By: waitressInGaza (beenthere.delete@this.donethat.com), February 3, 2003 1:15 pm
Room: Moderated Discussions
Bill Todd (billtodd@metrocast.net) on 2/3/03 wrote:
---------------------------
>Peter Gerassimoff (pgerassi@ticon.net) on 2/3/03 wrote:
>
>...
>
>>FYI, Itanium3 (Madison) is only going to be 1.3GHz for the 6MB version and 1,2GHz
>>for the 3MB version.
>
>Have you told Intel yet? Their public statements are that Madison is going to clock at 1.5 GHz.
>
>YOur predicted SPEC scores are 25% too high. You should multiply
>>them by 80% or SPECint/fp 6MB: 1000/1720 and 3MB: 920/1600.
>>
>>You should also give Opteron up to 2.6 to 2.8GHz by end of this year on PC3200.
>
>Really? Do you have a reference for this? The highest speed I've seen AMD claim
>for any Hammer this year is 2.6 GHz ("2.4 and 2.6 GHz in Q4", IIRC), and since that
>one statement I haven't seen anything beyond 2.4 GHz in Q4 (suggesting that the
>previous statement included 2.6 GHz as a best-case possibility which later started to look overoptimistic).
>
>Furthermore, I've seen no claim that the on-chip memory controller can handle anything faster than PC2700 memory.
>
>>Also the SPEC scores you cite are for 32 bit mode only.
>
>That does seem to be the case, at least if one believes Freb Weber's quoted 1202
>for 32-bit SPECint at 2 GHz. Paul has expressed skepticism that Fred's other claim
>(that the score will improve by 15% - 20% in 64-bit mode) will pan out, because
>he thinks that it will be difficult to get the 64-bit (K8-specific) compilers up
>to the standard set by the 32-bit Intel compiler used to obtain the 1202 score.
>
>Adding 64 bit speed up
>>of 10%
>
>That may either be a bit conservative (based on Fred's statement) or a bit optimistic
>(based on current performance differences between the Intel compiler and, e.g., gcc).
>
>and PC3200 speed up of another 10% (conservative),
>
>Or imaginary (again: reference, please?).
>
>2.0GHz Opteron gets 1440/1400,
>>2.4GHz gets 1650/1600, 2.6GHz gets 1775/1700 and 2.8GHz gets 1900/1800.
>>
>>Given these Opteron has a good chance of beating Itanium3 in SPECfp
>
>Dream on. Opteron won't even beat McKinley when Madison releases, since Opteron
>will still be at 2 GHz (or at most 2.2 GHz if Madison's late and the faster Opteron
>is early). And unless you can substantiate your claim that Madison won't run at
>1.5 GHz, there's no reason to expect Opteron to be able to challenge it in SPECfp
>at anything less than about 3.2 - 3.4 GHz.
>
>and Itanium3
>>may fall behind many other 64 bit CPUs in SPECint
>
>"Many" others? Not Alpha (EV7 is a bit slower than McKinley so even EV79 in 2004
>likely won't quite catch Madison, and EV68 is only about 5% faster than McKinley
>so won't nearly match Madison). Certainly not SPARC or MIPS (they're much slower
>than McKinley). Not PA-RISC either (faster than SPARC and MIPS, but notably slower
>than McKinley). Even POWER4+ will have to bump up its clock rate significantly
>to match Madison (it probably can do so, but whether that will happen before Madison's release is unclear).
>
>as Opteron runs far ahead of all of them.
>
>That one I'll agree with.
>
>- bill
>
>
---------------------------
>Peter Gerassimoff (pgerassi@ticon.net) on 2/3/03 wrote:
>
>...
>
>>FYI, Itanium3 (Madison) is only going to be 1.3GHz for the 6MB version and 1,2GHz
>>for the 3MB version.
>
>Have you told Intel yet? Their public statements are that Madison is going to clock at 1.5 GHz.
>
>YOur predicted SPEC scores are 25% too high. You should multiply
>>them by 80% or SPECint/fp 6MB: 1000/1720 and 3MB: 920/1600.
>>
>>You should also give Opteron up to 2.6 to 2.8GHz by end of this year on PC3200.
>
>Really? Do you have a reference for this? The highest speed I've seen AMD claim
>for any Hammer this year is 2.6 GHz ("2.4 and 2.6 GHz in Q4", IIRC), and since that
>one statement I haven't seen anything beyond 2.4 GHz in Q4 (suggesting that the
>previous statement included 2.6 GHz as a best-case possibility which later started to look overoptimistic).
>
>Furthermore, I've seen no claim that the on-chip memory controller can handle anything faster than PC2700 memory.
>
>>Also the SPEC scores you cite are for 32 bit mode only.
>
>That does seem to be the case, at least if one believes Freb Weber's quoted 1202
>for 32-bit SPECint at 2 GHz. Paul has expressed skepticism that Fred's other claim
>(that the score will improve by 15% - 20% in 64-bit mode) will pan out, because
>he thinks that it will be difficult to get the 64-bit (K8-specific) compilers up
>to the standard set by the 32-bit Intel compiler used to obtain the 1202 score.
>
>Adding 64 bit speed up
>>of 10%
>
>That may either be a bit conservative (based on Fred's statement) or a bit optimistic
>(based on current performance differences between the Intel compiler and, e.g., gcc).
>
>and PC3200 speed up of another 10% (conservative),
>
>Or imaginary (again: reference, please?).
>
>2.0GHz Opteron gets 1440/1400,
>>2.4GHz gets 1650/1600, 2.6GHz gets 1775/1700 and 2.8GHz gets 1900/1800.
>>
>>Given these Opteron has a good chance of beating Itanium3 in SPECfp
>
>Dream on. Opteron won't even beat McKinley when Madison releases, since Opteron
>will still be at 2 GHz (or at most 2.2 GHz if Madison's late and the faster Opteron
>is early). And unless you can substantiate your claim that Madison won't run at
>1.5 GHz, there's no reason to expect Opteron to be able to challenge it in SPECfp
>at anything less than about 3.2 - 3.4 GHz.
>
>and Itanium3
>>may fall behind many other 64 bit CPUs in SPECint
>
>"Many" others? Not Alpha (EV7 is a bit slower than McKinley so even EV79 in 2004
>likely won't quite catch Madison, and EV68 is only about 5% faster than McKinley
>so won't nearly match Madison). Certainly not SPARC or MIPS (they're much slower
>than McKinley). Not PA-RISC either (faster than SPARC and MIPS, but notably slower
>than McKinley). Even POWER4+ will have to bump up its clock rate significantly
>to match Madison (it probably can do so, but whether that will happen before Madison's release is unclear).
>
>as Opteron runs far ahead of all of them.
>
>That one I'll agree with.
>
>- bill
>
>
Topic | Posted By | Date |
---|---|---|
New Article Available | David Kanter | 2003/02/02 02:44 AM |
Excellent Article, Paul (NT) | Arcadian | 2003/02/02 04:57 PM |
Yikes! Slashdotted! | Dean Kent | 2003/02/02 07:53 PM |
Yikes! Slashdotted! | Singh, S.R. | 2003/02/03 12:38 AM |
Yikes! Slashdotted! | Dean Kent | 2003/02/03 12:53 AM |
Yikes! Slashdotted! | Anonymous | 2003/02/03 07:03 AM |
Yikes! Slashdotted! | Dean Kent | 2003/02/03 09:13 AM |
FYI, Paul: | Peter Gerassimoff | 2003/02/03 01:38 AM |
FYI, Paul: | Bill Todd | 2003/02/03 03:18 AM |
FYI, Paul: | Marc M. | 2003/02/03 10:08 AM |
Opteron SPEC Performance | Arcadian | 2003/02/03 12:15 PM |
Opteron SPEC Performance | Marc M. | 2003/02/03 12:18 PM |
i want to see those links pls!! (NT) | waitressInGaza | 2003/02/03 01:15 PM |
i want to see those links pls!! (NT) | José Javier Zarate | 2003/02/05 09:23 AM |
i want to see those links pls!! (NT) | waitressInGaza | 2003/02/05 02:50 PM |
i want to see those links pls!! (NT) | tecate | 2003/02/05 05:09 PM |
gender should be irrelevant | waitressInGaza | 2003/02/05 06:36 PM |
gender should be irrelevant | Dean Kent | 2003/02/05 07:03 PM |
gender should be irrelevant | tecate | 2003/02/05 09:27 PM |
well it is all about your viewpoint | waitressInGaza | 2003/02/06 12:44 AM |
well it is all about your viewpoint | doriangrey | 2003/02/07 12:39 AM |
Please be a girl. :p | NIKOLAS | 2003/02/06 06:28 AM |
FYI, Paul: | Paul DeMone | 2003/02/03 08:43 AM |
larger cache for POWER4+? | Anil Maliyekkel | 2003/02/03 05:08 AM |
larger cache for POWER4+? | Thu Nguyen | 2003/02/03 06:35 AM |
well written indeed | hobold | 2003/02/03 07:41 AM |
well written indeed | tecate | 2003/02/03 09:05 AM |
well written indeed | hobold | 2003/02/03 09:12 AM |
well written indeed | Paul DeMone | 2003/02/03 09:15 AM |
well written indeed | hobold | 2003/02/03 12:04 PM |
well written indeed | Paul DeMone | 2003/02/03 12:58 PM |
about Jim Keller | Marc M. | 2003/02/03 01:50 PM |
about Jim Keller | Paul DeMone | 2003/02/03 02:22 PM |
Nope but will now (NT) | Marc M. | 2003/02/03 02:50 PM |
patent info... | Marc M. | 2003/02/03 02:52 PM |
about the article... | Dean Kent | 2003/02/03 04:49 PM |
Er, I just have to point something out. | Anonymous | 2003/02/04 10:19 PM |
Next time check the date. | Paul DeMone | 2003/02/05 01:10 AM |
Yes, I know it was written in 2000. | Anonymous | 2003/02/05 12:42 PM |
Yes, I know it was written in 2000. | Paul DeMone | 2003/02/05 01:20 PM |
about Jim Keller | Alejandro G. Belluscio | 2003/02/09 01:09 PM |
about Jim Keller | Dean Kent | 2003/02/09 01:40 PM |
about Jim Keller | Paul DeMone | 2003/02/09 02:00 PM |
about Jim Keller | David Wang | 2003/02/09 02:18 PM |
about Jim Keller | Paul DeMone | 2003/02/09 03:47 PM |
about Jim Keller | Interested in Illinois | 2003/02/10 11:11 AM |
about Jim Keller | Dean Kent | 2003/02/10 12:06 PM |
about Jim Keller | Alejandro Belluscio | 2003/02/11 06:53 PM |
about Jim Keller | Dean Kent | 2003/02/11 09:52 PM |
about Jim Keller | Alejandro Belluscio | 2003/02/12 11:06 AM |
about Jim Keller | Interested in Illinois | 2003/02/13 04:19 PM |
about Jim Keller | Interested in Illinois | 2003/02/11 11:35 PM |
about Jim Keller | David Kanter | 2003/02/12 12:24 AM |
Taxation systems | Alejandro Belluscio | 2003/02/12 10:54 AM |
Taxation systems | Interested in Illinois | 2003/02/13 07:23 AM |
Taxation systems | Alejandro Bellusco | 2003/02/13 10:53 AM |
Taxation systems | Interested in Illinois | 2003/02/13 03:47 PM |
Taxation systems | Aleajdnro G. Belluscio | 2003/02/13 05:56 PM |
Taxation systems | Jouni Osmala | 2003/02/14 08:03 AM |
Taxation systems | Alejandro G. Belluscio | 2003/02/14 06:13 PM |
Taxation systems | David Kanter | 2003/02/15 12:18 AM |
Taxation systems | Alejandro Belluscio | 2003/02/15 08:36 AM |
well written indeed | hobold | 2003/02/03 02:40 PM |
E8870 Chipset | José Javier Zarate | 2003/02/04 03:19 PM |
E8870 Chipset | Arcadian | 2003/02/05 01:54 AM |
E8870 Chipset | José Javier Zarate | 2003/02/05 09:13 AM |
E8870 Chipset | Arcadian | 2003/02/05 12:49 PM |
Minor question | José Javier Zarate | 2003/02/04 03:24 PM |
well written indeed | Dean Kent | 2003/02/03 09:18 AM |
well written indeed | hobold | 2003/02/03 09:36 AM |
well written indeed | Dean Kent | 2003/02/03 10:33 AM |
hear hear... | Marc M. | 2003/02/03 12:16 PM |
well written indeed | hobold | 2003/02/03 03:02 PM |
well written indeed | Dean Kent | 2003/02/03 04:48 PM |
well written indeed | hobold | 2003/02/04 01:56 PM |
well written indeed | Marc M. | 2003/02/03 10:19 AM |
BTW Paul, it was VERY well written... BUT... =) | Marc M. | 2003/02/03 10:25 AM |
Ditto (NT) | William L. | 2003/02/10 08:28 PM |
New Article Available | JS | 2003/02/05 02:09 AM |
Changes in MPU design methodologies? | Richard Stacpoole | 2003/02/06 05:46 AM |
Changes in MPU design methodologies? | Paul DeMone | 2003/02/06 10:47 AM |
Changes in MPU design methodologies? | doriangrey | 2003/02/07 12:41 AM |
Changes in MPU design methodologies? | William L. | 2003/02/10 08:34 PM |
Changes in MPU design methodologies? | Singh, S.R. | 2003/02/10 10:34 PM |
Watch this | Singh, S.R. | 2003/02/10 10:42 PM |
excellent article, just a nit or two | mulp | 2003/02/16 12:11 AM |