Support async CUDA operations

.github/workflows/ci.yml

@@ -23,6 +23,16 @@ jobs:
         rust: [nightly]
 
     steps:
+      - name: Install CUDA
+        run: |
+          wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu1804/x86_64/cuda-ubuntu1804.pin
+          sudo mv cuda-ubuntu1804.pin /etc/apt/preferences.d/cuda-repository-pin-600
+          curl -L -O https://developer.download.nvidia.com/compute/cuda/repos/ubuntu1804/x86_64/cuda-keyring_1.0-1_all.deb
+          sudo dpkg -i cuda-keyring_1.0-1_all.deb
+          sudo add-apt-repository "deb https://developer.download.nvidia.com/compute/cuda/repos/ubuntu1804/x86_64/ /"
+          sudo apt-get update -q
+          sudo apt-get install cuda -y --no-install-recommends
+
       - name: Checkout the Repository
         uses: actions/checkout@v2
 
@@ -40,53 +50,26 @@ jobs:
           sudo ./llvm.sh $(rustc --version -v | grep -oP "LLVM version: \K\d+")
           rm llvm.sh
           cargo install rust-ptx-linker --git https://github.com/juntyr/rust-ptx-linker --force
+
+      - name: Install cargo-hack
+        uses: taiki-e/install-action@cargo-hack
 
-      - name: Check without features on CPU
-        run: |
-          cargo check
-
-      - name: Check with alloc feature on CPU
-        run: |
-          cargo check \
-            --features alloc
-
-      - name: Check with derive feature on CPU
-        run: |
-          cargo check \
-            --features derive
-
-      - name: Check with host feature on CPU
-        run: |
-          cargo check \
-            --features host
-
-      - name: Check with host,derive,alloc features on CPU
+      - name: Check feature powerset on the CPU
         run: |
-          cargo check \
-            --features host,derive,alloc
+          cargo hack check --feature-powerset --optional-deps \
+            --skip device \
+            --keep-going
 
-      - name: Check without features on CUDA
+      - name: Check feature powerset on CUDA
         run: |
-          cargo check \
+          cargo hack check --feature-powerset --optional-deps \
+            --skip host \
+            --keep-going \
             --target nvptx64-nvidia-cuda
 
-      - name: Check with alloc feature on CUDA
-        run: |
-          cargo check \
-            --target nvptx64-nvidia-cuda \
-            --features alloc
-
-      - name: Check with derive feature on CUDA
-        run: |
-          cargo check \
-            --target nvptx64-nvidia-cuda \
-            --features derive
-
       - name: Check all workspace targets
         run: |
-          cargo check \
-            --workspace \
-            --all-targets
+          cargo check --workspace --all-targets
 
   test:
     name: Test Suite
@@ -157,6 +140,16 @@ jobs:
         rust: [nightly]
 
     steps:
+      - name: Install CUDA
+        run: |
+          wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu1804/x86_64/cuda-ubuntu1804.pin
+          sudo mv cuda-ubuntu1804.pin /etc/apt/preferences.d/cuda-repository-pin-600
+          curl -L -O https://developer.download.nvidia.com/compute/cuda/repos/ubuntu1804/x86_64/cuda-keyring_1.0-1_all.deb
+          sudo dpkg -i cuda-keyring_1.0-1_all.deb
+          sudo add-apt-repository "deb https://developer.download.nvidia.com/compute/cuda/repos/ubuntu1804/x86_64/ /"
+          sudo apt-get update -q
+          sudo apt-get install cuda -y --no-install-recommends
+
       - name: Checkout the Repository
         uses: actions/checkout@v2
 
@@ -176,58 +169,24 @@ jobs:
           rm llvm.sh
           cargo install rust-ptx-linker --git https://github.com/juntyr/rust-ptx-linker --force
 
-      - name: Check the code style without features on CPU
-        run: |
-          cargo clippy \
-            -- -D warnings
-
-      - name: Check the code style with alloc feature on CPU
-        run: |
-          cargo clippy \
-            --features alloc \
-            -- -D warnings
-
-      - name: Check the code style with derive feature on CPU
-        run: |
-          cargo clippy \
-            --features derive \
-            -- -D warnings
-
-      - name: Check the code style with host feature on CPU
-        run: |
-          cargo clippy \
-            --features host \
-            -- -D warnings
-
-      - name: Check the code style with host,derive,alloc features on CPU
-        run: |
-          cargo clippy \
-            --features host,derive,alloc \
-            -- -D warnings
-
-      - name: Check the code style without features on CUDA
-        run: |
-          cargo clippy \
-            --target nvptx64-nvidia-cuda \
-            -- -D warnings
+      - name: Install cargo-hack
+        uses: taiki-e/install-action@cargo-hack
 
-      - name: Check the code style with alloc feature on CUDA
+      - name: Check feature powerset on the CPU
         run: |
-          cargo clippy \
-            --target nvptx64-nvidia-cuda \
-            --features alloc \
+          cargo hack clippy --feature-powerset --optional-deps \
+            --skip device \
+            --keep-going \
             -- -D warnings
-
-      - name: Check the code style with derive feature on CUDA
+      
+      - name: Check feature powerset on CUDA
         run: |
-          cargo clippy \
+          cargo hack clippy --feature-powerset --optional-deps \
+            --skip host \
+            --keep-going \
             --target nvptx64-nvidia-cuda \
-            --features derive \
             -- -D warnings
 
-      - name: Check the code style for all workspace targets
+      - name: Check all workspace targets
         run: |
-          cargo clippy \
-            --workspace \
-            --all-targets \
-            -- -D warnings
+          cargo clippy --workspace --all-targets -- -D warnings

.github/workflows/coverage.yml

@@ -59,8 +59,8 @@ jobs:
           ./grcov . -s . --binary-path ./target/debug/deps \
             -t lcov -o coverage.lcov --branch \
             --keep-only "src/*" \
-            --keep-only "rust-cuda-ptx-jit/*" \
             --keep-only "rust-cuda-derive/*" \
+            --keep-only "rust-cuda-kernel/*" \
             --ignore-not-existing \
             --excl-line GRCOV_EXCL_LINE \
             --excl-start GRCOV_EXCL_START \

.github/workflows/rustdoc.yml

@@ -28,6 +28,8 @@ jobs:
         run: |
           RUSTDOCFLAGS="\
             --enable-index-page \
+            --extern-html-root-url const_type_layout=https://docs.rs/const-type-layout/0.2.1/ \
+            --extern-html-root-url final=https://docs.rs/final/0.1.1/ \
             --extern-html-root-url rustacuda=https://docs.rs/rustacuda/0.1.3/ \
             --extern-html-root-url rustacuda_core=https://docs.rs/rustacuda_core/0.1.2/ \
             --extern-html-root-url rustacuda_derive=https://docs.rs/rustacuda_derive/0.1.2/ \

.gitignore

@@ -8,3 +8,6 @@ Cargo.lock
 
 # These are backup files generated by rustfmt
 **/*.rs.bk
+
+# cargo expand dev output files
+**/expanded.rs

.vscode/settings.json

@@ -4,5 +4,11 @@
     "rust-analyzer.updates.askBeforeDownload": false,
     "rust-analyzer.checkOnSave.command": "reap-clippy",
     "rust-analyzer.cargo.allFeatures": false,
-    "rust-analyzer.cargo.features": ["alloc", "derive", "host"],
+    "rust-analyzer.cargo.features": [
+        "derive",
+        "final",
+        "host",
+        "kernel"
+    ],
+    "rust-analyzer.showUnlinkedFileNotification": false,
 }

Cargo.toml

@@ -1,10 +1,10 @@
 [workspace]
 members = [
-    ".", "rust-cuda-derive", "rust-cuda-ptx-jit",
-    "examples/single-source", "examples/derive",
+    ".", "rust-cuda-derive", "rust-cuda-kernel",
+    "examples/derive", "examples/print", "examples/single-source",
 ]
 default-members = [
-    ".", "rust-cuda-derive", "rust-cuda-ptx-jit"
+    ".", "rust-cuda-derive", "rust-cuda-kernel",
 ]
 
 [package]
@@ -13,29 +13,32 @@ version = "0.1.0"
 authors = ["Juniper Tyree <[email protected]>"]
 license = "MIT OR Apache-2.0"
 edition = "2021"
-rust-version = "1.75" # nightly
+rust-version = "1.77" # nightly
 
 # See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
 
 [features]
 default = []
-alloc = ["hashbrown"]
-host = ["rustacuda", "rust-cuda-ptx-jit/host"]
-derive = ["rustacuda_derive", "rust-cuda-derive"]
+derive = ["dep:rustacuda_derive", "dep:rust-cuda-derive"]
+device = []
+final = ["dep:final"]
+host = ["dep:rustacuda", "dep:regex", "dep:oneshot", "dep:safer_owning_ref"]
+kernel = ["dep:rust-cuda-kernel"]
 
 [dependencies]
-rustacuda_core = "0.1.2"
+rustacuda_core = { git = "https://github.com/juntyr/RustaCUDA", rev = "c6ea7cc" }
 
-rustacuda = { version = "0.1.3", optional = true }
-rustacuda_derive = { version = "0.1.2", optional = true }
+rustacuda = { git = "https://github.com/juntyr/RustaCUDA", rev = "c6ea7cc", optional = true }
+rustacuda_derive = { git = "https://github.com/juntyr/RustaCUDA", rev = "c6ea7cc", optional = true }
 
-const-type-layout = { version = "0.2.0", features = ["derive"] }
+regex = { version = "1.10", optional = true }
 
-final = "0.1.1"
-hashbrown = { version = "0.14", default-features = false, features = ["inline-more"], optional = true }
+const-type-layout = { git = "https://github.com/juntyr/const-type-layout", branch = "compress", features = ["derive"] }
 
-rust-cuda-derive = { path = "rust-cuda-derive", optional = true }
-rust-cuda-ptx-jit = { path = "rust-cuda-ptx-jit" }
+safer_owning_ref = { version = "0.5", optional = true }
+oneshot = { version = "0.1", optional = true, features = ["std", "async"] }
+
+final = { version = "0.1.1", optional = true }
 
-[dev-dependencies]
-hashbrown = { version = "0.14", default-features = false, features = ["inline-more"] }
+rust-cuda-derive = { path = "rust-cuda-derive", optional = true }
+rust-cuda-kernel = { path = "rust-cuda-kernel", optional = true }

README.md

@@ -1,8 +1,11 @@
-# rust-cuda   [![CI Status]][workflow] [![Rust Doc]][docs] [![License Status]][fossa] [![Code Coverage]][codecov] [![Gitpod Ready-to-Code]][gitpod]
+# rust-cuda   [![CI Status]][workflow] [![MSRV]][repo] [![Rust Doc]][docs] [![License Status]][fossa] [![Code Coverage]][codecov] [![Gitpod Ready-to-Code]][gitpod]
 
 [CI Status]: https://img.shields.io/github/actions/workflow/status/juntyr/rust-cuda/ci.yml?branch=main
 [workflow]: https://github.com/juntyr/rust-cuda/actions/workflows/ci.yml?query=branch%3Amain
 
+[MSRV]: https://img.shields.io/badge/MSRV-1.77.0--nightly-orange
+[repo]: https://github.com/juntyr/rust-cuda
+
 [Rust Doc]: https://img.shields.io/badge/docs-main-blue
 [docs]: https://juntyr.github.io/rust-cuda/
 

examples/derive/Cargo.toml

@@ -1,12 +1,11 @@
 [package]
 name = "derive"
 version = "0.1.0"
-authors = ["Juniper Tyree <juniper.langenstein@helsinki.fi>"]
+authors = ["Juniper Tyree <juniper.tyree@helsinki.fi>"]
 license = "MIT OR Apache-2.0"
 edition = "2021"
 
 # See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
 
 [dependencies]
-const-type-layout = { version = "0.2.0" }
-rust-cuda = { path = "../../", features = ["derive", "host"] }
+rc = { package = "rust-cuda", path = "../../", features = ["derive", "host"] }

examples/derive/src/lib.rs

@@ -1,14 +1,15 @@
 #![deny(clippy::pedantic)]
 #![feature(const_type_name)]
-#![feature(offset_of)]
 
-#[derive(rust_cuda::common::LendRustToCuda)]
+#[derive(rc::lend::LendRustToCuda)]
+#[cuda(crate = "rc")]
 struct Inner<T: Copy> {
     #[cuda(embed)]
     inner: T,
 }
 
-#[derive(rust_cuda::common::LendRustToCuda)]
+#[derive(rc::lend::LendRustToCuda)]
+#[cuda(crate = "rc")]
 struct Outer<T: Copy> {
     #[cuda(embed)]
     inner: Inner<T>,

examples/print/.cargo/config.toml

@@ -0,0 +1,2 @@
+[target.nvptx64-nvidia-cuda]
+rustflags = ["-Clink-args=--arch sm_35", "-Clinker-plugin-lto", "-Ccodegen-units=1", "-Clink-arg=-O3", "-Clink-arg=--lto"]

examples/print/Cargo.toml

@@ -0,0 +1,14 @@
+[package]
+name = "print"
+version = "0.1.0"
+authors = ["Juniper Tyree <[email protected]>"]
+license = "MIT OR Apache-2.0"
+edition = "2021"
+
+# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
+
+[target.'cfg(target_os = "cuda")'.dependencies]
+rust-cuda = { path = "../../", features = ["kernel", "device"] }
+
+[target.'cfg(not(target_os = "cuda"))'.dependencies]
+rust-cuda = { path = "../../", features = ["kernel", "host"] }