Lines Matching full:rounding
677 -mfp-trap-mode=MODE -mfp-rounding-mode=MODE
5423 `-fno-trapping-math', `-ffinite-math-only', `-fno-rounding-math',
5492 floating point rounding behavior. This is round-to-zero for all
5495 for programs that change the FP rounding mode dynamically, or that
5496 may be executed with a non-default rounding mode. This option
5498 compile-time (which may be affected by rounding mode) and
5500 sign-dependent rounding modes.
5502 The default is `-fno-rounding-math'.
5505 disable all GCC optimizations that are affected by rounding mode.
8562 `-mfp-rounding-mode=ROUNDING-MODE'
8563 Selects the IEEE rounding mode. Other Alpha compilers call this
8564 option `-fprm ROUNDING-MODE'. The ROUNDING-MODE can be one of:
8567 Normal IEEE rounding mode. Floating point numbers are
8575 Chopped rounding mode. Floating point numbers are rounded
8579 Dynamic rounding mode. A field in the floating point control
8581 controls the rounding mode in effect. The C library
8582 initializes this register for rounding towards plus infinity.
13834 * `The rounding behaviors characterized by non-standard values of
13844 * `The direction of rounding when an integer is converted to a
13850 * `The direction of rounding when a floating-point number is
13875 * `Additional floating-point exceptions, rounding modes,
17944 there is a system register which can be set to control the rounding
20833 rounding are made.
30688 * mfp-rounding-mode: DEC Alpha Options. (line 85)
