Auto merge of rust-lang#57937 - denzp:nvptx, r=nagisa

NVPTX target specification

This change adds a built-in `nvptx64-nvidia-cuda` GPGPU no-std target specification and a basic PTX assembly smoke tests.

The approach is taken here and the target spec is based on `ptx-linker`, a project started about 1.5 years ago. Key feature: bitcode object files being linked with LTO into the final module on the linker's side.

Prior to this change, the linker used a `ld` linker-flavor, but I think, having the special CLI convention is a more reliable way.

Questions about further progress on reliable CUDA workflow with Rust:
1. Is it possible to create a test suite `codegen-asm` to verify end-to-end integration with LLVM backend?
1. How would it be better to organise no-std `compile-fail` tests: add `#![no_std]` where possible and mark others as `ignore-nvptx` directive, or alternatively, introduce `compile-fail-no-std` test suite?
1. Can we have the `ptx-linker` eventually be integrated as `rls` or `clippy`? Hopefully, this should allow to statically link against LLVM used in Rust and get rid of the [current hacky solution](https://github.com/denzp/rustc-llvm-proxy).
1. Am I missing some methods from `rustc_codegen_ssa::back::linker::Linker` that can be useful for bitcode-only linking?

Currently, there are no major public CUDA projects written in Rust I'm aware of, but I'm expecting to have a built-in target will create a solid foundation for further experiments and awesome crates.

Related to rust-lang#38789
Fixes rust-lang#38787
Fixes rust-lang#38786

Author: bors

.travis.yml

@@ -168,7 +168,7 @@ matrix:
       if: branch = auto
     - env: IMAGE=i686-gnu-nopt
       if: branch = auto
-    - env: IMAGE=wasm32-unknown
+    - env: IMAGE=test-various
       if: branch = auto
     - env: IMAGE=x86_64-gnu
       if: branch = auto

src/bootstrap/lib.rs

@@ -831,6 +831,7 @@ impl Build {
                   !target.contains("msvc") &&
                   !target.contains("emscripten") &&
                   !target.contains("wasm32") &&
+                  !target.contains("nvptx") &&
                   !target.contains("fuchsia") {
             Some(self.cc(target))
         } else {

src/bootstrap/sanity.rs

@@ -156,7 +156,7 @@ pub fn check(build: &mut Build) {
             panic!("the iOS target is only supported on macOS");
         }
 
-        if target.contains("-none-") {
+        if target.contains("-none-") || target.contains("nvptx") {
             if build.no_std(*target).is_none() {
                 let target = build.config.target_config.entry(target.clone())
                     .or_default();
@@ -165,7 +165,7 @@ pub fn check(build: &mut Build) {
             }
 
             if build.no_std(*target) == Some(false) {
-                panic!("All the *-none-* targets are no-std targets")
+                panic!("All the *-none-* and nvptx* targets are no-std targets")
             }
         }
 

src/ci/docker/dist-various-2/Dockerfile

@@ -70,6 +70,7 @@ ENV TARGETS=$TARGETS,x86_64-sun-solaris
 ENV TARGETS=$TARGETS,x86_64-unknown-linux-gnux32
 ENV TARGETS=$TARGETS,x86_64-unknown-cloudabi
 ENV TARGETS=$TARGETS,x86_64-fortanix-unknown-sgx
+ENV TARGETS=$TARGETS,nvptx64-nvidia-cuda
 
 ENV X86_FORTANIX_SGX_LIBS="/x86_64-fortanix-unknown-sgx/lib/"
 

src/ci/docker/wasm32-unknown/Dockerfile renamed to src/ci/docker/test-various/Dockerfile

@@ -13,14 +13,16 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
   gdb \
   xz-utils
 
+# FIXME: build the `ptx-linker` instead.
+RUN curl -sL https://github.com/denzp/rust-ptx-linker/releases/download/v0.9.0-alpha.2/rust-ptx-linker.linux64.tar.gz | \
+  tar -xzvC /usr/bin
+
 RUN curl -sL https://nodejs.org/dist/v9.2.0/node-v9.2.0-linux-x64.tar.xz | \
-    tar -xJ
+  tar -xJ
 
 COPY scripts/sccache.sh /scripts/
 RUN sh /scripts/sccache.sh
 
-ENV TARGETS=wasm32-unknown-unknown
-
 ENV RUST_CONFIGURE_ARGS \
   --set build.nodejs=/node-v9.2.0-linux-x64/bin/node \
   --set rust.lld
@@ -31,11 +33,18 @@ ENV RUST_CONFIGURE_ARGS \
 # other contexts as well
 ENV NO_DEBUG_ASSERTIONS=1
 
-ENV SCRIPT python2.7 /checkout/x.py test --target $TARGETS \
+ENV WASM_TARGETS=wasm32-unknown-unknown
+ENV WASM_SCRIPT python2.7 /checkout/x.py test --target $WASM_TARGETS \
   src/test/run-make \
   src/test/ui \
   src/test/run-pass \
   src/test/compile-fail \
   src/test/mir-opt \
   src/test/codegen-units \
-  src/libcore \
+  src/libcore
+
+ENV NVPTX_TARGETS=nvptx64-nvidia-cuda
+ENV NVPTX_SCRIPT python2.7 /checkout/x.py test --target $NVPTX_TARGETS \
+  src/test/run-make
+
+ENV SCRIPT $WASM_SCRIPT && $NVPTX_SCRIPT

src/librustc/ty/context.rs

@@ -1675,6 +1675,12 @@ impl<'a, 'gcx, 'tcx> TyCtxt<'a, 'gcx, 'tcx> {
         }
         false
     }
+
+    /// Determine whether identifiers in the assembly have strict naming rules.
+    /// Currently, only NVPTX* targets need it.
+    pub fn has_strict_asm_symbol_naming(&self) -> bool {
+        self.gcx.sess.target.target.arch.contains("nvptx")
+    }
 }
 
 impl<'a, 'tcx> TyCtxt<'a, 'tcx, 'tcx> {

src/librustc_codegen_ssa/back/link.rs

@@ -149,6 +149,7 @@ pub fn linker_and_flavor(sess: &Session) -> (PathBuf, LinkerFlavor) {
                 LinkerFlavor::Ld => "ld",
                 LinkerFlavor::Msvc => "link.exe",
                 LinkerFlavor::Lld(_) => "lld",
+                LinkerFlavor::PtxLinker => "rust-ptx-linker",
             }), flavor)),
             (Some(linker), None) => {
                 let stem = if linker.extension().and_then(|ext| ext.to_str()) == Some("exe") {

src/librustc_codegen_ssa/back/linker.rs

@@ -13,7 +13,7 @@ use rustc::hir::def_id::{LOCAL_CRATE, CrateNum};
 use rustc::middle::dependency_format::Linkage;
 use rustc::session::Session;
 use rustc::session::config::{self, CrateType, OptLevel, DebugInfo,
-                             CrossLangLto};
+                             CrossLangLto, Lto};
 use rustc::ty::TyCtxt;
 use rustc_target::spec::{LinkerFlavor, LldFlavor};
 use serialize::{json, Encoder};
@@ -83,6 +83,10 @@ impl LinkerInfo {
             LinkerFlavor::Lld(LldFlavor::Wasm) => {
                 Box::new(WasmLd::new(cmd, sess, self)) as Box<dyn Linker>
             }
+
+            LinkerFlavor::PtxLinker => {
+                Box::new(PtxLinker { cmd, sess }) as Box<dyn Linker>
+            }
         }
     }
 }
@@ -1080,3 +1084,129 @@ fn exported_symbols(tcx: TyCtxt, crate_type: CrateType) -> Vec<String> {
 
     symbols
 }
+
+/// Much simplified and explicit CLI for the NVPTX linker. The linker operates
+/// with bitcode and uses LLVM backend to generate a PTX assembly.
+pub struct PtxLinker<'a> {
+    cmd: Command,
+    sess: &'a Session,
+}
+
+impl<'a> Linker for PtxLinker<'a> {
+    fn link_rlib(&mut self, path: &Path) {
+        self.cmd.arg("--rlib").arg(path);
+    }
+
+    fn link_whole_rlib(&mut self, path: &Path) {
+        self.cmd.arg("--rlib").arg(path);
+    }
+
+    fn include_path(&mut self, path: &Path) {
+        self.cmd.arg("-L").arg(path);
+    }
+
+    fn debuginfo(&mut self) {
+        self.cmd.arg("--debug");
+    }
+
+    fn add_object(&mut self, path: &Path) {
+        self.cmd.arg("--bitcode").arg(path);
+    }
+
+    fn args(&mut self, args: &[String]) {
+        self.cmd.args(args);
+    }
+
+    fn optimize(&mut self) {
+        match self.sess.lto() {
+            Lto::Thin | Lto::Fat | Lto::ThinLocal => {
+                self.cmd.arg("-Olto");
+            },
+
+            Lto::No => { },
+        };
+    }
+
+    fn output_filename(&mut self, path: &Path) {
+        self.cmd.arg("-o").arg(path);
+    }
+
+    fn finalize(&mut self) -> Command {
+        // Provide the linker with fallback to internal `target-cpu`.
+        self.cmd.arg("--fallback-arch").arg(match self.sess.opts.cg.target_cpu {
+            Some(ref s) => s,
+            None => &self.sess.target.target.options.cpu
+        });
+
+        ::std::mem::replace(&mut self.cmd, Command::new(""))
+    }
+
+    fn link_dylib(&mut self, _lib: &str) {
+        panic!("external dylibs not supported")
+    }
+
+    fn link_rust_dylib(&mut self, _lib: &str, _path: &Path) {
+        panic!("external dylibs not supported")
+    }
+
+    fn link_staticlib(&mut self, _lib: &str) {
+        panic!("staticlibs not supported")
+    }
+
+    fn link_whole_staticlib(&mut self, _lib: &str, _search_path: &[PathBuf]) {
+        panic!("staticlibs not supported")
+    }
+
+    fn framework_path(&mut self, _path: &Path) {
+        panic!("frameworks not supported")
+    }
+
+    fn link_framework(&mut self, _framework: &str) {
+        panic!("frameworks not supported")
+    }
+
+    fn position_independent_executable(&mut self) {
+    }
+
+    fn full_relro(&mut self) {
+    }
+
+    fn partial_relro(&mut self) {
+    }
+
+    fn no_relro(&mut self) {
+    }
+
+    fn build_static_executable(&mut self) {
+    }
+
+    fn gc_sections(&mut self, _keep_metadata: bool) {
+    }
+
+    fn pgo_gen(&mut self) {
+    }
+
+    fn no_default_libraries(&mut self) {
+    }
+
+    fn build_dylib(&mut self, _out_filename: &Path) {
+    }
+
+    fn export_symbols(&mut self, _tmpdir: &Path, _crate_type: CrateType) {
+    }
+
+    fn subsystem(&mut self, _subsystem: &str) {
+    }
+
+    fn no_position_independent_executable(&mut self) {
+    }
+
+    fn group_start(&mut self) {
+    }
+
+    fn group_end(&mut self) {
+    }
+
+    fn cross_lang_lto(&mut self) {
+    }
+}

src/librustc_codegen_utils/lib.rs

@@ -12,6 +12,7 @@
 #![feature(nll)]
 #![allow(unused_attributes)]
 #![feature(rustc_diagnostic_macros)]
+#![feature(in_band_lifetimes)]
 
 #![recursion_limit="256"]