Hi,
the following excerpt of CL code:
float4 qf;
uint4 tmp=input_val;
qf= convert_float(tmp);
fails to compile with the following error:
...\Temp\OCL9B29.tmp.cl(2289): error: bad argument
type to opencl convert_* function: expected src and dst have the
same number of elements
qf= convert_float(tmp);
^
qf and tmp both are vectors of size 4, or am I missing something? If it is a compiler error, then it would be nice to have that fixed in one of the next releases ...
Thanks,
Bdot