On Thu, Aug 11, 2022 at 11:20 PM Lyude Paul <lyude@xxxxxxxxxx> wrote: > > On Thu, 2022-08-11 at 00:08 +0200, Karol Herbst wrote: > > the thing is, without this patch, the "hw path" fails with a timeout > > of... 30 seconds?, the code falls back to sw and it takes up to 2-3 > > minutes to finish up. So even if this solution is overkill, it fixes a > > real issue. I suspect _something_ is bonkers with the fencing we do > > here and we don't see that the stuff is actually finished or whatever, > > or maybe we never emit the fence in the first place.. I didn't dig > > deep enough. > > > > With this, it's really quick and everything. > > I guess with a todo comment this is probably fine then, since this would only > really be affecting GPUs using m2mf anyway > I was mostly wondering if this is safe, but it probably is and it does fix real user issues. I don't have a better solution at the moment anyway. > -- > Cheers, > Lyude Paul (she/her) > Software Engineer at Red Hat >
