POWER7 Spec

By: someone (someone.delete@this.somewhere.com), February 10, 2010 10:01 am
Room: Moderated Discussions
Linus Torvalds (torvalds@linux-foundation.org) on 2/10/10 wrote:
---------------------------
>someone (someone@somewhere.com) on 2/9/10 wrote:
>>
>>Nehalem beats Montvale by more than the frequency ratio?
>
>Yup.
>
>>You mean a processor that connects directly to 3 channels
>>of DDR3 beating a processor that uses a far narrower pipe
>>to memory through a front side bus, chipset (and in some
>>cases DIMM expander bridge chips) on a memory intensive
>>benchmark suite by more than the frequency ratio is a fault
>>at the core level?
>
>Yes. But your argument that this is somehow special is
>total crap, because if you had actually used your
>brain and been honest for one second, you would also
>have realized that SpecInt doesn't have that excessive
>a memory footprint, and the 9MB L3 (per core) of that
>Itanium is certainly quite large for the load.

According to this study:

http://www.spec.org/cpu2006/publications/SIGARCH-2007-03/05_cpu2006_wss.pdf

HALF of the integer programs in SPEC CPU 2006 have core
working sets of 16 MB or larger. In this context core working
set is the memory footprint touched in consecutive sampling
periods, i.e. regularly accessed.

Also SGI found with the 12 MB cache Montecito/Montvale there
was a 15% increase in BOTH SPECint2006 and SPECfp2006
performance from 1.6 GHz/533 MHz FSB to 1.66 GHz/666 MHz
FSB, both cases using version 10.1 of icc.

That is a 15% performance improvement from a 4.2% faster
CPU clock and 25% higher memory bandwidth. So much for
your dumb ass theory that SPECint2006 fits in a 9 MB cache.

BTW, Tukwila has more than 200% higher memory bandwidth
than the 666 MHz FSB version of Montvale. ;^)

[bunch of same old Linus shit deleted]


>How f*cking retarded do you have to be to still continue to
>make excuses for it? When do you just admit that it didn't
>work out? How many more failures do you need?

LOL, year after year IPF bashers just get more and more
frustrated. Things have gone only downhill after Merced.

I stop applying the cluebat of inconvenient facts to the side
of Itanium basher's heads when they stop spreading lies,
FUD, and misrepresentations about it.
< Previous Post in ThreadNext Post in Thread >
TopicPosted ByDate
POWER7 SpecParadox2010/02/08 10:05 AM
  POWER7 SpecThu Nguyen2010/02/08 11:58 AM
    POWER7 SpecIan Ameline2010/02/08 08:22 PM
      POWER7 SpecThu Nguyen2010/02/08 10:54 PM
        POWER7 SpecIan Ameline2010/02/09 05:46 AM
          POWER7 SpecLinus Torvalds2010/02/09 06:57 AM
            industry-standard single-threaded performance benchmarks absentMichael S2010/02/09 07:09 AM
              industry-standard single-threaded performance benchmarks absentParadox2010/02/09 07:33 AM
                industry-standard single-threaded performance benchmarks absentMichael S2010/02/09 08:30 AM
                  industry-standard single-threaded performance benchmarks absentParadox2010/02/09 09:52 AM
                    industry-standard single-threaded performance benchmarks absentJesper Frimann2010/02/09 10:33 AM
              industry-standard single-threaded performance benchmarks absentLinus Torvalds2010/02/09 07:48 AM
                industry-standard single-threaded performance benchmarks absentMichael S2010/02/09 08:26 AM
                  industry-standard single-threaded performance benchmarks absentLinus Torvalds2010/02/09 08:58 AM
                    industry-standard single-threaded performance benchmarks absentJesper Frimann2010/02/09 11:17 AM
                      industry-standard single-threaded performance benchmarks absentLinus Torvalds2010/02/09 11:54 AM
                        industry-standard single-threaded performance benchmarks absentJesper Frimann2010/02/09 01:10 PM
                    industry-standard single-threaded performance benchmarks absentParadox2010/02/09 12:22 PM
                industry-standard single-threaded performance benchmarks absentanon2010/02/09 09:21 AM
            POWER7 SpecJesper Frimann2010/02/09 11:30 AM
            POWER7 SpecDoug Siebert2010/02/09 04:38 PM
              POWER7 SpecLinus Torvalds2010/02/09 06:28 PM
                POWER7 SpecLinus Torvalds2010/02/09 06:28 PM
                  POWER7 SpecIan Ameline2010/02/09 07:02 PM
                    POWER7 SpecDoug Siebert2010/02/09 09:18 PM
                POWER7 Specsomeone2010/02/09 07:20 PM
                  POWER7 SpecLinus Torvalds2010/02/10 08:17 AM
                    POWER7 SpecLinus Torvalds2010/02/10 08:46 AM
                      POWER7 SpecEmil2010/02/10 10:06 AM
                    POWER7 SpecIan Ameline2010/02/10 09:13 AM
                    POWER7 Specsomeone2010/02/10 10:01 AM
                      POWER7 SpecLinus Torvalds2010/02/10 10:32 AM
                        POWER7 SpecMichael S2010/02/10 11:30 AM
                          POWER7 SpecLinus Torvalds2010/02/10 12:25 PM
                            POWER7 Specmpx2010/02/10 01:58 PM
                        POWER7 Specnemlis2010/02/10 11:24 PM
                          POWER7 Specnone2010/02/10 11:52 PM
                            POWER7 Specnemlis2010/02/11 12:52 PM
          POWER7 Specmpx2010/02/09 07:18 AM
          POWER7 SpecMichael S2010/02/09 08:08 AM
        POWER7 SpecJesper Frimann2010/02/16 01:29 AM
          POWER7 SpecJamie Lucier2010/02/16 05:35 AM
            POWER7 Specanon2010/02/16 06:16 AM
              POWER7 SpecJamie Lucier2010/02/16 09:46 AM
                POWER7 Specanon2010/02/16 02:42 PM
                  POWER7 SpecJamie Lucier2010/02/18 05:07 AM
              POWER7 SpecThu Nguyen2010/02/16 12:23 PM
            POWER7 SpecParadox2010/02/16 08:57 AM
              POWER7 SpecJamie Lucier2010/02/16 10:22 AM
                POWER7 SpecParadox2010/02/16 01:00 PM
            POWER7 SpecJesper Frimann2010/02/16 01:14 PM
              POWER7 SpecJamie Lucier2010/02/17 09:41 AM
  POWER7 SpecJesper Frimann2010/02/09 03:43 AM
Reply to this Topic
Name:
Email:
Topic:
Body: No Text
How do you spell tangerine? ūüćä