[CUDA] Align kernel launch args correctly when the LLVM type's alignment is different from the clang type's alignment.

Summary:
Before this patch, we computed the offsets in memory of args passed to
GPU kernel functions by throwing all of the args into an LLVM struct.

clang emits packed llvm structs basically whenever it feels like it, and
packed structs have alignment 1.  So we cannot rely on the llvm type's
alignment matching the C++ type's alignment.

This patch fixes our codegen so we always respect the clang types'
alignments.

Reviewers: rnk

Subscribers: cfe-commits, tra

Differential Revision: https://reviews.llvm.org/D22879

git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@276927 91177308-0d34-0410-b5e6-96231b3b80d8