Merge pull request #1202 from hunse/master

theano/tensor/blas_c.py

@@ -492,11 +492,19 @@ def gemv_c_code(aa, xx, yy, zz, alpha, beta, destructive, fail):
             {
                 if (PyArray_DESCR(%(xx)s)->type_num == NPY_FLOAT)
                 {
-                    //fprintf(stderr, "B %%i %%i %%i %%i\\n",
-                    //        Nz0, Nz1, Sz0, Sz1);
                     float alpha = ((dtype_%(alpha)s*)PyArray_DATA(%(alpha)s))[0];
-                    //fprintf(stderr, "alpha=%%f\\n", alpha);
-                    //fprintf(stderr, "sx  sy %%i %%i\\n", Sx, Sy);
+
+                    // Check for vector-vector dot (Nx0 == 1). The code may work
+                    // for Sx1 != 1 as well, but has not been tested for this case,
+                    // so Sx1 == 1 is required for safety.
+                    if (Nx0 == 1 && Sx1 == 1)
+                    {
+                        zz_data[0] = fbeta*zz_data[0] + alpha*sdot_(&Nx1, 
+                            (float*)(PyArray_DATA(%(xx)s)), &Sx1,
+                            (float*)yy_data, &Sy);
+                    }
+                    else
+                    {
                         sgemv_(&TRANS, &Nx1, &Nx0,
                             &alpha,
                             (float*)(PyArray_DATA(%(xx)s)), &Sx0,
@@ -504,9 +512,22 @@ def gemv_c_code(aa, xx, yy, zz, alpha, beta, destructive, fail):
                             &fbeta,
                             (float*)zz_data, &Sz);
                     }
+                }
                 else if (PyArray_DESCR(%(xx)s)->type_num == NPY_DOUBLE)
                 {
                     double alpha = ((dtype_%(alpha)s*)PyArray_DATA(%(alpha)s))[0];
+
+                    // Check for vector-vector dot (Nx0 == 1). The code may work
+                    // for Sx1 != 1 as well, but has not been tested for this case,
+                    // so Sx1 == 1 is required for safety.
+                    if (Nx0 == 1 && Sx1 == 1)
+                    {
+                        zz_data[0] = dbeta*zz_data[0] + alpha*ddot_(&Nx1, 
+                              (double*)(PyArray_DATA(%(xx)s)), &Sx1,
+                              (double*)yy_data, &Sy);
+                    }
+                    else
+                    {
                         dgemv_(&TRANS, &Nx1, &Nx0,
                             &alpha,
                             (double*)(PyArray_DATA(%(xx)s)), &Sx0,
@@ -514,6 +535,7 @@ def gemv_c_code(aa, xx, yy, zz, alpha, beta, destructive, fail):
                             &dbeta,
                             (double*)zz_data, &Sz);
                     }
+                }
                 else
                 {
                     PyErr_SetString(PyExc_AssertionError,
@@ -556,7 +578,7 @@ class CGemv(BaseBLAS, Gemv):
         return code
 
     def c_code_cache_version(self):
-        return (9,)
+        return (10,)
 
 
 @local_optimizer([gemv_inplace, gemv_no_inplace])