euclidean layer update

[jacinto-ai/caffe-jacinto.git] / src / caffe / util / math_functions.cpp

diff --git a/src/caffe/util/math_functions.cpp b/src/caffe/util/math_functions.cpp
index 1949a703d75a9e71c91182dff0a7c6ae24689ef8..a3a94cd52d75c0817ca6f6bc59d5921ef4b4134c 100644 (file)
--- a/src/caffe/util/math_functions.cpp
+++ b/src/caffe/util/math_functions.cpp
@@ -103,6 +103,18 @@ template <>
 void caffe_axpy<double>(const int N, const double alpha, const double* X,
     double* Y) { cblas_daxpy(N, alpha, X, 1, Y, 1); }
 
+template <>
+void caffe_axpby<float>(const int N, const float alpha, const float* X,
+    const float beta, float* Y) {
+  cblas_saxpby(N, alpha, X, 1, beta, Y, 1);
+}
+
+template <>
+void caffe_axpby<double>(const int N, const double alpha, const double* X,
+    const double beta, double* Y) {
+  cblas_daxpby(N, alpha, X, 1, beta, Y, 1);
+}
+
 template <>
 void caffe_copy<float>(const int N, const float* X, float* Y) {
   cblas_scopy(N, X, 1, Y, 1);
@@ -123,6 +135,16 @@ void caffe_scal<double>(const int N, const double alpha, double *X) {
   cblas_dscal(N, alpha, X, 1);
 }
 
+template <>
+void caffe_gpu_scal<float>(const int N, const float alpha, float *X) {
+  CUBLAS_CHECK(cublasSscal(Caffe::cublas_handle(), N, &alpha, X, 1));
+}
+
+template <>
+void caffe_gpu_scal<double>(const int N, const double alpha, double *X) {
+  CUBLAS_CHECK(cublasDscal(Caffe::cublas_handle(), N, &alpha, X, 1));
+}
+
 template <>
 void caffe_sqr<float>(const int n, const float* a, float* y) {
   vsSqr(n, a, y);
@@ -133,6 +155,22 @@ void caffe_sqr<double>(const int n, const double* a, double* y) {
   vdSqr(n, a, y);
 }
 
+template <>
+void caffe_add<float>(const int n, const float* a, const float* b,
+    float* y) { vsAdd(n, a, b, y); }
+
+template <>
+void caffe_add<double>(const int n, const double* a, const double* b,
+    double* y) { vdAdd(n, a, b, y); }
+
+template <>
+void caffe_sub<float>(const int n, const float* a, const float* b,
+    float* y) { vsSub(n, a, b, y); }
+
+template <>
+void caffe_sub<double>(const int n, const double* a, const double* b,
+    double* y) { vdSub(n, a, b, y); }
+
 template <>
 void caffe_mul<float>(const int n, const float* a, const float* b,
     float* y) { vsMul(n, a, b, y); }