Quoting Tvrtko Ursulin (2019-02-05 09:24:24) > > On 04/02/2019 13:22, Chris Wilson wrote: > > Having introduced per-context seqno, we now have a means to identity > > progress across the system without feel of rollback as befell the > > global_seqno. That is we can program a MI_SEMAPHORE_WAIT operation in > > advance of submission safe in the knowledge that our target seqno and > > address is stable. > > > > However, since we are telling the GPU to busy-spin on the target address > > until it matches the signaling seqno, we only want to do so when we are > > sure that busy-spin will be completed quickly. To achieve this we only > > submit the request to HW once the signaler is itself executing (modulo > > preemption causing us to wait longer), and we only do so for default and > > above priority requests (so that idle priority tasks never themselves > > hog the GPU waiting for others). > > > > v3: Drop the older NEQ branch, now we pin the signaler's HWSP anyway. > > v4: Tell the world and include it as part of scheduler caps. > > Looks okay to me. > > Just a paragraph about power and performance, with ideally a latest > table of results from media-bench, would be the usual requirement for > these kind of additions. "A bunch of vague waffle about how well it performs in microbenchmarks, single client configs and doesn't regress multiple clients, without mentioning any details that may be construed as an absolute promise of performance metrics, despite that we give you the tools to measure and confirm what we are trying not to say." -Chris _______________________________________________ Intel-gfx mailing list Intel-gfx@xxxxxxxxxxxxxxxxxxxxx https://lists.freedesktop.org/mailman/listinfo/intel-gfx
