one possible way is like:
using 4 insertelement ir to generate one <4x i32> vector, then use a bitcast 
from <4 x i32> to <16 x i8>. suppose gen backend have already support such kind 
of bitcast between vectors. hope it works!
_______________________________________________
Beignet mailing list
[email protected]
http://lists.freedesktop.org/mailman/listinfo/beignet

Reply via email to