Why is Intel out doing AMD

[Just Having Fun]

Why does intel have cpu up to 1.7 ghz, and amd is laging behind with a 1.4. Anyone have any news on the schedule for amd chip speeds, or do i need to buy intel to stay on the cutting edge.

[Machupo]

you know... it's this attitude that just reminds me that most people in the world are idiots

Intel's trying the same thing Apple is quite comfortable with... the mhz myth...

the # and efficiency of pipeline stages is just as important (and sometimes more) than sheer mhz...

read this: http://www.amazon.com/exec/obidos/ASIN/1558604286/qid=999034695/sr=1-1/ref=sc_b_1/002-7216084-4320003

[Just Having Fun]

Thanks... i guess. Just wanted some info.. So i like cutting edge stuff. Thanks for the link to buy a book. Sorry not for me! I guess what i am getting at is if we do not have people pushing the envelope, then we will still be using commador 64! Don't get me wrong c-64 was fun but not that good.

We need to keep having things evolve.

[giant69]

To answer your question is a complicated one! AMD is ramping up their CPU's nearly as fast as intel. The difference is the way they achieve their goal. AMD and Intel both have areas that their CPU's perform better than the other. Currently an Athlon 1.4 blows the doors off a 2.0 P4 and scores nearly the same as a 2.2. Here is a link to a great comparson by the fine folks over at [H]ARD OCP where they compare a 1.4 T-Bird vs. a 2.0 and 2.2 P4. Read that and it should answer any questions you have...steve http://hardocp.com/reviews/cpus/intel/p42ghz/

[Hellmund]

Oh and Intel is officially at 2ghz now, not 1.7ghz. The 2ghz has a much lower IPC(instructions per clockcycle) so it HAS to run at a higher speed. Intel P4 has to have optimisation to preform. An Athlon runs everything well and just get's better with optimisation. Only now with 2ghz is Intel actually beating the 1.4ghz T-bird in about half the popular benchmarks. Not to mention the tremendous price premium you have to pay for a P4 system. I850 + RDRAM + the P4 itself is quite an expensive package.

[Machupo]

true, so true, hellmund...

gotta just love it how one company charges x5 for the same performance, yet still manages to make headway in the workstation market thanks to the oblivious nature of the normal consumer...

if people only took 5 minutes to investigate what they were about to purchase instead of taking the word of some idiot at staples, circuit city, best buy, etc... (no offense if anyone works there... a good buddy of mine works at CC, but he also knows where to get his procs....)

it's like Dell... i swear, nothing pisses me off than a company that is sworn to uphold a less effective price point.. what a "wonderful way to run a business"... jeeez.. what clods...

i'm glad we in the enthusiast crowd have a bit of reasoning going on http://www.sysopt.com/forum/biggrin.gif

[paul233]

Nice handle, Just Having Fun :-).

Remember guys and gals, if it weren't for Apple we would still be typing c:/ to get anything started and if it weren't for AMD we would be squeezing 300 out of a 266 at most. And if it weren't for Intel sharing their goodies we would be paying 4k for that!

It's called competition, folks, and that, and opposable thumbs, have got humanity where it is today.

[Hellmund]

Maybe Paul, but I think we would still have a GUI, just not as advanced and as easy to use. Actaully I think we'd still be at around 800mhz, intel would be keeping ahead of cyrix's Samuel III still. Of course we certainly wouldn't have P4's around. Intel would probaly just be sitting at 1ghz with the PIII and be charging a HELL of a lot for it. We'd also have only RDRAM.........with I820 ('shudder').

[TechDude]

Well .. the reason Intel is pushing so hard to bring out those 298Ghz cpus because they know what AMD cpus can do.

Look at it this way, the main reason the Athlon 1.4Ghz outperforms the P4 1.8Ghz cpu is because intel was rushing as fast as they can to finish the P4 and get them on the shelf since their P3 sucked compared to Duron and Athlon cpus. The price they paid for brining out so fast is performance, they had to drop off A LOT of features, that if were kept then it would kill the Athlon cpu.

Also right now Intel is going up in hertz so fast because they want people who know nothing about pcs to buy them. If you knew nothing about pcs, and i offered you a Athlon 1.4Ghz cpu (From AMD who you have never heard of.. btw has anybody here seen comercials??) or a P4 1.6Ghz (From Intel who you have heard of sicne they rerun their comercials ever few minutes.). You would choose the 1.6ghz right? Of course the people who know even the slightest about athlon processers will of course choose the athlon anyday, unless of course they wanna brag and say "haha i have a p4 and u dont haha u suxxorz".

And also from the benchmarks at anandtech.com, it looks like the Athlon cpus' still stomp the 2Ghz P4 cpu by a score of 8-5.

[TechDude]

And imo.. Intel has gotta drop those P4 prices by a lot if they hope to sell them to people who cant dish out $600 for a cpu.

Athlon 1.4Ghz = $130, and performs better than 1.8ghz, and just as well as 2ghz.

P4 2Ghz = $600.. and is really slacking off in performance.

You also gotta consider that the reason AMD is taking so long because they are probably trying to actually make the cpu better overall, rather than just incrase the clock speed.

[Machupo]

lol... so basically, this has turned into a circle-jerk of those of us "in the know".... because we all know that the athlon is better and cheaper http://www.sysopt.com/forum/wink.gif

oh well, persecution of the better, yet less "tied in" product is the norm in our society

this is definately one of those times that if i were rich i would run an AMD Athlon4 commercial (because AMD seems to not give a flying f*ck about their adverts) so that at least some people knew :p

sorry for the pointless rant :-/

[RobRich]

Run a real-time non-linear video editor on a P4 with Rambus, then on an Athlon with DDR. You'll spend the extra money for Intel's 1500+ MB/s of PC-800 memory bandwidth.

Otherwise, for most day-to-day tasks, AMD does have a superior product. I am using a 1.2 GHz Thunderbird in my primary box. http://www.sysopt.com/forum/smile.gif

My $.02,
Robert Richmond

[Machupo]

Robritch...

hate to tell you, but DDR / AMD systems have gotten over 1500mb/sec mem bandwidth (beathen p4/rdram sys in sandra)... it's not quite the gap it's cracked up to be

if anyone to the time to tweak their systems, maybe this would be commonplace, but the age of complacent overclocking has struck us...

[TCWolffe]

Rambus Bandwidth Myths 101:

(I'm back in school, lame pun...hehehehe)

ahem...

The P-4 uses a 128-byte sectored cache (across 8k, that is 64 sectors), leading to (obviously) 128-byte external bursts. Occasionally 64-byte bursts are seen for write-backs, code-fetches, etc (by the way, this leads to about 20% of the L1 cache being unused, empty, wasted, but that's a delve into microarchitectural theory we'll save for another day, okay?).

The PIII uses 32-byte cache line (not sectored), all (ALL) external accesses are 32-byte (allowing excellent L1 cache hit rates). When a burst from main memory comes in, the information demanded by the processor is put in first, then the neighboring data is brough in (up to the cache line size for that burst). As you can easily predict, the 4-times-larger cache lines of the P4 artificially inflate the Bandwidth to, you guessed it, 4-times the amount (100MB/s PIII vs. 400MB/s P4).

In the end, this results in a latency delta of 19% over the P4's own predecessor, as well as a 33% increase in burst time.

SPECint Vortex Benchmark scores show the P4@1.5GHz running only 3.5% faster than a PIII@1GHz, and the Athlon T-Bird@1.33GHz with DDR running 13.7% Higher than the PIII (scores are 710, 735, and 807 - respectively).

worth twice as much money to you? and when my 1.2GHz AXIA gets paired up with nForce's dual memory controllers, it's going to 1.5GHz (150x10, 300MHz DDRx2!!!!)

[RobRich]

I would like to see those benchmarks, and I am not referring to results from a nForce 128-bit dual channel DDR board that isn't even available outside of nVidia R&D. Then again, I have internal specs for that one as well, and they are definitely not near 1.5 GB/s.

The SIS735 chipset is the lowest latency, highest bandwidth EV6 bus compatbile DDR solution available for the K7 architecture. Looking at around 1.0 GB/s with a Athlon MP at 1.5 GHz here, so this doesn't add up here either.

The is only one current Athlon chipset capable of higher memory bandwith than the P4 RAMBUS architecture, and it will never be released for public usage. Micron's MAMBA architecture uses a traditional EV6 design, but a chipset level L3 cache is added to offset memory latency. The internal numbers look impressive, especially for branch-predictive tasks. However, Micron can not release the chipset due to high production costs and potential liscencing issues.

I do hope you're not talking about nVidia's attempt at an integrated low-cost product. The 128-bit nF chipset can not produce significant performance gains in terms of memory bandwidth or latency. The Athlon only allows for a 64-bit memory bus which limits bandwidth without effective ramps in processor to chipset to memory bus MHz speeds. Forget trying to improve latency without a chipset level cache mechanism (nForce does not have!), as the Athlon has relatively poor scheduling efficiency due to its severly limited g-share branch predicition routine combined with absolutely no capabilities for L2 cache instruction re-sequencing without completely stalling and flushing the execution pipeline. Definitely not optimal for ideal memory op efficiency.

While I'm on Athlon chipsets, here is one tidbit that you'll never see in a nVidia press release: The nForce audio controller doesn't even work correctly. And I'm not talking about driver probs either......

While discussing benchmarks, new Spec date was published earlier this week:

SPECint2000
P4 2.0 GHz: 640 peak
Athlon 1.4 GHz: 554 peak
AthlonMP 1.2 GHz: 522 peak

SPECfp2000
P4 2.0 GHz: 704 peak
Athlon 1.4 GHz: 458 peak
AthlonMP 1.2 GHz: 481 peak

People are starting to realize the potential of Pentium IV optimizations. The addition of code vectorization for SSE2 with additional hardware code hint conventions had afforded significant gains. Also, programmers seem to have finally learned how to properly code for datagram alignment. Many write of the P4 FPU as being weak, but this is not the reality. Programs featuring poor data alignment in terms of cache operations will suffer with the P4. The above SPEC results were obtained through optimizated alignment ops. Notice the serious increase in performance.

Why is it hard to believe that the P4 platform is a superior architectural design in certain situations as compared to current Athlon offerings? Intel can't help that none seem to ever bother to read the P4 programmers guide, even though the documentation is freely available. The tricks that were possible with the Athlon or P6 core (PPro through P3) are no longer viable for the P4, but programmers seem to still hold on to these legacy code conventions for some reason.

Best Regards,
Robert Richmond

[This message has been edited by RobRich (edited 08-28-2001).]

[RobRich]

Yes, tech talk for once! Been awhile since I posted a true tech article here at SysOpt, but I'll give this a go with a forum post from my experience. First read this:

http://www.sysopt.com/articles/p4/index.html

The reason for poor software performance in some applications stems to a completely revamped programming structure as compared to any x86 platform available before the P4's introduction. The issue is not impart to branch prediction as many think, as the P4 features one of the most efficient branch prediction routines currently available, especially when combined with its large branch TLB table. Actually, did ya' know the Athlon has a poor branch prediction routine, as even the P3 offers higher efficiency. This is one of the major reasons for the next-gen Athlon Palomino introduction, though only the TLB size is increased with this revision.

Let's take on some other common misconceptions as well:

Before trying to dismiss the pipeline length as associated to the P4's branch prediction routine, did ya' know that the Athlon offers only a relatively simple G-share routine? This means it is limited to only two branch predictions per 16-bit byte code window. To increase the branch table without offering any modification to the branch predictor itself would prove rather useless for the most part. What is the point of adding more buffering space when the Athlon can only carry out two standard branch predictions per cycle? Hopefully AMD will choose to implement a better branch routine to better correlate with the larger TLB table size later generation Thoroughbred or H-series.

For further evidence, one must examine currently available programs. Most programs feature 13-14% of branch predictive coding, with several of the operations often requiring atleast three branch predictions for maximum ILP and IPC. By performing some quick calculations, it can be estimated that ~10% of all branch prediction tasks are not even assigned a predictor bit by the scheduling engine! This leads to a back log, thus creates an effective stall of the Athlon processor. Simply increasing the TLB size does not offset the problems associated with the G-share branch prediction algorithm.

The above scenario does not even account for a cache miss when associated with a branch prediction. The Athlon offers instruction re-ordering for L1 cache misses, but lacks any form of L2 re-sequencing capabilities while in flight during a clock cycle. For loads and stores, the K7 has 2 queues, a 12-entry LS1 and a 32-entry LS2. Load/store-ops are dispatched to LS1 and removed in-order two at a time when the addresses are available (stores and load misses are moved to LS2). So if the oldest op in LS1 does not have its address available, then LS1 stalls. This in-order nature of LS1 allows load-load reordering only for L1 cache misses. To compare, the Pentium 4 offers full re-ordering for all L1 and L2 cache misses associated with all operations, except IN, OUT, and serializing instrctions. Now consider that the P4’s 64-bit inclusive cache architecture offers nearly 150% the bandwidth for L1 cache operations and upwards of 400% the bandwidth for L2 cache operations (SSE2, 128-bit datagram) as compared to the Athlon Thunderbird’s exclusive cache design.

Not only does an Athlon stall during an L2 cache miss, the tendency to stall is quite often. The Athlon’s decode unit can issue 2.8 instructions per clock cycle, but the Athlon’s L2 cache require 11 cycles to return data. Branch predictive operations often operate with L2 data due to large storage arrays. In order to maintain a standard IPC rate of 1.5, the Athlon Thunderbird must find atleast 11 x 5 = 17 instructions per L2 cache miss. The Athlon’s integer instruction buffer can only allow for 18 instructions, thus the processor will effectively stall during an L2 cache miss. Factor in the moderate potential for a branch predictive operation in actually setting forth the condition for this L2 miss, than one can easily see the Athlon will effectively stall, and must flush/reset the execution pipe to continue normal operation.

The Athlon’s short pipeline length does help, but it is not a solution to the concern I’ve noted above. For once, a longer pipeline could prove more effective. For instance, the P4 can buffer upto 126 micro-ops in flight during a single clock cycle due to a split buffering architecture using multiple schedulers and buffering regions along the 28 stage (20 after the trace cache) pipeline. The Athlon only has the capability for 18 in flight operations. Compare the pipeline lengths to the in flight op rate, then one can easily realize the P4 offers a higher degree of instruction efficiency per clock cycle.

Now examine how this relates to the P4’s branch predictor. The Athlon Thunderbird will offer superior branch prediction only situations where highly dependant code utilizing a data of under 512 KB is taking place. The Pentium 4 offers a more linear performance approach due to a higher efficiency capability (more proof, examine the ILP and IPC nature of the P4 as they compare to latency and bandwidth). With large data arrays, the P4 will still offer the same linear performance curve, while the Athlon will continue to degrade at an exponential rate. To examine this in action, try running the industry accepted Queen’s Loop routine (wrote in standard x86 assembly, of course). This test creates a small array of 32x32 for data manipulation while loading an intensive sequence of branch predictive tasks. For comparison, the Athlon TB outscores a similar clocked P4 by less than .2 seconds! Assuming we converted the code to C++, then utilized the Intel’s C++ compiler, the P4 would actually outscore the Athlon by a large margin. This is due to compiler feed back directed optimizations for the HWNT and HST hint prefix instructions. The addition of these two factors can increase branch prediction by upto an estimated 25+%, thus propelling the Pentium 4 past the Athlon in all branch predictive scenarios.

We all know the Pentium 4 offers superior integer performance, but I can go on to produce evidence that the P4 offers superior floating point (x87 and SIMD) as compared to the Athlon, assuming anyone wants to read through the boring technical aspects. Any rate, the above revised SPEC results speak for themselves. The problem with the P4 is the lack of software optimization for the architecture. Most current software does not include any real P4 specific coding outside of the occasional SSE2 instruction. Worse yet, a large variety of today’s software is improperly coded and compiled to meet the programming specifications definied within the P4 programmer's guide, thus leading to even lower performance. However, wait until the next generation of vertorized compilers with dynamic re-coding capabilties arrive! Factor in the expanding acceptance of the Intel P4 IA-32 programmer’s guide, and the P4 should be an exciting platform in the near future, especially considering it only at the early stages of its overall product lifecycle as compared to the AMD Athlon.

Hope this helps,
Robert Richmond

[This message has been edited by RobRich (edited 08-29-2001).]

[Tron]

anyways Intel will be at min. 3500mhz next year and amd just comes up with a hole lot of new cpu´s: 1400mhz & 1533mhz Athlon(Palomino), the 1,1Ghz Duron and some workstations and server cpu´s(MP?) at 1.333, 1.400 und 1.533 MHz

http://www.sysopt.com/forum/smile.gif

[Hellmund]

That was good reading rob http://www.sysopt.com/forum/smile.gif

So nVidia's MPU isn't ....perfected yet, I wonder if it would be viable to attach a different southbridge, I mean the thing of most interest is dual-channel DDR RAM. Even though as you've said before where the chipset with be very expensive the price would be offset due to the DDR RAM and Athlon itself. Is the K7 core actually fully capable of utilising the bandwidth though?

the P4 should be an exciting platform in the near future, especially considering it only at the early stages of its overall product lifecycle as compared to the AMD Athlon
How far into the future do you think it'll actually be? The original Katmai's SSE instructions are still not entirely used.

One other thing, will the K8 hammer series actually have any impact on the desktop, or is AMD just working on a die shrink in the form thoroughbred to clock-speed competitive in the desktop arena. Seems trange that AMD has nothing to directly compete clock-speed wise. I read on anand Intel demonstrated a Northwood core PIV running at 3.5ghz already. Also of interest they showcased a 4ghz Processor with dual-ALU's. I like the little comment he put though, "essentially 8ghz", yeah just like 2 MP's on a Tyan Thunder is 2.4ghz http://www.sysopt.com/forum/smile.gif

[aldtech]

It seems to me that this entire post has gotten of the beaten subject. The original question was:

"Anyone have any news on the schedule for amd chip speeds"

I too would like to know AMD's schedule on new CPUs. Is the latest and greatest coming out soon? I think that given the previous posts that we can all agree that AMD smokes Intel's ****.

AL

[mudoggy]

Forgot the topic?

Heck, I forgot who I was just going to call after reading the following line above:
"...the Athlon has relatively poor scheduling efficiency due to its severly limited g-share branch predicition routine combined with absolutely no capabilities for L2 cache instruction re-sequencing without completely stalling and flushing the execution pipeline. "

Took me a little while to chew and 'process' that one.

Thanks for your insight, Rob, backed up with some numbers and theory. While I am a big AMD fan, I realize that Intel still has a lot of innovation up it's sleeve (sleeves that are also stuffed full of money/capital), and that in the end, innovation that is properly positioned and priced, and yes, promoted, wins the day.

[camaro]

Price factor will always outweight the innovation factor. Intel could be kicking ****, but if it's for much more $$$ then it won't matter. Let's face it. There is no difference running word on 2.0GHz vs 200MHz. Heck I didn't notice ANY difference surfing online with my PII 233 vs my 1.2 Bird. Only hardcore gamers and CAD design people might be interested in absolut best.

[gyoung]

I agree with you on that camaro, I just upgraded from a Duron 600Mhz to a Athlon 1.2Ghz and you don't notice the difference in everyday computing. Though my QuakeIII FPS increased by 20 frames.

The difference is that in order to get the same performance in Word in WinXP you need a boost in the CPU. Every new OS from Micro$oft adds more bloat and slows things down. Plus, over the next year or so who knows what new software will be out to push the systems.

Though you still are right. To do everyday tasks you could still run Win98/Win2k and Word 2000 to get everything done that you need to on that 233Mhz machine. It works great for my parents.

[This message has been edited by gyoung (edited 08-29-2001).]

[Turnip12]

sorry, double post

[This message has been edited by Turnip12 (edited 08-29-2001).]

[Turnip12]

Can anyone reccomend any good sites to help explain Rob's post? http://www.sysopt.com/forum/smile.gif I'd like to get into it more but most, ok just about all, was over my head. I'd love to understand more about hardware without shooting for an engineering degree. On the subject about "innovative" Intel, the T-bird is at it's end right? I mean the T-birds aren't really meant to compete with the P4s are they? Isn't that what the Hammer line is for? These are just the tweaks for the end of the T-bird line right?

[This message has been edited by Turnip12 (edited 08-29-2001).]

[gyoung]

I think the Athlon is meant to be the direct competitor to the P4. The Hammer series is meant to compete with Intel's Itanium.

Here's a good article: http://www.anandtech.com/cpu/showdoc.html?i=1524

Basically clock speed isn't enough anymore. You also have to look at instructions per clock. This snippet may help explain it a little better:

How much work the processor can do in a single clock cycle, measured in Instructions Per Clock (IPC), matters just as much as clock speed. At the same time, measuring a processor’s performance in IPC wouldn’t make much sense either since a CPU capable of an average IPC of 5 instructions per clock yet only capable of running at 50MHz wouldn’t be faster than a CPU capable of an average IPC of 1.5 instructions per clock yet capable of running at 1GHz. The combination of IPC and clock frequency determines the true performance of the CPU.

[The Beav]

Hey Tron,

Are you a phsycic or had you already read this...........
http://news.excite.com/news/ap/010828/20/intel-future-processors

http://www.sysopt.com/forum/wink.gif

[Machupo]

arggg.. i'm tryin' to remember the website of a comparison between the K7 and the Willamette (kinda outdated, but still good info)... it was like www.chip-something.com (http://www.chip-something.com) or something like that...

it was written for the investor, so it isn't too nutso into theory, but it does go into discussions of prefetch, pipelines, and trace cache...

[RobRich]

I recommend these in-house articles for people interested on the more technical aspects of computing:

http://www.sysopt.com/articles/usparc-3/index.html
http://www.sysopt.com/articles/p4/index.html
http://www.sysopt.com/articles/k8/index.html
http://www.sysopt.com/articles/soi/index.html
http://www.sysopt.com/articles/samurai/index.html
http://www.sysopt.com/articles/qdr-sram/index.html

Now to condense my earlier statements, the Athlon is the best choice for most day-to-day activities. I use one myself. It just happens that the P4 is a better solution for certain activities, such as multimedia editing or 3D design work. I am not accounting for cost, as people who generally buy P4 2.0 GHz workstations are usually not concerned over a few hundred dollars anyway. Must be nice...... http://www.sysopt.com/forum/wink.gif

Hellmund, I forsee the AMD Hammer as a potential desktop competitior in 2003 at the earliest. The ClawHammer should actually ship by mid-2002, but I doubt we will see prices below the server/workstation range until 6-12 months after release.

About the nForce, it should be possible to pair it with a VIA or AMD southbridge assuming nVidia does not use a proprietarty bus-link protocol. I believe specs for a MSI or Asus board featuring a hybrid nForce/VIA chipset was recently posted on Usenet, but I can not confirm this rumor until I receive the information for a trusted source.

The bandwidth of the nForce with 128-bit memory operation is suspect at this time. The Athlon only features a 64-bit memory interface, thus the other 1/2 of provided memory bandwidth will be utilized for other connceted hardware components. This additional 64-bit path is great for the integrated video controller, but it is questionable about the impact of this extra throughput when a standard AGP card is being used.

I personally would like to see AMD integrate the memory controller directly into the processor core to lower latency, then possible move the chipset architecture away from a bus to a crossbar-type design to increase bandwidth. This design has done wonders for Sun's UltraSparc-3 platform, but no desktop manufacturers have moved forward with this type of technology yet.

Catch ya' later,
Robert Richmond

[This message has been edited by RobRich (edited 08-29-2001).]

[Just Having Fun]

Hi all,

I think I started a good discussion here. This has been a great education for me, and I am glad to be an Amd user. There have been some great links here, and it still shows that Intel is not as good as all these places pushing the chip claims... Bang for Buck Amd has Intel Beat!

I purchased a Duron 650 for maybe 43 bucks last year, and was able to OC it to 950, with just a basic fan. I am ready to upgrade to the 1.4 T-bird for 128.00.. I can’t wait to see what it will do.

Thanks all for the education on the speeds. I knew this would get a lot of reaction..

Did I mention AMD is the BomB!

Just Having Fun!

[gyoung]

Not to bring you down JustHavingFun, but don't expect leaps and bounds going from a Duron 650 to the Athlon 1.4Ghz.

I just did the Duron 600 to the 1.2Ghz and you don't notice anything really in day to day computing. I don't notice anything even in gaming. Only if I look at a benchmark number I see an increase, but I don't feel it when I'm playing a game.

[gyoung]

I wouldn't say it's lack of talent from programmers, I'd say it's lack of time.

Most of these guys are under pressure to get things done yesterday, and when it comes to planning to take advantage of the new processors that aren't even out yet... well, that is the first thing to get dropped from list of "things to do".

So I would agree with RobRich that programmers don't take advantage of this stuff, but most of the time it isn't there fault. Developers target their software at desktops that are on the market and not at those that aren't. There is always a time lag for software to catch up with hardware.

[hirschY]

gyoung, did you also update your video card?

All this tech talk is making my head swell! http://www.sysopt.com/forum/frown.gif
I need a beer http://www.sysopt.com/forum/smile.gif

[gyoung]

I am still using the same video card that I had before. I'm using the ATI Radeon 32MB DDR retail card.

I did some benches using my Duron 600 clocked at multiple speeds (by changing the multiplier) and my new 1.2Ghz Athlon. I'll post them for you to look at.

[This message has been edited by gyoung (edited 08-29-2001).]

[Hellmund]

Thx Rob, I'd thank ya for the Links but I already read them around last year when you put em up. I think you'd know I read the QDR article, QDR in Vid-cards (http://www.sysopt.com/forum/Forum4/HTML/005066.html) was quite a memorable little thread http://www.sysopt.com/forum/smile.gif

Almost forget, yeah I've been trying to read as many tech documents as possible to better understand things. Recently Dputiger mentioned Tom's article "Rambus Requiem". I had always wondered why SDRAM never went over to dual-channel which boosted RDRAM so much. RDRAM only actually runs on a 16bit bus, it has to run 4X the speed of SDRAM just to keep up. In dual-channel it still only utilising 32bits....common SDRAM runs on a 64bit bus, in dual-channel it's gotta use a 128bit bus.....

Would you have any idea why AMD kept the K7 using 64bit memory bus?

[This message has been edited by Hellmund (edited 08-30-2001).]

[Jixor]

sorry to sound like a broken record but here is another site which reviews P4 and explains why P2 celery and P3 are the same processor and what Intel did to make P4 suck so much a** www.emulators.com/pentium4.htm (http://www.emulators.com/pentium4.htm)
one of the things mentioned is that P4 has as much L1 cache memory as the old 80486 :LOL

[gwinters]

I think that it is a good thing that Intel is pushing chip speeds up. They constantly have to refine their manufacturing processes to get the higher speeds. At least people can see that it can be done.

On the other end of the spectrum, AMD is making chips that are faster than Intel chips running at 150% higher clock speeds. It seems that AMD chips are more efficient, while Intel just wants more clock cycles. At least these companies are going in diferent directions rather than producing the same hardware with different names. If the same efficiency could be applied to the higher clock speeds, wow...

[samwichse]

"the P-4/Rambus architecture is a technically superior design."

It just doesn't perform as well because it doesn't have the right code?

To me that is like saying a high performance sports car is technically superior to a high performance off road buggy. Sure, the sports car has a great top end speed, but only on nice smooth flat roads. The buggy might be slower on a nice smooth road, but it kicks behind in non-ideal conditions.

[RobRich]

one of the things mentioned is that P4 has as much L1 cache memory as the old 80486 :LOL

Make sense, as the trace cache architecture does not require any more L1 cache than the P4 already offers. Read the P4 article I link above. Also, since the P4 can perform re-order sequencing for most common L2 ops, the need for a massive L1 cache is no longer an issue.

Robert Richmond

[RobRich]

About forget, it appears manual code optimization for vectorization may become less of an issue, atleast if CodePlay is sucessful in marketing its new VectorC compiler.

Check out these VectorC results when compiling the TestBench benchmarking program on a P3 600 MHz system:

VectorC P3 optimized
INT: 75
FP: 199
MEM: 71

Micrsoft Visual C++
INT: 41
FP: 52
MEM: 53

Micrsosoft VC++ optimized:
INT: 74
FP: 93
MEM: 76

These results where with VectorC v1.1. Version 1.2 is a couple of weeks away from release, so expect even greater returns when available. The ANSI C version is ready right now, though it will be another couple of months before the C++ version is ready for public release.

Now for the big news, check out this page of official results:

http://www.codeplay.com/vectorc/bench.html

Notice which architecture outperforms the rest. The Pentium IV 1.4 GHz outperforms the Athlon 1.0 GHz by nearly 3x in all tests!

The same general source code was used across the board for all tests. No manual optimizations are performed, only compiler time ops are being utlized. These perforamnce returns are the results what a properly optimized and aligned program can offer with the Pentium IV.

To AMD's credit, the Athlon Thunderbird did completely trash the Pentium 3 for the more intensive tests. It would also like to see results with an Athlon4/MP since it supports SSE. According to these results, I believe the current Athlon core will no longer prove to be a viable solution after 2002. Hopefully AMD is developing architecture changes that I am not currently aware of.

Robert Richmond

[EasyFast]

All I know is that AMD works!

I am no expert! Most of you forgot more then I will ever want to learn!

I just watch what you do, what you use, and copy it! SIMPLE! http://www.sysopt.com/forum/smile.gif

I build my own systems based on what works. If you guys have problems, I wait. Once you have it figured out and stablized, I build!

I just like things to work and I enjoy building my own system! I don't like problems and I don't like to beat my head against the walls.

So while you guys are working hard to gain that extra .05 mhz from you system, I'm playing wild 3D games and having a blast!

You work, I play!! Got to love the way this works http://www.sysopt.com/forum/smile.gif

Keep up the great work and please post when it's time for me to upgrade my system to an Intel, which I don't think will be anytime soon!

Can someone please summerize this thread for me? Is AMD still on top?

[Big B]

It depends on what area you're talking about.
For dual processors, Intel is the king here between the two. They've been actually doing it for a while; AMD has just come out with their first duallie. It's true AMD has had SMP support in their CPU's since at least the K-6's, there has not been an SMP chipset for AMD until now. AMD still has no proven track record in this area. I have had most of my rigs running Intel, and have not had a problem with them. My AMD system originally had a bad motherboard, so I had to replace that, but it runs fine now, and overclocked under Windows 2000.
For overclocking AMD is king here, hands down. I have had poor luck overclocking Intel CPU's.