generating and calling, into a normal IR to IR lowering pass.

Includes adding struct handling intrinsics to LLVM and C++ backends.

Still a work in progress.

closure. Ensure all types are carried through exactly the same to both
make_struct_type and make_typed_struct.

Fixes to call graph checker. Disable tests related to this while
Andrew and I figure out how to get it to work across closures.

bludgeoning types into submission via subterfuge.

LoweredFunctions in the future.

Don't declare halide_buffer_t type if there are no buffers in closure.

the function. This makes generating the C++ declaration in the C++
backend trivial.

Few more changes to type handling and naming.

Don't generate For loops with no variable.

Update internal test for C++ output.

…mpiler.

Formating fixes.

cases where it is valid.

…alide into factor_parallel_codegen

Fix qurt_hvx_lock issues

- normalize local functions to snake_case
- put all local functions & classes in anon namespace
- move MinThreads visitor to file scope to reduce nestedness of code

* Minor cleanup of parallel refactor intrinsics

- Renamed `load_struct_member` to `load_typed_struct_member` to make it more clear that it is intended for use only with the results of `make_typed_struct`.
- Split `declare_struct_type` into two intrinsics, `define_typed_struct` and `forward_declare_typed_struct`, removing the need for the underdocumented `mode` argument and hopefully making usage clearer
- Added / clarified comments for the intrinsics modified above

* Update comments

* Fix comments

This is a direct adaptation of what #6481 does for the old LLVM-based code, and allows elimination of one use of `get_pointer_or_null()`. PR is meant to be merged into factor_parallel_codegen, not master.

…-needed get_pointer_or_symbol() intrinsic (#6486)

I think this is the right fix for this case; that said, I can't find a single instance in any of our test cases that actually triggers this.

* Rework some of parallel closure lowering to avoid some intrinsics

This version relies more heavily on the existing make_struct, and puts
function names in the Variable namespace as globals.

Co-authored-by: Steven Johnson <srj@google.com>