Pentium 4 Discussion - Round 2

[Arcadian]

I want this discussion to take a slightly different route than the Pentium 4 Pros and Cons discussion of last week. Here, we already know how the Pentium 4 performs. If you have not, I suggest you check out the following sites. www.sharkyextreme.com (if you haven't been here yet, what are you doing on the forums ) www.anandtech.com www.tomshardware.com www.aceshardware.com

I want to concentrate this discussion on the following topics.

A) Pure performance. At 1.5GHz, the Pentium 4 is underwhelming. However, from multiple prerelease scores leaked around the Internet, expectations were down. However, in light of current offerings from other processor families, how do you rate the Pentium 4 in regards to the Pentium III 1GHz, the Athlon with 1.2GHz SDR, and the Athlon 1.2GHz with DDR.

B) Performance with individual programs. It is clear that the Pentium 4 really underperforms with Office Productivity software. How would this affect you. Do you think that Office Productivity does not need to go faster anyways, or is it a big deal for you? How about video and audio encoding. The Pentium 4 beats all compeition with video, but audio seems to lag. How do you feel about this? Next, how about 3D games? The Pentium 4 really accelerates Quake III, yet Expendable seriously underperforms. MDK and Unreal Tournement seem at parity. What is you comment here, and do you have a technical explaination on why the performance varies so much? Finally, workstation apps really underperform, including 3D Studio. How do you feel about this, and do you have any technical information about why this happens?

C) Optimizations. This is a common theme among reviewers. Even AMD biased Tom Pabst agrees that the Pentium 4 will grow with time, and with optimizations, especially SSE-2. How do you think these enhansements will affect programs mentioned above. Also, how long do you expect these optimizations to filter into the market? Finally, do you think AMD's K8 system will be able to take advantage of such optimizations in SSE-2 when it is released?

D) Overclocking. Sharky and Tom Pabst both have looked into overclocking. Sharky was able to adjust the multiplier to reach 1.6GHz, and Tom was able to adjust both multiplier and front side bus to achieve speeds of up to 1.73GHz. Holy Moly, that's fast! Clearly this demonstrates superiority in the Pentium 4 design with regard to clock speed. It also shows that 1.7GHz Pentium 4 chips are right around the corner. How do you feel about this? Does overclocking add value to the Pentium 4?

E) Future products. This will be mostly speculation, but I want to hear discussions on how you think the Pentium 4 will compete with Palomino. Do you think that faster clock speeds will allow the Pentium 4 to keep up? Do you think that Palomino will be able to be as low priced as the Thunderbird? Also, how do you see price being affected for Intel and AMD over the next months. Finally, do you expect Intel's second generation Pentium 4, Northwood, to increase performance and compete with Palomino?

Let's hear your discussions. Opinions are welcome, as long as you can back yourself up. One line opinions are not appropriate, in other words. Any technical knowledge is encouraged, since this is the technical forum. I look forward to hearing from you guys.

[Sol]

Well, I have read only one review and looking at the background, I believe the P4 wont be very popular right now. However, I believe intel has positioned it to be very promising in the future. With 2ghz coming out in the near future (I will believe it when it happens). Once I read some more reviews I will give a little more feedback.

[cracKrock]

It seems like the first releases of every generation of the Pentium processor iteration are underwhelming performers. I guess I shouldn't have been, but I was really disappointed with the performance benchmarks I've seen so far. I was expecting the P4 to destroy everything that's currently out. Instead, the Athlon 1.2Ghz kept up quite nicely. The P3 1Ghz isn't too far behind to make it obsolete, either.

If you factor price into the equation, the P4 is a huge loser. Dual RDRAM channels??? Holy cow, this thing is going to seriously set you back some bucks. If Rambus could solve their high latency problems, their technology might be worth it. But, their high-bancwidth is negated by their high-latency.

Our computers, by definition, are general purpose devices. Ok, so the P4 may get 200fps in Q3 at 640x480 resolution. But, it really lags behind in general office-type applications. So, what's the incentive for businesses to upgrade? Also, home users aren't playing Quake all the time. We also use office apps.

So... overall, I'm disappointed with the P4.


------------------


...
check out: http://www.tranzor.net

[Humus]

A)
My point of view of general performance:
Athlon 1.2GHz DDR - 135%
Athlon 1.2GHz SDR - 125%
P4 1.5GHz - 110%
P3 1GHz - 100%

B)
Office productivity, well, no big deal for me at least.
Video and Audio can take much advantage of SIMD optimizations and the high bandwidth. DCT/iDCT which is very central part of MPEG/MP3/JPEG etc are when properly optimized very parallel and could gain a lot of SIMD.
Quake 3 has always been a memory hog, with the quad bus it wasn't a surprise that P4 would shine on this one. Other games seams to bring less impressive scores. Partly it could be still unoptimized drivers, but also that the P4 only has one SSE unit while P3 has two. The poor FPU isn't helping either, which probably is the key to the bad workstation apps performance.

C)
I think P4 will improve over time. The improvement will mostly be on P4 adapted instruction flow, and not SSE-2 optimizations. Don't expect SSE-2 to your improve gaming experience, the old SSE is much more suited for this since it works on floats while SSE-2 works on doubles. Games will always use floats, and graphic card drivers will always run optimally when passed floats. The extra precision added by doubles isn't needed for games, so processing two doubles in parallel instead of four floats isn't going to happend.

D)
Sure, o/c possibilities adds some value, but I think P4 will need to be released in higher frequencies soon to be really competitive.

[Arcadian]

Originally posted by Humus:
A)
My point of view of general performance:
Athlon 1.2GHz DDR - 135%
Athlon 1.2GHz SDR - 125%
P4 1.5GHz - 110%
P3 1GHz - 100%

I wanted to do a little analysis to see if your estimation prooves useful. I'm going to average actual scores from Sharky's, Anand's, Ace's, and Tom's Hardware web pages in productivity, games, video/audio, and other. The order will be Pentium III 1GHz (on i815 if possible), Pentium 4 1.5GHz, Athlon 1.2GHz, Athlon 1.2GHz+DDR. The Pentium III has a base of 100%

Productivity:

Tom's Hardware Sysmark:
100% 95.2% 104.3% 115.5%

Anand's Content Creation Winstone:
100% 110.9% 111.1% 117.6%

Sharky's Content Creation Winstone:
100% 116.8% N/A 121.6%

Sharky's Sysmark:
100% 101.5% N/A 113.6%

Average:
100% 106.1% 107.7% 117.1%

3D and Games

Tom's Quake III:
100% 132.7% 104.5% 116.7%

Tom's MDK:
100% 121.9% N/A 123.6%

Anand's Unreal Tournament:
100% 102.4% 104.1% 112.2%

Sharky's 3D Mark (Win98):
100% 127.8% N/A 117.5%

Average:
100% 121.2% 104.3% 117.5%

Video/Audio

Tom's Mpeg4 compression:
100% 160% 114.3% 127.7%

Ace's Hardware Soundforge (couldn't find similar bench on Anand's):
100% 105.6% N/A 131.9%

Ace's Hardware GoGo MP3:
100% 113.6% N/A 129.3%

Sharky's Windows Media Encoder:
100% 194% N/A 125.5%

Average:
100% 143.3% 114.3% 128.6%

Other
Here I will take a wide range of tests where the Pentium 4 both underperforms and overperforms.

Tom's 3D Studio MAX:
100% 93.3% 175% 175%

Tom's Linux Compile:
100% 102.2% 122.7% 123.8%

Anand's Spec Viewperf (average):
100% 121.6% 115.5% 127.8%

Sharky's Dragon Naturally Speaking:
100% 114.5% N/A 112.5%

Average: (Athlon 1.2GHz SDR weighs strangly due to excellent 3D Studio scores and missing Dragon score)
100% 107.6% 137.7% 134.8%

Now if we take Productivity, 3D games, Audio/Video, and other, and take a final average, this is what I get for overall processor advantage.

Pentium III 1GHz on i815: 100%
Pentium 4 1.5GHz on i850: 119.6%
Athlon 1.2GHz on KT133 : 116%
Athlon 1.2GHz on 760 DDR: 124.5%

This is using a wide range of programs that show the strengths and weaknesses of the Pentium 4. I believe this to be a fair representation of the programs out there, and although the Athlon at 1.2GHz with DDR outpaces the Pentium 4 at 1.5GHz, the amount is not as much as you have made out. I think this is a much better comparison. Any comments from anyone?

[Arcadian]

I also wanted to add to my analysis the fact the SSE/SSE-2 optimizations should really improve upon the Pentium 4 is a lot of those scores, so I can see the Pentium 4 really leading by a larger margin by the end of 2001. I also wanted to mention that the Palomino Athlon may further AMD's lead as well, so between Intel's optimizations and AMD's new processor, things may get interesting, and either one can take the lead. Right now, though, the Pentium 4 is not a bad performer. It just costs too much.

[JabberJaw]

Arcadian, why do you suppose that the P4 performance spiked with Tom's Mpeg4 compression @160%, and Sharky's Windows Media Encoder @194%?

[Arcadian]

Originally posted by JabberJaw:
Arcadian, why do you suppose that the P4 performance spiked with Tom's Mpeg4 compression @160%, and Sharky's Windows Media Encoder @194%?

I can't find where I read it, but someone on Ace's Forums had a theory that the compression codec found in mpeg and jpeg files is a very optimized codec with very predictable program flow. This is really what the Pentium 4 accels at, and also what it was designed from the beginning to do well in.

You will probably also notice Tom's 3D Studio MAX test that has the complete opposite effect on the Pentium 4. I believe this may be a result of very floating point intensive code. The Pentium 4 was designed to have a powerful floating point engine, but only around the SSE/SSE-2 core. I really do expect to see the Pentium 4 meet or exceed the large Athlon performance gains in this test with proper SSE/SSE-2 enhansements.

It goes to show that some applications should be able to benefit from Pentium 4 optimizations. These programs will probably be a long time in coming, but a year down the road, when Northwood becomes popular, I definately see Pentium 4 being the most compelling choice. This is just my opinion, though.

[JabberJaw]

So Arcadian, does that corollate to "streaming media performance", which along with high-bandwidth Internet connection, is touted to bring the next "killer apps" to the home? Will the Itanium also use the same SSE/SSE-2 core? (3D Studio MAX, and other such apps, will likely be optimized for workstations.)

Also, I read that the performance 'hit' presently caused by large branch misprediction, essentially diminishes, as the core clock speed increases in relation to the memory bus speed. Along this line of thought, I've heard speculation that Intel could have split their production volume, and released 1.7Ghz (or faster) chips along with these 1.4/1.5 Ghz chips, but at lower quantities. Everything faster than 1.5Ghz was 'locked' to 1.4/1.5Ghz to ensure order volumes are being met. In other words, we could see major performance increases very soon, due simply to production ramping up. Does that make sense?

Guess I'm bringing more questions than answers, I appreciate your responses, Thanks!

[Phoenix]

I was wondering how fast the P4 will reach, at it's max, with these increasingly fast speeds, it would seem to me that making sure the timing in these systems would be very har to control. Any repsonses would be appreciated

------------------
"Only two things are infinite, the universe and human stupidity, and I'm not sure about the former." - Albert Einstein

[FragMaster]

P4 LOOKS GOOD ON PAPER AND MIGHT PREFORM WELL WHEN SSE2 COMES OUT IN MORE POPULAR APPS, BUT THE COMPARISONS HAVE BEEN MESSURED BY SLOWER CLOCKED 1.2 GHZ ATHLONS. GIVEN THE DEPTH AMD'S PROCESSORS HAVE SCALED THERE IS MORE OF A MINOR GHZ PRE GHZ PREFORMANCE INCREASE!

i like the idea that intel is trying to remove as many bottleneks as possible.
but in tests is it really working?

isn't one of AMD's new processors coming out this year going to be able to take advantage of sse and sse-2 ??

just as many thought AMD was looking down the road building the new athlon core, intel is also took a peek when designing the P4.

witch new generation cpu will stand the test of time?

[Arcadian]

Originally posted by JabberJaw:
So Arcadian, does that corollate to "streaming media performance", which along with high-bandwidth Internet connection, is touted to bring the next "killer apps" to the home? Will the Itanium also use the same SSE/SSE-2 core? (3D Studio MAX, and other such apps, will likely be optimized for workstations.)

Also, I read that the performance 'hit' presently caused by large branch misprediction, essentially diminishes, as the core clock speed increases in relation to the memory bus speed. Along this line of thought, I've heard speculation that Intel could have split their production volume, and released 1.7Ghz (or faster) chips along with these 1.4/1.5 Ghz chips, but at lower quantities. Everything faster than 1.5Ghz was 'locked' to 1.4/1.5Ghz to ensure order volumes are being met. In other words, we could see major performance increases very soon, due simply to production ramping up. Does that make sense?

Guess I'm bringing more questions than answers, I appreciate your responses, Thanks!

Well, let me address you first question first. The Itanium will not use SSE or SSE-2, and the reason is that it won't have to. The Itanium actually has a more advanced SIMD operation native in the hardware.

SSE gives the Pentium III and Pentium 4 128-bit SSE registers. By filling these registers with four 32-bit single precision numbers, SSE instructions can execute the contents simultaneously. SSE-2 allows 2 double precision 64-bit numbers to be used instead, which can accelerate apps that need the extra precision (scientific apps, for example).

I believe the Itanium has 128 80-bit floating point registers. The extra bits allow for extended precision calculations, something that even SSE-2 doesn't allow. The Itanium is able to simultaneously execute the contents of 4 of these extended precision floating point registers, for a total of 4 extended or double precision floating point calculations, or 8 single precision floating point calculations EVERY CLOCK! So even though the Itanium doesn't clock higher than 800MHz, it packs a whallop in every one of those hertz. Consider it the antithesis of the Pentium 4 .

Regarding your question on ramping up megahertz, I definately think it's possible. However, the last thing Intel wants is another 1.13GHz Pentium III fiasco. In other words, Intel will not release a new Pentium 4 unless it has plenty of headroom. This should be good news to overclockers, as they will probably be able to squeeze a couple hundred megahertz out of every Pentium 4 they buy. This means that if Intel decides to release 2.0GHz in Q3 2001, they should be able to actually produce them up to 2.2GHz. And this is all on a .18u process!

I believe scalability to be much higher on .13u. To address a concern made by Phoenix, I believe that Intel has already thought ahead, and is already prepared to deal with the problems associated with > 2.0GHz clock speeds. The EMI grounding clamp and new 12 volt power supplies are just a few of the obvious precautions already being implemented. You didn't think that 1.5GHz actually needed these things, did you?

There are actually some other goodies that I know about, but am not at liberty to divulge. There are also some VERY interesting features that will come on a soon to be released update to the Pentium 4 architecture that I have recently been made aware of, but yet again, I am not at liberty to divulge. I will say one thing, though. Do not count Intel out of the server market because they don't have a dual processor solution just yet .

[CajnDave]

I saw on Tech TV tonight that Intel is recalling the P4 because of wrong software codeing or something to that effect.

------------------
I am an enigma in my families gene pool.

[Arcadian]

Originally posted by CajnDave:
I saw on Tech TV tonight that Intel is recalling the P4 because of wrong software codeing or something to that effect.

I am making this post less rude, since I don't think my last post was very deserving. I kind of jumped the gun, too, so I appologize. However, I still believe it inappropriate to spread rumors that are unsubstantiated, and can give a wrong impression of the facts, especially when the truth can easily be looked up. If anyone is interested in the actual article, you can read my reply to CajnDave in the CPU forum, so I don't have to make the same post thrice.


[This message has been edited by Arcadian (edited November 21, 2000).]

[CajnDave]

Originally posted by Arcadian:
[B] You DOLT! Here is the excerpt from Tech TV's web site.

B]

Thanks for the nice correction.
Talk to Tech TV. I just repeated what they said . I wasn't trying to start rumors I thought someone might find it interesting. I'm not in the rumor business. I didn't mean any harm. I have nothing agianst Intel I have a PIII in my current sys.

------------------
I am an enigma in my families gene pool.



[This message has been edited by CajnDave (edited November 21, 2000).]