Displaying 3 results from an estimated 3 matches for "syncobj_reset".
2023 Jul 25
1
[PATCH drm-misc-next v8 11/12] drm/nouveau: implement new VM_BIND uAPI
....org/mesa/crucible/-/merge_requests/141>
>
> The test, roughly, does the following:
> ?1. Allocates and binds 1000 BOs
> ?2. Constructs a pushbuf that executes a no-op compute shader.
> ?3. Does a single EXEC/wait combo to warm up the kernel
> ?4. Loops 10,000 times, doing SYNCOBJ_RESET (fast), EXEC, and then
> SYNCOBJ_WAIT and times the loop
>
> Of course, there's a bit of userspace driver overhead but that's
> negledgable.
>
> If you drop the top patch which allocates 1k buffers, the submit time on
> the old uAPI is 54 us/exec vs. 66 us/exec on...
2023 Jul 25
1
[PATCH drm-misc-next v8 11/12] drm/nouveau: implement new VM_BIND uAPI
...quests/141>
> >
> > The test, roughly, does the following:
> > 1. Allocates and binds 1000 BOs
> > 2. Constructs a pushbuf that executes a no-op compute shader.
> > 3. Does a single EXEC/wait combo to warm up the kernel
> > 4. Loops 10,000 times, doing SYNCOBJ_RESET (fast), EXEC, and then
> > SYNCOBJ_WAIT and times the loop
> >
> > Of course, there's a bit of userspace driver overhead but that's
> > negledgable.
> >
> > If you drop the top patch which allocates 1k buffers, the submit time on
> > the old uAPI is...
2023 Jul 25
1
[PATCH drm-misc-next v8 11/12] drm/nouveau: implement new VM_BIND uAPI
...> > The test, roughly, does the following:
> >? ?1. Allocates and binds 1000 BOs
> >? ?2. Constructs a pushbuf that executes a no-op compute shader.
> >? ?3. Does a single EXEC/wait combo to warm up the kernel
> >? ?4. Loops 10,000 times, doing SYNCOBJ_RESET (fast), EXEC, and then
> > SYNCOBJ_WAIT and times the loop
> >
> > Of course, there's a bit of userspace driver overhead but that's
> > negledgable.
> >
> > If you drop the top patch which allocates 1k buffers, the submit
>...