How long before Core2 becomes like Pentium4?

Page 2 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.

Arkaign

Lifer
Oct 27, 2006
20,736
1,377
126
No, but the ones that weren't super slow were super expensive, right until the A64 hit, and the slow ones weren't any cheaper than AXPs.

865P came in force around summer of '03. Until that time, the P4s either used RDRAM, which was painfully expensive, sometimes more than the rest of the whole PC cost, or [SDR] SDRAM, which ran slow, and felt, in actual use, worse than it looked in benchmarks.

Northwood made the 850 more viable, but it still used RDRAM.

By the time the 865 came, Bartons were out, and AMD just needed to tweak prices to stay quite competitive, even though the P4C took their thunder, until they got the A64 out. Outside of the untouchable duallies, the A64s were very good values, compared to most of Intel's chips, right to Conroe.

P4s weren't all absolutely terrible (they were poor successors to the P3), but Intel helped them to get that reputation, and those of us that needed to stretch our wallets a bit saw very few good values in the P4 line-up, while the majority of AMD's line-up offered very good performance for the money.

Huh? I think your memory too has been a bit faded.

http://www.sharkyextreme.com/hardware/cpu/article.php/941741/Intel-845-DDR-Chipset-Review.htm

December 2001. Intel 845. DDR. Benches showed it to be so close to RDRAM that it didn't matter.

1.6A was cheap, and of course by summer '02 :

http://www.anandtech.com/show/896

"Intel's Pentium 4 2.4GHz: Taking the Lead"

Building a cheap fast P4 system by overclocking 1.6A, 2.0A, 2.4B, etc, was easy. On the AXP side, using the AXP Mobile or 2500+ were great options. Both AMD and Intel's top options were quite expensive at any given time anyway.

As for Socket A mobos, they pretty much sucked until Nforce2 and KT333A. Just like the 850 was okay but way overpriced, and 845 with sdram sucked.

It was very much a situation of parity, but yet people seem to remember the P4 as this terrible abomination. From '02 to the time when the 3500+ and beyond started hitting, the P4 was either tops or tied with the AXP and early A64s, and smart people could build great cheap systems from either platform.

I think it's the fact that P4 started badly (Willamette/RDRAM), and ended badly (Prescott vs. 3500+ and beyond) that it's remembered so weirdly. In the main, it was just fine. It's extremely debatable, and I fully agree, that the whole experiment with high clockspeed at the sacrifice of IPC was a questionable idea in the first place, and probably Intel should have just continued development of better IPC / multicore instead of going down that road, but P4 definitely wasn't the useless pile that so many people remember. Whether you had a 2.4B @ 3.2ghz, or an AXP 2500+ @ 3200+ levels, they were great chips and great values for the day.
 

Voo

Golden Member
Feb 27, 2009
1,684
0
76
Wouldn't that completely depend on the actual workload we're looking at?

An e8500 may become insufficient for gaming about now (and already is for one or two games), but for the average consumer for whom the most taxing task is to hear music and browse the web at the same time I don't see the CPU being the limiting factor anytime soon. Heck since c2ds also handle pretty much every flash site you can throw at them and 1080p video (without using the GPU) I don't see many workloads where they'd be the problem.
 

Inspire

Member
Aug 2, 2001
87
0
0
April 8th 2014.

The drop dead date for windows XP.

Heck, my dad still uses a 486 DX 25. So, I would say we got just under 3 years left for most C2D. At that point, Windows 9 will be coming out to replace the *turd OS called Windows 8*.

*Speculation.
 

Cerb

Elite Member
Aug 26, 2000
17,484
33
86
Huh? I think your memory too has been a bit faded.

http://www.sharkyextreme.com/hardware/cpu/article.php/941741/Intel-845-DDR-Chipset-Review.htm

December 2001. Intel 845. DDR. Benches showed it to be so close to RDRAM that it didn't matter.

1.6A was cheap, and of course by summer '02 :

http://www.anandtech.com/show/896

"Intel's Pentium 4 2.4GHz: Taking the Lead"

Building a cheap fast P4 system by overclocking 1.6A, 2.0A, 2.4B, etc, was easy. On the AXP side, using the AXP Mobile or 2500+ were great options. Both AMD and Intel's top options were quite expensive at any given time anyway.
OK, you got me on the 845D release. I could have sworn it was many months later than that. That both AMD and Intel had top models constantly priced too high...well, frankly, AMD even does that right now (it's impossible to say for Intel, since AMD's best only barely touches Intel's midrange). I guess people buy 'em (I think the Phenom II X6 CPUs are still way too high).

However, the overall mobo and CPU costs turned the charts with the P4 just edging out the AXPs on their heads: $75-150 savings for <10% performance drop would not have been uncommon, or, just as often, since budgets are fixed, often 10-20% more performance for the money. I specifically recall one gaming build I did, where a 2200+ was the same cost as a P4 1.8...kind of a no-brainer. Sometimes AMD was faster, but they remained competitive right up until the P4C and 865 could be paired up.

FI:
http://www.anandtech.com/show/1066/16
845D would generally be 5-10% slower, most of the mobos as expensive or more, and the CPUs more. Except for the 3000+ and later 3200+, they were all very well priced, and the mobos were significantly cheaper, too. You didn't see too many value price guides with P4s in them, and for good reason.

Then, this happened:
http://www.anandtech.com/show/1106/13

So, with no changes but the chipset:
http://www.anandtech.com/show/1117/11

Ouch. The 865/875 (and later, 848 for cheap office boxes) tended to be enough of an edge to make Intel CPUs really good values, and there was nothing AMD could do, as the Bartons were already not scaling linearly, and it occurred in a way that did not require Intel to reduce prices.

The P4 was more a failure due to needing high speeds, tons of RAM IO, and high power envelopes for what it did, and not being nearly as competitive with the P3 as a new high performance CPU should have been, and Intel expecting to ignore physics, expecting customers to ignore utility bills, and expecting developers to rebuild everything from scratch to try to make it work with their newfangled miracle-working CPU.
 

gevorg

Diamond Member
Nov 3, 2004
5,075
1
0
For average user who uses a comp for web, email, word, flash games, music & video, etc:

At least another 5 years, won't be surprised if up to 10 more years. A C2D can easily be their "last" desktop computer before tablets become mainstream. People will replace C2D not because its slow (like they did with P4), but because they want something simpler like a tablet or ultra-portable laptop (Macbook Air, Samsung 9, etc).
 

pitz

Senior member
Feb 11, 2010
461
0
0
I kept a dual core Intel P3-450 machine for 10 years, working perfectly fine. The leap from single core to dual core was massive, and improved stability/smoothness dramatically. But the returns really diminish after 2 cores in a system.

I suspect for a non-gamer who is willing to plunk down some cash to get a SSD, the Core2 platform can serve most people for 10 years.

Licensing schemes that heavily encourage computer upgrading will put quite a few of them into dumpsters. For instance, my T7500 Core2 duo laptop -- by the time I replace the backlight, replace the HDD with something newer/faster, and plunk down $150 for a new copy of Windows -- I'm within a few hundred $$ of being able to buy a new machine with all the fancy bells and whistles!
 

LOL_Wut_Axel

Diamond Member
Mar 26, 2011
4,310
8
81

DominionSeraph

Diamond Member
Jul 22, 2009
8,391
31
91
On anything decently threaded

Which, in general office use is... pretty much nothing.
Faster dual-core is still better than a slow quad for most anything that isn't embarrassingly parallel.

The pace of software has slowed, which gave the P4 an extremely long life. The C2D is leaps and bounds above the P4.
Most people will never have a reason to "upgrade" to a slower quad.
 

LOL_Wut_Axel

Diamond Member
Mar 26, 2011
4,310
8
81
Which, in general office use is... pretty much nothing.
Faster dual-core is still better than a slow quad for most anything that isn't embarrassingly parallel.

The pace of software has slowed, which gave the P4 an extremely long life. The C2D is leaps and bounds above the P4.
Most people will never have a reason to "upgrade" to a slower quad.


Nope, wrong. Office 2007 and 2010 are both decently threaded and will generally take longer to complete tasks on the Core 2 Duo. I don't know where you're getting this idea that the Core 2 Duo E7500 is faster, as that's simply not true (and this is coming from someone rocking a Core 2 Duo T9600 @ 3.2GHz on his laptop).

A dual-core/dual-threaded CPU IS NOT more responsive than a quad-core/quad-thread CPU in any task. If anything, the opposite is true. In a single-threaded app, the Core 2 Duo will only have one free core and will be less responsive, while the three remaining cores on the Athlon II X4 will make the system stay responsive. On multi-threaded apps, well, we all know the result. This argument you're making would only really make sense if you were talking about a Core i3 2100, which you are not.

Just to give you some perspective, the Athlon II X4 640 is about the same speed as the Core 2 Quad Q9400. Would you say the Q9400 is slower than the E7500? If you do, there's something wrong...
 

DominionSeraph

Diamond Member
Jul 22, 2009
8,391
31
91
Just to give you some perspective, the Athlon II X4 640 is about the same speed as the Core 2 Quad Q9400. Would you say the Q9400 is slower than the E7500? If you do, there's something wrong...

Lose 500MHz and it still spanks the Athlon II in single-threaded apps?

Oh looks, everybody! Hurry up and turn in your obsolete C2D's for these here new-fangled quads!


A dual-core/dual-threaded CPU IS NOT more responsive than a quad-core/quad-thread CPU in any task. If anything, the opposite is true.

You're missing where the C2D spanks the Athlon II in IPC.
 
Last edited:

LOL_Wut_Axel

Diamond Member
Mar 26, 2011
4,310
8
81
Lose 500MHz and it still spanks the Athlon II in single-threaded apps?

Oh looks, everybody! Hurry up and turn in your obsolete C2D's for these here new-fangled quads!

LOL, SysMark 2007... that pretty much says everything. Funny that you use the least accurate performance benchmark. How about you give a screenshot of all the others?

Also, I like how you switched from a Core 2 Duo E7500 to an E8600. If you want to play this game, so be it:

http://www.anandtech.com/bench/Product/102?vs=54

Learn to be honest. You wanted to compare an E7500 to a $100 Quad from AMD, so that means the Athlon II X4 640. Instead, you bring in the old 620, en EOL model. Then, when I call you out and provide a more accurate comparison, you switch yet again and use a Core 2 Duo E8600 instead of the original E7500. Funny how that is.

For productivity and any other task that is not audio encoding the Athlon II X4 640 is faster than the E7500. You're wrong; get over it. Everyone is at some point.
 

DominionSeraph

Diamond Member
Jul 22, 2009
8,391
31
91
Also, I like how you switched from a Core 2 Duo E7500 to an E8600. If you want to play this game, so be it:

http://www.anandtech.com/bench/Product/102?vs=54

And how is that a "low end AMD quad under $100"?

And the C2D still beats it in single-threaded.

Learn to be honest. You wanted to compare an E7500 to a $100 Quad from AMD, so that means the Athlon II X4 640. Instead, you bring in the old 620, en EOL model. Then, when I call you out and provide a more accurate comparison, you switch yet again and u

You're shaving Hz in a question of obsolescence. L2Think.

If you have a C2D desktop now, going to a quad Opteron 6168 is probably not going to see you much benefit. Cores != single threaded IPC.
 
Last edited:

Idontcare

Elite Member
Oct 10, 1999
21,118
59
91
LOL, SysMark 2007... that pretty much says everything.

Touch&#233;!

In DominionSeraph defense though I don't think he's been around CPU lately to have been apprised of the goings ons surrounding Bapco and Sysmark.

But yeah, ouch, talk about salt on fresh wounds...too soon DominionSeraph, too soon
 

LOL_Wut_Axel

Diamond Member
Mar 26, 2011
4,310
8
81
And how is that a "low end AMD quad under $100"?

And the C2D still beats it in single-threaded.

I thought $99.99 was less than $100... maybe I'm just crazy.

http://www.newegg.com/Product/Produc...-871-_-Product

And single-threaded apps have less relevance now, and boasting about them in a dual-threaded CPU is not a very smart thing. Like I said, if one of the cores in a Core 2 Duo is in heavy usage, the system will be a lot less responsive than the Athlon II X4 with its three idle cores, which is something you need to factor in.

My main point is: single-threaded apps nowadays are only a few. Productivity apps are decently threaded now, as are business applications, games, video encoding, 3D rendering, and others. About the only thing where the Core 2 Duo will be faster is in audio encoding (and even then you have to take into account the C2D being less responsive), so it's inaccurate to say that the Core 2 Duo will be faster in everyday apps. For what this will be used, which is probably productivity, web browsing and maybe multi-tasking, it'll be slower or the same speed (in the case of web browsing).
 
Last edited:

LOL_Wut_Axel

Diamond Member
Mar 26, 2011
4,310
8
81
And how is that a "low end AMD quad under $100"?

And the C2D still beats it in single-threaded.



You're shaving Hz in a question of obsolescence. L2Think.

If you have a C2D desktop now, going to a quad Opteron 6168 is probably not going to see you much benefit. Cores != single threaded IPC.

Except for the fact that the single-threaded performance in an Athlon II X4 640 is MUCH higher than that in an Opteron 6168. Even taking into account single-threaded apps, the 640 is not far off from the E7500. Look at Cinebench single-threaded.

And again, almost all programs now are at least decently threaded. Even if they don't take advantage of four cores, they'll take advantage of three (in the case of games). Productivity now takes advantage of all four cores, and Windows can take good advantage of multi-tasking thanks to making use of all cores as well.
 

DominionSeraph

Diamond Member
Jul 22, 2009
8,391
31
91
I thought $99.99 was less than $100... maybe I'm just crazy.

You are if you think an Athlon II X4 640 is a Phenom II X4 965.

And single-threaded apps have less relevance now, and boasting about them in a dual-threaded CPU is not a very smart thing. Like I said, if one of the cores in a Core 2 Duo is in heavy usage, the system will be a lot less responsive than the Athlon II X4 with its three idle cores, which is something you need to factor in.

Two cores is where the main benefit is. You do not need three cores to run Windows' background tasks.

A quad Opteron 6168 is not going to give you an amazingly responsive desktop over an i3 2120 just because it has 46 more cores.

Productivity apps are decently threaded now, as are business applications, games, video encoding, 3D rendering, and others.

Riiiight, which is why everyone recommends the X6 for a gaming rig.



Single-threaded performance? What's that? Cores are all that matter!



And what a horrible showing by the unquestionably obsolete C2D!
 
Last edited:

LOL_Wut_Axel

Diamond Member
Mar 26, 2011
4,310
8
81
You are if you think an Athlon II X4 640 is a Phenom II X4 965.

I did that because you thought it would be smart to change from an E7500 to an E8600. I thought you'd be okay with me making a comparable change, given that we're playing being dishonest.

Two cores is where the main benefit is. You do not need three cores to run Windows' background tasks.

This has already been argued time and time again.

A quad Opteron 6168 is not going to give you an amazingly responsive desktop over an i3 2120 just because it has 46 more cores.

Never said the Athlon II X4 would be a huge amount more responsive. Just that it would be more responsive. Also, there's points of diminishing returns once you go from anything higher than two threads, which is why the difference in responsiveness going from a Core 2 Duo to an Athlon II X4 is higher than from an Athlon II X4 to a 12-core Opteron.

Riiiight, which is why everyone recommends the X6 for a gaming rig.

Don't know where you're trying to get with this. I said most games take advantage of three cores but not four, which is true. A Phenom II X4 is a smarter choice for anyone not doing video encoding or 3D rendering, though the Core i5 now surpasses it [the Phenom II X6] in those as well.

Most apps take advantage of either three or four cores, but not more than that.
 
Last edited:

LOL_Wut_Axel

Diamond Member
Mar 26, 2011
4,310
8
81
You are if you think an Athlon II X4 640 is a Phenom II X4 965.



Two cores is where the main benefit is. You do not need three cores to run Windows' background tasks.

A quad Opteron 6168 is not going to give you an amazingly responsive desktop over an i3 2120 just because it has 46 more cores.



Riiiight, which is why everyone recommends the X6 for a gaming rig.



Single-threaded performance? What's that? Cores are all that matter!



And what a horrible showing by the unquestionably obsolete C2D!


No, but they do matter in many cases. There's a big difference in most apps when going from two cores to four, but not in most when going from four to six. That's the point I was trying to make from a long time ago, but it looks like you're fixated on not accepting that you're wrong.

First you go from comparing a Core 2 Duo E7500 to an Athlon II X4 620 (which according to you, even though it's EOL, represents $100 AMD Quad-Cores) to comparing a Core 2 Duo E8600 to an AMD Athlon II X4 635, and then go mad when I compare the E8600 to the 965. Then you try to step it up and compare the E8600 to a 1055T. Man, you really are desperate. But then that's how people are when in denial that they're wrong...
 
sale-70-410-exam    | Exam-200-125-pdf    | we-sale-70-410-exam    | hot-sale-70-410-exam    | Latest-exam-700-603-Dumps    | Dumps-98-363-exams-date    | Certs-200-125-date    | Dumps-300-075-exams-date    | hot-sale-book-C8010-726-book    | Hot-Sale-200-310-Exam    | Exam-Description-200-310-dumps?    | hot-sale-book-200-125-book    | Latest-Updated-300-209-Exam    | Dumps-210-260-exams-date    | Download-200-125-Exam-PDF    | Exam-Description-300-101-dumps    | Certs-300-101-date    | Hot-Sale-300-075-Exam    | Latest-exam-200-125-Dumps    | Exam-Description-200-125-dumps    | Latest-Updated-300-075-Exam    | hot-sale-book-210-260-book    | Dumps-200-901-exams-date    | Certs-200-901-date    | Latest-exam-1Z0-062-Dumps    | Hot-Sale-1Z0-062-Exam    | Certs-CSSLP-date    | 100%-Pass-70-383-Exams    | Latest-JN0-360-real-exam-questions    | 100%-Pass-4A0-100-Real-Exam-Questions    | Dumps-300-135-exams-date    | Passed-200-105-Tech-Exams    | Latest-Updated-200-310-Exam    | Download-300-070-Exam-PDF    | Hot-Sale-JN0-360-Exam    | 100%-Pass-JN0-360-Exams    | 100%-Pass-JN0-360-Real-Exam-Questions    | Dumps-JN0-360-exams-date    | Exam-Description-1Z0-876-dumps    | Latest-exam-1Z0-876-Dumps    | Dumps-HPE0-Y53-exams-date    | 2017-Latest-HPE0-Y53-Exam    | 100%-Pass-HPE0-Y53-Real-Exam-Questions    | Pass-4A0-100-Exam    | Latest-4A0-100-Questions    | Dumps-98-365-exams-date    | 2017-Latest-98-365-Exam    | 100%-Pass-VCS-254-Exams    | 2017-Latest-VCS-273-Exam    | Dumps-200-355-exams-date    | 2017-Latest-300-320-Exam    | Pass-300-101-Exam    | 100%-Pass-300-115-Exams    |
http://www.portvapes.co.uk/    | http://www.portvapes.co.uk/    |