int islessgreater (double x ,
double y ) // if double extension enabled
longn islessgreater (doublen x ,
doublen y ) // if double extension enabled

int islessgreater (half x ,
half y ) // if half extension enabled
shortn islessgreater (halfn x ,
halfn y ) // if half extension enabled

This function returns a 0 if the specified relation is false and a 1 if the specified relation is true for scalar argument types. It returns a 0 if the specified relation is false and a 1 (i.e. all bits set) if the specified relation is true for vector argument types. This function always return 0 if either argument is not a number (NaN).
The relational and equality operators (<, <=, >, >=, !=, ==) can be used with scalar and vector builtin types and produce a scalar or vector signed integer result respectively.
This function can be used with builtin scalar or vector types as arguments and return a scalar vector integer result. The argument type igentype refers to signed integer vector types i.e. char, charn
, short, shortn
, int, intn
, long, and longn
.
If extended with cl_khr_fp64, generic type name gentype may indicate double and double{24816} as arguments and return values. If extended with cl_khr_fp16, generic type name gentype may indicate half and half{24816} as arguments and return values.