Identify my AMD K6-2 300 66 or 100MHz bus??
JavaScript is disabled. For a better experience, please enable JavaScript in your browser before proceeding.
- Status
- Not open for further replies.
#1
-
Add bookmark
-
#1
Surfed around lookin for help and didnt get any View image: /infopop/emoticons/icon_frown. gif<BR>Here is all the info on the chip<P><BR>AMD<BR>AMD-K6-2tm — 2<BR>AMD-K6-2/300AFR<BR>2.2V CORE/3.3V I/O<BR>A 983OCPEW<BR>m c 1998 AMD<P>26050 k<P>Thats it cnat reaad the batch number in upper right hand corner TOOOOO small<BR>Styles
#2
-
Add bookmark
-
#2
66mhz<P>-BELMONT View image: /infopop/emoticons/icon_cool. gif
#3
-
Add bookmark
-
#3
Tell me how you figured that out Belmont??
#4
-
Add bookmark
-
#4
Actually the K6-2 (all of them) is a 100FSB part. However since the clock isn’t locked it can run at either depending on the board. What motherboard?
#5
-
Add bookmark
-
#5
Well, I don’t know how belmont or redleader came by their information, but I’ll add my input:<P>Since a processor is rated by its core speed, and the K6-x line is not multiplyer locked, it really shouldn’t matter if you run it at 66 or 100Mhz — just whatever the rest of your system can handle. I don’t claim to get any of this information from any source other than my own experiance. I would say run it at 100Mhz x 3.0 for 300Mhz and get the higher performance of the 100Mhz front side bus. Regardless of weather or not the part is intended to run on a 66Mhz bus, I don’t think it should matter because the core speed is the same. <P>Once again, this is all IMO, so take it as that. But I think 100Mhz should work fine.
#6
-
Add bookmark
-
#6
Yes, the early K6-2s ran on a 66 MHz bus. There were 266 MHz and 300/66 MHz K6-2s. IIRC when Super7 came about the 66 FSB parts were actually marked «300/66» (I think they actually had trouble running on a 100 MHz FSB).<P>Also it’s interesting to note that the 333 MHz K6-2s actually ran at a 95 MHz FSB, not 66.
#7
-
Add bookmark
-
#7
Yes, but when they switched over (the 300 and 350 were the first parts switched) they began shipping millions of K6-2 300s intended for a 100 MHz bus. Alot of people were amazed to discover that the K6-2 300/100 was faster than the 333/66. <P>Then AMD did some wierd stuff later like the 475 and 380, both of which everybody just popped up to 500 and 400 MHz, respectively, but saved a few bucks doing it.
#8
-
Add bookmark
-
#8
If you check out the k6-2 pdf spec sheet, you will find that the cpu you have is listed for 100MHz FSB.
#9
-
Add bookmark
-
#9
Ill check that PDF sheet again Kalahari thats the documentation I was looking for!!<BR> Styles
#10
-
Add bookmark
-
#10
your k6-2 300 is a 66 mHz part. the «afr» designation tells you that it’s a 66 mHz part; cpu’s with this designation are reject parts that failed at 100 mHz.
#11
-
Add bookmark
-
#11
AFR has nothing to do with the speed.<P>A= package type (CPGA)<BR>F= core voltage (2.1-2.3v)<BR>R= maximum case temperature (70 C)
#12
-
Add bookmark
-
#12
hmmm . . . i know i read somewhere that the «afr» designation indicates a 66 mHz bus. i’ll have to look for where i got that.
#13
-
Add bookmark
-
#13
Go to AMD’s website and look at the K6-2 datasheet. It explains what the different codes means (AFR, AFX, AHX, AFQ, ACZ, ACK, etc…)
#14
-
Add bookmark
-
#14
Well reading what other people have wrote here it seems that both answers are right. I know for a fact the K6-II I built was a 66mhz, and overclocked to 83mhz that was as stable as it got..perhaps later revisions of the chip were different….?<P>-BELMONT View image: /infopop/emoticons/icon_eek.gif
#15
-
Add bookmark
-
#15
BELMONT : Any K6-2 can be both a 100 or 66FSB part. It determined by what the MB supports and not the chip.<P>What the argument comes down to is what FSB did it say on the box. This is pretty stupid since 100 FSB MBs are plentifull. And I still say all K6-2s are meant for 100FSB and I can prove it View image: /infopop/emoticons/icon_smile.gif <P><BLOCKQUOTE><font size=»-1″>quote:</font><HR>However another feature of the, at the time, unreleased K6-3D processor was the fact that it ran on a 100MHz FSB instead of the 66MHz FSB that most Socket-7 CPUs ran at during that period. <HR></BLOCKQUOTE><P><BLOCKQUOTE><font size=»-1″>quote:</font><HR> the K6-3D was eventually released as the K6-2 <HR></BLOCKQUOTE><BR> From http://www.anandtech.com/showdoc.html?i=1373<P>BWAHAhahahhahahah View image: /infopop/emoticons/icon_biggrin.gif
#16
-
Add bookmark
-
#16
It is very interesting that they actually list a K62-300/66 and K62-333/66 part on AMD’s site.
#17
-
Add bookmark
-
#17
the chips slated as AFR-66 will not run stable at 100. this i have seen with my own eyes. But it must say -66 on the chip.<P>I still have a few afr-66’s at work.<P>100 mhz bus can start introducing a lot of harmonics and noise into the IO of the chip. The bus speed of any chip is definatly not limitless.
- Status
- Not open for further replies.
AMD’s New K6-2 Processor | Tom’s Hardware
Skip to main content
When you purchase through links on our site, we may earn an affiliate commission. Here’s how it works.
Last year in April AMD was able to offer the fastest Windows x86 CPU for a very short period until Intel released the Pentium II processor. Today, many people have already forgotten about this, simply being used to Intel as the all-time high end CPU supplier. Not only are Pentium II processors ruling the high end market but drops in prices have enabled the Pentium II to becoming more and more affordable. Intel decided to also get into the low end market and released the Celeron CPU, which is nothing other than a Pentium II without L2 cache. At the same time, the Pentium II at 100 MHz front side bus was also launched, assuring Intel’s lead in the upper class systems sector. It won’t be long before Intel comes out with the Pentium II Xeon CPU, which will also use the Pentium II core but with a second level cache that is running at the processor clock speed. Today you can look into almost any PC market segment and Intel is pretty much dominant. The alternative CPUs are becoming less and less popular.
Office Application Performance Becoming Less Significant In Favor Of 3D Performance
Times are not only changing in terms of Intel’s dominance. The way of how the performance of a processor has to be evaluated has changed a lot too. Whilst everyone was used to using office applications for system performance measuring in the last 5 years, nowadays there is a trend to veer away from these old trails. It’s not that people wouldn’t use office applications anymore, in the business sector as well as in SOHO people are still using a lot of or even mainly office apps. However, system performance has today reached a level where the user isn’t waiting for Winword or Excel anymore, but Winword or Excel are most of the time waiting for the user instead. This lead to the funny expression of ’Winstone is today measuring how fast the system is waiting for the user’.
Office application performance is still measurable and there are certainly still differences, but it’s really questionable how important office application performance is nowadays. Particularly in the lower end SOHO sector, people don’t really care about how fast their Winword is running. What is of prime importance today is getting more and more important today are the eye candy joys brought about by 3D gaming. A lot of the old fashioned computer journalists are going on about how bad the Celeron processor is, completely missing the point that nobody cares how fast it runs Winword, as long as it runs it as fast as a Pentium MMX 233. What matters instead is its 3D gaming performance and, surprise surprise, it’s performing very well in this field, making this CPU a lot better than what many publications have cited.
Floating Point SIMD Vs. Brute FPU Power
AMD saw this development taking place already a year ago, when they decided to improve the K6 CPU by specifically increasing the 3D performance. Whilst Pentium II CPUs are taking their great 3D performance from their brute FPU power, AMD decided to go a more elegant way of approaching 3D performance. The FPU of a CPU can do an amazing amount of complicated floating point calculations, but for 3D games only some of the FPU calculations are needed. Picking these special ’3D’ calculations and enabling the CPU to do them on several single numbers at the same time was what AMD did. Grabbing and then processing several data packets at the same time is called ’SIMD’ or ’single instruction multiple data’. This does not say that only one instruction is needed to work on multiple data, but this means that you do this instruction on multiple data of the same sort at the same time. 3D processing and rendering is using an incredible number of matrix operations. Huge amounts of data has to be processed all the same, usually done one after the other. SIMD can improve this significantly, because grabbing for example, four words and processing them at the same time is obviously faster than grabbing one word four times.
The first time SIMD was implemented into a x86 CPU was when the Pentium w/MMX was released. Intel did a lot of work convincing us that MMX would accelerate any kind of multi media, including 3D. Today Intel admits that MMX is mainly good for image processing, MMX2 or ’KNI’=’Katmai New Instructions’ is supposed to change that significantly though. The difference of the K6-2’s new instruction set ’3DNow !’ and what we know from MMx already is that ’3DNow !’ as well as KNI are able to do SIMD with floating point numbers (MMX could do this only with integers). Here’s where the 3D acceleration takes place.
Problem No.1 — New Instructions Require New Software
It took a long while for MMX software to materialise after Intel had released the Pentium w/MMX and it seems as if this was a painful experience for them. AMD is facing a similar problem with its 3DNow !. However their situation doesn’t seem to be quite so dire. Whilst MMX software wasn’t necessarily exciting, 3D games can easily amaze people, so that the demand will be higher, thus pushing game developers as well as 3D chip manufacturers into using 3DNow ! features as long as Intel will let them.
If anyone wants to take advantage of the new K6-2 and 3DNow !, there are three possible options on how that can be done. Either the 3D game is taking advantage of DirectX 6 by using the geometry engine of Direct3D 6, or the game has got its own geometry engine which is using 3DNow ! directly. Games that are only written for DirectX 5 or which don’t use 3DNow ! in their own engine will show only small or no improvements at all with the K6-2. The third option is a 3D chip/card driver that is optimized for 3DNow !. NVIDIA is the first 3D chip manufacturer who supplies a special driver for 3DNow !. It would be sensible to assume that AMD prefers game developers to use 3DNow ! directly in their games, but if this should not be an option, it’s still of advantage if the game is at least programmed for DirectX 6. It will be up to us consumers to push 3D chip makers into providing drivers that are optimized for 3DNow !.
Problem No. 2 — The Future Of Socket 7
On April 15, 1998 Intel had quite a memorable day. Not only were the next generation of Pentium II CPUs with 100 MHz FSB released, but there was also the release of the Celeron CPU, which was targeted at the low end market segment. Both CPUs are use Slot 1 instead of good old Socket 7. Intel wants Socket 7 to die a quick and painful death and AMD will have a rough job keeping people on this platform. It is certainly not easy to say what is going to happen with Socket 7, but it’s difficult to overlook meaning that Slot 1 looks the more future proof route to take right now. The K6-2 has to be a good enough product to convince people to stick to the Socket 7 platform. I doubt that any Slot 1 system owner will go back to Socket 7 however.
Office Application Performance
The 3D performance may be becoming more and more important, but the business application performance shouldn’t be ignored either. Although the K6-2 has got a new chip design, the integer part of the CPU is pretty much still the same as found in the K6. It was only optimized for the 100 MHz front side bus clock, mainly assuring a more stable timing at this speed. The K6 was already able to do the 100 MHz FSB, but AMD is not officially supporting this, due to above timing issues. More conservative timing slows down the CPU by a very small amount, which is why a K6 at 300/100 MHz is running business apps about 1% faster than the K6-2.
Compared to the Intel sixth generation CPUs the K6 was already running relatively better under Windows 95 than under Windows NT, and this hasn’t changed with the K6-2. However, you may remember how much performance increase the K6 gets out of the 100 MHz system bus, compared to the 66 MHz bus. Thus the K6-2 is now defintely the fastest Socket 7 CPU for Socket 7 in office applications, far ahead of the Cyrix ’M2’ and the IBM 6x86MX as well as the Pentium MMX to boot.
The Pentium II, especially the new 100 MHz FSB versions at 350 and 400 MHz core clock, is still holding the office application performance crown and this crown will only go over to the Pentium II Xeon processors with their L2 cache running at CPU clock once they’re released at the end of June. However, the K6-2 stands up pretty well to its Pentium II competitors at the same clock speed. Remember that the Pentium II is unlike the K6-2, hardly getting any benefit out of the higher front side bus clock, which is why we can expect the K6-2 at 350 and 400 MHz being around the performance of the PII 333 and 350, once AMD releases these versions later on this year.
Under Windows 95 the K6-2 300/100 is slightly slower than the Pentium II 300 and the K6-2 333/95 is slightly slower than the Pentium II 333. The performance of the K6-2 in office applications can still raise with better motherboards and larger L2 caches. The test system was only using 512 kB L2 cache, 1 MB and even 2 MB are possible as well though and it will improve the speed. The VIA mVP3 chipset looks pretty promising too, possibly scoring higher than ALI’s Aladdin V.
Windows NT is the domain of Intel’s sixth generation CPUs, so that the K6-2 300/100 and 333/95 can here only score somewhere in between the results of the PII 266 and PII 300. The Celeron overclocked to 400/100 MHz is slightly slower than these CPUs under Windows 95, under Windows NT it’s a tad faster than both of them though. We should also not forget that you can run multiple CPU systems with Pentium II CPUs, accelerating professional software at a very significant level. AMD’s CPUs cannot do that.
Running the high end application Winstone 98 shows the superiority of Intel’s sixth generation processors even more. The K6-2 300/100 as well as the 333/95 version are both in between the Pentium II 233 and 266, and the Celeron overclocked to 300/100 is in the same area too.
All in all the K6-2 is offering a new office application performance push for Socket 7 and as long as you are using Windows 95 with normal business apps the performance is impressively close to what a Pentium II at the same clock speed is able to do.
Benchmark Setup
Socket 7 System :
- Microstar MS-5169 motherboard w/512 kB L2 cache (ALI Aladdin V Chipset rev. C)
- 64 MB Corsair PC100 SDRAM
- IBM DGVS 09U Ultra wide SCSI hard drive
- Adaptec 2940UW SCSI host adapter
- Diamond Viper V330 AGP graphics card, NVIDIA reference driver 4.10.01.0250
- Resolution 1024×768
- Color depth 16 bit
- Refresh rate 85 Hz
Slot 1 System :
- Asus P2B motherboard (Intel 440BX chipset, final revision)
- 64 MB Corsair PC100 SDRAM
- IBM DGVS 09U Ultra wide SCSI hard drive
- Adaptec 2940UW SCSI host adapter
- Diamond Viper V330 AGP graphics card, NVIDIA reference driver 4.10.01.0250
- Resolution 1024×768
- Color depth 16 bit
- Refresh rate 85 Hz
- 1
Current page:
Intel’s Dominance
Next Page Benchmark Results
Get instant access to breaking news, in-depth reviews and helpful tips.
Contact me with news and offers from other Future brandsReceive email from us on behalf of our trusted partners or sponsors
Tom’s Hardware is part of Future US Inc, an international media group and leading digital publisher. Visit our corporate site .
©
Future US, Inc. Full 7th Floor, 130 West 42nd Street,
New York,
NY 10036.
Processor AMD K6-2
So, the passions subsided, it’s time to calmly figure out what is and what gives the new AMD K6-2 processor. This processor is a logical continuation of the K6 line and differs from its predecessor only in the addition of a new module to the core that processes «3D instructions» and is called 3DNow!. In fact, this is another coprocessor of the MMX type, but able to execute 21 new instructions. These new instructions are intended primarily to speed up the processing of data related to three-dimensional graphics. Therefore, the 3DNow! includes commands that work with single-precision floating-point arguments. That is why the MMX technology did not come to life — MMX works with integers, and when calculating three-dimensional scenes, you have to operate with real ones. Like MMX, 3DNow! uses the same registers as the coprocessor, this is because operating systems must save and reset all processor registers when switching tasks.
Theoretically, 3DNow! should replace the coprocessor in the calculations of three-dimensional geometry and significantly speed up the execution of these calculations. 3DNow! can execute up to four SIMD (Single Instruction Multiple Data) instructions (from its 21-instruction set) in parallel, which, if used correctly, can give an unprecedented performance boost. A good illustration of this thesis is Quake2, which runs on K6 processors one and a half times slower than on Pentiums of the same frequency. However, contrary to popular belief, this is not due to the slowness of the AMD coprocessor, but to the fact that Intel has implemented in its chip the possibility of parallel operation of the processor with an arithmetic coprocessor. In Quake2, the code is optimized for this feature, so if processor and coprocessor instructions cannot be executed simultaneously (as on AMD K6), performance is extremely poor. K6-2 should solve this problem, but in a different way — by pipelining 3D calculations in the 3DNow! However, the issue of parallelization of calculations must be solved by the programmer, which causes certain difficulties in the implementation of algorithms, especially since the process of calculating the geometry of 3D scenes is far from being linear. Therefore, the theoretical performance of K6-2, which significantly exceeds the speed of all modern PII processors, cannot be achieved.
So that 3DNow! there was at least some effect, it is necessary that the application uses those same 21 instructions. And not somehow, but taking into account the pipeline structure of this processor module. Now all the optimization for K6-2 is either using graphics APIs with 3DNow! support, or releasing special versions of programs. Let’s take a closer look at optimization.
All tests were performed on a FIC VA-503+ motherboard with VIA MVP-3 chipset, 64 MB SDRAM, Diamond Viper V330 video card, and Diamond Monster II 3D accelerator with 12 MB of memory. Testing was performed under Windows 98 and DirectX 6.0 beta 1. The games used resolutions of 640×480 and 800×600. The PII system used an ASUS P2B board.
DirectX 6.0
As you know, DirectX 6.0 (with optimized video drivers) includes support for 3DNow! However, you need to imagine how. Direct3D consists of two layers: high-level (Retained Mode) and low-level (Immediate Mode). Immediate mode allows applications to simply manipulate video memory directly, while retained mode includes some geometry pipeline functionality. This shows that there can be no optimization in immediate mode in principle. All hope for retained mode. However, Microsoft, at least in DirectX 5.0, didn’t work too hard on retained mode. The result is that the DirectX 5.0 geometry pipeline is not just slow, but very slow. Remember how frames twitch in 3D WinBench? This is precisely because this test is practically the only application that implements the geometry pipeline through DirectX. The rest rely on their own strength. 3D Winbench 9 benchmark results below8 thus only show what can theoretically be squeezed out of 3DNow! using DirectX.
In practice, in DirectX 6.0 the situation with the implementation of geometric functions began to change for the better. Game developers have figured this out, and are cautiously starting to use elements of this pipeline. For example, in Forsaken, some functions are used, but the performance gain is extremely insignificant.
So until developers start using DirectX geometry to the fullest, K6-2 owners can’t hope for anything here.
Glide 3.0
Until optimized Glide drivers are available, only theoretical estimates can be reported. Glide includes a small number of geometry functions, so AMD itself estimates that using drivers optimized for K6-2 will only give a 15% performance boost.
OpenGL
The OpenGL API includes almost all the functions of the graphics pipeline, and SGI, when developing its libraries, took care of both high efficiency and the possibility of parallelizing calculations. In our opinion, using OpenGL and drivers optimized for this library is the best solution. An illustration of this thesis is the unmeasured increase in fps in Quake2 when using 3DNow! miniport.
And game makers, not only don’t have to worry too much about geometric things, besides, optimization itself happens, if you want one processor, you want another.
There is only one problem — games that work through OpenGL once, twice — and miscalculated. And video card manufacturers are not that under 3DNow! they can’t sharpen their OpenGL drivers, they can’t make them at all. So there is little hope for the use of this technology.
Application optimization
Let’s try to explain why the optimization of the programs themselves is bad. The matter is that the compilers generating 3DNow!-instructions in the nature are absent. Yes, and they are unlikely to appear. It is very difficult to design pipelined parallel processing of 3D calculations, and even so that there are no exceptions, and the machine algorithm is most likely beyond its power at all. As for manual optimization, it is also difficult and expensive. Therefore, optimization is often done purely formally, as in Unreal, where 3DNow! the elements of calculating the kinematics of monsters are assigned, which does not give any (!) gain at all. The only more or less positive effect of manual optimization is noticeable in Incoming.
But with the gain from using OpenGL, a bright flag that AMD waved at the presentation (the programmers did their best here), showing Quake2, this gain cannot be compared.
Conclusions
Assuming that the K6-2 is a regular K6 processor plus something else, and therefore a processor that shows very good results in office applications and, if a number of additional conditions are met, also in games, as well as Considering the price, the K6-2 is just a godsend.
However, six months later, when Intel Katmai comes out with its set of 3D KNI instructions (MMX2), which with 3DNow! are not compatible, all application and driver manufacturers will most likely forget about K6-2. Therefore, we will not recommend AMD K6-2 as an alternative to PII.
But, as a solution for upgrading an old Socket-7 system, K6-2 is an almost perfect solution. However, keep in mind that for use in an old K6-2 motherboard, a supply voltage of 2.2 V is required, and, in the absence of an external frequency of 100 MHz, a multiplication of 4 or more.
Note that the above list of applications is pretty much everything you can squeeze out of AMD’s new processor. It will, of course, expand, but hardly at a rapid pace due to the complexity of optimizing for 3DNow! Moreover, a simple compiler will be released under MMX2, which will free developers from unnecessary efforts.
So, perhaps, Celeron will live 🙂
Test equipment provided by IPLabs and CHI
July 11, 1998
News
-
“The deal was cashless” – the Rosatom structure gained control over the Elbrus processor developer
February 10, 2023
-
Is this really an enthusiast processor? Xeon W7-2495X loses to Core i9-13900K in Geekbench test
February 10, 2023
-
One of the most unusual motherboards. The Asus X670 Mini-ITX has one of the chipset chips located on a hidden separate board
February 9, 2023
News section >
AMD K6-2 processor with 3DNow!
This article was written in connection with the release of the AMD K6-2 processor with 3DNow! technology, and also in connection with the increased interest from potential users.
The main purpose of this article is an attempt to answer the two most important questions for the consumer: «What is this processor like?», And also «Who needs it and why?»
After much thought, I came to the conclusion that this article should not be overloaded with technical details important for a specialist, but should contain as much information as possible that is understandable and necessary for the end user.
So, let’s start with a little history. A little over a year ago, a grand event took place on the market for processors for personal computers (hereinafter PC) — Intel announced that future processors of the company will support MMX (Multi Media eXtension) technology, which is a set of 57 new instructions, and also the appearance of registers intended to be used by these instructions. This technology, according to Intel, was supposed to greatly increase the performance of computers in the case of using multimedia applications.
Naturally, this application must use these processor capabilities. Quite a lot of time has passed, and programs and games using MMX — the cat cried.
After this event, the market for processors that could increase the speed of multimedia came to a lull. Most processor manufacturers solved this problem in the traditional way — by increasing the frequency of the processor, increasing the power of the calculation module with non-integer numbers (hereinafter FPU), creating pipelines of commands working in parallel to each other (super scalar technology), etc.
As you know, after a calm, you have to wait for a storm, and it did not take long to wait.
On May 28, 1998 , AMD announced the release of its new processor — AMD K6-2, which uses a new technology developed by AMD itself and called 3DNow!
Unlike its number one competitor (Intel), AMD engineers implemented their own technology differently than they did with MMX. The main and very important difference is the fact that instructions from the 3DNow! (there are only 21 of them) real (i. e. non-integer) numbers can be used as data (operands). MMX instructions can only work with integers. As you know, 3D graphics and non-integer numbers are almost synonymous, so the importance of 3DNow! instructions can operate on real numbers. Also, these instructions can be executed by FPU is faster than than others and thus achieves high speed of 3D games, multimedia applications and applications designed to work with 3D graphics. The next difference is the ability to process multiple data units (floating point operands) with one instruction (SIMD — Single Instruction Multiply Data), and up to two instructions can be executed simultaneously, which was not in MMX and which is not yet in any of the competing products.
Intel intends to implement this technology only in Katmai, the next processor from the Pentium II family, which will appear as early as 1999th year.
All this bouquet of innovations, according to AMD, should increase the adrenaline in the blood of gamers (smile, please :), as well as graphics and people of other professions who are interested in good 3D graphics for a reasonable price.
But be that as it may, you need to understand that all these benefits can be felt in practice only on the condition that applications use these instructions in one way or another.
There are three ways to use them :
- using graphics drivers
- when using an application programming interface (hereinafter API) optimized for 3DNow!
- directly by the application itself
Only the last two are the most desirable, since they lead to the best results.
Therefore, in general, it’s up to software developers. At the time of this writing, I personally know of only one game that uses (meaning directly) 3DNow! instructions. It’s a popular Quake II game that has bogged down any PC processor in its time, including early versions of the Pentium II. Given the fact that AMD competes strongly with Intel, it is reasonable to assume that even before the release of K6-2, AMD tried to make every effort to ensure that this processor was accepted on the market with a bang. The following facts may serve as evidence of this:0003
- Microsoft has enabled support for 3DNow! in DirectX 6.0, coming out in early July this year (this is an example of API level support)
- OpenGL API (by Silicon Graphics) version 1.2 also allows you to take advantage of 3DNow!
- Matrox Graphics, nVIDIA, and others have announced that they will support 3DNow! using drivers for their graphics adapters
In addition, many developers of games and applications designed to work with graphics are already working hard to use the K6-2 to its fullest. Some games that use 3DNow! are already able to achieve almost twice the performance they had when they didn’t use these instructions.
As for the rest of the programs, the results are also generally higher than those of K6 without 3DNow!
In some programs, the 300 MHz version of K6-2 catches up with the Pentium II 300 MHZ and at the same time costs significantly less (test results can be seen on Thomas Pabst’s website, as well as on our iXBT).
This is partly due to the use of the K6-2 100 MHz bus.
On June 8, the Pentium II 300 MHZ was $410 in New York, and the K6-2 300 MHZ was $290. The minimum price for a Pentium II motherboard was $139, for K6-2 about $120. In total, the is $139 cheaper than the than the Pentium II with its motherboard. Thus, choosing K6-2 is cost-effective, both in the case of buying a new computer, and in case of upgrading an old one (and if you are lucky and your motherboard supports K6-2, then the costs will be minimal — you buy only a processor and possibly a new fan).
As for the overall benefit of such a purchase, this is a moot point, since do not forget that «buying a computer that will last for a long time» is almost impossible now — there can always be a program whose execution speed may not suit you. In addition, due to the imminent release of K6-3 (second half of 1998), and after it the K7, the transition to the Pentium II, as well as to the K6-2, may be inappropriate, because K6-3 will already require completely new technologies for the manufacture of motherboards for it. Another obstacle for AMD processors to conquer the market is the attitude of people who are not specialists in this field. Advertising plays an important role here, as well as the fact that «the people» know that Intel is the «parent» of PC processors. That is why all breakthroughs in technology are attributed to Intel, despite the fact that competing firms (among them AMD) are the main reason for the rapid changes in the processor market. If Intel had not had a serious competitor in the face of AMD, which is constantly advancing on Intel’s heels, Andy Groove would hardly have urged his engineers — why constantly change production lines and rush to release faster processors (and also spend huge amounts of money on their development), if do people have no choice what to buy?
Intel would calmly sell its processors at «cosmic» prices, absolutely not worrying about its position in the market.
In today’s situation, however, not everything is so rosy for Intel, and this is the reason why Intel is pushing its engineers so as not to lose any other market sector. More recently, it was announced that Xeon (the next processor from the Pentium II family) will be released at the end of June.
Another reason why Intel is in a precarious position is the fact that most users around the world do not want to change their computers to more powerful ones due to the high cost of processors and motherboards, and also because they do not feel the need to do so (according to According to a survey published in a recent issue of Computer Shopper, about 53% of Americans use computers based on the 486th or older processor). Considering that Intel has already thrown the Socket 7 architecture into the far corner, which is currently the most common, then if the above 53% of users decide to upgrade their computers, then the choice will most likely fall on AMD or even Cyrix.
AMD’s policy is also attractive to demanding customers: the K7 processor will run on the high-performance EV-6 bus developed by Digital for its Alpha processors. An even greater advantage will be the use of a special slot, common for K-7 and future Alpha processors from Digital. Only one thing can be said about the power of the latter — the Pentium II lags behind even in terms of maximum operating frequency, not to mention real performance (you can read about Digital Alpha on our website here).
In conclusion, I want to say that the final choice is yours, the reader, but do not forget the iron rule of the free market: «Competition is always beneficial to the end user.» Therefore, I think everyone will agree that the existence of AMD is beneficial to everyone, but the existence of the latter also depends on you and me, i.e. from sales of products.
If these processors become popular, software developers will have to take this into account, and then all K6-2 owners will get more from it than they expected at the beginning.
In addition, I would like to note that seven of my friends at one time chose AMD K6 (on my recommendation). There are no dissatisfied.
P.S. In the future, I may write an article about 3DNow!, when it becomes clear in practice how beneficial it is to use these instructions in certain programs.