change the format of the linked issue number

[rust.git] / src / doc / unstable-book / src / abi-ptx.md

diff --git a/src/doc/unstable-book/src/abi-ptx.md b/src/doc/unstable-book/src/abi-ptx.md
index 9c1b8868aceb4bd5d208cf14691f4d781abd4874..0ded3ceeaef2ce9ea0457dc563aa53a0014b6737 100644 (file)
--- a/src/doc/unstable-book/src/abi-ptx.md
+++ b/src/doc/unstable-book/src/abi-ptx.md
@@ -1,5 +1,60 @@
 # `abi_ptx`
 
-The tracking issue for this feature is: None.
+The tracking issue for this feature is: [#38788]
+
+[#38788]: https://github.com/rust-lang/rust/issues/38788
 
 ------------------------
+
+When emitting PTX code, all vanilla Rust functions (`fn`) get translated to
+"device" functions. These functions are *not* callable from the host via the
+CUDA API so a crate with only device functions is not too useful!
+
+OTOH, "global" functions *can* be called by the host; you can think of them
+as the real public API of your crate. To produce a global function use the
+`"ptx-kernel"` ABI.
+
+<!-- NOTE(ignore) this example is specific to the nvptx targets -->
+
+``` rust,ignore
+#![feature(abi_ptx)]
+#![no_std]
+
+pub unsafe extern "ptx-kernel" fn global_function() {
+    device_function();
+}
+
+pub fn device_function() {
+    // ..
+}
+```
+
+``` text
+$ xargo rustc --target nvptx64-nvidia-cuda --release -- --emit=asm
+
+$ cat $(find -name '*.s')
+//
+// Generated by LLVM NVPTX Back-End
+//
+
+.version 3.2
+.target sm_20
+.address_size 64
+
+        // .globl       _ZN6kernel15global_function17h46111ebe6516b382E
+
+.visible .entry _ZN6kernel15global_function17h46111ebe6516b382E()
+{
+
+
+        ret;
+}
+
+        // .globl       _ZN6kernel15device_function17hd6a0e4993bbf3f78E
+.visible .func _ZN6kernel15device_function17hd6a0e4993bbf3f78E()
+{
+
+
+        ret;
+}
+```