Re: [Intel-gfx] [PATCH 02/19] drm/i915: Micro-optimise gen6_ppgtt_insert_entries()

Thu, 09 Feb 2017 03:35:43 -0800 

On 2 February 2017 at 15:02, Chris Wilson <[email protected]> wrote:
> Inline the address computation to avoid the vfunc call for every page.
> We still have to pay the high overhead of sg_page_iter_next(), but now
> at least GCC can optimise the inner most loop, giving a significant
> boost to some thrashing Unreal Engine workloads.
>
> Signed-off-by: Chris Wilson <[email protected]>
Reviewed-by: Matthew Auld <[email protected]>
_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

Reply via email to