[2/2] OpenACC routine support
Nathan Sidwell
nathan@acm.org
Mon Nov 2 20:01:00 GMT 2015
On 11/02/15 14:41, Jakub Jelinek wrote:
>
> Does this work even with -O0? I mean, the assembler is invalid
> for any target other than PTX, so you are relying on aggressively folding
> this away.
Correct. As thread identification is inherently target-specific, I don't see
how to do otherwise.
We know _builtin_acc_on_device is folded for a constant arg, and -O2 enables
dead code elimination such that non-PTX targets (such as the host) don't see
that assembler.
nathan
More information about the Gcc-patches
mailing list