CUDA on non-NVIDIA GPUs
Find a file
Violet 629158ce2c
Some checks failed
ZLUDA / Build (Linux) (push) Has been cancelled
ZLUDA / Build (Windows) (push) Has been cancelled
ZLUDA / Build AMD GPU unit tests (push) Has been cancelled
ZLUDA / Run AMD GPU unit tests (push) Has been cancelled
[CLEANUP] Rename refactored modules, update test golden files (#582)
* [CLEANUP] Rename refactored modules, update test golden files

* Update ptx/src/pass/mod.rs

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

---------

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2025-12-16 15:40:27 -08:00
.cargo Try to make ZLUDA more robust on Windows (#442) 2025-07-28 13:20:04 -07:00
.devcontainer Update devcontainer Dockerfile, bump CUDA version to 13, split cuDNN into v8 and v9 (#536) 2025-10-06 10:51:51 -07:00
.github Improve Windows loader (zluda.exe) (#550) 2025-12-08 21:03:14 -08:00
compiler Enable ROCm7 support (#579) 2025-12-15 14:01:53 -08:00
cuda_macros Improve Windows loader (zluda.exe) (#550) 2025-12-08 21:03:14 -08:00
cuda_types Improve Windows loader (zluda.exe) (#550) 2025-12-08 21:03:14 -08:00
dark_api Improve Windows loader (zluda.exe) (#550) 2025-12-08 21:03:14 -08:00
detours-sys Improve Windows loader (zluda.exe) (#550) 2025-12-08 21:03:14 -08:00
docs Improve Windows loader (zluda.exe) (#550) 2025-12-08 21:03:14 -08:00
ext Enable ROCm7 support (#579) 2025-12-15 14:01:53 -08:00
format Improve Windows loader (zluda.exe) (#550) 2025-12-08 21:03:14 -08:00
llvm_zluda Use LLVM for optimized i8 MMAs (#571) 2025-12-12 13:41:40 -08:00
ptx [CLEANUP] Rename refactored modules, update test golden files (#582) 2025-12-16 15:40:27 -08:00
ptx_parser Allow implicit conversion from vec to bit scalar for ld (#580) 2025-12-16 11:36:46 -08:00
ptx_parser_macros Add pass test mechanism for insert_implicit_conversions (#477) 2025-08-22 13:01:39 -07:00
ptx_parser_macros_impl Add pass test mechanism for insert_implicit_conversions (#477) 2025-08-22 13:01:39 -07:00
ptxas Add a precompilation tool (#558) 2025-11-25 09:34:30 -08:00
xtask Improve Windows loader (zluda.exe) (#550) 2025-12-08 21:03:14 -08:00
zluda Enable ROCm7 support (#579) 2025-12-15 14:01:53 -08:00
zluda_bindgen Enable ROCm7 support (#579) 2025-12-15 14:01:53 -08:00
zluda_blas Enable ROCm7 support (#579) 2025-12-15 14:01:53 -08:00
zluda_blaslt Improve Windows loader (zluda.exe) (#550) 2025-12-08 21:03:14 -08:00
zluda_cache Remove trailing whitespaces and add missing newlines at EOF (#530) 2025-10-03 11:52:18 -07:00
zluda_common Additional NVML functionality (#574) 2025-12-12 11:23:42 -08:00
zluda_dnn Implement functionality required by katago (#541) 2025-11-09 23:42:13 -08:00
zluda_dnn8 Enable ROCm7 support (#579) 2025-12-15 14:01:53 -08:00
zluda_dnn9 Enable ROCm7 support (#579) 2025-12-15 14:01:53 -08:00
zluda_fft Improve Windows loader (zluda.exe) (#550) 2025-12-08 21:03:14 -08:00
zluda_inject Improve Windows loader (zluda.exe) (#550) 2025-12-08 21:03:14 -08:00
zluda_ld Update devcontainer Dockerfile, bump CUDA version to 13, split cuDNN into v8 and v9 (#536) 2025-10-06 10:51:51 -07:00
zluda_ml Enable ROCm7 support (#579) 2025-12-15 14:01:53 -08:00
zluda_precompile Add a precompilation tool (#558) 2025-11-25 09:34:30 -08:00
zluda_redirect Improve Windows loader (zluda.exe) (#550) 2025-12-08 21:03:14 -08:00
zluda_sparse Improve Windows loader (zluda.exe) (#550) 2025-12-08 21:03:14 -08:00
zluda_trace Improve Windows loader (zluda.exe) (#550) 2025-12-08 21:03:14 -08:00
zluda_trace_blas Improve Windows loader (zluda.exe) (#550) 2025-12-08 21:03:14 -08:00
zluda_trace_blaslt Improve Windows loader (zluda.exe) (#550) 2025-12-08 21:03:14 -08:00
zluda_trace_common Improve Windows loader (zluda.exe) (#550) 2025-12-08 21:03:14 -08:00
zluda_trace_dnn8 Improve Windows loader (zluda.exe) (#550) 2025-12-08 21:03:14 -08:00
zluda_trace_dnn9 Improve Windows loader (zluda.exe) (#550) 2025-12-08 21:03:14 -08:00
zluda_trace_fft Improve Windows loader (zluda.exe) (#550) 2025-12-08 21:03:14 -08:00
zluda_trace_nvml Improve Windows loader (zluda.exe) (#550) 2025-12-08 21:03:14 -08:00
zluda_trace_sparse Improve Windows loader (zluda.exe) (#550) 2025-12-08 21:03:14 -08:00
zluda_windows Enable ROCm7 support (#579) 2025-12-15 14:01:53 -08:00
.git-blame-ignore-revs Make blame ignore formatting commit (#502) 2025-09-09 13:12:31 -07:00
.gitattributes Improve Windows loader (zluda.exe) (#550) 2025-12-08 21:03:14 -08:00
.gitignore Add support for shfl.sync.MODE.b32 (#409) 2025-07-16 17:23:11 -07:00
.gitmodules Emit llvm.zluda.mma intrinsic for MMA and switch to our LLVM fork (#546) 2025-11-18 18:23:03 -08:00
.rustfmt.toml Always use Unix line endings (#453) 2025-07-30 15:09:47 -07:00
Cargo.lock Enable ROCm7 support (#579) 2025-12-15 14:01:53 -08:00
Cargo.toml Improve Windows loader (zluda.exe) (#550) 2025-12-08 21:03:14 -08:00
geekbench.svg Remove trailing whitespaces and add missing newlines at EOF (#530) 2025-10-03 11:52:18 -07:00
LICENSE-APACHE Update wording, add license 2020-11-24 23:23:53 +01:00
LICENSE-MIT Update wording, add license 2020-11-24 23:23:53 +01:00
README.md Update quick start link in README.md (#493) 2025-09-03 14:18:28 -07:00

ZLUDA is a drop-in replacement for CUDA on non-NVIDIA GPUs. ZLUDA allows running unmodified CUDA applications using non-NVIDIA GPUs with near-native performance