The World's First

On November 15, 1971, a group of three engineers revealed the World's first Microprocessor, the Intel 4004^TM.  While this processor could only be used for simple mathematics calculations, and while it was no more powerful than a simple hand held calculator, the 4004 was the beginning of an industry that now dominates our media time, our air-waves, and our Internet bandwidth.

Since that memorable day in 1971 the microprocessor has come a long way, separated by 12 - 24 month intervals after which a new generation was added to the line, each more powerful, more productive, and naturally, more expensive than its predecessor.  A series of small enhancements and improvements were made to the 4004 to make it more useful of a microprocessor, however it wasn't until the 8086 and the 8088 that the microprocessor became a product for the masses.  After the huge introduction of the 8086/8088 Intel didn't really release a processor that provided any huge improvement over the 808x line until approximately 7 years later, in 1985. 

Intel proposed a dramatic change in the architecture of their processors in 1985, they proposed a change that would double the width of the Processor's Bus Interface, a change that would also provide users with the ability to address 250 times as much memory as they previously could, and this very change would lay another layer of solid rock on the foundation of what became today's high speed microprocessor market...this new processor was Intel's very first 32-bit processor, the Intel 386^TM DX.  No processor since then has made an impact even remotely as great as that of the 386 DX, primarily because we are still living in a 32-bit world, regardless of what fractional part of our entire system makes use of a 64-bit Data Bus.  Some speculate that the next major jump will occur in late 1999, or early in the year 2000 when Intel unveils their Merced processor which will make use of Intel's IA64 [64bit] Microprocessor Architecture, very similar to that of the DEC Alpha in most respects however according to sources at Intel the processor will make use of a new type of Instruction Set (consider the Instruction Set of a processor its "language") never seen before, dubbed EPIC (Explicitly Parallel Instruction Computing).  Whether the release of the Merced will achieve this predicted affect is up to your own speculation, however what is important now is to reflect upon how far the architecture of our x86 processors has evolved in the past 2 - 3 years...if it has at all.

Leveling the playing field

What makes a Pentium MMX different from a Pentium II?  How about from a K6?   A 6x86MX?  Well, the microprocessor giants, Intel, AMD, and Cyrix respectively, have all taken measures to make sure that you, as a user, can't really compare the "core" (or internal electronics) of their processors to each other.   Intel's Pentium II is supposedly a much more advanced microprocessor than its predecessor, the Pentium MMX...however how do we know this for sure?  The slowest Pentium II runs at 233MHz, with the most common chips ranging in speed from 266 to 333MHz, while the slowest desktop Pentium MMX runs at 166MHz, with the most common chips clocking in at 200 - 233MHz.  Comparing a Pentium II - 300 to a Pentium MMX 233 won't really accomplish much, even comparing a Pentium II - 233 to a Pentium MMX 233 won't do much either since the Pentium II's Level 2 Cache operates at 1/2 the clock speed where as the Pentium MMX 233's Level 2 Cache operates at 66MHz.  A nice little predicament we have here, we have 4 different processors, but no way to know for sure which is the most advanced...or do we?

Have you ever wondered if Intel's Slot-1 architecture used by the Pentium II is really necessary?  Is the Socket-7 market really dead...or are we experiencing the calm eye of the storm?  Could the Pentium II last a second without its precious high speed L2 cache?  Is AMD's K6 as advanced as the folks down in Texas boast it to be?  ...and truthfully, how bad is the FPU of the Cyrix 6x86MX?   Let's start answering some of these questions shall we?

Setting up the Pins

Comparing Socket-7 processors to each other isn't all that difficult since they all operate on the same bus, using the same interface architecture...throwing in a Slot-1 processor into the comparison, such as the Pentium II, complicates things.  How does one bridge the gap between the worlds of Intel's 7th Socket and their first Slot? 

Well, take a look at it this way, the Socket-7 processors have anywhere from 32KB - 64KB of Level 1 Cache, operating at clock speed.  Meaning if you have a 200MHz Socket-7 processor (i.e. AMD K6-200) its Level 1 Cache, which is essentially high speed memory located on the processor, will run at 200MHz.  Slot-1 processors, the only one at this point being the Pentium II, currently have 32KB of Level 1 Cache that also operates at clock speed.  This leaves us with a very small gap to bridge, and if it were that easy this article would've never been written...however it isn't that easy.  

The Level 2 Cache on a Socket-7 system runs on an external bus and isn't located on the processor, the speed of this external bus is called the memory bus speed, and is commonly known as the bus speed of a system.  So if you have a normally clocked 200MHz Socket-7 processor, its L2 cache will run at a 66.6 MHz bus speed provided you are using a 3.0x clock multiplier.  The memory bus speed, when multiplied by the clock multiplier yields the actual clock speed of the processor and in turn the actual clock speed of the L1 cache (66.6 MHz x 3.0 = 200MHz).  However, the Level 2 Cache on a Slot-1 system runs on an independent bus which is located on the processor's cartridge, this independent bus was designed, according to Intel, in order to allow for a high speed L2 cache which operates at 1/2 the speed of your CPU.  In this case, if you have a 200MHz Slot-1 processor, its L2 cache will run at 1/2 the clock speed, which would be a clock speed of 100MHz, a clock speed 50% greater than that of an equivalently clocked Socket-7 system.  This is where the problem lies...keep that in mind as we explore another possibility.

You may be wondering why Intel didn't chose to run all the cache, L1 and L2, at the clock speed of the processor.  Intel did try this, with the Pentium Pro (Socket-8), however by placing their own L2 cache on the chip Intel did two things:   Intel managed to cut out the cache memory manufacturers from the equation since the L2 cache would be integrated into the processor, and for the most part that cache came directly from Intel and no where else.  Intel also managed to increase the costs of producing a processor by an enormous amount, not only did they have to factor in the cost of the expensive L2 cache, but they also had to be more careful with the production of their processors.  If a processor failed its quality assurance tests the entire processor had to be thrown away, INCLUDING the expensive L2 cache.  Those two reasons combined lead to the outrageous prices of the Pentium Pro, they also lead to the fairly unsuccessful Socket-8 market...Intel needed a solution to this problem as well as another one they faced...the competition [AMD & Cyrix] were quickly gaining on them in the Socket-7 market, mainly because anyone could make a Socket-7 processor...so Intel needed an architecture that would keep the competition from having a chance as well as an architecture that would allow them to place their L2 cache off the processor without sacrificing much performance. 

We're back to step 1, we have two different architectures, with the main difference being the placement and the speed of the L2 cache, and we have no way to bridge the gap between them...or do we?

Knocking them down

Comparing Socket-7 processors to each other isn't all that difficult since they all operate on the same bus, using the same interface architecture...throwing in a Slot-1 processor into the comparison, such as the Pentium II, complicates

Take any Socket-7 processor, regardless of its rated clock speed, run it at an external bus frequency of 83.3MHz (if you've ever wondered what the term Megahertz meant, 1 MHz is just 1 million cycles per second) and use a 2.0x clock multiplier.  By doing that you obtain a system whose processor runs at a 166MHz clock speed, whose L1 cache runs at 166MHz, whose memory bus runs at 83.3MHz, and whose L2 cache runs at 83.3MHz.  Now take a Pentium II, or Slot-1 processor, regardless of its rated clock speed, run it at a bus frequency of 83.3MHz and use a 2.0x clock multiplier.   In this case you have a system whose processor/L1 cache runs at 166MHz, whose memory bus runs at 83.3MHz...and since the speed of the L2 cache on a Pentium II is derived by halving the speed of the actual processor, the system's L2 cache will also run at 83.3MHz.  That way we have isolated quite a few variables in the attempt to level the playing field and we have essentially bridged the gap between the Slot-1 and Socket-7 worlds. 

You may believe that in order for a fair comparison one would have to disable the L1 cache on all the processors, however doing so is penalizing a processor for being "itself," the way its manufacturer intended it to be.   For example, the Pentium II mutates from a hideously fast daemon to a mere tortoise when you take away its precious L1 cache, to put it into perspective, imagine running Win95 on a 286..it isn't pretty, try running it on a Pentium II without L1 cache...the scene isn't all that different.  So none of the processors were penalized for any enhancements that happened to be included in the physical die of the chip (the actual chip, not any additional enhancements made outside of the chip's packaging) since you can't order a 6x86MX with only 32KB of L1 cache and you can't order a Pentium II with 64KB of L2 (not yet at least), the L1 cache is part of the processor so it would be unfair to disable it.  Now let's get to the testing...

The Test

Here's how the tests were conducted, each processor was run at 83.3MHz x 2.0 for a resulting clock speed of 166MHz.  The only variable introduced in the tests was, naturally, the motherboard since you can't use a Socket-7 processor in a Slot-1 motherboard and vise versa.  The breakdown of how each individual processor was benchmarked is as follows:

Each processor was benchmarked using Ziff-Davis Publications' Winstone 97, each test was run a total of 3 times and an average of the three scores was taken and recorded as the final score.  Each test system used 2 x 32MB Advanced Megatrends SDRAM DIMMs, a 1.6GB Western Digital EIDE HDD, a Matrox Millennium II (PCI) Video Card, and the latest drivers for all of the devices installed in the test system.  None of the processors failed the tests so without further adieu here are the results:

The Results

* These tests had to be run at 66 x 2.5, at the 2.0x clock multiplier the Pentium II, by default, disables its L2 cache

* Using the 2.0x clock multiplier the L2 cache of the Pentium II is disabled by default, this unfortunately cannot be avoided with the current design of the Pentium II.

Take a minute to digest the shock from those results ;)

The most peculiar result from this test is this, the Intel Pentium II, when using a 2.0x clock multiplier (regardless of which motherboard you run it on) disables its L2 cache, resulting in the 83.3MHz x 2.0 scores of the Pentium II being much lower, approximately 20% lower, due to the L2 cache being disabled.  Now when you clock the Pentium II at 66MHz x 2.5 (166MHz as well) the L2 cache is enabled, and the performance of the Pentium II is much greater...however still not as fast as the performance of the Pentium MMX, K6, or the 6x86MX.  But why does the Pentium II still reign as the fastest desktop processor?  We'll find out in a second.

Coming in first place in all of the tests was the Cyrix 6x86MX of all processors, the truly amazing part is that the 6x86MX received a higher High End Winstone 97 score than that of the Pentium MMX, Pentium II, and K6...the High End Winstone 97 tests make fairly heavy use of the processor's FPU, supposedly Cyrix's weak point...well, when the playing field was leveled Cyrix's weak point turned out to be much stronger of a device. 

In second place was the AMD K6 producing pretty decent scores, I should add that both the 6x86MX and K6 have 64KB of L1 cache...had they been limited to 32KB the tests may have been different...looks like it's time to make use of that L1 Cache Enabled/Disabled feature in the BIOS Setup.

The most surprising result was that of the Pentium II, at 166MHz it came in an absolute last place!  It just goes to show you that the Pentium II isn't necessarily a better processor than its competitors, its just that it runs at speeds the competition has yet to achieve.  Chances are when AMD and Cyrix catch up to the 300MHz mark, their processors will outperform Intel's Pentium II - 300, but by then Intel will have already made it past 400...so the cycle continues. 

Here's an interesting note, the Pentium II "Deschutes" underclocked to 166MHz like the rest of its competitors displayed a 6% increase in the High End Winstone 97 score, and a 4% increase in the Business Winstone 97 score...quite interesting indeed.  Is the Pentium II - 333 a little more than just a Pentium II with a higher clock speed?

Taking away the L2 cache of all the processors does produce some more interesting and expected results, at the top, the Cyrix 6x86MX reigns as the Business Application King...followed by the Deschutes, the K6, the Pentium II, and finally the Pentium MMX.  The High End Applications are also dominated by the Cyrix 6x86MX, but does that mean that the 6x86MX has an excellent FPU?  Absolutely not.  Take a look at the FPU Winmark scores, the King of the High End Applications seems to drop to be the peasant when looking at the FPU Winmark scores, the Pentium II Deschutes maintains a 204 point lead over the Pentium II which is 12 points under the performance of the Pentium MMX, the second place leader.

The AMD K6 does begin to show off its shiny top in the CPU Mark 32 scores where it imposes a tiny lead over the second place 6x86MX.   What's even more interesting is that the 6x86MX actually beats the K6 in Quake 2 at 640 x 480 when looking at the Timedemo scores, although it is by a margin of 0.5 frames per second, it is still something.  Of course Intel rules Quake 2 here, with the Pentium MMX, Pentium II, and Deschutes processors occupying the top three spots...now remember that this is using Un-accelerated Quake 2, wonder how GL Quake 2 will be affected by this...sounds like another update to me

Intel's Latest

While Cyrix is quite far from reaching even the 266MHz marker, AMD is about to break the 300MHz barrier this half of the year (can't be too specific now can I ;)...) so Intel, being the reigning champ and industry giant has moved to release a new revision of their Pentium II.  This version of the Pentium II is a special low power processor, operating at around 2.5V [core] and running cool courtesy of its 0.25 micron manufacturing process (the current Pentium II uses a 0.35 micron process and runs at a 2.8v core), this Pentium II has slowly been dubbed the "Deschutes."

Deschutes is actually the name of a river close to an Intel Manufacturing plant as I am told, and although very little is known about the river, the exact opposite is true for the processor.  On January 26, 1998, Intel will officially release the very first "Deschutes" class of Pentium II processors, the Pentium II - 333.  This 333MHz processor will continue to run at a bus speed of 66.6MHz, while its L2 cache will run at 166.6MHz, and it will be based on a 0.25 micron manufacturing process which will allow it to run much cooler than previous Pentium II units.  Now, approximately a week before Intel's release of the Pentium II - 333, a few of these mystery processors are finding their way into the hands of Value Added Resellers from un-identified sources.  It is interesting to note that on the label of these prematurely released Pentium II - 333's, the world "Philippines" is printed next to the processor's serial number.  In any case, the Pentium II - 333 offers one thing the Pentium II - 300 couldn't...the ability to see into the future.   What can we expect from a 400MHz Pentium II whose L2 cache is running at approximately 200MHz?  Will we notice a huge increase in performance?  Once again, let's put our theories to the test...this time using ABIT's LX6 as the test bed.

Dey Shoots and Dey Scores

The title of this section, taken from a frequent visitor to the Anand's Hardware Tech Page Bulletin Board (hope ya don't mind ;)...)   is fairly self explanatory...let's take a look at the scores Intel's Pentium II "Deschutes" 333 produced when using ABIT's LX6:

Not a bad future we've got here...the ABIT LX6's BIOS detected the Pentium II - 333 as being a Pentium PRO processor, while other motherboards either do the same or detect it as a Deschutes processor.  AOpen AX6L users should download the newest revision of the AX6L BIOS in order to make use of the 333MHz Pentium II, otherwise upon the Power On Self Test (POST) your processor will be detected as a "-MMX 857MHz" and the system will halt.  Other motherboards which don't support the 5.0x clock multiplier required by the Pentium II - 333 are out of luck however...sorry guys.

So what if you're the fastest at 166? Let's see you top 400

Does anyone really care that the Cyrix 6x86MX is the fastest out of the processors reviewed here at 166MHz?  Its pretty obvious that people do care, but the important thing to realize here is that although the 6x86MX at 166MHz kills the Pentium II...move up to 300MHz and see who's on top.  None other than Intel with their Pentium II, simply because they have no competition at that high of a clock rate.  AMD is just now releasing their 266MHz processor which can be overclocked to 300MHz, however Intel's Pentium II is sitting pretty up there at 300 and 333 for now. 

Cyrix is having problems getting their chips to run at speeds above 200MHz properly, not to mention breaking the 300MHz barrier.  AMD has the technology and the skill to compete with Intel at those clock speeds however they can't seem to produce/release enough chips to do so effectively (not yet at least...let's see how well that K6-3D performs).  So although at 166MHz the Pentium II comes out last, consider that at 300MHz the Pentium II's L2 cache is running at 150MHz, and at 416MHz with the Deschutes its L2 cache is running at 208MHz!  So long as Intel can keep a healthy gap between the clock rate of their processors and that of the competition, they will remain on top regardless of what benchmarks may say, because for the most part people are concerned with the clock speed their processor is running at (which is the wrong idea in the first place).  Its the classic "mine's faster" childish attitude, however in this case Intel is using it against the market which is crippling the competition that has yet to achieve actual clock speeds of that caliber. 

The actual speed difference between an AMD K6/233 and a Pentium II - 333 in Windows 95 is negligible (note that this is comparing general Windows performance, copying of files, boot time, etc... however when it boils down to processing power used in games, applications, etc... the Pentium II - 333 has a clear advantage over the K6), certainly not worth the $700+ extra for the Pentium II (unless you don't have a budget of any sort)...unfortunately Intel uses their clock speed "advantage" to influence potential buyers into purchasing their products over the competition.  In the end it all comes down to making a few bucks, in this case, making a few billion bucks.  In the computer industry, and in many others, money is the deciding factor and making a profit has become more of a quest than that for knowledge.  It is sad that we have come to this, but in business very few large corporations have "kept it real" in that they abandon their original ways of thought and business in favor of more cost efficient methods, while it is better for the manufacturer it can be terror on the buyers...but soon enough a small company will come along and challenge the large monopoly, forcing it to change its ways, and the cycle continues...in most cases that is ;)

Slot-1...necessity or evil?

It seems like in almost any situation the "top dog" will always be criticized regardless of what he or she, or in this case, regardless of what the company does.  Intel, being the microprocessor giant must endure all of the attacks they are faced with simply because they are the largest microprocessor manufacturer in the world, although the personal intentions of many varies, the bottom line is that Intel does have their faults, however without them just imagine where we would be today. 

Intel pushed the market forward with the release of their "Triton" Line of Chipsets, they pushed the graphics industry beyond the limits with the release of their Accelerated Graphics Port Technology and recently they have taken a step into uncharted waters, with the release of their Slot-1 based Pentium II.  If you look at the Slot-1 design, it is simply a new way of connecting the CPU to the motherboard, which allows for the L2 cache to be placed off chip, but on a card that allows for it to be run at extremely high clock speeds while keeping costs at a minimum.  But if you look around the newsgroups,  websites (including this one), and discussion boards a common topic for discussion is the "evil" nature of Intel's decision to move to Slot-1...but is it really all that bad...or has it just been blown out of proportion?

When you look at a Pentium II motherboard, you immediately notice the odd-looking Slot on the motherboard in place of the conventional Socket design you are probably accustomed to...however if you shape the Pentium II's Slot-1 in the shape of a socket does it slowly lose its intimidation factor?  Sound insane to you?  Let's pursue this a little further...

If you were to walk into a auto-dealership, and while looking at a car the salesman walked over to you and presented you with another option...a car with the steering-wheel in the backseat, would you gladly accept the new change?   For most people, the answer would be no, simply because you aren't accustomed to it and frankly, a car with the steering-wheel in the backseat would look and feel quite odd to a driver with a few years of experience.  Let's extend this analogy to say that the new backseat steering-wheel was only offered, and patented by one single company, and you wouldn't be able to find it with any other car...however according to the company spokesperson, the backseat steering-wheel does offer a few advantages over the classic design.  Would you gladly accept the change now?  Probably not, because the weird new layout of the car is very intimidating, and something you aren't used to...history has once again shown us that it is human nature to fear the unknown as well as to fear that which is different.  We see it in our society daily, with matters such as race, religion, sex, and now, computers.

Remember that comment from above about shaping a Slot-1 into the form of a Socket?  Consider the Slot-1 nothing more than a Socket-8 (Pentium Pro Socket)...because that is pretty much all that the Slot-1 design is, just a Socket-8 in the form of a Slot.  Now does Slot-1 seem too incredibly evil?  Hardly anyone complains about Socket-8, simply because it looks very much like the Socket-7 IC's we're all used to, Intel is the only company to make processors for Socket-8...and they are the only company that makes processors for Slot-1 (as of now), so what's the big deal?

There have been rumors of Cyrix and AMD considering entering the Slot-1 market soon enough, AMD even displayed a K7 processor which made use of a similar Slot technology, what will it take to make everyone realize that Slot-1 isn't all that bad.  It is true that it doesn't have any support from companies other than Intel (CPU manufacturers that is), however think back to the debut of the Socket-5 for the Pentium.  Were AMD and Cyrix making processors for Socket-5 motherboards when the interface made its debut?  Of course not, it took Cyrix over a year to release a Socket-7 processor after the interface was released, and even after that it took AMD an additional 3 months to make their K5 a reality...does anyone complain now about the Socket-7 interface being "evil?" 

The law of the industry has always seemed to have been this: the leading company makes the first move, then its competitors follow, sort of like a game of chess.  Intel made the first move by migrating from the Socket-7 interface, so give the competition a chance to respond before jumping to conclusions about whether Slot-1 is a necessity or pure evil.  Has Intel done more harm than good for the industry?  That is open for debate, however in my mind Intel has done a fine job so far...will they be dethroned?  Eventually, yes, nothing can last forever, however who's lap that job happens to fall on is beyond the vision of most right now.  

That's all folks

What's next...let's see if we can get a non-x86 processor in this lineup and do a RISC vs CISC comparison...