[Intel-gfx] [PATCH i-g-t v2 4/7] tests/gem_scheduler: Add gem_scheduler test

2016-03-02 Thread Derek Morton
This is intended to test the scheduler behaviour is correct. The subtests are -basic Tests that batch buffers of the same priority submitted to a ring execute in the order they are submitted. -read Submits a batch buffer with a read dependency to a buffer object to a ring which is held in the sched

Re: [Intel-gfx] [PATCH i-g-t v2 4/7] tests/gem_scheduler: Add gem_scheduler test

2016-03-07 Thread Dave Gordon
On 02/03/16 20:15, Chris Wilson wrote: +static struct ring { + const char *name; + int id; + bool exists; +} rings[] = { + { "render", I915_EXEC_RENDER, false }, + { "bsd1",I915_EXEC_BSD | 1<<13, false }, + { "bsd2",I915_EXEC_BSD | 2<<13, false }, Thi

Re: [Intel-gfx] [PATCH i-g-t v2 4/7] tests/gem_scheduler: Add gem_scheduler test

2016-03-02 Thread Chris Wilson
> +static struct ring { > + const char *name; > + int id; > + bool exists; > +} rings[] = { > + { "render", I915_EXEC_RENDER, false }, > + { "bsd1",I915_EXEC_BSD | 1<<13, false }, > + { "bsd2",I915_EXEC_BSD | 2<<13, false }, This is wrong. The timeline is coupled to

Re: [Intel-gfx] [PATCH i-g-t v2 4/7] tests/gem_scheduler: Add gem_scheduler test

2016-03-04 Thread Morton, Derek J
EXEC_BSD | 2<<13 constitute separate exec_id's? //Derek -Original Message- From: Chris Wilson [mailto:ch...@chris-wilson.co.uk] Sent: Wednesday, March 2, 2016 8:15 PM To: Morton, Derek J Cc: intel-gfx@lists.freedesktop.org; daniel.vet...@ffwll.ch Subject: Re: [Intel-gfx]