float support for vec
This commit is contained in:
jiri committed
1 parent
f6da197192
commit
9ada78c9bb
4 files changed
+992
-2
No files matched your search
@@ -106,6 +106,23 @@ const NRVec<double> NRVec<double>::operator-() const {
|
||||
return result;
|
||||
}
|
||||
|
||||
template<>
|
||||
const NRVec<float> NRVec<float>::operator-() const {
|
||||
NRVec<float> result(*this);
|
||||
result.copyonwrite();
|
||||
#ifdef CUDALA
|
||||
if(location == cpu){
|
||||
#endif
|
||||
cblas_sscal(nn, -1.0, result.v, 1);
|
||||
#ifdef CUDALA
|
||||
}else{
|
||||
cublasSscal(nn, -1.0, result.v, 1);
|
||||
TEST_CUBLAS("cublasSscal");
|
||||
}
|
||||
#endif
|
||||
return result;
|
||||
}
|
||||
|
||||
|
||||
|
||||
/***************************************************************************//**
|
||||
@@ -129,6 +146,23 @@ const NRVec<std::complex<double> > NRVec<std::complex<double> >::operator-() con
|
||||
return result;
|
||||
}
|
||||
|
||||
template<>
|
||||
const NRVec<std::complex<float> > NRVec<std::complex<float> >::operator-() const {
|
||||
NRVec<std::complex<float> > result(*this);
|
||||
result.copyonwrite();
|
||||
#ifdef CUDALA
|
||||
if(location == cpu){
|
||||
#endif
|
||||
cblas_csscal(nn, -1.0, result.v, 1);
|
||||
#ifdef CUDALA
|
||||
}else{
|
||||
cublasCsscal(nn, -1.0, (cuComplex*)result.v, 1);
|
||||
TEST_CUBLAS("cublasCsscal");
|
||||
}
|
||||
#endif
|
||||
return result;
|
||||
}
|
||||
|
||||
/***************************************************************************//**
|
||||
* unary minus operator for vector of general type
|
||||
* @return the modified vector
|
||||
@@ -199,6 +233,16 @@ void NRVec<double>::randomize(const double &x){
|
||||
}
|
||||
}
|
||||
|
||||
template<>
|
||||
void NRVec<float>::randomize(const float &x){
|
||||
NOT_GPU(*this);
|
||||
copyonwrite();
|
||||
|
||||
for(register int i=0; i<nn; ++i){
|
||||
v[i] = x*RANDDOUBLESIGNED();
|
||||
}
|
||||
}
|
||||
|
||||
/***************************************************************************//**
|
||||
* fill the complex vector with pseudorandom numbers generated using uniform distribution
|
||||
* the real and imaginary parts are generated independently
|
||||
@@ -217,6 +261,16 @@ void NRVec<std::complex<double> >::randomize(const double &x) {
|
||||
}
|
||||
}
|
||||
|
||||
template<>
|
||||
void NRVec<std::complex<float> >::randomize(const float &x) {
|
||||
NOT_GPU(*this);
|
||||
copyonwrite();
|
||||
|
||||
for(register int i=0; i<nn; ++i){
|
||||
v[i] = std::complex<float>(x*RANDDOUBLESIGNED(), x*RANDDOUBLESIGNED());
|
||||
}
|
||||
}
|
||||
|
||||
/***************************************************************************//**
|
||||
* constructor creating complex vector from a real one
|
||||
* @param[in] rhs the real vector being converted into the complex one
|
||||
@@ -252,6 +306,31 @@ NRVec<std::complex<double> >::NRVec(const NRVec<double> &rhs, bool imagpart): nn
|
||||
#endif
|
||||
}
|
||||
|
||||
template<>
|
||||
NRVec<std::complex<float> >::NRVec(const NRVec<float> &rhs, bool imagpart): nn(rhs.size()){
|
||||
|
||||
count = new int;
|
||||
*count = 1;
|
||||
#ifdef CUDALA
|
||||
location = rhs.getlocation();
|
||||
if(location == cpu){
|
||||
#endif
|
||||
v = (std::complex<float>*)new std::complex<float>[nn];
|
||||
memset(v, 0, nn*sizeof(std::complex<float>));
|
||||
cblas_scopy(nn, &rhs[0], 1, ((float *)v) + (imagpart?1:0), 2);
|
||||
#ifdef CUDALA
|
||||
}else{
|
||||
v = (std::complex<float>*) gpualloc(nn*sizeof(std::complex<float>));
|
||||
|
||||
cublasCscal(nn, CUZERO, (cuComplex*)v, 1);
|
||||
TEST_CUBLAS("cublasCscal");
|
||||
|
||||
cublasScopy(nn, &rhs[0], 1, ((float *)v) + (imagpart?1:0), 2);
|
||||
TEST_CUBLAS("cublasScopy");
|
||||
}
|
||||
#endif
|
||||
}
|
||||
|
||||
/***************************************************************************//**
|
||||
* perform the <b>axpy</b> operation on the current real vector \f$\vec{v}\f$, i.e.
|
||||
* \f[ \vec{v} \leftarrow \vec{v} + \alpha\vec{x} \f]
|
||||
@@ -278,6 +357,26 @@ void NRVec<double>::axpy(const double alpha, const NRVec<double> &x) {
|
||||
#endif
|
||||
}
|
||||
|
||||
template<>
|
||||
void NRVec<float>::axpy(const float alpha, const NRVec<float> &x) {
|
||||
#ifdef DEBUG
|
||||
if (nn != x.nn) laerror("incompatible vectors");
|
||||
#endif
|
||||
SAME_LOC(*this, x);
|
||||
copyonwrite();
|
||||
|
||||
#ifdef CUDALA
|
||||
if(location == cpu){
|
||||
#endif
|
||||
cblas_saxpy(nn, alpha, x.v, 1, v, 1);
|
||||
#ifdef CUDALA
|
||||
}else{
|
||||
cublasSaxpy(nn, alpha, x.v, 1, v, 1);
|
||||
TEST_CUBLAS("cublasSaxpy");
|
||||
}
|
||||
#endif
|
||||
}
|
||||
|
||||
/***************************************************************************//**
|
||||
* perform the <b>axpy</b> operation on the current complex vector \f$\vec{v}\f$, i.e.
|
||||
* \f[ \vec{v} \leftarrow \vec{v} + \alpha\vec{x} \f]
|
||||
@@ -306,6 +405,28 @@ void NRVec<std::complex<double> >::axpy(const std::complex<double> alpha, const
|
||||
|
||||
}
|
||||
|
||||
template<>
|
||||
void NRVec<std::complex<float> >::axpy(const std::complex<float> alpha, const NRVec<std::complex<float> > &x){
|
||||
#ifdef DEBUG
|
||||
if (nn != x.nn) laerror("incompatible vectors");
|
||||
#endif
|
||||
SAME_LOC(*this, x);
|
||||
copyonwrite();
|
||||
|
||||
#ifdef CUDALA
|
||||
if(location == cpu){
|
||||
#endif
|
||||
cblas_caxpy(nn, &alpha, x.v, 1, v, 1);
|
||||
#ifdef CUDALA
|
||||
}else{
|
||||
const cuComplex _alpha = make_cuComplex(alpha.real(), alpha.imag());
|
||||
cublasCaxpy(nn, _alpha, (cuComplex*)x.v, 1, (cuComplex*)v, 1);
|
||||
TEST_CUBLAS("cublasCaxpy");
|
||||
}
|
||||
#endif
|
||||
|
||||
}
|
||||
|
||||
/***************************************************************************//**
|
||||
* perform the <b>axpy</b> operation on the current real vector \f$\vec{v}\f$, i.e.
|
||||
* \f[ \vec{v} \leftarrow \vec{v} + \alpha\vec{x} \f]
|
||||
@@ -321,6 +442,14 @@ void NRVec<double>::axpy(const double alpha, const double *x, const int stride){
|
||||
cblas_daxpy(nn, alpha, x, stride, v, 1);
|
||||
}
|
||||
|
||||
template<>
|
||||
void NRVec<float>::axpy(const float alpha, const float *x, const int stride){
|
||||
NOT_GPU(*this);
|
||||
|
||||
copyonwrite();
|
||||
cblas_saxpy(nn, alpha, x, stride, v, 1);
|
||||
}
|
||||
|
||||
/***************************************************************************//**
|
||||
* perform the <b>axpy</b> operation on the current complex vector \f$\vec{v}\f$, i.e.
|
||||
* \f[ \vec{v} \leftarrow \vec{v} + \alpha\vec{x} \f]
|
||||
@@ -336,6 +465,14 @@ void NRVec<std::complex<double> >::axpy(const std::complex<double> alpha, const
|
||||
cblas_zaxpy(nn, &alpha, x, stride, v, 1);
|
||||
}
|
||||
|
||||
template<>
|
||||
void NRVec<std::complex<float> >::axpy(const std::complex<float> alpha, const std::complex<float> *x, const int stride){
|
||||
NOT_GPU(*this);
|
||||
|
||||
copyonwrite();
|
||||
cblas_caxpy(nn, &alpha, x, stride, v, 1);
|
||||
}
|
||||
|
||||
/***************************************************************************//**
|
||||
* assign real scalar value to every element of the current vector
|
||||
* @param[in] a scalar value to be assigned
|
||||
@@ -357,6 +494,22 @@ copyonwrite();
|
||||
return *this;
|
||||
}
|
||||
|
||||
template<>
|
||||
NRVec<float>& NRVec<float>::operator=(const float &a){
|
||||
copyonwrite();
|
||||
|
||||
#ifdef CUDALA
|
||||
if(location == cpu){
|
||||
#endif
|
||||
cblas_scopy(nn, &a, 0, v, 1);
|
||||
#ifdef CUDALA
|
||||
}else{
|
||||
smart_gpu_set(nn, (float)0, v);
|
||||
}
|
||||
#endif
|
||||
return *this;
|
||||
}
|
||||
|
||||
/***************************************************************************//**
|
||||
* assign complex scalar value to every element of the current vector
|
||||
* @param[in] a scalar value to be assigned
|
||||
@@ -378,6 +531,22 @@ copyonwrite();
|
||||
return *this;
|
||||
}
|
||||
|
||||
template<>
|
||||
NRVec<std::complex<float> >& NRVec<std::complex<float> >::operator=(const std::complex<float> &a){
|
||||
copyonwrite();
|
||||
|
||||
#ifdef CUDALA
|
||||
if(location == cpu){
|
||||
#endif
|
||||
cblas_ccopy(nn, &a, 0, v, 1);
|
||||
#ifdef CUDALA
|
||||
}else{
|
||||
smart_gpu_set(nn, (std::complex<float>)0, v);
|
||||
}
|
||||
#endif
|
||||
return *this;
|
||||
}
|
||||
|
||||
/***************************************************************************//**
|
||||
* assign scalar value to every element of the current vector of general type <code>T</code>
|
||||
* @param[in] a scalar value to be assigned
|
||||
@@ -433,6 +602,38 @@ NRVec<double>& NRVec<double>::normalize(double *norm){
|
||||
return *this;
|
||||
}
|
||||
|
||||
template<>
|
||||
NRVec<float>& NRVec<float>::normalize(float *norm){
|
||||
float tmp(0.0);
|
||||
#ifdef CUDALA
|
||||
if(location == cpu){
|
||||
#endif
|
||||
tmp = cblas_snrm2(nn, v, 1);
|
||||
if(norm) *norm = tmp;
|
||||
#ifdef DEBUG
|
||||
if(!tmp) laerror("attempt to normalize zero vector");
|
||||
#endif
|
||||
copyonwrite();
|
||||
tmp = 1.0 / tmp;
|
||||
cblas_sscal(nn, tmp, v, 1);
|
||||
#ifdef CUDALA
|
||||
}else{
|
||||
tmp = cublasSnrm2(nn, v, 1);
|
||||
TEST_CUBLAS("cublasSnrm2");
|
||||
|
||||
if(norm) *norm = tmp;
|
||||
#ifdef DEBUG
|
||||
if(!tmp) laerror("attempt to normalize zero vector");
|
||||
#endif
|
||||
copyonwrite();
|
||||
tmp = 1.0 / tmp;
|
||||
cublasSscal(nn, tmp, v, 1);
|
||||
TEST_CUBLAS("cublasSscal");
|
||||
}
|
||||
#endif
|
||||
return *this;
|
||||
}
|
||||
|
||||
/***************************************************************************//**
|
||||
* normalize current complex vector (in the Euclidean norm)
|
||||
* @param[in] norm if not NULL, the norm of this vector is stored into *norm
|
||||
@@ -471,6 +672,39 @@ NRVec<std::complex<double> > & NRVec<std::complex<double> >::normalize(double *n
|
||||
return *this;
|
||||
}
|
||||
|
||||
template<>
|
||||
NRVec<std::complex<float> > & NRVec<std::complex<float> >::normalize(float *norm){
|
||||
float tmp(0.0);
|
||||
#ifdef CUDALA
|
||||
if(location == cpu){
|
||||
#endif
|
||||
tmp = cblas_scnrm2(nn, v, 1);
|
||||
if(norm) *norm = tmp;
|
||||
#ifdef DEBUG
|
||||
if(tmp == 0.0) laerror("attempt to normalize zero vector");
|
||||
#endif
|
||||
copyonwrite();
|
||||
tmp = 1.0 / tmp;
|
||||
cblas_csscal(nn, tmp, v, 1);
|
||||
#ifdef CUDALA
|
||||
}else{
|
||||
tmp = cublasScnrm2(nn, (cuComplex*)v, 1);
|
||||
TEST_CUBLAS("cublasScnrm2");
|
||||
|
||||
if(norm) *norm = tmp;
|
||||
#ifdef DEBUG
|
||||
if(tmp == 0.0) laerror("attempt to normalize zero vector");
|
||||
#endif
|
||||
copyonwrite();
|
||||
|
||||
tmp = 1.0 / tmp;
|
||||
cublasCsscal(nn, tmp, (cuComplex*)v, 1);
|
||||
TEST_CUBLAS("cublasCsscal");
|
||||
}
|
||||
#endif
|
||||
return *this;
|
||||
}
|
||||
|
||||
/***************************************************************************//**
|
||||
* perform the \b gemv operation on this real vector \f$\vec{y}\f$, i.e.
|
||||
* \f[\vec{y}\leftarrow \alpha\operatorname{op}(A)\cdot\vec{x}+\beta\vec{y}\f]
|
||||
@@ -503,6 +737,28 @@ void NRVec<double>::gemv(const double beta, const NRMat<double> &A,
|
||||
#endif
|
||||
}
|
||||
|
||||
template<>
|
||||
void NRVec<float>::gemv(const float beta, const NRMat<float> &A,
|
||||
const char trans, const float alpha, const NRVec &x) {
|
||||
#ifdef DEBUG
|
||||
if((tolower(trans) == 'n'?A.ncols():A.nrows()) != x.size()){ laerror("incompatible vectors"); }
|
||||
if((tolower(trans) == 'n'?A.nrows():A.ncols()) != nn){ laerror("incompatible result vector in gemv"); }
|
||||
#endif
|
||||
SAME_LOC3(*this, x, A);
|
||||
copyonwrite();
|
||||
|
||||
#ifdef CUDALA
|
||||
if(location==cpu){
|
||||
#endif
|
||||
cblas_sgemv(CblasRowMajor, (tolower(trans)=='n' ? CblasNoTrans:CblasTrans), A.nrows(), A.ncols(), alpha, A, A.ncols(), x.v, 1, beta, v, 1);
|
||||
#ifdef CUDALA
|
||||
}else{
|
||||
cublasSgemv((tolower(trans)=='n'?'T':'N'), A.ncols(), A.nrows(), alpha, A, A.ncols(), x.v, 1, beta, v, 1);
|
||||
TEST_CUBLAS("cublasSgemv");
|
||||
}
|
||||
#endif
|
||||
}
|
||||
|
||||
/***************************************************************************//**
|
||||
* perform the \b gemv operation on this complex vector \f$\vec{y}\f$, i.e.
|
||||
* \f[\vec{y}\leftarrow \alpha\operatorname{op}(A)\cdot\vec{x}+\beta\vec{y}\f]
|
||||
@@ -541,6 +797,34 @@ void NRVec<std::complex<double> >::gemv(const double beta, const NRMat<double> &
|
||||
#endif
|
||||
}
|
||||
|
||||
template<>
|
||||
void NRVec<std::complex<float> >::gemv(const float beta, const NRMat<float> &A,
|
||||
const char trans, const float alpha, const NRVec<std::complex<float> > &x) {
|
||||
#ifdef DEBUG
|
||||
if ((tolower(trans) == 'n'?A.ncols():A.nrows()) != x.size()){ laerror("incompatible vectors"); }
|
||||
if((tolower(trans) == 'n'?A.nrows():A.ncols()) != nn){ laerror("incompatible result vector in gemv"); }
|
||||
#endif
|
||||
SAME_LOC3(*this, x, A);
|
||||
copyonwrite();
|
||||
|
||||
#ifdef CUDALA
|
||||
if(location==cpu){
|
||||
#endif
|
||||
cblas_sgemv(CblasRowMajor, (tolower(trans)=='n'?CblasNoTrans:CblasTrans),
|
||||
A.nrows(), A.ncols(), alpha, A, A.ncols(), (float *)x.v, 2, beta, (float *)v, 2);
|
||||
cblas_sgemv(CblasRowMajor, (tolower(trans)=='n'?CblasNoTrans:CblasTrans),
|
||||
A.nrows(), A.ncols(), alpha, A, A.ncols(), ((float *)x.v) + 1, 2, beta, ((float *)v)+1, 2);
|
||||
#ifdef CUDALA
|
||||
}else{
|
||||
cublasSgemv((tolower(trans)=='n'?'T':'N'), A.ncols(), A.nrows(), alpha, A, A.ncols(), (float*)(x.v), 2, beta, (float *)v, 2);
|
||||
TEST_CUBLAS("cublasSgemv");
|
||||
|
||||
cublasSgemv((tolower(trans)=='n'?'T':'N'), A.ncols(), A.nrows(), alpha, A, A.ncols(), ((float *)x.v) + 1, 2, beta, ((float *)v)+1, 2);
|
||||
TEST_CUBLAS("cublasSgemv");
|
||||
}
|
||||
#endif
|
||||
}
|
||||
|
||||
|
||||
/***************************************************************************//**
|
||||
* perform the \b gemv operation on this complex vector \f$\vec{y}\f$, i.e.
|
||||
@@ -581,6 +865,35 @@ void NRVec<std::complex<double> >::gemv(const std::complex<double> beta,
|
||||
#endif
|
||||
}
|
||||
|
||||
template<>
|
||||
void NRVec<std::complex<float> >::gemv(const std::complex<float> beta,
|
||||
const NRMat<std::complex<float> > &A, const char trans,
|
||||
const std::complex<float> alpha, const NRVec<std::complex<float> > &x) {
|
||||
#ifdef DEBUG
|
||||
if ((tolower(trans) == 'n'?A.ncols():A.nrows()) != x.size()){ laerror("incompatible vectors"); }
|
||||
if((tolower(trans) == 'n'?A.nrows():A.ncols()) != nn){ laerror("incompatible result vector in gemv"); }
|
||||
#endif
|
||||
SAME_LOC3(*this, x, A);
|
||||
copyonwrite();
|
||||
#ifdef CUDALA
|
||||
if(location == cpu){
|
||||
#endif
|
||||
cblas_cgemv(CblasRowMajor, (tolower(trans)=='n' ? CblasNoTrans : (tolower(trans)=='c'?CblasConjTrans:CblasTrans)),
|
||||
A.nrows(), A.ncols(), &alpha, A, A.ncols(), x.v, 1, &beta, v, 1);
|
||||
#ifdef CUDALA
|
||||
}else{
|
||||
if(tolower(trans)=='c') laerror("gemv with conjugate transposition not implemented on GPU");
|
||||
|
||||
const cuComplex _alpha = make_cuComplex(alpha.real(), alpha.imag());
|
||||
const cuComplex _beta = make_cuComplex(beta.real(), beta.imag());
|
||||
|
||||
cublasCgemv((tolower(trans)=='n'?'T':'N'), A.ncols(), A.nrows(),
|
||||
_alpha, (cuComplex*)(A[0]), A.ncols(), (cuComplex*)(x.v), 1, _beta, (cuComplex*)v, 1);
|
||||
TEST_CUBLAS("cublasCgemv");
|
||||
}
|
||||
#endif
|
||||
}
|
||||
|
||||
/***************************************************************************//**
|
||||
* perform the \b gemv operation on this real vector \f$\vec{y}\f$, i.e.
|
||||
* \f[\vec{y}\leftarrow \alpha\operatorname{op}(A)\cdot\vec{x}+\beta\vec{y}\f]
|
||||
@@ -613,6 +926,28 @@ void NRVec<double>::gemv(const double beta, const NRSMat<double> &A,
|
||||
#endif
|
||||
}
|
||||
|
||||
template<>
|
||||
void NRVec<float>::gemv(const float beta, const NRSMat<float> &A,
|
||||
const char trans, const float alpha, const NRVec &x) {
|
||||
#ifdef DEBUG
|
||||
if(A.ncols() != x.size()){ laerror("incompatible dimensions"); }
|
||||
if(A.nrows() != nn){ laerror("incompatible result vector in gemv"); }
|
||||
#endif
|
||||
SAME_LOC3(*this, A, x);
|
||||
copyonwrite();
|
||||
|
||||
#ifdef CUDALA
|
||||
if(location==cpu){
|
||||
#endif
|
||||
cblas_sspmv(CblasRowMajor, CblasLower, A.ncols(), alpha, A, x.v, 1, beta, v, 1);
|
||||
#ifdef CUDALA
|
||||
}else{
|
||||
cublasSspmv('U', A.ncols(), alpha, A, x.v, 1, beta, v, 1);
|
||||
TEST_CUBLAS("cublasSspmv");
|
||||
}
|
||||
#endif
|
||||
}
|
||||
|
||||
|
||||
/***************************************************************************//**
|
||||
* perform the \c gemv operation on this complex vector \f$\vec{y}\f$, i.e.
|
||||
@@ -650,6 +985,32 @@ void NRVec<std::complex<double> >::gemv(const double beta, const NRSMat<double>
|
||||
#endif
|
||||
}
|
||||
|
||||
template<>
|
||||
void NRVec<std::complex<float> >::gemv(const float beta, const NRSMat<float> &A,
|
||||
const char trans, const float alpha, const NRVec<std::complex<float> > &x) {
|
||||
#ifdef DEBUG
|
||||
if(A.ncols() != x.size()){ laerror("incompatible dimensions"); }
|
||||
if(A.nrows() != nn){ laerror("incompatible result vector in gemv"); }
|
||||
#endif
|
||||
SAME_LOC3(*this, A, x);
|
||||
copyonwrite();
|
||||
|
||||
#ifdef CUDALA
|
||||
if(location == cpu){
|
||||
#endif
|
||||
cblas_sspmv(CblasRowMajor, CblasLower, A.ncols(), alpha, A, (float *)x.v, 2, beta, (float *)v, 2);
|
||||
cblas_sspmv(CblasRowMajor, CblasLower, A.ncols(), alpha, A, ((float *)x.v) + 1, 2, beta, ((float *)v) + 1, 2);
|
||||
#ifdef CUDALA
|
||||
}else{
|
||||
cublasSspmv('U', A.ncols(), alpha, A, (float*)(x.v), 2, beta, (float*)v, 2);
|
||||
TEST_CUBLAS("cublasSspmv");
|
||||
|
||||
cublasSspmv('U', A.ncols(), alpha, A, ((float*)(x.v)) + 1, 2, beta, ((float*)v) + 1, 2);
|
||||
TEST_CUBLAS("cublasSspmv");
|
||||
}
|
||||
#endif
|
||||
}
|
||||
|
||||
/***************************************************************************//**
|
||||
* perform the \b gemv operation on this complex vector \f$\vec{y}\f$, i.e.
|
||||
* \f[\vec{y}\leftarrow \alpha\operatorname{op}(A)\cdot\vec{x}+\beta\vec{y}\f]
|
||||
@@ -689,6 +1050,35 @@ void NRVec<std::complex<double> >::gemv(const std::complex<double> beta,
|
||||
#endif
|
||||
}
|
||||
|
||||
template<>
|
||||
void NRVec<std::complex<float> >::gemv(const std::complex<float> beta,
|
||||
const NRSMat<std::complex<float> > &A, const char trans,
|
||||
const std::complex<float> alpha, const NRVec<std::complex<float> > &x){
|
||||
#ifdef DEBUG
|
||||
if(A.ncols() != x.size()) laerror("incompatible dimensions");
|
||||
if(A.nrows() != nn){ laerror("incompatible result vector in gemv"); }
|
||||
#endif
|
||||
SAME_LOC3(*this, A, x);
|
||||
copyonwrite();
|
||||
|
||||
#ifdef CUDALA
|
||||
if(location == cpu){
|
||||
#endif
|
||||
if(tolower(trans) == 't') //row-major lower packed H is column-major upper packed H^T
|
||||
cblas_chpmv(CblasColMajor, CblasUpper, A.ncols(), &alpha, A, x.v, 1, &beta, v, 1);
|
||||
else
|
||||
cblas_chpmv(CblasRowMajor, CblasLower, A.ncols(), &alpha, A, x.v, 1, &beta, v, 1);
|
||||
#ifdef CUDALA
|
||||
}else{
|
||||
const cuComplex _alpha = make_cuComplex(alpha.real(), alpha.imag());
|
||||
const cuComplex _beta = make_cuComplex(beta.real(), beta.imag());
|
||||
|
||||
cublasChpmv('U', A.ncols(), _alpha, (cuComplex*)((const std::complex<float>*)A), (cuComplex*)(x.v), 1, _beta, (cuComplex*)(this->v), 1);
|
||||
TEST_CUBLAS("cublasChpmv");
|
||||
}
|
||||
#endif
|
||||
}
|
||||
|
||||
/***************************************************************************//**
|
||||
* computes the outer product of this real vector \f$\vec{a}\f$ with given
|
||||
* real vector \f$\vec{b}\f$ and scales the resulting matrix with factor \f$\alpha\f$, i.e.
|
||||
@@ -716,6 +1106,24 @@ const NRMat<double> NRVec<double>::otimes(const NRVec<double> &b,const bool conj
|
||||
return result;
|
||||
}
|
||||
|
||||
template<>
|
||||
const NRMat<float> NRVec<float>::otimes(const NRVec<float> &b,const bool conj, const float &scale) const {
|
||||
|
||||
SAME_LOC(*this, b);
|
||||
NRMat<float> result(0.0, nn, b.nn, this->getlocation());
|
||||
#ifdef CUDALA
|
||||
if(location == cpu){
|
||||
#endif
|
||||
cblas_sger(CblasRowMajor, nn, b.nn, scale, v, 1, b.v, 1, result, b.nn);
|
||||
#ifdef CUDALA
|
||||
}else{
|
||||
cublasSger(b.nn, nn, scale, b.v, 1, v, 1, result[0], b.nn);
|
||||
TEST_CUBLAS("cublasSger");
|
||||
}
|
||||
#endif
|
||||
return result;
|
||||
}
|
||||
|
||||
template<>
|
||||
const NRVec<double> NRVec<double>::otimes2vec(const NRVec<double> &b,const bool conj, const double &scale) const {
|
||||
|
||||
@@ -734,6 +1142,24 @@ const NRVec<double> NRVec<double>::otimes2vec(const NRVec<double> &b,const bool
|
||||
return result;
|
||||
}
|
||||
|
||||
template<>
|
||||
const NRVec<float> NRVec<float>::otimes2vec(const NRVec<float> &b,const bool conj, const float &scale) const {
|
||||
|
||||
SAME_LOC(*this, b);
|
||||
NRVec<float> result(0.0, nn*b.nn, this->getlocation());
|
||||
#ifdef CUDALA
|
||||
if(location == cpu){
|
||||
#endif
|
||||
cblas_sger(CblasRowMajor, nn, b.nn, scale, v, 1, b.v, 1, result.v, b.nn);
|
||||
#ifdef CUDALA
|
||||
}else{
|
||||
cublasSger(b.nn, nn, scale, b.v, 1, v, 1, result.v, b.nn);
|
||||
TEST_CUBLAS("cublasSger");
|
||||
}
|
||||
#endif
|
||||
return result;
|
||||
}
|
||||
|
||||
/***************************************************************************//**
|
||||
* computes the outer product of this complex vector \f$\vec{a}\f$ with given
|
||||
* complex vector \f$\vec{b}\f$ and scales the resulting matrix with factor \f$\alpha\f$, i.e.
|
||||
@@ -780,6 +1206,41 @@ NRVec<std::complex<double> >::otimes(const NRVec<std::complex<double> > &b, cons
|
||||
return result;
|
||||
}
|
||||
|
||||
template<>
|
||||
const NRMat<std::complex<float> >
|
||||
NRVec<std::complex<float> >::otimes(const NRVec<std::complex<float> > &b, const bool conj, const std::complex<float> &scale) const {
|
||||
|
||||
SAME_LOC(*this, b);
|
||||
NRMat<std::complex<float> > result(0., nn, b.nn, this->getlocation());
|
||||
|
||||
#ifdef CUDALA
|
||||
if(location == cpu){
|
||||
#endif
|
||||
if(conj){
|
||||
cblas_cgerc(CblasRowMajor, nn, b.nn, &scale, v, 1, b.v, 1, result, b.nn);
|
||||
}else{
|
||||
cblas_cgeru(CblasRowMajor, nn, b.nn, &scale, v, 1, b.v, 1, result, b.nn);
|
||||
}
|
||||
#ifdef CUDALA
|
||||
}else{
|
||||
if(conj){
|
||||
const cuComplex alpha = make_cuComplex(scale.real(), -scale.imag());
|
||||
|
||||
cublasCgerc(b.nn, nn, alpha, (cuComplex*)(b.v), 1, (cuComplex*)(v), 1, (cuComplex*)(result[0]), b.nn);
|
||||
TEST_CUBLAS("cublasCgerc");
|
||||
|
||||
result.conjugateme();
|
||||
}else{
|
||||
const cuComplex alpha = make_cuComplex(scale.real(), +scale.imag());
|
||||
|
||||
cublasCgeru(b.nn, nn, alpha, (cuComplex*)(b.v), 1, (cuComplex*)(v), 1, (cuComplex*)(result[0]), b.nn);
|
||||
TEST_CUBLAS("cublasCgeru");
|
||||
}
|
||||
}
|
||||
#endif
|
||||
return result;
|
||||
}
|
||||
|
||||
template<>
|
||||
const NRVec<std::complex<double> >
|
||||
NRVec<std::complex<double> >::otimes2vec(const NRVec<std::complex<double> > &b, const bool conj, const std::complex<double> &scale) const {
|
||||
@@ -815,6 +1276,41 @@ NRVec<std::complex<double> >::otimes2vec(const NRVec<std::complex<double> > &b,
|
||||
return result;
|
||||
}
|
||||
|
||||
template<>
|
||||
const NRVec<std::complex<float> >
|
||||
NRVec<std::complex<float> >::otimes2vec(const NRVec<std::complex<float> > &b, const bool conj, const std::complex<float> &scale) const {
|
||||
|
||||
SAME_LOC(*this, b);
|
||||
NRVec<std::complex<float> > result(0., nn*b.nn, this->getlocation());
|
||||
|
||||
#ifdef CUDALA
|
||||
if(location == cpu){
|
||||
#endif
|
||||
if(conj){
|
||||
cblas_cgerc(CblasRowMajor, nn, b.nn, &scale, v, 1, b.v, 1, result.v, b.nn);
|
||||
}else{
|
||||
cblas_cgeru(CblasRowMajor, nn, b.nn, &scale, v, 1, b.v, 1, result.v, b.nn);
|
||||
}
|
||||
#ifdef CUDALA
|
||||
}else{
|
||||
if(conj){
|
||||
const cuComplex alpha = make_cuComplex(scale.real(), -scale.imag());
|
||||
|
||||
cublasCgerc(b.nn, nn, alpha, (cuComplex*)(b.v), 1, (cuComplex*)(v), 1, (cuComplex*)(result.v), b.nn);
|
||||
TEST_CUBLAS("cublasCgerc");
|
||||
|
||||
result.conjugateme();
|
||||
}else{
|
||||
const cuComplex alpha = make_cuComplex(scale.real(), +scale.imag());
|
||||
|
||||
cublasCgeru(b.nn, nn, alpha, (cuComplex*)(b.v), 1, (cuComplex*)(v), 1, (cuComplex*)(result.v), b.nn);
|
||||
TEST_CUBLAS("cublasCgeru");
|
||||
}
|
||||
}
|
||||
#endif
|
||||
return result;
|
||||
}
|
||||
|
||||
|
||||
template<>
|
||||
NRVec<std::complex<double> > complexify(const NRVec<double> &rhs) {
|
||||
@@ -834,6 +1330,24 @@ NRVec<std::complex<double> > complexify(const NRVec<double> &rhs) {
|
||||
return r;
|
||||
}
|
||||
|
||||
template<>
|
||||
NRVec<std::complex<float> > complexify(const NRVec<float> &rhs) {
|
||||
NRVec<std::complex<float> > r(rhs.size(), rhs.getlocation());
|
||||
|
||||
#ifdef CUDALA
|
||||
if(rhs.getlocation() == cpu){
|
||||
#endif
|
||||
cblas_scopy(rhs.size(), &rhs[0], 1, (float *)(&r[0]), 2);
|
||||
#ifdef CUDALA
|
||||
}else{
|
||||
r = 0;
|
||||
cublasScopy(rhs.size(), rhs.v, 1, (float*)(r.v), 2);
|
||||
TEST_CUBLAS("cublasScopy");
|
||||
}
|
||||
#endif
|
||||
return r;
|
||||
}
|
||||
|
||||
|
||||
|
||||
|
||||
@@ -1073,6 +1587,22 @@ const double NRVec<double>::sum() const {
|
||||
return result;
|
||||
}
|
||||
|
||||
template <>
|
||||
const float NRVec<float>::sum() const {
|
||||
float result=0;
|
||||
#ifdef CUDALA
|
||||
if(location == cpu){
|
||||
#endif
|
||||
cblas_saxpy(nn, 1.0, v, 1, &result, 0);
|
||||
#ifdef CUDALA
|
||||
}else{
|
||||
laerror("not implemented");
|
||||
}
|
||||
}
|
||||
#endif
|
||||
return result;
|
||||
}
|
||||
|
||||
/***************************************************************************//**
|
||||
* sum up the all of the current double-precision complex vector
|
||||
* @return sum
|
||||
@@ -1093,6 +1623,22 @@ const std::complex<double> NRVec<std::complex<double> >::sum() const {
|
||||
return result;
|
||||
}
|
||||
|
||||
template <>
|
||||
const std::complex<float> NRVec<std::complex<float> >::sum() const {
|
||||
std::complex<float> result=0;
|
||||
#ifdef CUDALA
|
||||
if(location == cpu){
|
||||
#endif
|
||||
cblas_caxpy(nn, &CONEF, v, 1, &result, 0);
|
||||
#ifdef CUDALA
|
||||
}else{
|
||||
laerror("not implemented");
|
||||
}
|
||||
}
|
||||
#endif
|
||||
return result;
|
||||
}
|
||||
|
||||
|
||||
|
||||
|
||||
@@ -1232,8 +1778,8 @@ INSTANTIZE_CONCAT(std::complex<double>)
|
||||
|
||||
|
||||
|
||||
//template class NRVec<float>;
|
||||
//template class NRVec<std::complex<float> >;
|
||||
template class NRVec<float>;
|
||||
template class NRVec<std::complex<float> >;
|
||||
template class NRVec<double>;
|
||||
template class NRVec<std::complex<double> >;
|
||||
template class NRVec<char>;
|
||||
|
||||
Reference in new issue
Block a user