Skip to content

Pull requests: NVlabs/cuda-oxide

Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort

Pull requests list

Report the shared cache in doctor
#447 opened Jul 22, 2026 by alejandro-soto-franco Contributor Loading…
4 of 5 tasks
Publish the backend to the shared cache on setup
#445 opened Jul 22, 2026 by alejandro-soto-franco Contributor Loading…
4 of 5 tasks
Make generated intrinsic checks warning-free
#442 opened Jul 21, 2026 by uurl Contributor Loading…
Emit CUDA diagnostics for gpu_assert! messages
#440 opened Jul 21, 2026 by uurl Contributor Loading…
9 tasks
Translate CopyForDeref as a place read
#438 opened Jul 21, 2026 by uurl Contributor Loading…
Test unsupported CheckedBinaryOp rejection
#436 opened Jul 21, 2026 by uurl Contributor Loading…
Clarify unsupported backend compilation
#434 opened Jul 21, 2026 by uurl Contributor Loading…
Clarify ConstantMemory::UNINIT initialization semantics
#432 opened Jul 21, 2026 by uurl Contributor Loading…
Fix Miri handling of nonzero program exit codes
#430 opened Jul 21, 2026 by uurl Contributor Loading…
Avoid duplicate local traversal in PlaceGraph::exit_fn
#428 opened Jul 21, 2026 by uurl Contributor Loading…
Remove stale Literal::ty TODO
#426 opened Jul 20, 2026 by uurl Contributor Loading…
2 tasks
Use HashSet membership in overlap checks
#425 opened Jul 20, 2026 by uurl Contributor Loading…
Reuse primitive integer type IDs in generation
#423 opened Jul 20, 2026 by uurl Contributor Loading…
Mark async launch trybuild stubs as unreachable
#421 opened Jul 20, 2026 by uurl Contributor Loading…
Clean up unsafe launch compile-fail fixture
#419 opened Jul 20, 2026 by uurl Contributor Loading…
fix(mir): keep small runtime-indexed arrays in SSA bug Something isn't working build-related Build scripts, toolchain discovery, or compilation setup codegen Device code-generation pipeline (Rust MIR to IR to PTX) enhancement New feature or request IR-lowering Lowering between dialects (dialect-mir to LLVM dialect) on-hold Paused: valid but deferred until a prerequisite decision or dependency resolves perf Performance of generated code or of the compiler itself
#398 opened Jul 13, 2026 by niklebedenko Contributor Draft
fix(mir-importer): read aggregate constant fields at their layout offsets bug Something isn't working codegen Device code-generation pipeline (Rust MIR to IR to PTX) IR-lowering Lowering between dialects (dialect-mir to LLVM dialect) miscompile Produces incorrect PTX/IR (wrong generated code) on-hold Paused: valid but deferred until a prerequisite decision or dependency resolves tests Adds or improves test coverage
#394 opened Jul 13, 2026 by alejandro-soto-franco Contributor Loading…
fix(mir-importer): load DisjointSlice through &self before extracting len bug Something isn't working codegen Device code-generation pipeline (Rust MIR to IR to PTX) examples Example kernels and host harnesses under crates/rustc-codegen-cuda/examples IR-lowering Lowering between dialects (dialect-mir to LLVM dialect) maintainer-owned tests Adds or improves test coverage
#392 opened Jul 13, 2026 by SomeB1oody Contributor Loading…
5 tasks done
fix(mir-lower): keep scalar float math on the LLVM-to-PTX path enhancement New feature or request intrinsics Device intrinsics and libdevice math mappings IR-lowering Lowering between dialects (dialect-mir to LLVM dialect) on-hold Paused: valid but deferred until a prerequisite decision or dependency resolves perf Performance of generated code or of the compiler itself
#391 opened Jul 13, 2026 by niklebedenko Contributor Loading…
6 tasks done
fix(cuda-host): accept CUDA-specific cubin ELF versions build-related Build scripts, toolchain discovery, or compilation setup host-apis Host-side runtime APIs (cuda-host, cuda-core, cuda-async) on-hold Paused: valid but deferred until a prerequisite decision or dependency resolves perf Performance of generated code or of the compiler itself
#389 opened Jul 12, 2026 by niklebedenko Contributor Loading…
5 tasks done
fix(ptx): internalize non-root device helpers codegen Device code-generation pipeline (Rust MIR to IR to PTX) llvm-export Textual LLVM/NVVM IR exporter (llvm-export crate) on-hold Paused: valid but deferred until a prerequisite decision or dependency resolves perf Performance of generated code or of the compiler itself tests Adds or improves test coverage
#387 opened Jul 12, 2026 by niklebedenko Contributor Loading…
5 tasks done
fix(codegen): prune monomorphization-dead MIR branches bug Something isn't working codegen Device code-generation pipeline (Rust MIR to IR to PTX) examples Example kernels and host harnesses under crates/rustc-codegen-cuda/examples IR-lowering Lowering between dialects (dialect-mir to LLVM dialect) maintainer-owned tests Adds or improves test coverage
#385 opened Jul 12, 2026 by niklebedenko Contributor Loading…
4 tasks done
fix(mir-importer): lower tuple array constants with rustc layout bug Something isn't working codegen Device code-generation pipeline (Rust MIR to IR to PTX) examples Example kernels and host harnesses under crates/rustc-codegen-cuda/examples IR-lowering Lowering between dialects (dialect-mir to LLVM dialect) maintainer-owned tests Adds or improves test coverage
#383 opened Jul 12, 2026 by niklebedenko Contributor Loading…
4 tasks done
ProTip! Mix and match filters to narrow down what you’re looking for.