Quoting Tvrtko Ursulin (2018-05-14 11:27:56) > > On 14/05/2018 10:37, Chris Wilson wrote: > > Store whether or not we need to kick the guc's execlists emulation on > > the engine itself to avoid chasing the device info. > > > > gen8_cs_irq_handler 512 428 -84 > > Impressive, or not, depends whether you look at the saving or code > generation. The code generation also looked better, at least in my eyes. Fewer chained movs and simpler test? > Hm, actually, is it just GEM_BUG_ON in intel_uc_is_using_guc_submission? > > But blimey, didn't we pencil in long time ago to stop using modparams at > runtime in favour of caching the values? This one looks like one to > confuse the driver easily if fiddled with at runtime. Yes, this is one where once upon a time we had an engine->guc_client to inspect that we traded in for a common i915->guc_client, but that will still require a pointer dance. -Chris _______________________________________________ Intel-gfx mailing list Intel-gfx@xxxxxxxxxxxxxxxxxxxxx https://lists.freedesktop.org/mailman/listinfo/intel-gfx
