widening_optab_handler had the comment:

      /* ??? Why does find_widening_optab_handler_and_mode attempt to
         widen things that can't be widened?  E.g. add_optab... */
      if (op > LAST_CONV_OPTAB)
        return CODE_FOR_nothing;

I think it comes from expand_binop using
find_widening_optab_handler_and_mode for two things: to test whether
a "normal" optab like add_optab is supported for a standard binary
operation and to test whether a "convert" optab is supported for a
widening operation like umul_widen_optab.  In the former case from_mode
and to_mode must be the same, in the latter from_mode must be narrower
than to_mode.

For the former case, find_widening_optab_handler_and_mode is only really
testing the modes that are passed in.  permit_non_widening must be true
here.

For the latter case, find_widening_optab_handler_and_mode should only
really consider new from_modes that are wider than the original
from_mode and narrower than the original to_mode.  Logically
permit_non_widening should be false, since widening optabs aren't
supposed to take operands that are the same width as the destination.
We get away with permit_non_widening being true because no target
would/should define a widening .md pattern with matching modes.

But really, it seems better for expand_binop to handle these two
cases itself rather than pushing them down.  With that change,
find_widening_optab_handler_and_mode is only ever called with
permit_non_widening set to false and is only ever called with
a "proper" convert optab.  We then no longer need widening_optab_handler,
we can just use convert_optab_handler directly.

The patch also passes the instruction code down to expand_binop_directly.
This should be more efficient and removes an extra call to
find_widening_optab_handler_and_mode.

2017-11-01  Richard Sandiford  <richard.sandiford@linaro.org>
	    Alan Hayward  <alan.hayward@arm.com>
	    David Sherwood  <david.sherwood@arm.com>

gcc/
	* optabs-query.h (convert_optab_p): New function, split out from...
	(convert_optab_handler): ...here.
	(widening_optab_handler): Delete.
	(find_widening_optab_handler): Remove permit_non_widening parameter.
	(find_widening_optab_handler_and_mode): Likewise.  Provide an
	override that operates on mode class wrappers.
	* optabs-query.c (widening_optab_handler): Delete.
	(find_widening_optab_handler_and_mode): Remove permit_non_widening
	parameter.  Assert that the two modes are the same class and that
	the "from" mode is narrower than the "to" mode.  Use
	convert_optab_handler instead of widening_optab_handler.
	* expmed.c (expmed_mult_highpart_optab): Use convert_optab_handler
	instead of widening_optab_handler.
	* expr.c (expand_expr_real_2): Update calls to
	find_widening_optab_handler.
	* optabs.c (expand_widen_pattern_expr): Likewise.
	(expand_binop_directly): Take the insn_code as a parameter.
	(expand_binop): Only call find_widening_optab_handler for
	conversion optabs; use optab_handler otherwise.  Update calls
	to find_widening_optab_handler and expand_binop_directly.
	Use convert_optab_handler instead of widening_optab_handler.
	* tree-ssa-math-opts.c (convert_mult_to_widen): Update calls to
	find_widening_optab_handler and use scalar_mode rather than
	machine_mode.
	(convert_plusminus_to_widen): Likewise.

Co-Authored-By: Alan Hayward <alan.hayward@arm.com>
Co-Authored-By: David Sherwood <david.sherwood@arm.com>

From-SVN: r254302