HIPBackend

class brainevent.HIPBackend

Compile HIP sources for AMD GPUs (stub — not yet implemented).

To implement HIP support:

1. Add detect_hip_toolchain() to kernix_toolchain that locates hipcc and the ROCm include directories.

2. Implement HIP compilation logic in this class using hipcc.

3. Update load_cuda_inline() (or add load_hip_inline) to select HIPBackend when platform="hip" is requested.

compile_source(source, output_path, build_dir, **kwargs)

Compile preprocessed source code to a shared library.

Parameters:

• source (str) – Preprocessed C++/CUDA source (user code + auto-generated FFI wrappers, as produced by preprocess_source()).

• output_path (str) – Desired path for the output shared library.

• build_dir (str) – Directory for intermediate build artefacts.

• extra_cflags (list[str], optional) – Additional compiler flags.

• extra_ldflags (list[str], optional) – Additional linker flags.

• extra_include_paths (list[str], optional) – Additional header search paths.

• verbose (bool) – Print the full compiler command.

• **kwargs (Any) – Backend-specific keyword arguments (e.g. gpu_arch for CUDA, optimization_level, use_fast_math).

Returns:

Absolute path to the compiled shared library.

Return type:

str

platform_name: str = 'hip'

Human-readable platform identifier, e.g. "cuda", "cpu", "hip".