On Thu, Oct 27, 2016 at 04:22:31PM +0100, Chris Wilson wrote: > On Thu, Oct 27, 2016 at 03:05:16PM +0100, Chris Wilson wrote: > > Use a priority stored in the context as the initial value when > > submitting a request. This allows us to change the default priority on a > > per-context basis, allowing different contexts to be favoured with GPU > > time at the expense of lower importance work. The user can adjust the > > context's priority via I915_CONTEXT_PARAM_PRIORITY, with more positive > > values being higher priority (they will be serviced earlier, after their > > dependencies have been resolved). Any prerequisite work for an execbuf > > will have its priority raised to match the new request as required. > > Not in mesa yet, but use case would in supporting EGL_IMG_context_priority > https://www.khronos.org/registry/egl/extensions/IMG/EGL_IMG_context_priority.txt > > EGL_CONTEXT_PRIORITY_LEVEL_IMG determines the priority level of > the context to be created. This attribute is a hint, as an > implementation may not support multiple contexts at some > priority levels and system policy may limit access to high > priority contexts to appropriate system privilege level. The > default value for EGL_CONTEXT_PRIORITY_LEVEL_IMG is > EGL_CONTEXT_PRIORITY_MEDIUM_IMG." > > i.e. > PRIORITY_HIGH -> 1023 [privileged, will failback to 0] > PRIORITY_MED -> 0 [default] > PRIORITY_LOW -> -1023 > > Does anyone has a real use for this? On the transcode side? Also applies to VkQueue as each can have a distinct priority. Queues need a bit more work in the anv implmentation to marry the spec to a kernel context, mostly working out the details of QueueFamilies and the like and seeing if we require new abi. -Chris -- Chris Wilson, Intel Open Source Technology Centre _______________________________________________ Intel-gfx mailing list Intel-gfx@xxxxxxxxxxxxxxxxxxxxx https://lists.freedesktop.org/mailman/listinfo/intel-gfx