Most real.h routines used machine modes to specify the format of
an operation and converted that to a float_format * internally.
Some also had alternative versions that accepted a float_format *.

In an upcoming patch it seemed more convenient for the callers
I was adding to use float_format directly, since the callers need
to examine the format themselves for other reasons.  This patch
therefore replaces the machine_mode arguments with a new class that
allows both machine modes and float_format pointers to be used.

Tested on x86_64-linux-gnu, arm-linux-gnueabi and aarch64-linux-gnu.

gcc/
	* real.h (format_helper): New.
	(real_convert, exact_real_truncate, real_from_string3, real_to_target)
	(real_from_target, real_nan, real_2expN, real_value_truncate)
	(significand_size, real_from_string2, exact_real_inverse)
	(exact_real_inverse, real_powi, real_trunc, real_floor, real_ceil)
	(real_round, real_isinteger, real_from_integer): Replace
	machine_mode arguments with format_helper arguments.
	* real.c (exact_real_inverse, real_from_string2, real_from_string3)
	(real_from_integer, real_nan, real_2expN, real_convert)
	(real_value_truncate, exact_real_truncate, real_to_target)
	(real_from_target, significand_size, real_powi, real_trunc)
	(real_floor, real_ceil, real_round, real_isinteger): Replace
	machine_mode arguments with format_helper arguments.
	(real_to_target_fmt, real_from_target_fmt): Delete.
	* dfp.h (decimal_real_convert): Replace mode argument with real_format.
	* dfp.c (decimal_to_binary, decimal_real_convert): Replace mode
	argument with real_format.
	* builtins.c (do_real_to_int_conversion): Update type of fn argument.

gcc/java/
	* jcf-parse.c (get_constant): Use real_from_target rather than
	real_from_target_fmt.

From-SVN: r229581