[PACKET] Enable generic Packet optimization, one step toward beyond sse

guide/basic.cpp

@@ -21,14 +21,14 @@ int main(void) {
 
   // shaape of matrix, note size order is same as numpy
   printf("%u X %u matrix\n", mat.size(0), mat.size(1));
-  return 0;
+
   // initialize all element to zero
   mat = 0.0f;
   // assign some values
   mat[0][1] = 1.0f; mat[1][0] = 2.0f;
   // elementwise operations
   mat += (mat + 10.0f) / 10.0f + 2.0f;
-  
+
   // print out matrix, note: mat2 and mat1 are handles(pointers)
   for (index_t i = 0; i < mat.size(0); ++i) {
     for (index_t j = 0; j < mat.size(1); ++j) {

guide/config.mk

@@ -22,7 +22,7 @@ USE_CUDA_PATH = NONE
 #
 # choose the version of blas you want to use
 # can be: mkl, blas, atlas, openblas, apple
-USE_BLAS = openblas
+USE_BLAS = blas
 #
 # add path to intel library, you may need it
 # for MKL, if you did not add the path to enviroment variable