nvptx: fix _syncthreads to use unaligned barrier

* Deprecate _syncthreads (the CUDA name) in favor of new
_barrier_sync (NVPTX name barrier.sync).

* The: barrier.sync instruction is equivalent to barrier.sync.aligned
prior to sm_70, and will lead to errors/deadlock if passes (such as MIR
JumpThreading) lose the aligned property.
rust-lang/rust#137086
https://docs.nvidia.com/cuda/parallel-thread-execution/index.html#parallel-synchronization-and-communication-instructions-bar

* Since: MIR does not currently have a way to apply something like
LLVM's convergent
attribute (https://llvm.org/docs/ConvergentOperations.html), we cannot
prevent loss of alignment, and thus we require target feature sm_70.

Author: jedbrown

crates/core_arch/src/nvptx/mod.rs

@@ -20,8 +20,8 @@ pub use packed::*;
 
 #[allow(improper_ctypes)]
 unsafe extern "C" {
-    #[link_name = "llvm.nvvm.barrier0"]
-    fn syncthreads() -> ();
+    #[link_name = "llvm.nvvm.barrier.sync"]
+    fn barrier_sync(_: u32) -> ();
     #[link_name = "llvm.nvvm.read.ptx.sreg.ntid.x"]
     fn block_dim_x() -> i32;
     #[link_name = "llvm.nvvm.read.ptx.sreg.ntid.y"]
@@ -48,11 +48,46 @@ unsafe extern "C" {
     fn thread_idx_z() -> i32;
 }
 
+/// Synchronizes all threads in the block.
+///
+/// The argument `a` is a logical barrier resource with value `0` through `15`.
+///
+/// This does not require textual alignment, so the following code is valid.
+///
+/// ```
+/// if tid % 2 == 0 {
+///     shared[tid] *= 2;
+///     _barrier_sync(0);
+///     myval += shared[tid + 1];
+/// } else {
+///     shared[tid] *= 4;
+///     _barrier_sync(0);
+/// }
+/// ```
+///
+/// This intrinsic has different execution semantics prior to `sm_70`, and thus
+/// it requires the `sm_70` target feature.
+///
+/// TODO: The more restrictive "aligned" semantics of
+/// `llvm.nvvm.barrier.sync.aligned` are [currently
+/// miscompiled](https://github.com/rust-lang/rust/issues/137086) due to MIR
+/// JumpThreading and lack of `convergent` attribute propagated to LLVM. Once
+/// resolved, this intrinsic should be exposed at all target features
+///
+#[inline]
+#[target_feature(enable = "sm_70")]
+#[unstable(feature = "stdarch_nvptx", issue = "111199")]
+pub unsafe fn _barrier_sync(a: u32) -> () {
+    barrier_sync(a)
+}
+
 /// Synchronizes all threads in the block.
 #[inline]
+#[target_feature(enable = "sm_70")]
 #[unstable(feature = "stdarch_nvptx", issue = "111199")]
+#[deprecated(since = "1.87.0", note = "use _barrier_sync(0)")]
 pub unsafe fn _syncthreads() -> () {
-    syncthreads()
+    _barrier_sync(0)
 }
 
 /// x-th thread-block dimension.