[ARM/AArch64] Improve modeled latency between FP operations and FP->GP register moves

[ARM/AArch64] Improve modeled latency between FP operations and FP->GP register moves

	* config/arm/cortex-a15-neon.md (cortex_a15_vfp_to_from_gp):
	Split into...
	(cortex_a15_gp_to_vfp): ...This.
	(cortex_a15_fp_to_gp): ...And this.
	Define and comment bypass from vfp operations to fp->gp moves.

From-SVN: r217725