[pull] main from Rust-GPU:main

.github/workflows/container_images.yml

@@ -7,6 +7,8 @@ on:
       - ".github/workflows/container_images.yml"
       - "container/**"
   push:
+    branches:
+      - main
     paths:
       - ".github/workflows/container_images.yml"
       - "container/**"
@@ -162,4 +164,4 @@ jobs:
             $(printf '${{ env.REGISTRY }}/${{ matrix.variance.image }}@sha256:%s ' *)
       - name: Inspect image
         run: |
-          docker buildx imagetools inspect ${{ env.REGISTRY }}/${{ matrix.variance.image }}:${{ steps.meta.outputs.version }}
+          docker buildx imagetools inspect ${{ env.REGISTRY }}/${{ matrix.variance.image }}:${{ steps.meta.outputs.version }}

.github/workflows/deploy_guide.yml

@@ -12,7 +12,6 @@ concurrency:
 jobs:
   deploy:
     # Only run on the main repository, not on forks
-    if: github.repository == 'rust-gpu/Rust-CUDA'
     runs-on: ubuntu-latest
     environment:
       name: github-pages

README.md

@@ -61,7 +61,7 @@ The current line-up of libraries is the following:
 - `cuda_std` for GPU-side functions and utilities, such as thread index queries, memory allocation, warp intrinsics, etc.
   - _Not_ a low level library, provides many utility functions to make it easier to write cleaner and more reliable GPU kernels.
   - Closely tied to `rustc_codegen_nvvm` which exposes GPU features through it internally.
-- [`cudnn`](https://github.com/Rust-GPU/Rust-CUDA/tree/master/crates/cudnn) for a collection of GPU-accelerated primitives for deep neural networks.
+- [`cudnn`](https://github.com/Rust-GPU/rust-cuda/tree/master/crates/cudnn) for a collection of GPU-accelerated primitives for deep neural networks.
 - `cust` for CPU-side CUDA features such as launching GPU kernels, GPU memory allocation, device queries, etc.
   - High level with features such as RAII and Rust Results that make it easier and cleaner to manage the interface to the GPU.
   - A high level wrapper for the CUDA Driver API, the lower level version of the more common CUDA Runtime API used from C++.
@@ -92,7 +92,7 @@ Other projects related to using Rust on the GPU:
 cargo build
 ```
 
-## Use Rust-CUDA in Container Environments
+## Use Rust CUDA in Container Environments
 
 The distribution related Dockerfile are located in `container` folder.
 Taking ubuntu 24.04 as an example, run the following command in repository root:

container/rockylinux9-cuda12/Dockerfile

@@ -72,8 +72,8 @@ RUN curl -sSf -L https://sh.rustup.rs | bash -s -- -y
 ENV PATH="/root/.cargo/bin:${PATH}"
 
 # Setup the workspace
-WORKDIR /data/Rust-CUDA
-RUN --mount=type=bind,source=rust-toolchain.toml,target=/data/Rust-CUDA/rust-toolchain.toml \
+WORKDIR /data/rust-cuda
+RUN --mount=type=bind,source=rust-toolchain.toml,target=/data/rust-cuda/rust-toolchain.toml \
     rustup show
 
 # Add nvvm to LD_LIBRARY_PATH.

container/ubuntu22-cuda11/Dockerfile

@@ -71,8 +71,8 @@ RUN curl -sSf -L https://sh.rustup.rs | bash -s -- -y
 ENV PATH="/root/.cargo/bin:${PATH}"
 
 # Setup the workspace
-WORKDIR /data/Rust-CUDA
-RUN --mount=type=bind,source=rust-toolchain.toml,target=/data/Rust-CUDA/rust-toolchain.toml \
+WORKDIR /data/rust-cuda
+RUN --mount=type=bind,source=rust-toolchain.toml,target=/data/rust-cuda/rust-toolchain.toml \
     rustup show
 
 # Add nvvm to LD_LIBRARY_PATH.

container/ubuntu22-cuda12/Dockerfile

@@ -71,8 +71,8 @@ RUN curl -sSf -L https://sh.rustup.rs | bash -s -- -y
 ENV PATH="/root/.cargo/bin:${PATH}"
 
 # Setup the workspace
-WORKDIR /data/Rust-CUDA
-RUN --mount=type=bind,source=rust-toolchain.toml,target=/data/Rust-CUDA/rust-toolchain.toml \
+WORKDIR /data/rust-cuda
+RUN --mount=type=bind,source=rust-toolchain.toml,target=/data/rust-cuda/rust-toolchain.toml \
     rustup show
 
 # Add nvvm to LD_LIBRARY_PATH.

container/ubuntu24-cuda12/Dockerfile

@@ -71,8 +71,8 @@ RUN curl -sSf -L https://sh.rustup.rs | bash -s -- -y
 ENV PATH="/root/.cargo/bin:${PATH}"
 
 # Setup the workspace
-WORKDIR /data/Rust-CUDA
-RUN --mount=type=bind,source=rust-toolchain.toml,target=/data/Rust-CUDA/rust-toolchain.toml \
+WORKDIR /data/rust-cuda
+RUN --mount=type=bind,source=rust-toolchain.toml,target=/data/rust-cuda/rust-toolchain.toml \
     rustup show
 
 # Add nvvm to LD_LIBRARY_PATH.

crates/blastoff/Cargo.toml

@@ -3,7 +3,7 @@ name = "blastoff"
 version = "0.1.0"
 edition = "2021"
 authors = ["Riccardo D'Ambrosio <rdambrosio016@gmail.com>"]
-repository = "https://github.com/Rust-GPU/Rust-CUDA"
+repository = "https://github.com/Rust-GPU/rust-cuda"
 
 [dependencies]
 bitflags = "2.8"

crates/cuda_builder/Cargo.toml

@@ -5,7 +5,7 @@ edition = "2021"
 authors = ["Riccardo D'Ambrosio <rdambrosio016@gmail.com>", "The rust-gpu Authors"]
 license = "MIT OR Apache-2.0"
 description = "Builder for easily building rustc_codegen_nvvm crates"
-repository = "https://github.com/Rust-GPU/Rust-CUDA"
+repository = "https://github.com/Rust-GPU/rust-cuda"
 readme = "../../README.md"
 
 [dependencies]

crates/cuda_std/Cargo.toml

@@ -4,7 +4,7 @@ version = "0.2.2"
 edition = "2018"
 license = "MIT OR Apache-2.0"
 description = "Standard library for CUDA with rustc_codegen_nvvm"
-repository = "https://github.com/Rust-GPU/Rust-CUDA"
+repository = "https://github.com/Rust-GPU/rust-cuda"
 readme = "../../README.md"
 
 [dependencies]

crates/cuda_std_macros/Cargo.toml

@@ -4,7 +4,7 @@ version = "0.2.0"
 edition = "2018"
 license = "MIT OR Apache-2.0"
 description = "Macros for cuda_std"
-repository = "https://github.com/Rust-GPU/Rust-CUDA"
+repository = "https://github.com/Rust-GPU/rust-cuda"
 readme = "../../README.md"
 
 [lib]

crates/cudnn-sys/Cargo.toml

@@ -3,7 +3,7 @@ name = "cudnn-sys"
 version = "0.1.0"
 edition = "2024"
 license = "MIT OR Apache-2.0"
-repository = "https://github.com/Rust-GPU/Rust-CUDA"
+repository = "https://github.com/Rust-GPU/rust-cuda"
 readme = "../../README.md"
 links = "cudnn"
 build = "build/main.rs"

crates/cust/CHANGELOG.md

@@ -145,7 +145,7 @@ it much easier to write multigpu code. The CUDA API is fully thread-safe except
 - Added `MemoryAdvise::advise_read_mostly`.
 - Added `MemoryAdvise::preferred_location` and `MemoryAdvise::unset_preferred_location`.
 Note that advising APIs are only present on high end GPUs such as V100s.
-- `StreamFlags::NON_BLOCKING` has been temporarily disabled because of [soundness concerns](https://github.com/Rust-GPU/Rust-CUDA/issues/15).
+- `StreamFlags::NON_BLOCKING` has been temporarily disabled because of [soundness concerns](https://github.com/Rust-GPU/rust-cuda/issues/15).
 
 ## 0.2.0 - 11/26/21
 

crates/cust/Cargo.toml

@@ -9,7 +9,7 @@ authors = [
 edition = "2021"
 license = "MIT OR Apache-2.0"
 description = "High level bindings to the CUDA Driver API"
-repository = "https://github.com/Rust-GPU/Rust-CUDA"
+repository = "https://github.com/Rust-GPU/rust-cuda"
 readme = "../../README.md"
 
 [dependencies]

crates/cust/src/stream.rs

@@ -30,7 +30,7 @@ bitflags::bitflags! {
 
         /// This stream does not synchronize with the NULL stream.
         ///
-        /// **Note: this flag has been temporarily disabled because of [soundness concerns](https://github.com/Rust-GPU/Rust-CUDA/issues/15)**
+        /// **Note: this flag has been temporarily disabled because of [soundness concerns](https://github.com/Rust-GPU/rust-cuda/issues/15)**
         ///
         /// Note that the name is chosen to correspond to CUDA documentation, but is nevertheless
         /// misleading. All work within a single stream is ordered and asynchronous regardless
@@ -93,7 +93,7 @@ impl Stream {
     /// # }
     /// ```
     pub fn new(mut flags: StreamFlags, priority: Option<i32>) -> CudaResult<Self> {
-        // NOTE(RDambrosio016): See https://github.com/Rust-GPU/Rust-CUDA/issues/15
+        // NOTE(RDambrosio016): See https://github.com/Rust-GPU/rust-cuda/issues/15
         flags.remove(StreamFlags::NON_BLOCKING);
         unsafe {
             let mut stream = Stream {

crates/cust_core/Cargo.toml

@@ -4,7 +4,7 @@ version = "0.1.1"
 edition = "2021"
 license = "MIT OR Apache-2.0"
 description = "Core library for cust that can be shared across CPU and GPU"
-repository = "https://github.com/Rust-GPU/Rust-CUDA"
+repository = "https://github.com/Rust-GPU/rust-cuda"
 readme = "../../README.md"
 
 [dependencies]

crates/cust_derive/Cargo.toml

@@ -5,7 +5,7 @@ authors = ["Brook Heisler <brookheisler@gmail.com>", "Riccardo D'Ambrosio <rdamb
 edition = "2018"
 license = "MIT OR Apache-2.0"
 description = "Macros for cust"
-repository = "https://github.com/Rust-GPU/Rust-CUDA"
+repository = "https://github.com/Rust-GPU/rust-cuda"
 readme = "../../README.md"
 
 [lib]

crates/cust_raw/Cargo.toml

@@ -4,7 +4,7 @@ version = "0.11.3"
 edition = "2021"
 license = "MIT OR Apache-2.0"
 description = "Low level bindings to the CUDA Driver API"
-repository = "https://github.com/Rust-GPU/Rust-CUDA"
+repository = "https://github.com/Rust-GPU/rust-cuda"
 readme = "../../README.md"
 links = "cuda"
 build = "build/main.rs"

crates/gpu_rand/Cargo.toml

@@ -5,7 +5,7 @@ authors = ["The Rand Project Developers", "The Rust CUDA Project Developers"]
 license = "MIT OR Apache-2.0"
 edition = "2021"
 description = "GPU-friendly random number generators for the Rust CUDA Project"
-repository = "https://github.com/Rust-GPU/Rust-CUDA"
+repository = "https://github.com/Rust-GPU/rust-cuda"
 readme = "../../README.md"
 
 [dependencies]

crates/nvvm/Cargo.toml

@@ -5,7 +5,7 @@ authors = ["Riccardo D'Ambrosio <rdambrosio016@gmail.com>"]
 edition = "2018"
 license = "MIT OR Apache-2.0"
 description = "High level bindings to libnvvm"
-repository = "https://github.com/Rust-GPU/Rust-CUDA"
+repository = "https://github.com/Rust-GPU/rust-cuda"
 readme = "../../README.md"
 
 [dependencies]

crates/optix-sys/Cargo.toml

@@ -3,7 +3,7 @@ name = "optix-sys"
 version = "0.1.0"
 edition = "2024"
 license = "MIT OR Apache-2.0"
-repository = "https://github.com/Rust-GPU/Rust-CUDA"
+repository = "https://github.com/Rust-GPU/rust-cuda"
 readme = "../../README.md"
 links = "optix"
 build = "build/main.rs"

crates/optix/Cargo.toml

@@ -3,7 +3,7 @@ name = "optix"
 version = "0.1.0"
 edition = "2021"
 license = "MIT OR Apache-2.0"
-repository = "https://github.com/Rust-GPU/Rust-CUDA"
+repository = "https://github.com/Rust-GPU/rust-cuda"
 readme = "../../README.md"
 authors = ["Anders Langlands <anderslanglands@gmail.com>", "Riccardo D'Ambrosio <rdambrosio016@gmail.com>"]
 

crates/optix_device_macros/Cargo.toml

@@ -4,7 +4,7 @@ version = "0.1.0"
 edition = "2018"
 license = "MIT OR Apache-2.0"
 description = "Macros for optix_device"
-repository = "https://github.com/Rust-GPU/Rust-CUDA"
+repository = "https://github.com/Rust-GPU/rust-cuda"
 readme = "../../README.md"
 
 [lib]

crates/ptx/Cargo.toml

@@ -4,7 +4,7 @@ version = "0.1.0"
 edition = "2018"
 license = "MIT OR Apache-2.0"
 description = "PTX parser and analyzer"
-repository = "https://github.com/Rust-GPU/Rust-CUDA"
+repository = "https://github.com/Rust-GPU/rust-cuda"
 readme = "../../README.md"
 
 [dependencies]

crates/ptx_compiler/Cargo.toml

@@ -4,7 +4,7 @@ version = "0.1.1"
 edition = "2021"
 license = "MIT OR Apache-2.0"
 description = "High level bindings to CUDA's ptx compilation APIs"
-repository = "https://github.com/Rust-GPU/Rust-CUDA"
+repository = "https://github.com/Rust-GPU/rust-cuda"
 readme = "../../README.md"
 
 [dependencies]

crates/ptx_compiler/src/lib.rs

@@ -102,6 +102,7 @@ impl CompilerFailure {
                 .to_result()?;
             let size = size.assume_init();
             let mut vec = Vec::with_capacity(size);
+            #[allow(clippy::unnecessary_cast)]
             nvptx_compiler_sys::nvPTXCompilerGetErrorLog(
                 self.handle,
                 vec.as_mut_ptr() as *mut c_char,
@@ -138,6 +139,7 @@ impl CompiledProgram {
                 .to_result()?;
             let size = size.assume_init();
             let mut vec = Vec::with_capacity(size);
+            #[allow(clippy::unnecessary_cast)]
             nvptx_compiler_sys::nvPTXCompilerGetInfoLog(
                 self.handle,
                 vec.as_mut_ptr() as *mut c_char,

crates/rustc_codegen_nvvm/Cargo.toml

@@ -8,7 +8,7 @@ authors = [
 edition = "2024"
 license = "MIT OR Apache-2.0"
 description = "A codegen backend for Rustc which targets the libnvvm CUDA library"
-repository = "https://github.com/Rust-GPU/Rust-CUDA"
+repository = "https://github.com/Rust-GPU/rust-cuda"
 readme = "../../README.md"
 
 [lib]