On 01/28/2013 09:00 PM, Eric Anholt wrote:
> Part of my motivation here was the number of cache misses we have in the first
> reference of a region after referencing the miptree wrapping it, for things
> that should all live in the first cacheline of one struct.
>
> I think I've made it as far int
Abdiel Janulgue writes:
> Hi,
>
> On Tuesday, January 29, 2013 04:00:28 PM Eric Anholt wrote:
>> Part of my motivation here was the number of cache misses we have in the
>> first reference of a region after referencing the miptree wrapping it, for
>> things that should all live in the first cache
Hi,
On Tuesday, January 29, 2013 04:00:28 PM Eric Anholt wrote:
> Part of my motivation here was the number of cache misses we have in the
> first reference of a region after referencing the miptree wrapping it, for
> things that should all live in the first cacheline of one struct.
>
> I think I
Part of my motivation here was the number of cache misses we have in the first
reference of a region after referencing the miptree wrapping it, for things
that should all live in the first cacheline of one struct.
I think I've made it as far into killing the region as I want to go before
Abdiel la
