jiri/LA_library
1
0 Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

float support for sparse matrices

Browse Source
This commit is contained in:
jiri committed 2026-11-05 16:37:24 +01:00
1 parent 2ed864bda4
commit c711270e25
6 files changed
+187 -33
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

sparsemat.cc
+92 -22
View File
@@ -334,7 +334,7 @@ return nonzero; //number of (in principle) nonzero elements
template <class T>
void SparseMat<T>::simplify(const double sparseepsilon)
void SparseMat<T>::simplify(const typename LA_traits<T>::normtype sparseepsilon)
{
unsigned int n;
if(!list) return;
@@ -431,7 +431,7 @@ void SparseMat<T>::addsafe(const SPMatindex n, const SPMatindex m, const T elem)
#ifdef debug
if(n<0||n>=nn||m<0||m>=mm) laerror("SparseMat out of range");
#endif
if(std::abs(elem)<=SPARSEEPSILON) return;
if(std::abs(elem)<=LA_precision<typename LA_traits<T>::normtype>::sparse_epsilon()) return;
if(!count) {count=new int; *count=1; list=NULL;} //blank new matrix
else copyonwrite(); //makes also unsort
add(n,m,elem);
@@ -482,7 +482,7 @@ register matel<T> *l=rhs.list;
while(l)
{
if(rhs.symmetric || lower && l->row <=l->col || !lower && l->row >=l->col)
if(std::abs(l->elem)>SPARSEEPSILON)
if(std::abs(l->elem)>LA_precision<typename LA_traits<T>::normtype>::sparse_epsilon())
add( l->row,l->col,sign=='+'?l->elem:- l->elem);
l=l->next;
}
@@ -501,14 +501,14 @@ register matel<T> *l=rhs.list;
if(symmetrize)
while(l)
{
if(std::abs(l->elem)>SPARSEEPSILON)
if(std::abs(l->elem)>LA_precision<typename LA_traits<T>::normtype>::sparse_epsilon())
{add( l->row,l->col,l->elem); if( l->row!=l->col) add( l->col,l->row,l->elem);}
l=l->next;
}
else
while(l)
{
if(std::abs(l->elem)>SPARSEEPSILON)
if(std::abs(l->elem)>LA_precision<typename LA_traits<T>::normtype>::sparse_epsilon())
add( l->row,l->col,l->elem);
l=l->next;
}
@@ -528,14 +528,14 @@ register matel<T> *l=rhs.list;
if(symmetrize)
while(l)
{
if(std::abs(l->elem)>SPARSEEPSILON)
if(std::abs(l->elem)>LA_precision<typename LA_traits<T>::normtype>::sparse_epsilon())
{add( l->row,l->col,- l->elem); if( l->row!=l->col) add( l->col,l->row,- l->elem);}
l=l->next;
}
else
while(l)
{
if(std::abs(l->elem)>SPARSEEPSILON)
if(std::abs(l->elem)>LA_precision<typename LA_traits<T>::normtype>::sparse_epsilon())
add( l->row,l->col,- l->elem);
l=l->next;
}
@@ -559,7 +559,7 @@ SPMatindex i,j;
for(i=0;i<nn;++i)
for(j=0; j<mm;++j)
{register T t(rhs(i,j));
if( std::abs(t)>SPARSEEPSILON)
if( std::abs(t)>LA_precision<typename LA_traits<T>::normtype>::sparse_epsilon())
add(i,j,t);
}
}
@@ -598,12 +598,12 @@ if(nn==mm) //square
else //diagonal of A^TA, assuming it has been simplified (only one entry per position), will be used as preconditioner only anyway
while(l)
{
(*rr)[l->col] += l->elem*l->elem *(l->col!=l->row && symmetric?2.:1.);
(*rr)[l->col] += l->elem*l->elem *(T)(l->col!=l->row && symmetric?2:1);
l= l->next;
}
if(divide)
{
for(unsigned int i=0; i<mm; ++i) if((*rr)[i]!=0.) r[i]/=(*rr)[i];
for(unsigned int i=0; i<mm; ++i) if((*rr)[i]!=(T)0) r[i]/=(*rr)[i];
delete rr;
}
return divide?NULL:&r[0];
@@ -693,7 +693,7 @@ SparseMat<T> & SparseMat<T>::operator=(const T &a)
if(!count ||nn<=0||mm<=0) laerror("assignment of scalar to undefined sparse matrix");
if(nn!=mm) laerror("assignment of scalar to non-square sparse matrix");
resize(nn,mm);//clear
if(std::abs(a)<=SPARSEEPSILON) return *this;
if(std::abs(a)<=LA_precision<typename LA_traits<T>::normtype>::sparse_epsilon()) return *this;
SPMatindex i;
for(i=0;i<nn;++i) add(i,i,a);
return *this;
@@ -741,7 +741,7 @@ for(i=0;i<nn;++i)
for(j=0; j<=i;++j)
{register T t;
if(
std::abs(t=rhs(i,j))>SPARSEEPSILON
std::abs(t=rhs(i,j))>LA_precision<typename LA_traits<T>::normtype>::sparse_epsilon()
) add(i,j,t);
}
}
@@ -774,7 +774,7 @@ matel<T> *l=list;
while(l) //include the mirror picture of elements into the list
{
if(
std::abs(l->elem)>SPARSEEPSILON &&
std::abs(l->elem)>LA_precision<typename LA_traits<T>::normtype>::sparse_epsilon() &&
l->row!=l->col) add(l->col,l->row,l->elem); //not OK for complex-hermitean
l=l->next;
}
@@ -812,12 +812,32 @@ while(l)
return r;
}
template<>
const float SparseMat<float>::dot(const NRMat<float> &rhs) const
{
float r=0;
matel<float> *l=list;
while(l)
{
r+= l->elem*rhs[l->row][l->col];
if(symmetric&&l->row!=l->col) r+=l->elem*rhs[l->col][l->row];
l=l->next;
}
return r;
}
template<>
void NRMat<std::complex<double> >::gemm(const std::complex<double> &beta, const SparseMat<std::complex<double> > &a, const char transa, const NRMat<std::complex<double> > &b, const char transb, const std::complex<double> &alpha)
{
laerror("not implemented yet");
}
template<>
void NRMat<std::complex<float> >::gemm(const std::complex<float> &beta, const SparseMat<std::complex<float> > &a, const char transa, const NRMat<std::complex<float> > &b, const char transb, const std::complex<float> &alpha)
{
laerror("not implemented yet");
}
template<>
void NRMat<double>::gemm(const double &beta, const SparseMat<double> &a, const char transa, const NRMat<double> &b, const char transb, const double &alpha)
@@ -867,6 +887,54 @@ else
}
template<>
void NRMat<float>::gemm(const float &beta, const SparseMat<float> &a, const char transa, const NRMat<float> &b, const char transb, const float &alpha)
{
bool transpa = tolower(transa)!='n'; //not OK for complex
bool transpb = tolower(transb)!='n'; //not OK for complex
if(nn!=(int)(transpa?a.ncols():a.nrows()) | mm!= (transpb?b.nrows():b.ncols()) || (int)(transpa?a.nrows():a.ncols()) != (transpb?b.ncols():b.nrows())) laerror("incompatible sizes in gemm");
copyonwrite();
if(beta!=(float)0) (*this) *= beta;
else memset(v,0,nn*mm*sizeof(float));
matel<float> *l=a.getlist();
if(alpha==(float)0 || !l) return;
//raw pointers to the full matrices
const float *bp= b;
float *p= *this;
int ldb=(transpb?b.ncols():1);
int bstep=(transpb?1:b.ncols());
int len=(transpb?b.nrows():b.ncols());
if(a.issymmetric())
{
while(l)
{
cblas_saxpy(len, alpha*l->elem , bp+l->row*bstep, ldb, p+l->col*mm, 1);
if(l->row!=l->col) cblas_saxpy(len, alpha*l->elem , bp+l->col*bstep, ldb, p+l->row*mm, 1);
l=l->next;
}
}
else
{
if(transpa)
while(l)
{
cblas_saxpy(len, alpha*l->elem , bp+l->row*bstep, ldb, p+l->col*mm, 1);
l=l->next;
}
else
while(l)
{
cblas_saxpy(len, alpha*l->elem , bp+l->col*bstep, ldb, p+l->row*mm, 1);
l=l->next;
}
}
}
template<class T>
@@ -1036,7 +1104,7 @@ if(transp)
while(l)
{
register T t=alpha*l->elem;
if(std::abs(t)>SPARSEEPSILON)
if(std::abs(t)>LA_precision<typename LA_traits<T>::normtype>::sparse_epsilon())
add( l->col,l->row,t);
l=l->next;
}
@@ -1044,7 +1112,7 @@ else
while(l)
{
register T t=alpha*l->elem;
if(std::abs(t)>SPARSEEPSILON)
if(std::abs(t)>LA_precision<typename LA_traits<T>::normtype>::sparse_epsilon())
add( l->row,l->col,t);
l=l->next;
}
@@ -1329,7 +1397,7 @@ incsize(rhs.nrows(), rhs.ncols());
T tmp;
for(SPMatindex i=0; i<(SPMatindex)rhs.nrows(); ++i)
for(SPMatindex j=0; j<(SPMatindex)rhs.ncols(); ++j)
if(std::abs(tmp=rhs(i,j))>SPARSEEPSILON) add(n0+i,m0+j,tmp);
if(std::abs(tmp=rhs(i,j))>LA_precision<typename LA_traits<T>::normtype>::sparse_epsilon()) add(n0+i,m0+j,tmp);
return *this;
}
@@ -1345,7 +1413,7 @@ T tmp;
incsize(rhs.nrows(), rhs.ncols());
for(SPMatindex i=0; i<(SPMatindex)rhs.nrows(); ++i)
for(SPMatindex j=0; j<=i; ++j) //symmetric storage: one triangle only
if(std::abs(tmp=rhs(i,j))>SPARSEEPSILON) add(n0+i,m0+j,tmp);
if(std::abs(tmp=rhs(i,j))>LA_precision<typename LA_traits<T>::normtype>::sparse_epsilon()) add(n0+i,m0+j,tmp);
return *this;
}
@@ -1364,7 +1432,7 @@ incsize(rhs.nrows(), rhs.ncols());
register matel<T> *l=rhs.list;
while(l)
{
if(std::abs(l->elem)>SPARSEEPSILON)
if(std::abs(l->elem)>LA_precision<typename LA_traits<T>::normtype>::sparse_epsilon())
add(n0+l->row,m0+l->col,l->elem);
l=l->next;
}
@@ -1429,8 +1497,12 @@ INSTANTIZE(std::complex<double>) //some functions are not OK for hermitean matri
//// forced instantization in the corresponding object file
template class SparseMat<double>;
template class SparseMat<std::complex<double> >;
template class SparseMat<float>;
template class SparseMat<std::complex<float> >;
template class SemiSparseMat<double>;
template class SemiSparseMat<std::complex<double> >;
template class SemiSparseMat<float>;
template class SemiSparseMat<std::complex<float> >;
#define INSTANTIZE(T) \
@@ -1443,10 +1515,8 @@ template void NRVec<T>::gemv(const T beta, const SparseMat<T> &a, const char tra
INSTANTIZE(double)
INSTANTIZE(std::complex<double>)
//needed by the instantiation of NRVec<float> and NRVec<std::complex<float> >
template void NRVec<float>::gemv(const float beta, const SparseMat<float> &a, const char trans, const float alpha, const NRVec<float> &x, const bool treat_as_symmetric);
template void NRVec<std::complex<float> >::gemv(const std::complex<float> beta, const SparseMat<std::complex<float> > &a, const char trans, const std::complex<float> alpha, const NRVec<std::complex<float> > &x, const bool treat_as_symmetric);
INSTANTIZE(float)
INSTANTIZE(std::complex<float>)
}//namespace