Article: ISSCC 2006: Intel Tulsa
By: Eric Bron (eric.bron.delete@this.adeptdevelopment.com), February 22, 2006 6:39 am
Room: Moderated Discussions
>Are you sure?
it is not strictly inclusive, a way to describe it is "non-exclusive" since most of the time data are duplicated in the DL1 and DL2 since L1 is writethrough. But imagine for example a small data set, say a 256 bytes look-up table, you know the "isalpha()" kind of LUT, if it's accessed frequently in some inner loop, it may well stay for a long period in the L1 while it's flushed from the L2 since there was no L1 miss to keep it alive in the L2, then these data will be in the L1 but not in the L2 anymore.
>Not being strictly inclusive would seem to cause many
>nasty issues with the L2 having a different line size
>than the L1, and also makes it much harder to snoop.
L2 cache line are also 64-bytes, two lines are fetched in case of L2 *read miss* but only one line in read for ownership in case of L2 write miss
it is not strictly inclusive, a way to describe it is "non-exclusive" since most of the time data are duplicated in the DL1 and DL2 since L1 is writethrough. But imagine for example a small data set, say a 256 bytes look-up table, you know the "isalpha()" kind of LUT, if it's accessed frequently in some inner loop, it may well stay for a long period in the L1 while it's flushed from the L2 since there was no L1 miss to keep it alive in the L2, then these data will be in the L1 but not in the L2 anymore.
>Not being strictly inclusive would seem to cause many
>nasty issues with the L2 having a different line size
>than the L1, and also makes it much harder to snoop.
L2 cache line are also 64-bytes, two lines are fetched in case of L2 *read miss* but only one line in read for ownership in case of L2 write miss
| Topic | Posted By | Date |
|---|---|---|
| Intel Tulsa Coverage from ISSCC | David Kanter | 2006/02/21 02:45 AM |
| Intel Tulsa Coverage from ISSCC | Alberto | 2006/02/21 04:43 AM |
| Intel Tulsa Coverage from ISSCC | Paul DeMone | 2006/02/21 06:52 AM |
| Inclusive L3? Wow | Michael S | 2006/02/21 04:51 AM |
| Inclusive L3? Wow | Wouter Tinus | 2006/02/21 07:06 AM |
| Inclusive L3? Wow | Michael S | 2006/02/21 08:20 AM |
| Inclusive L3? Wow | slim | 2006/02/21 11:40 AM |
| It is? | anonymous | 2006/02/21 09:57 AM |
| Inclusive L3? Wow | Linus Torvalds | 2006/02/21 10:10 AM |
| Inclusive L3? Wow | Michael S | 2006/02/21 11:03 AM |
| Inclusive L3? Wow | Linus Torvalds | 2006/02/21 11:52 AM |
| Inclusive L3? Wow | Eric Bron | 2006/02/22 06:39 AM |
| Inclusive L3 | David Kanter | 2006/02/22 12:16 PM |
| Inclusive L3 | Eric Bron | 2006/02/22 01:00 PM |