do arithmetic operations on gcc's __float128 floating point numbers take current rounding mode account? for instance, if using c++11 function std::fesetenv , change rounding mode fe_downward , results of arithmetic operations on __float128 rounded down? is guaranteed __float128 specification? i believe guaranteed operations on __float128 take rounding mode account. according gnu c library documentation floating-point calculations respect rounding mode. according gcc manual __float128 floating type supports arithmetic operations division etc. from deduce, operations on __float128 , rounding mode has be taken account. the gnu c library documentation states: 20.6 rounding modes floating-point calculations carried out internally precision, , rounded fit destination type. ensures results precise input data. ieee 754 defines 4 possible rounding modes: [...] reference: http://www.gnu.org/software/libc/manual/html_node/rounding.html ...
Comments
Post a Comment