Advanced Computing Platform for Theoretical Physics

commit大文件会使得服务器变得不稳定,请大家尽量只commit代码,不要commit大的文件。

Commit f89cf306 authored by mikeaclark's avatar mikeaclark
Browse files

pack18 function, will be for no reconstruct double precision

git-svn-id: http://lattice.bu.edu/qcdalg/cuda/quda@439 be54200a-260c-0410-bdd7-ce6af2a381ab
parent 0bf35c40
......@@ -87,6 +87,15 @@ inline void pack12(short4 *res, Float *g, int dir, int V) {
}
}
template <typename Float>
inline void pack18(double2 *res, Float *g, int dir, int V) {
double2 *r = res + dir*9*V;
for (int j=0; j<9; j++) {
r[j*V].x = g[j*2+0];
r[j*V].y = g[j*2+1];
}
}
// Assume the gauge field is "QDP" ordered directions inside of
// space-time column-row ordering even-odd space-time
template <typename Float, typename FloatN>
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment