(rhs.size(), &(rhs[0]), 1, (double*)(&(r[0])), 2);
|
||||
#ifdef CUDALA
|
||||
}else{
|
||||
cublasDcopy(rhs.size(), &(rhs[0]), 1, (double*)(&(r[0])), 2);
|
||||
TEST_CUBLAS("cublasDcopy");//"NRSMat<std::complex<double> > complexify(const NRSMat<double> &)"
|
||||
}
|
||||
#endif
|
||||
return r;
|
||||
}
|
||||
*/
|
||||
//BLAS versions for double and float are in smat.cc (a full specialization defined in the header would be multiply defined)
|
||||
template<> NRSMat<std::complex<double> > complexify<double>(const NRSMat<double> &rhs);
|
||||
template<> NRSMat<std::complex<float> > complexify<float>(const NRSMat<float> &rhs);
|
||||
/***************************************************************************//**
|
||||
* output operator
|
||||
* @param[in,out] s output stream
|
||||
|
||||
Reference in new issue
Block a user