[CUDA] Add math forward declares to CUDA header wrapper.
This is necessary for a future patch which will make all constexpr
functions implicitly host+device. cmath may declare constexpr
functions, but these we do *not* want to be host+device. The forward
declares added in this patch prevent this (because the rule will be,
constexpr functions become implicitly host+device unless they're
preceeded by a decl with device).
Subscribers: cfe-commits, rnk, rsmith
Differential Revision: http://reviews.llvm.org/D18539