OpenACC Tutorial - Adding directives: Difference between revisions

OpenACC Tutorial - Adding directives (view source)

120 bytes added , 3 years ago

no edit summary

Bureaucrats, cc_docs_admin, cc_staff, rsnt_translations

2,837

edits

@@ Line 260: / Line 260: @@
 </translate>
 {{Command
-|pgc++ -fast -Minfo{{=}}accel -ta{{=}}tesla:managed main.cpp -o challenge
+|nvc++ -fast -Minfo{{=}}accel -ta{{=}}tesla:managed main.cpp -o challenge
 |result=
 matvec(const matrix &, const vector &, const vector &):
 , include "matrix_functions.h"
-, Generating copyout(ycoefs[:num_rows])
+, Generating implicit copyout(ycoefs[:num_rows]) [if not already present]
-               Generating copyin(xcoefs[:],Acoefs[:],cols[:],row_offsets[:num_rows+1])
+               Generating implicit copyin(xcoefs[:],row_offsets[:num_rows+1],Acoefs[:],cols[:]) [if not already present]
 , Loop is parallelizable
-              Accelerator kernel generated
                Generating Tesla code
-, #pragma acc loop gang, vector(128) /* blockIdx.x threadIdx.x */
+, #pragma acc loop gang /* blockIdx.x */
-, Loop is parallelizable
+, #pragma acc loop vector(128) /* threadIdx.x */
+                  Generating implicit reduction(+:sum)
+, Loop is parallelizable
 }}
 <translate>