1b9ba2b233
Too many changes to list, but broadly: * Remove Intel GPU support from the compiler * Add AMD GPU support to the compiler * Remove Intel GPU host code * Add AMD GPU host code * More device instructions. From 40 to 68 * More host functions. From 48 to 184 * Add proof of concept implementation of OptiX framework * Add minimal support of cuDNN, cuBLAS, cuSPARSE, cuFFT, NCCL, NVML * Improve ZLUDA launcher for Windows
2 lines
421 B
Plaintext
2 lines
421 B
Plaintext
bindgen build/wrapper.h -o src/cuda.rs --no-partialeq "CUDA_HOST_NODE_PARAMS_st" --no-partialeq "CUDA_HOST_NODE_PARAMS_v2_st" --with-derive-eq --allowlist-function="^cu.*" --allowlist-var="^CU.*" --default-enum-style=newtype --no-layout-tests --no-doc-comments --new-type-alias "^CUdevice_v\d+$|^CUdeviceptr_v\d+$" --must-use-type "cudaError_enum" -- -I"C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.2\include"
|