Lines Matching full:rounding
737 -mfp-trap-mode=MODE -mfp-rounding-mode=MODE
5901 `-ffinite-math-only', `-fno-rounding-math', `-fno-signaling-nans'
5954 which relies on rounding behavior like `(x + 2**52) - 2**52)'.
6011 floating point rounding behavior. This is round-to-zero for all
6014 for programs that change the FP rounding mode dynamically, or that
6015 may be executed with a non-default rounding mode. This option
6017 compile-time (which may be affected by rounding mode) and
6019 sign-dependent rounding modes.
6021 The default is `-fno-rounding-math'.
6024 disable all GCC optimizations that are affected by rounding mode.
9363 `-mfp-rounding-mode=ROUNDING-MODE'
9364 Selects the IEEE rounding mode. Other Alpha compilers call this
9365 option `-fprm ROUNDING-MODE'. The ROUNDING-MODE can be one of:
9368 Normal IEEE rounding mode. Floating point numbers are
9376 Chopped rounding mode. Floating point numbers are rounded
9380 Dynamic rounding mode. A field in the floating point control
9382 controls the rounding mode in effect. The C library
9383 initializes this register for rounding towards plus infinity.
10411 Setting the rounding of floating-point operations to less than the
10642 instructions have a different rounding behavior compared to
15068 * `The rounding behaviors characterized by non-standard values of
15078 * `The direction of rounding when an integer is converted to a
15084 * `The direction of rounding when a floating-point number is
15109 * `Additional floating-point exceptions, rounding modes,
16322 * Pragmas to control overflow and rounding behaviors are not
19561 there is a system register which can be set to control the rounding
22641 rounding are made.
39378 * mfp-rounding-mode: DEC Alpha Options. (line 85)
