From b3b023bfc3d9069285980d5c62984b414e1a2d70 Mon Sep 17 00:00:00 2001
From: Jiri Pittner <jiri@pittnerovi.com>
Date: Thu, 5 Nov 2026 16:43:09 +0100
Subject: [PATCH] float support for tensor

---
 tensor.cc | 26 ++++++++++++++++++++++++++
 1 file changed, 26 insertions(+)

diff --git a/tensor.cc b/tensor.cc
index af8842c..6b7428a 100644
--- a/tensor.cc
+++ b/tensor.cc
@@ -1187,6 +1187,16 @@ std::cout<<"cblas_dgemm CPU time " << (clock()-t0)/(double)CLOCKS_PER_SEC<<std::
 #endif
 }
 
+template<>
+void auxmatmult<float>(int nn, int mm, int kk, float *r, const float *a, const float *b, float alpha, float beta, bool conjugate)
+{
+clock_t t0=clock();
+cblas_sgemm(CblasRowMajor, CblasNoTrans, CblasTrans, nn, mm, kk, alpha, a, kk, b, kk, beta, r, mm);
+#ifdef TIMING
+std::cout<<"cblas_sgemm CPU time " << (clock()-t0)/(double)CLOCKS_PER_SEC<<std::endl;
+#endif
+}
+
 template<>
 void auxmatmult<std::complex<double> >(int nn, int mm, int kk, std::complex<double> *r, const std::complex<double> *a, const std::complex<double> *b,  std::complex<double> alpha,  std::complex<double> beta, bool conjugate)
 {
@@ -1197,6 +1207,16 @@ std::cout<<"cblas_zgemm CPU time " << (clock()-t0)/(double)CLOCKS_PER_SEC<<std::
 #endif
 }
 
+template<>
+void auxmatmult<std::complex<float> >(int nn, int mm, int kk, std::complex<float> *r, const std::complex<float> *a, const std::complex<float> *b,  std::complex<float> alpha,  std::complex<float> beta, bool conjugate)
+{
+clock_t t0=clock();
+cblas_cgemm(CblasRowMajor, CblasNoTrans, (conjugate?CblasConjTrans:CblasTrans), nn, mm, kk, &alpha, a, kk, b, kk, &beta, r, mm);
+#ifdef TIMING
+std::cout<<"cblas_cgemm CPU time " << (clock()-t0)/(double)CLOCKS_PER_SEC<<std::endl;
+#endif
+}
+
 
 
 template<typename T>
@@ -2646,6 +2666,12 @@ template std::ostream & operator<<(std::ostream &s, const Tensor<double> &x);
 template std::ostream & operator<<(std::ostream &s, const Tensor<std::complex<double> > &x);
 template std::istream & operator>>(std::istream &s, Tensor<double> &x);
 template std::istream & operator>>(std::istream &s, Tensor<std::complex<double> > &x);
+template class Tensor<float>;
+template class Tensor<std::complex<float> >;
+template std::ostream & operator<<(std::ostream &s, const Tensor<float> &x);
+template std::ostream & operator<<(std::ostream &s, const Tensor<std::complex<float> > &x);
+template std::istream & operator>>(std::istream &s, Tensor<float> &x);
+template std::istream & operator>>(std::istream &s, Tensor<std::complex<float> > &x);
 
 
 }//namespace