[nvptx] Fix .local atomic regressions

[nvptx] Fix .local atomic regressions

In PR target/104364, two problems were reported:
- in muniform-simt mode, an atom.cas insn is no longer executed in the
  "master lane" only.
- in msoft-stack mode, an __atomic_compare_exchange_n on stack memory is
  translated assuming it accesses local memory, while that's not the case.

Fix these by:
- ensuring that all insns with atomic attribute are also predicable, such
  that the validate_change in nvptx_reorg_uniform_simt will succeed, and
  asserting that it does, and
- guarding the local atomics implementation with a new function
  nvptx_mem_local_p that correctly handles msoft-stack.

Tested on x86_64 with nvptx accelerator.

gcc/ChangeLog:

2022-02-04  Tom de Vries  <tdevries@suse.de>

	PR target/104364
	* config/nvptx/nvptx-protos.h (nvptx_mem_local_p): Declare.
	* config/nvptx/nvptx.cc (nvptx_reorg_uniform_simt): Assert that
	change is validated.
	(nvptx_mem_local_p): New function.
	* config/nvptx/nvptx.md: Use nvptx_mem_local_p.
	(define_c_enum "unspecv"): Add UNSPECV_CAS_LOCAL.
	(define_insn "atomic_compare_and_swap<mode>_1_local"): New
	non-atomic, non-predicable define_insn, factored out of ...
	(define_insn "atomic_compare_and_swap<mode>_1"): ... here.
	Make predicable again.
	(define_expand "atomic_compare_and_swap<mode>"): Use
	atomic_compare_and_swap<mode>_1_local.

gcc/testsuite/ChangeLog:

2022-02-04  Tom de Vries  <tdevries@suse.de>

	PR target/104364
	* gcc.target/nvptx/softstack-2.c: New test.
	* gcc.target/nvptx/uniform-simt-1.c: New test.