Revert Enzyme hack

[maleadt]

https://github.com/JuliaGPU/GPUCompiler.jl/pull/619

[vchuravy]

Not fully up to speed here, but my hope is #582 will help with these situations. But currently it does still create the issue that Enzyme want's to run some optimization passes,

For C++ we solve this by using Enzyme as a plugin, via a magic function, instead of using it as a frontend driver, so maybe we could use a "EnzymePass", but the challenge would be to register that.

So the Idea would be to write:

ptr =  var"gpuc.deferred"(f, primal_args...)
__enzyme_autodiff(ptr, ad_args...)

Instead of #599, but then schedule a custom pass that recognizes __enzyme_autodiff.

[maleadt]

the challenge would be to register that

What about a ScopedValue allowing a third-party app to customize the GPUCompiler pipeline? We could do something like LLVM, with different extension points that allow Enzyme to insert passes where needed.

[vchuravy]

That would be wicked, but currently

function mykernel_grad(x, dx)
     autodiff_deferred(mykernel, Duplicated(x, dx))
end

@cuda mykernel_grad

And so we never enter on the CPU an Enzyme scope.