[CUDA] Give templated device functions internal linkage, templated kernels external linkage.

Summary:
This lets LLVM perform IPO over these functions.  In particular, it
allows LLVM to emit ld.global.nc for loads to __restrict pointers in
kernels that are never written to.

Reviewers: rsmith

Subscribers: cfe-commits, tra

Differential Revision: http://reviews.llvm.org/D21337

llvm-svn: 274261