cuda-api-wrappers
cuda-api-wrappers copied to clipboard
Support mipmapped array allocation & destruction
Both the runtime and the driver API allow allocation of mipmapped arrays:
Runtime:
cudaMallocMipmappedArray()cudaFreeMipmappedArray()cudaGetMipmappedArrayLevel()
Driver:
cuMipmappedArrayCreate()cuMipmappedArrayDestroy()cuMipmappedArrayGetLevel()
We should add support for these sometime... (probably just one variant suffices, it seems like these do the exact same thing).