Sign in with
Sign up | Sign in
Your question

ExtremeTech: 3.2Ghz P4 vs Opteron 2Ghz

Last response: in CPUs
Share
September 9, 2003 8:07:16 PM

More conclusive proof that this is a 'gamers' processor.

<A HREF="http://www.extremetech.com/print_article/0,3998,a=59324..." target="_new">ExtremeTech - </A><i><font color=blue>It's apparent that the Opteron 146 is a natural born killer when it comes to gaming performance. The Pentium 4 only manages a dead heat in one test, Comanche 4, which had previously been a "no contest" lead for the P4. In all the other tests, the Opteron 146, running at a 1.2GHz deficit, walks all over the Intel CPU.</i></font color=blue>

<b>However rather worryingly it seems to fall short in the rest of the benchmarks i.e Content Creation and any software that utilises HyperThreading or SSE2. I dont think the performance crown can be easily claimed by AMD in this respect.</b>

<font color=purple>Ladies and Gentlemen, its...Hammer Time !</font color=purple>
September 9, 2003 8:28:55 PM

Nice results, but I'm afraid all future games will use SSE2 and support Hyper-Threading...

I'm also very curious how the non-server model, Althlon 64, will perform, and especially how much it will cost. Is it possible that Opterons are so expensive to recover some of the research costs? Or will high-clocked Hammers cost as much?
September 9, 2003 9:05:03 PM

Then why do some of the latest games using DX9 perform up to 40% better on Opteron ?

<A HREF="http://www.anandtech.com/cpu/showdoc.html?i=1856" target="_new">Anandtech</A> - <font color=blue><i>When you find game benchmarks 10% to 20% higher, you are genuinely impressed.<b> However, in some of the very latest DX9 benchmarks, Athlon64/Opteron was 40% to 50% faster.</b> </i>

<font color=purple>Ladies and Gentlemen, its...Hammer Time !</font color=purple>
Related resources
September 9, 2003 9:19:47 PM

And what does DirectX 9 have to do with it?
September 9, 2003 9:28:07 PM

Everything!!!

Well, I didn't think that was gonna happen!!!
September 9, 2003 10:03:18 PM

Everything? As far as I know, DirectX library and driver run in a single thread, and SSE is only used when in software emulation mode.
September 9, 2003 10:35:54 PM

Um, the DX library runs with direct access to video cards and CPU resources. It supports SSE and SSE2, and every other instructions that can potentially speed up 2D and 3D operations.

Intelligence is not merely the wealth of knowledge but the sum of perception, wisdom, and knowledge.
September 9, 2003 10:55:43 PM

Not really. SIMD optimizations usually require hand-optimizing to achieve best results. Such a thing is very difficult, if not impossible to do in high-level languages without some type of SIMD primitive and currently, DX9 doesn't support such a thing.

"We are Microsoft, resistance is futile." - Bill Gates, 2015.
September 9, 2003 10:55:46 PM

Sure, it 'supports' it. But exaclty what would use it except for the software emulator? Things like geometry processing is nowadays done completely hardware accelerated with vertex shaders. Physics is done with hand-optimized libraries.

So I believe there must be another reason for Opteron's performance increase with DirectX games. And I also think that games that do use libraries optimized for SSE (Commanche?) and Hyper-Threading (next-gen games?) will benefit from Intel's architecture.

AMD has always had rather poor SIMD performance and they probably are not going to add Hyper-Threading soon. On the other hand they have more execution units for plain 386 instructions, which still form the majority in most applications. So I still think that, when applications take advantage of Intel's architecture, we might see a totally different picture.

Anyway, I'm glad AMD is finally back in the high-end market and kicking some Intel ass!
September 10, 2003 12:14:09 AM

I've read some of these all ready. But!!!! I waiting till they match A64 or Opti with Scotty.
September 10, 2003 12:34:24 AM

Why the Opteron is such a great gaming platform? Let's look at the advancements that brought gaming performance increases in the past:

P2 increased FSB and memory from 66MHz to 100MHz.
P3 added better caching and a higher FSB/memory.
Athlon added higher FSB (DDR) and memory.
P4 added a higher FSB.
P4 added more cache and an even higher FSB.
P4 yet again added a higher FSB and memory subsystem.
Opteron adds an integrated memory controller that has lower latency and achieves a higher throughput than the P4-C.

Notice a pattern?

"We are Microsoft, resistance is futile." - Bill Gates, 2015.
September 10, 2003 1:30:56 AM

Ok let's not get overhyped here.

I agree totally, and I said it before, what I think of the gaming perf.

But if this CPU indicates what a 2GHZ 3200+ will perform, I don't believe it will do well in multimedia. The scores, albeit better than the 3200+ AXP, are still NO MATCH and FAR from it from the P4. The outdated K7 design is so blatantly apparent. I wished it would've finally sped ahead with SSE2, but imgod2u is right, it really now rests on clock speed mainly, since we are talking streaming SIMD.

Oh and btw, those 3dMark scores? They sure contradict Tbreak's results if we extrapolate 1024*768 results, which would lie what, around 20000 point, with the FX5900 Ultra?

--
<A HREF="http://www.lochel.com/THGC/album.html" target="_new"><font color=blue><b>Are you ugly and looking into showing your mug? Then the THGC Album is the right place for you!</b></font color=blue></A>
September 10, 2003 1:33:36 AM

Quote:
Then why do some of the latest games using DX9 perform up to 40% better on Opteron ?

Anandtech - When you find game benchmarks 10% to 20% higher, you are genuinely impressed. However, in some of the very latest DX9 benchmarks, Athlon64/Opteron was 40% to 50% faster.

40-50% is a great number, but it means jack if the game already ran choppy!
It doesn't mean anything until you see the actual numbers. It jumped from the 30s to the 50s, that doesn't make the game THAT much more playable, it is still under the 60FPS smoothly playable barrier. If 40-50% came at 60FPS and gave you like 80FPS, then yeah that means a lot, but if a game ran at 15FPS and now runs at 22FPS, I could care less if the % is 50%! It's still not any better for my game!

--
<A HREF="http://www.lochel.com/THGC/album.html" target="_new"><font color=blue><b>Are you ugly and looking into showing your mug? Then the THGC Album is the right place for you!</b></font color=blue></A>
September 10, 2003 2:26:28 AM

Yes i see a pattern, you left out a bunch of fsb and cache enhancements that AMD did.
September 10, 2003 2:29:01 AM

you didn't mention new instruction sets


Proud owner of DOS 3.3 :smile:
September 10, 2003 4:56:24 AM

I left out many of the Athlon's FSB increases for a reason. Mainly that they didn't provide that much of a speed up in gaming at all. The K7 (and K8) architecture are much more latency dependent than bandwidth dependent like the P4. The only advancement in latency in the K7 series has been the introduction of the nForce2 chipset (which, yes, I forgot to mention) and the integrated memory controller in the K8. And surprise surprise, both offered significantly higher gaming performance.

"We are Microsoft, resistance is futile." - Bill Gates, 2015.
September 10, 2003 6:11:22 AM

Could the separation of AGP and memory controller, via Xbar, have something to do with this gaming performance? The Opteron seems to do average on operations the strictly involve memory and above average on operations that involve the Hyper-Transport tunnel to AGP.

Dichromatic for your viewing plesure...
September 10, 2003 9:37:06 AM

It could be but if that were true, wouldn't the K7 benefit from having a higher FSB running async with memory as well?

"We are Microsoft, resistance is futile." - Bill Gates, 2015.
September 10, 2003 2:27:37 PM

Quote:

I wished it would've finally sped ahead with SSE2, but imgod2u is right, it really now rests on clock speed mainly, since we are talking streaming SIMD.

Do we know which core stepping this Opteron is?

Remember, the first released Opteron revisions stumble a bit on SSE2--specifically converting between integer and SSE2 data types. It's supposedly corrected in later steppings, but which stepping do we have here? If it's an engineering sample (review pieces often are), it's likely to be an early stepping.

<i>I can love my fellow man...but I'm damned if I'll love yours.</i>
September 10, 2003 3:39:31 PM

They never improved SSE on the K7 so I hardly think they will on the K8 thats R&D money they dont have. They will probably focus on process techniques and technologies with IBM. They need to scale not increase the IPC anymore because if the Prescotts like anything I think it is they are going to need to scale quickly to stay in this race.

-Jeremy

:evil:  <A HREF="http://service.futuremark.com/compare?2k1=6940439" target="_new">Busting Sh@t Up!!!</A> :evil: 
:evil:  <A HREF="http://service.futuremark.com/compare?2k3=1228088" target="_new">Busting More Sh@t Up!!!</A> :evil: 
September 10, 2003 5:19:36 PM

Schmide I think you are right in thinking the Graphics performance is mainly attributed to the HT AGP Tunnel/Chipset and not the Opteron.....

<A HREF="http://www.anandtech.com/cpu/showdoc.html?i=1856&p=8" target="_new">AnandTech </A> - <font color=blue><i> To satisfy curiosity, we also compared performance of the Workstation nVidia Quadro FX2000 video card on both the <b>dual Xeon</b> Intel 875 platform and the single-CPU Opteron platform.

You would expect that 2 Xeon 3.06 CPUs with 1MB of cache would be the clear winner of this comparison. The results, however, are quite surprising.

<b>The results are basically even, which is amazing considering we are comparing a single 2.0 GHz Opteron to Dual 3.06 Xeon with 1Mb cache.</b></i>

<font color=purple>Ladies and Gentlemen, its...Hammer Time !</font color=purple>
September 10, 2003 9:43:29 PM

Quote:
They never improved SSE on the K7 so I hardly think they will on the K8 thats R&D money they dont have.

They didn't "improve" Palomino's SSE support because it worked just fine from the official get-go. It just wasn't SSE2, which was arguably a much bigger mod than was technically feasible--mainly the XMM register size expansion. Updated instructions are relatively simple to add on a microcoded CPU; bigger registers are not.

(IIRC the K7 core taped out with some SSE instruction support, it just wasn't officially finalized--and didn't set the feature register bit--until the Palomino. So implementing SSE with Palomino's introduction wasn't a terribly big deal engineering-wise.)

Also, note that AMD already committed to correcting the SSE2 implementation hangups. According to their optimization guide, the most recent steppings do indeed fix the glitches. Problem is, considering that many (most? all?) review sites are currently working off older-revision overclocked parts, or possibly even engineering samples, reviews probably won't reflect the SSE2 revisions until sometime after the official release.

Quote:
They need to scale not increase the IPC anymore because if the Prescotts like anything I think it is they are going to need to scale quickly to stay in this race.

So far it doesn't seem like AMD will have much problem scaling. AFAIK they're already planning a quick bump to 2.4GHz not long after the September 23rd release.

Plus, Prescott clearly has a few teething problems of its own, so don't expect it to ramp immediately.

<i>I can love my fellow man...but I'm damned if I'll love yours.</i>
September 10, 2003 9:57:12 PM

I would have to agree on this too. I think that hypertransport makes a difference.

<font color=blue>"You know, that my backstab attack does double the damage. I can make an off button for him." </font color=blue> :cool:
September 10, 2003 10:35:21 PM

Not sure I follow you on that...if AGP8x gains us so little over AGP4x, and its host-bus bandwidth demands could be met by simple PC133, why would the HyperTransport tunnel make much difference?

<i>I can love my fellow man...but I'm damned if I'll love yours.</i>
September 10, 2003 10:40:23 PM

More importantly, if there was such a lack of bandwidth in the part of processor -> AGP bus communication, why wouldn't running a K7's FSB at higher speeds (async with memory) bring the same results in terms of higher performance?

"We are Microsoft, resistance is futile." - Bill Gates, 2015.
September 10, 2003 10:51:24 PM

I would not say the bandwidth would make the difference, it more like the lower latency. I thought is why they design the chipset the way they did, so that it has lower latency.

<font color=blue>"You know, that my backstab attack does double the damage. I can make an off button for him." </font color=blue> :cool:
September 11, 2003 1:42:41 AM

That'd make sense if Hypertransport provided lower latency than the traditional point to point bus on the K7, but it doesn't. AGP has never been particularly sensitive to latency anyway.

"We are Microsoft, resistance is futile." - Bill Gates, 2015.
September 11, 2003 1:53:20 AM

Dave in the GFX Forum may be raising a point from a paradigm to this here. PCI-Express is great deal for graphics because the CPU to GFX card performance is often very weak. According to him, PCI-Exp will change that, and as he is a GFX Programmer, he seems to have experimented or seen actual proof on how performance is weak with AGP 8X at the moment. One could perhaps assume HT helps the CPU to GFX transfer much more than AGP 8X does.

I might be babbling though as I forgot most of what Dave said.

--
<A HREF="http://www.lochel.com/THGC/album.html" target="_new"><font color=blue><b>Are you ugly and looking into showing your mug? Then the THGC Album is the right place for you!</b></font color=blue></A>
September 11, 2003 2:44:47 AM

You raise a good point on the ES' reviewers get. My best guess would be (since chips need 3 months of testing, which would mean that if they recently solved the issues, it'd take time before they are out) we'd have to wait for faster FX 64 versions.

I'd be interested in seeing if it did help.

--
<A HREF="http://www.lochel.com/THGC/album.html" target="_new"><font color=blue><b>Are you ugly and looking into showing your mug? Then the THGC Album is the right place for you!</b></font color=blue></A>
September 11, 2003 3:55:26 AM

Ya Kelledin 128 single precision instructions are so damned easy to implement in native 32bit core. What is that hmm 7 million transistor increase to core overall transistor count then we add the register, new access ports, additional prefect module ports, bus ports also we cant forget the power consumption increase. Also the skew lvl's due to the change in core tick sync. Its funny dude you have no damned clue on semi conductor architectures do you? Easily implemented my ass sounds like a fagboy AMD fanboy playing down the poor engineering form AMD as usual.

You’re a funny guy kind of funny how I was right about the Northwood core smoking da shiznit out of the Athlon and scaled as well too. It’s also more quaint you show up when the hybrid is about to beat up on my beloved P7. Buts it’s all good the Prescott’s coming :evil:  . You’re a bad bad man Kelly!!! I like it that way just like when Eden talks dirty to me :smile: .

-Jeremy

:evil:  <A HREF="http://service.futuremark.com/compare?2k1=6940439" target="_new">Busting Sh@t Up!!!</A> :evil: 
:evil:  <A HREF="http://service.futuremark.com/compare?2k3=1228088" target="_new">Busting More Sh@t Up!!!</A> :evil: 
September 11, 2003 5:27:25 AM

Quote:
Ya Kelledin 128 single precision instructions are so damned easy to implement in native 32bit core. What is that hmm 7 million transistor increase to core overall transistor count then we add the register, new access ports, additional prefect module ports, bus ports also we cant forget the power consumption increase. Also the skew lvl's due to the change in core tick sync.

That's why I pointed out, the first K7 core taped out with the basics of an SSE implementation, it was just left "turned off" for the most part. The silicon groundwork for XMM registers and access ports was already in place before Palomino, so turning it on wasn't that big of a deal. All the skew level testing and layout optimization was being done anyways at that point, because the T-bird's power consumption was getting a bit high.

But of course, the groundwork for SSE2 couldn't be laid back with the original K7, because SSE2 didn't even exist then outside of Intel's labs and dreams. I believe that's at least partly why we never saw SSE2 on the K7 core.

First-revision production Opterons, on the other hand, had a fully functional SSE2 implementation, but it wasn't fully optimized for speed. AMD already committed to improving that. The AMD64 optimization manuals state that it's fixed in a specific core revision level, but there are doubtless a lot of reviewers outside of AMD that don't have the revised part in their possession--or if they do, they can't talk about it. Seeing sites having to base their AMD64 previews on Opterons <i>overclocked</i> to 2GHz is fairly telling.

Quote:
Its funny dude you have no damned clue on semi conductor architectures do you? Easily implemented my ass sounds like a fagboy AMD fanboy playing down the poor engineering form AMD as usual.

My god, I've been ad-hommed.

The pain! The pain!

Oh wait...that's just indigestion. Never mind. :lol: 

Quote:
You're a funny guy kind of funny how I was right about the Northwood core smoking da shiznit out of the Athlon and scaled as well too.

Yup. What do you expect? The Athlon was made to compete with and crush the P3, which it did very well. Even put the Willamette to shame after that. But of course, you (and the other Intel zealots) could never admit that...

Quote:
It's also more quaint you show up when the hybrid is about to beat up on my beloved P7. Buts it's all good the Prescott's coming.

Oh, I've been around.

As for the Prescott, yes, it's coming. Faster AMD64 parts are also coming. May we live in interesting times.

<i>I can love my fellow man...but I'm damned if I'll love yours.</i>
September 11, 2003 6:07:42 PM

Quote:
The Athlon was made to compete with and crush the P3, which it did very well. Even put the Willamette to shame after that. But of course, you (and the other Intel zealots) could never admit that...

Was there really someone who couldn't admit that the Athlon put Willy to shame? :o  I want proof. (I need a good laugh at a zealot's expense. He he he.)

Though technically I'd argue the semantics. Willy more or less put himself to shame. No one needed an Athlon to do that. Heck, even the P3 did that. **ROFL** Poor Willy... It could have been worse though. It could have been a Wilty. :o  Imagine if Intel had cut the cache like that from the beginning... Ooooo... He he he he he.

<pre><A HREF="http://ars.userfriendly.org/cartoons/?id=20030905" target="_new"><font color=black>People don't understand how hard being a dark god can be. - Hastur</font color=black></A></pre><p>
September 11, 2003 10:35:15 PM

Quote:
Was there really someone who couldn't admit that the Athlon put Willy to shame? :o 

I hate to rehash old characters...but remember FUGGER? He was probably the worst of the lot. Actually went so far as to stupidly fabricate bogus test scores a few times. His infamous 3DMark2K1 score thread is probably still in the archives somewhere--even most of the Intel fans were calling BS on that one.

AMDMeltdown is/was just a troll. His arguments were so off-base, I doubt he even believed them himself.

<i>I can love my fellow man...but I'm damned if I'll love yours.</i>
September 12, 2003 2:04:14 AM

Considering Matisaro is gonna be around soon, it wouldn't make any better entrance and welcome here than reminding him of Fugger's 3dMark01 thread in which he put his entire convictions on with arguments and used it dozens of times in debates! :smile:

--
<A HREF="http://www.lochel.com/THGC/album.html" target="_new"><font color=blue><b>Are you ugly and looking into showing your mug? Then the THGC Album is the right place for you!</b></font color=blue></A>
September 13, 2003 3:10:30 AM

Mat rocks!

--
<A HREF="http://www.lochel.com/THGC/album.html" target="_new"><font color=blue><b>Are you ugly and looking into showing your mug? Then the THGC Album is the right place for you!</b></font color=blue></A>
September 14, 2003 9:38:03 PM

Not soon enough it seems...

"I hate to rehash old characters...but remember FUGGER? He was probably the worst of the lot. Actually went so far as to stupidly fabricate bogus test scores a few times. His infamous 3DMark2K1 score thread is probably still in the archives somewhere--even most of the Intel fans were calling BS on that one."

Ignorance has kept your mind closed to the thruth my friend. My scores were real, I never faked anything so you claim. I have never stopped pushing.

Rather than flame you with hate, I will let you ponder the possiblility that if my scores were real and I put up with all the crap...

<A HREF="http://fugger.netfirms.com/45ghz.jpg" target="_new">FUGGER @ 4.5Ghz</A> on my gamming machine.

2 years page 1 on 3Dmark (in the top 10 + hall of fame now), one of the world top 10 super pi, #6 world overall, #1 non Ln2, and you still doubt my score when I rebenched and was off by what? less 100 points?

I am glad you guys still think of me.

<b>"Granted I dont own a P4. But I read enough stuff and waste enough time on forums newsgroups IRC and computer news sites that I proberly know more then if I DID own a P4." -vk2amv</b>
September 14, 2003 9:53:33 PM

I was outnumbered badly, yet I survived.

Matisaro was the grand poobah of the zealots, and it showed.

Looks like you are still keep the flame lit for him.

<b>"Granted I dont own a P4. But I read enough stuff and waste enough time on forums newsgroups IRC and computer news sites that I proberly know more then if I DID own a P4." -vk2amv</b>
September 14, 2003 9:56:15 PM

"fagboy fanboy" ROFL

This place is still the same.

<b>"Granted I dont own a P4. But I read enough stuff and waste enough time on forums newsgroups IRC and computer news sites that I proberly know more then if I DID own a P4." -vk2amv</b>
September 15, 2003 1:15:48 AM

Quote:
Ignorance has kept your mind closed to the thruth my friend. My scores were real, I never faked anything so you claim.

Thou still dost protest too much. :wink:

Quote:
2 years page 1 on 3Dmark (in the top 10 + hall of fame now), one of the world top 10 super pi, #6 world overall, #1 non Ln2, and you still doubt my score when I rebenched and was off by what? less 100 points?

We mainly remember you "conveniently forgetting" that your vidcard was overclocked, then frying your vidcard trying to get the scores you claimed. That little debacle will probably haunt you forever, no matter how well you can push it now.

All great fun, at least for the spectators. :lol: 

<i>I can love my fellow man...but I'm damned if I'll love yours.</i>
September 15, 2003 2:49:20 AM

Bah, I don't care what you two got on yourselves, I respect you both now anyways.

I just like Mat cuz he was fun to read debates with in this forum.

--
<A HREF="http://www.lochel.com/THGC/album.html" target="_new"><font color=blue><b>Are you ugly and looking into showing your mug? Then the THGC Album is the right place for you!</b></font color=blue></A>
September 15, 2003 3:24:18 AM

Nothing to haunt me, my life does not revolve around this forum.

Its amazing how you regurgitate what fagboy fanboy spoon fed you so long ago. Now we know you dont swollow.

<b>"Granted I dont own a P4. But I read enough stuff and waste enough time on forums newsgroups IRC and computer news sites that I proberly know more then if I DID own a P4." -vk2amv</b>
!