Fwd: [RFC][gomp4] Offloading patches (2/3): Add tables generation
Wed Jan 29 16:06:00 GMT 2014
2014/1/29 Bernd Schmidt <firstname.lastname@example.org>:
> I was worried the answer was going to be something like this. These are
> produced by two different compilers/linkers, aren't they? This seems really
> fragile to me and a recipe for hard-to-debug silent failures.
> First we let the driver compile and load all the ptx code, then we'd call a
> cuda library function with the name of the function passed as a string. So I
> guess the host table would contain pointers to the host version of the
> functions, and the target table would contain a pointer to the name.
We also wanted to use function names at the beginning of our work .
Then Jakub noticed that the names aren't necessarily unique: , , , etc.
This led to the current approach of host/target address tables.
More information about the Gcc-patches