Microprocessor Types and Specifications

Processor Specifications

Many confusing specifications often are quoted in discussions of processors. The following sections discuss some of these specifications, including the data bus, address bus, and speed. The next section includes a table that lists the specifications of virtually all PC processors.

Processors can be identified by two main parameters: how wide they are and how fast they are. The speed of a processor is a fairly simple concept. Speed is counted in megahertz (MHz), which means millions of cycles per second—and faster is better! The width of a processor is a little more complicated to discuss because there are three main specifications in a processor that are expressed in width. They are

• Internal registers

• Data input and output bus

• Memory address bus

Systems below 16MHz usually had no cache memory at all. Starting with 16MHz systems, high-speed cache memory appeared on the motherboard because the main memory at the time could not run at 16MHz. Prior to the 486 processor, the cache on the motherboard was the only cache used in the system.

Starting with the 486 series, processors began including what was called L1 (Level 1) cache directly on the processor die. This meant that the L1 cache always ran at the full speed of the chip, especially important when the later 486 chips began to run at speeds higher than the motherboards they were plugged into. During this time the cache on the motherboard was called the second level or L2 cache, which ran at the slower motherboard speed.

Starting with the Pentium Pro and Pentium II, Intel began including L2 cache memory chips directly within the same package as the main processor. Originally this built-in L2 cache was implemented as physically separate chips contained within the processor package but not a part of the processor die. Since the speed of commercially available cache memory chips could not keep pace with the main processor, most of the L2 cache in these processors ran at one-half speed (Pentium II/III and AMD Athlon), while some ran the cache even slower, at two-fifths or even one-third the processor speed (AMD Athlon).

The original Pentium II, III, Celeron, and Athlon (Model 1 and 2) processors use 512KB of either one-half, two-fifths, or one-third speed L2 cache as Table 3.1 shows:

Table 3.1 L2 Cache Speeds

The Pentium Pro, Pentium II/III Xeon, newer Pentium III, Celeron, K6-3, Athlon (Model 4), and Duron processors include full-core speed L2 as shown in Table 3.2.

Table 3.2 Full-Core Speed Cache

The problem originally forcing the L2 cache to run at less than the processor core speed was simple: The cache chips available on the market simply couldn't keep up. Intel built its own high-speed cache memory chips for the Xeon processors, but it also made them very expensive. A breakthrough occurred in the second-generation Celeron, where Intel built both the L1 and L2 caches directly on the processor die, where they both ran at the full-core speed of the chip. This type of design was then quickly adopted by the second generation Pentium III, as well as the AMD K6-3, Athlon, and Duron processors. In fact virtually all future processors from Intel and AMD have adopted or will adopt on-die L2 cache as it is the only cost-effective way to include the L2 and bring the speed up.

Table 3.3 lists the primary specifications for the Intel family of processors used in IBM and compatible PCs. Table 3.4 lists the Intel-compatible processors from AMD, Cyrix, NexGen, IDT, and Rise.

Processor Speed Ratings

A common misunderstanding about processors is their different speed ratings. This section covers processor speed in general, and then provides more specific information about Intel processors.

A computer system's clock speed is measured as a frequency, usually expressed as a number of cycles per second. A crystal oscillator controls clock speeds using a sliver of quartz sometimes contained in what looks like a small tin container. Newer systems include the oscillator circuitry in the motherboard chipset, so it might not be a visible separate component on newer boards. As voltage is applied to the quartz, it begins to vibrate (oscillate) at a harmonic rate dictated by the shape and size of the crystal (sliver). The oscillations emanate from the crystal in the form of a current that alternates at the harmonic rate of the crystal. This alternating current is the clock signal that forms the time base on which the computer operates. A typical computer system runs millions of these cycles per second, so speed is measured in megahertz. (One hertz is equal to one cycle per second.) An alternating current signal is like a sine wave, with the time between the peaks of each wave defining the frequency (see Figure 3.1).

Figure 3.1 Alternating current signal showing clock cycle timing.

A single cycle is the smallest element of time for the processor. Every action requires at least one cycle and usually multiple cycles. To transfer data to and from memory, for example, a modern processor such as the Pentium II needs a minimum of three cycles to set up the first memory transfer and then only a single cycle per transfer for the next three to six consecutive transfers. The extra cycles on the first transfer are normally called wait states. A wait state is a clock tick in which nothing happens. This ensures that the processor isn't getting ahead of the rest of the computer.

Table 3.3 Intel Processor Specifications

Table 3.4 AMD, Cyrix, NexGen, IDT, and Rise Processors

FPU = Floating-Point Unit (internal math coprocessor)

WT = Write-Through cache (caches reads only)

WB = Write-Back cache (caches both reads and writes)

Bus = Processor external bus speed (motherboard speed)

Core = Processor internal core speed (CPU speed)

MMX = Multimedia extensions, 57 additional instructions for graphics and sound processing

3DNow = MMX plus 21 additional instructions for graphics and sound processing

Enh. 3DNow = 3DNow plus 24 additional instructions for graphics and sound processing

SSE = Streaming SIMD (Single Instruction Multiple Data) Extensions, MMX plus 70 additional instructions for graphics and sound processing

The time required to execute instructions also varies:

• 8086 and 8088. The original 8086 and 8088 processors take an average of 12 cycles to execute a single instruction.

• 286 and 386. The 286 and 386 processors improve this rate to about 4.5 cycles per instruction.

• 486. The 486 and most other fourth-generation Intel compatible processors such as the AMD 5x86 drop the rate further, to about two cycles per instruction.

• Pentium, K6 series. The Pentium architecture and other fifth-generation Intel compatible processors such as those from AMD and Cyrix include twin instruction pipelines and other improvements that provide for operation at one or two instructions per cycle.

• Pentium Pro, Pentium II/III/Celeron and Athlon/Duron. These P6 class processors, as well as other sixth-generation processors such as those from AMD and Cyrix, can execute as many as three or more instructions per cycle.

Different instruction execution times (in cycles) make it difficult to compare systems based purely on clock speed or number of cycles per second. How can two processors that run at the same clock rate perform differently with one running "faster" than the other? The answer is simple: efficiency.

The main reason why the 486 was considered fast relative to a 386 is that it executes twice as many instructions in the same number of cycles. The same thing is true for a Pentium; it executes about twice as many instructions in a given number of cycles as a 486. This means that given the same clock speed, a Pentium will be twice as fast as a 486, and consequently a 133MHz 486 class processor (such as the AMD 5x86-133) is not even as fast as a 75MHz Pentium! That is because Pentium megahertz are "worth" about double what 486 megahertz are worth in terms of instructions completed per cycle. The Pentium II and III are about 50 percent faster than an equivalent Pentium at a given clock speed because they can execute about that many more instructions in the same number of cycles.

Comparing relative processor performance, you can see that a 1000MHz Pentium III is about equal to a (theoretical) 1,500MHz Pentium, which is about equal to an 3,000MHz 486, which is about equal to a 6,000MHz 386 or 286, which is about equal to a 12,000MHz 8088. The original PC's 8088 ran at only 4.77MHz; today, we have systems that are comparatively about 2,500 times faster! As you can see, you have to be careful in comparing systems based on pure MHz alone, because many other factors affect system performance.

Evaluating CPU performance can be tricky. CPUs with different internal architectures do things differently and may be relatively faster at certain things and slower at others. To fairly compare different CPUs at different clock speeds, Intel has devised a specific series of benchmarks called the iCOMP (Intel Comparative Microprocessor Performance) index that can be run against processors to produce a relative gauge of performance. The iCOMP index benchmark has been updated twice and released in original iCOMP, iCOMP 2.0, and now iCOMP 3.0 versions.

Table 3.5 shows the relative power, or iCOMP 2.0 index, for several processors.

Table 3.5 Intel iCOMP 2.0 Index Ratings

The iCOMP 2.0 index is derived from several independent benchmarks and is a stable indication of relative processor performance. The benchmarks balance integer with floating point and multimedia performance.

Recently Intel discontinued the iCOMP 2.0 index and released the iCOMP 3.0 index. iCOMP 3.0 is an updated benchmark that incorporates an increasing use of 3D, multimedia, and Internet technology and software, as well as the increasing use of rich data streams and compute-intensive applications, including 3D, multimedia, and Internet technology. iCOMP 3.0 combines six benchmarks: WinTune 98 Advanced CPU Integer test, CPUmark 99, 3D WinBench 99-3D Lighting and Transformation Test, MultimediaMark 99, Jmark 2.0 Processor Test, and WinBench 99-FPU WinMark. These newer benchmarks take advantage of the SSE (Streaming SIMD Extensions), additional graphics and sound instructions built in to the PIII. Without taking advantage of these new instructions, the PIII would benchmark at about the same speed as a PII at the same clock rate.

Table 3.6 shows the iCOMP Index 3.0 ratings for newer Intel processors.

Table 3.6 Intel iComp 3.0 Ratings

Processor Speeds and Markings Versus Motherboard Speed

Another confusing factor when comparing processor performance is that virtually all modern processors since the 486DX2 run at some multiple of the motherboard speed. For example, a Celeron 600 runs at a multiple of nine times the motherboard speed of 66MHz, while a Pentium III 1GHz runs at 7 1/2 times the motherboard speed of 133MHz. Up until early 1998, most motherboards ran at 66MHz or less because that is all Intel supported with its processors until then. Starting in April 1998, Intel released both processors and motherboard chipsets designed to run at 100MHz. Cyrix has a few processors designed to run on 75MHz motherboards, and many Pentium motherboards are capable of running that speed as well, although technically Intel never supported it. AMD also has versions of the K6-2 designed to run at motherboard speeds of 100MHz.

Starting in late 1999, chipsets and motherboards running at 133MHz became available to support the newer Pentium III processors. At that time AMD Athlon motherboards and chipsets were introduced running at 100MHz but using a double transfer technique for an effective 200MHz data rate between the Athlon processor and the main chipset North Bridge chip.

Normally, you can set the motherboard speed and multiplier setting via jumpers or other configuration mechanism (such as BIOS setup) on the motherboard. Modern systems use a variable- frequency synthesizer circuit usually found in the main motherboard chipset to control the motherboard and CPU speed. Most Pentium motherboards will have three or four speed settings. The processors used today are available in a variety of versions that run at different frequencies based on a given motherboard speed. For example, most of the Pentium chips run at a speed that is some multiple of the true motherboard speed. For example, Pentium processors and motherboards run at the speeds shown in Table 3.7.

Table 3.7 Intel Processor and Motherboard Speeds

If all other variables are equal—including the type of processor, the number of wait states (empty cycles) added to different types of memory accesses, and the width of the data bus—you can compare two systems by their respective clock rates. However, the construction and design of the memory controller (contained in the motherboard chipset) as well as the type and amount of memory installed can have an enormous effect on a system's final execution speed.

In building a processor, a manufacturer tests it at different speeds, temperatures, and pressures. After the processor is tested, it receives a stamp indicating the maximum safe speed at which the unit will operate under the wide variation of temperatures and pressures encountered in normal operation. These ratings are clearly marked on the processor package.

It is possible in some systems to set the processor speed higher than the rating on the chip; this is called overclocking the chip. In many cases, you can get away with a certain amount of overclocking since Intel, AMD, and others often build safety margins into their ratings. This means that a chip rated for, say, 800MHz may in fact run at 900MHz or more, but is instead down-rated to allow for a greater margin of reliability. By overclocking you are using this margin and running the chip closer to its true maximum speed. I don't normally recommend overclocking for a novice, but if you are comfortable with playing with your system, and you can afford and are capable of dealing with any potential consequences, overclocking may allow you to get more performance from your system.

If you are intent on overclocking, there are several issues to consider. One is that most Intel processors since the Pentium II have been multiplier-locked before they are shipped out. This means that any changes to the multiplier setting on the motherboard will simply be ignored by the chip. Both Intel and AMD lock the multipliers on most of their newer processors. Although originally done to prevent remarkers from fraudulently relabeling processors, this has impacted the computing performance enthusiast, leaving tweaking the motherboard bus speed as the only way to achieve a clock speed higher than standard.

You can run into problems increasing motherboard bus speed as well. Intel motherboards, for example, simply don't support clock speeds other than the standard 66MHz, 100MHz, or 133MHz settings. Also all of their boards with speed settings done via software (BIOS Setup) will read the proper settings from the installed processor and only allow those settings. In other words, you simply plug in the processor, and the Intel motherboard won't allow any other settings other than what that processor is designed for.

Even if you could fool the processor into accepting a different setting, the jump from 66MHz to 100MHz, or from 100 to 133MHz, is a large one, and many processors would not make that much of a jump reliably. For example, a Pentium III 800E runs at a 100MHz bus speed with an 8x multiplier. Bumping the motherboard speed to 133MHz would cause the processor to try to run at 8x133 or 1066MHz. It is highly unlikely that the chip would run reliably at that speed. Likewise, a Celeron 600E runs at 9x66MHz. Raising the bus speed to 100MHz would cause the chip to try and run at 9x100MHz or 900MHz, likely an unsuccessful change.

What is needed is a board that supports intermediate speed settings and that allows the settings to be changed in smaller increments. For example, the Asus P3V4X motherboard supports front-side bus speed settings of 66, 75, 83, 90, 95, 100, 103, 105, 110, 112, 115, 120, 124, 133, 140, and 150MHz. By setting the 800MHz Pentium IIIE to increments above 100MHz, you'd have

Likewise, using this motherboard with a Celeron 600, you could try settings above the standard 66MHz bus speed as follows:

Normally a 10–20 percent increase will be successful, so with this motherboard, you are likely to get your processor running 100MHz or more faster than it was originally designed for.

Another trick used by overclockers is to play with the voltage settings for the CPU. All Slot 1, Slot A, Socket 8, Socket 370, and Socket A processors have automatic voltage detection, where the system will detect and set the correct voltage by reading certain pins on the processor. Some motherboards, such as those made by Intel, do not allow any changes to these settings manually. Other motherboards, such as the Asus P3V4X I mentioned earlier, allow you to tweak the voltage settings from the automatic setting up or down by tenths of a volt. Some experimenters have found that by either increasing or decreasing voltage slightly from the standard, a higher speed of overclock can be achieved with the system running stable.

My recommendation is to be careful when playing with voltages. It is possible to damage the chip in this manner. Even without changing voltage, overclocking with an adjustable bus speed motherboard is very easy and fairly rewarding. I do recommend you make sure you are using a high-quality board, good memory, and especially a good system chassis with additional cooling fans and a heavy-duty power supply. Especially when overclocking, it is essential that the system components and especially the CPU remain properly cooled. Going a little bit overkill on the processor heat sink and adding extra cooling fans to the case will never hurt and in many cases help a great deal when hotrodding a system in this manner.

Cyrix P-Ratings

Cyrix/IBM 6x86 processors use a PR (Performance Rating) scale that is not equal to the true clock speed in megahertz. For example, the Cyrix 6x86MX/MII-PR366 actually runs at only 250MHz (2.5 x 100MHz). This is a little misleading—you must set up the motherboard as if a 250MHz processor were being installed, not the 366MHz you might suspect. Unfortunately this leads people to believe these systems are faster than they really are. Table 3.8 shows the relationship between the Cyrix 6x86, 6x86MX, and M-II P-Ratings versus the actual chip speeds in MHz.

Table 3.8 Cyrix P-Ratings Versus Actual Chip Speeds in MHz

Note that a given P-Rating can mean several different actual CPU speeds, for example a Cyrix 6x86MX-PR200 might actually be running at 150MHz, 165MHz, 166MHz, or 180MHz, but not at 200MHz.

This P-Rating was supposed to indicate speed in relation to an Intel Pentium processor, but the processor they are comparing to is the original non-MMX, small L1 cache version running on an older motherboard platform with an older chipset and slower technology memory. The P-Rating does not compare well against the Celeron, Pentium II, or Pentium III processors. In that case these chips are more comparative at their true speed. In other words, the MII-PR366 really runs at only 250MHz and compares well against Intel processors running at closer to that speed. I consider calling a chip an MII-366 when it really runs at only 250MHz very misleading, to say the least.

AMD P-Ratings

Although both AMD and Cyrix concocted this misleading P-Rating system, AMD thankfully only used it for a short time and only on the older K5 processor. It still has the PR designation stamped on its newer chips, but all K6 and Athlon processors have PR numbers that match their actual CPU speed in MHz. Table 3.9 shows the P-Rating and actual speeds of the AMD K5, K6, and Athlon processors.

Table 3.9 AMD P-Ratings Versus Actual Chip Speeds in MHz

Data Bus

Perhaps the most common way to describe a processor is by the speed at which it runs and the width of the processor's external data bus. This defines the number of data bits that can be moved into or out of the processor in one cycle. A bus is a series of connections that carry common signals. Imagine running a pair of wires from one end of a building to another. If you connect a 110v AC power generator to the two wires at any point and place outlets at convenient locations along the wires, you have constructed a power bus. No matter which outlet you plug the wires into, you have access to the same signal, which in this example is 110v AC power. Any transmission medium that has more than one outlet at each end can be called a bus. A typical computer system has several internal and external buses.

The processor bus discussed most often is the external data bus—the bundle of wires (or pins) used to send and receive data. The more signals that can be sent at the same time, the more data can be transmitted in a specified interval and, therefore, the faster (and wider) the bus. A wider data bus is like having a highway with more lanes, which allows for greater throughput.

Data in a computer is sent as digital information consisting of a time interval in which a single wire carries 5v to signal a 1 data bit, or 0v to signal a 0 data bit. The more wires you have, the more individual bits you can send in the same time interval. A chip such as the 286 or 386SX, which has 16 wires for transmitting and receiving such data, has a 16-bit data bus. A 32-bit chip, such as the 386DX and 486, has twice as many wires dedicated to simultaneous data transmission as a 16-bit chip; a 32-bit chip can send twice as much information in the same time interval as a 16-bit chip. Modern processors such as the Pentium series have 64-bit external data buses. This means that Pentium processors including the original Pentium, Pentium Pro, and Pentium II can all transfer 64 bits of data at a time to and from the system memory.

A good way to understand this flow of information is to consider a highway and the traffic it carries. If a highway has only one lane for each direction of travel, only one car at a time can move in a certain direction. If you want to increase traffic flow, you can add another lane so that twice as many cars pass in a specified time. You can think of an 8-bit chip as being a single-lane highway because one byte flows through at a time. (One byte equals eight individual bits.) The 16-bit chip, with two bytes flowing at a time, resembles a two-lane highway. You may have four lanes in each direction to move a large number of automobiles; this structure corresponds to a 32-bit data bus, which has the capability to move four bytes of information at a time. Taking this further, a 64-bit data bus is like having an 8-lane highway moving data in and out of the chip!

Just as you can describe a highway by its lane width, you can describe a chip by the width of its data bus. When you read an advertisement that describes a 32-bit or 64-bit computer system, the ad usually refers to the CPU's data bus. This number provides a rough idea of the chip's performance potential (and, therefore, the system).

Perhaps the most important ramification of the data bus in a chip is that the width of the data bus also defines the size of a bank of memory. This means that a 32-bit processor, such as the 486 class chips, reads and writes memory 32 bits at a time. Pentium class processors, including the Pentium III and Celeron, read and write memory 64 bits at a time. Because standard 72-pin SIMMs (Single Inline Memory Modules) are only 32 bits wide, they must be installed one at a time in most 486 class systems; they're installed two at a time in most Pentium class systems. Newer DIMMs (Dual Inline Memory Modules) are 64 bits wide, so they are installed one at a time in Pentium class systems. Each DIMM is equal to a complete bank of memory in Pentium systems, which makes system configuration easy, because they can then be installed or removed one at a time.

See "Memory Banks."

Internal Registers (Internal Data Bus)

The size of the internal registers indicate how much information the processor can operate on at one time and how it moves data around internally within the chip. This is sometimes also referred to as the internal data bus. The register size is essentially the same as the internal data bus size. A register is a holding cell within the processor; for example, the processor can add numbers in two different registers, storing the result in a third register. The register size determines the size of data the processor can operate on. The register size also describes the type of software or commands and instructions a chip can run. That is, processors with 32-bit internal registers can run 32-bit instructions that are processing 32-bit chunks of data, but processors with 16-bit registers cannot. Most advanced processors today—chips from the 386 to the Pentium III—use 32-bit internal registers and can therefore run the same 32-bit operating systems and software.

Some processors have an internal data bus (made up of data paths and storage units called registers) that is larger than the external data bus. The 8088 and 386SX are examples of this structure. Each chip has an internal data bus twice the width of the external bus. These designs, which sometimes are called hybrid designs, usually are low-cost versions of a "pure" chip. The 386SX, for example, can pass data around internally with a full 32-bit register size; for communications with the outside world, however, the chip is restricted to a 16-bit-wide data path. This design enables a systems designer to build a lower-cost motherboard with a 16-bit bus design and still maintain software and instruction set compatibility with the full 32-bit 386.

Internal registers often are larger than the data bus, which means that the chip requires two cycles to fill a register before the register can be operated on. For example, both the 386SX and 386DX have internal 32-bit registers, but the 386SX has to "inhale" twice (figuratively) to fill them, whereas the 386DX can do the job in one "breath." The same thing would happen when the data is passed from the registers back out to the system bus.

The Pentium is an example of this type of design. All Pentiums have a 64-bit data bus and 32-bit registers—a structure that might seem to be a problem until you understand that the Pentium has two internal 32-bit pipelines for processing information. In many ways, the Pentium is like two 32-bit chips in one. The 64-bit data bus provides for very efficient filling of these multiple registers. Multiple pipelines are called superscalar architecture, which was introduced with the Pentium processor.

See "Pentium Processor."

More advanced sixth-generation processors such as the Pentium Pro and Pentium II/III have as many as six internal pipelines for executing instructions. Although some of these internal pipes are dedicated to special functions, these processors can still execute as many as three instructions in one clock cycle.

Address Bus

The address bus is the set of wires that carries the addressing information used to describe the memory location to which the data is being sent or from which the data is being retrieved. As with the data bus, each wire in an address bus carries a single bit of information. This single bit is a single digit in the address. The more wires (digits) used in calculating these addresses, the greater the total number of address locations. The size (or width) of the address bus indicates the maximum amount of RAM that a chip can address.

The highway analogy can be used to show how the address bus fits in. If the data bus is the highway and the size of the data bus is equivalent to the number of lanes, the address bus relates to the house number or street address. The size of the address bus is equivalent to the number of digits in the house address number. For example, if you live on a street in which the address is limited to a two-digit (base 10) number, no more than 100 distinct addresses (00–99) can exist for that street (10²). Add another digit, and the number of available addresses increases to 1,000 (000–999), or 10³.

Computers use the binary (base 2) numbering system, so a two-digit number provides only four unique addresses (00, 01, 10, and 11) calculated as 2². A three-digit number provides only eight addresses (000–111), which is 2³. For example, the 8086 and 8088 processors use a 20-bit address bus that calculates as a maximum of 2²⁰ or 1,048,576 bytes (1MB) of address locations. Table 3.10 describes the memory-addressing capabilities of processors.

Table 3.10 Processor Memory-Addressing Capabilities

The data bus and address bus are independent, and chip designers can use whatever size they want for each. Usually, however, chips with larger data buses have larger address buses. The sizes of the buses can provide important information about a chip's relative power, measured in two important ways. The size of the data bus is an indication of the chip's information-moving capability, and the size of the address bus tells you how much memory the chip can handle.

Internal Level 1 (L1) Cache

All modern processors starting with the 486 family include an integrated L1 cache and controller. The integrated L1 cache size varies from processor to processor, starting at 8KB for the original 486DX and now up to 32KB, 64KB, or more in the latest processors.

Since L1 cache is always built in to the processor die, it runs at the full-core speed of the processor internally. By full-core speed, I mean this cache runs at the higher clock multiplied internal processor speed rather than the external motherboard speed. This cache basically is an area of very fast memory built in to the processor and is used to hold some of the current working set of code and data. Cache memory can be accessed with no wait states because it is running at the same speed as the processor core.

Using cache memory reduces a traditional system bottleneck because system RAM often is much slower than the CPU. This prevents the processor from having to wait for code and data from much slower main memory therefore improving performance. Without the L1 cache, a processor frequently would be forced to wait until system memory caught up.

L1 cache is even more important in modern processors because it is often the only memory in the entire system that can truly keep up with the chip. Most modern processors are clock multiplied, which means they are running at a speed that is really a multiple of the motherboard they are plugged into. The Pentium III 1GHz, for example, runs at a multiple of 7 1/2 times the true motherboard speed of 133MHz. Because the main memory is plugged in to the motherboard, it can also run at only 133MHz maximum. The only 1GHz memory in such a system is the L1 and L2 caches built into the processor core. In this example, the Pentium III 1GHz processor has 32KB of integrated L1 cache in two separate 16KB blocks and 256KB of L2, all running at the full speed of the processor core.

If the data that the processor wants is already in the internal cache, the CPU does not have to wait. If the data is not in the cache, the CPU must fetch it from the Level 2 cache or (in less sophisticated system designs) from the system bus, meaning main memory directly.

In order to understand the importance of cache, you need to know the relative speeds of processors and memory. The problem with this is that processor speed is normally expressed in MHz (millions of cycles per second), while memory speeds are often expressed in nanoseconds (billionths of a second per cycle).

Both are really time- or frequency-based measurements, and a chart comparing them can be found in Chapter 6, "Memory," Table 6.3. In this table, you will note that a 233MHz processor equates to 4.3 nanosecond cycling, which means you would need 4ns memory to keep pace with a 200MHz CPU. Also note that the motherboard of a 233MHz system will normally run at 66MHz, which corresponds to a speed of 15ns per cycle, and require 15ns memory to keep pace. Finally note that 60ns main memory (common on many Pentium class systems) equates to a clock speed of approximately 16MHz. So in a typical Pentium 233 system, you have a processor running at 233MHz (4.3ns per cycle), a motherboard running at 66MHz (15ns per cycle), and main memory running at 16MHz (60ns per cycle).

How Cache Works

To learn how the L1 and L2 cache work, consider the following analogy.

This story involves a person (in this case you) eating food to act as the processor requesting and operating on data from memory. The kitchen where the food is prepared is the main memory (SIMM/DIMM) RAM. The cache controller is the waiter, and the L1 cache is the table you are seated at. L2 cache will be introduced as a food cart, which is positioned between your table and the kitchen.

Okay, here's the story. Say you start to eat at a particular restaurant every day at the same time. You come in, sit down, and order a hot dog. To keep this story proportionately accurate, let's say you normally eat at the rate of one bite (byte? <g>) every four seconds (233MHz = about 4ns cycling). It also takes 60 seconds for the kitchen to produce any given item that you order (60ns main memory).

So, when you first arrive, you sit down, order a hot dog, and you have to wait for 60 seconds for the food to be produced before you can begin eating. Once the waiter brings the food, you start eating at your normal rate. Pretty quickly you finish the hot dog, so you call the waiter and order a hamburger. Again you wait 60 seconds while the hamburger is being produced. When it arrives again you begin eating at full speed. After you finish the hamburger, you order a plate of fries. Again you wait, and after it is delivered 60 seconds later you eat it at full speed. Finally, you decide to finish the meal and order cheesecake for dessert. After another 60-second wait, you can again eat dessert at full speed. Your overall eating experience consists of mostly a lot of waiting, followed by short bursts of actual eating at full speed.

After coming into the restaurant for two consecutive nights at exactly 6 p.m. and ordering the same items in the same order each time, on the third night the waiter begins to think; "I know this guy is going to be here at 6 p.m., order a hot dog, a hamburger, fries, and then cheesecake. Why don't I have these items prepared in advance and surprise him, maybe I'll get a big tip?" So you enter the restaurant and order a hot dog, and the waiter immediately puts it on your plate, with no waiting! You then proceed to finish the hot dog and right as you were about to request the hamburger, the waiter deposits one on your plate. The rest of the meal continues in the same fashion, and you eat the entire meal, taking a bite every five seconds, and never have to wait for the kitchen to prepare the food. Your overall eating experience this time consists of all eating, with no waiting for the food to be prepared, due primarily to the intelligence and thoughtfulness of your waiter.

This analogy exactly describes the function of the L1 cache in the processor. The L1 cache itself is the table that can contain one or more plates of food. Without a waiter, the space on the table is a simple food buffer. When stocked, you can eat until the buffer is empty, but nobody seems to be intelligently refilling it. The waiter is the cache controller who takes action and adds the intelligence to decide what dishes are to be placed on the table in advance of your needing them. Like the real cache controller, he uses his skills to literally guess what food you will require next, and if and when he guesses right, you never have to wait.

Let's now say on the fourth night you arrive exactly on time and start off with the usual hot dog. The waiter, by now really feeling confident, has the hot dog already prepared when you arrive, so there is no waiting.

Just as you finish the hot dog, and right as he is placing a hamburger on your plate, you say "Gee, I'd really like a bratwurst now; I didn't actually order this hamburger." The waiter guessed wrong, and the consequence is that this time you have to wait the full 60 seconds as the kitchen prepares your brat. This is known as a cache miss, where the cache controller did not correctly fill the cache with the data the processor actually needed next. The result is waiting, or in the case of a sample 233MHz Pentium system, the system essentially throttles back to 16MHz (RAM speed) whenever there is a cache miss. According to Intel, the L1 cache in most of its processors has approximately a 90 percent hit ratio. This means that the cache has the correct data 90 percent of the time and consequently the processor runs at full speed, 233MHz in this example, 90 percent of the time. However, 10 percent of the time the cache controller guesses wrong and the data has to be retrieved out of the significantly slower main memory, meaning the processor has to wait. This essentially throttles the system back to RAM speed, which in this example was 60ns or 16MHz.

The main feature of L1 cache is that it has always been integrated into the processor core, where it runs at the same speed as the core. This, combined with the hit ratio of 90 percent or greater, makes L1 cache very important for system performance.

Level 2 (L2) Cache

To mitigate the dramatic slowdown every time there is a L1 cache miss, a secondary or L2 cache can be employed.

Using the restaurant analogy I used to explain L1 cache in the previous section, I'll equate the L2 cache to a cart of additional food items placed strategically such that the waiter can retrieve food from it in 15 seconds. In an actual Pentium class (Socket 7) system, the L2 cache is mounted on the motherboard, which means it runs at motherboard speed—66MHz or 15ns in this example. Now if you ask for an item the waiter did not bring in advance to your table, instead of making the long trek back to the kitchen to retrieve the food and bring it back to you 60 seconds later, he can first check the cart where he has placed additional items. If the requested item is there, he will return with it in only 15 seconds. The net effect in the real system is that instead of slowing down from 233MHz to 16MHz waiting for the data to come from the 60ns main memory, the data can instead be retrieved from the 15ns (66MHz) L2 cache instead. The effect is that the system slows down from 233MHz to 66MHz.

Just as with the L1 cache, most L2 caches have a hit ratio also in the 90 percent range, which means that if you look at the system as a whole, 90 percent of the time it will be running at full speed (233MHz in this example) by retrieving data out of the L1 cache. Ten percent of the time it will slow down to retrieve the data from the L2 cache. Ninety percent of the time the processor goes to the L2 cache the data will be in the L2, and 10 percent of that time you will have to go to the slow main memory to get the data due to an L2 cache miss. This means that by combining both caches, our sample system runs at full processor speed 90 percent of the time (233MHz in this case), motherboard speed nine percent (90 percent of 10 percent) of the time (66MHz in this case), and RAM speed about one percent (10 percent of 10 percent) of the time (16MHz in this case). You can clearly see the importance of both the L1 and L2 caches; without them the system will be using main memory more often, which is significantly slower than the processor.

This brings up other interesting points. If you could spend money doubling the performance of either the main memory (RAM) or the L2 cache, which would you improve? Considering that main memory is only used directly about one percent of the time, if you doubled performance there, you would double the speed of your system only one percent of the time! That doesn't sound like enough of an improvement to justify much expense. On the other hand, if you doubled L2 cache performance, you would be doubling system performance nine percent of the time, a much greater improvement overall. I'd much rather improve L2 than RAM performance.

The processor and system designers at Intel and AMD know this and devised methods of improving the performance of L2 cache. In Pentium (P5) class systems, the L2 cache was normally found on the motherboard and had to therefore run at motherboard speed. Intel made the first dramatic improvement by migrating the L2 cache from the motherboard directly into the processor and initially running it at the same speed as the main processor. The cache chips were made by Intel and mounted next to the main processor die in a single chip housing. This proved too expensive, so with the Pentium II Intel began using cache chips from third-party suppliers like Sony, Toshiba, NEC, Samsung, and others. Since these were supplied as complete packaged chips and not raw die, Intel mounted them on a circuit board alongside the processor. This is why the Pentium II was designed as a cartridge rather than what looked like a chip.

One problem was the speed of the available third-party cache chips. The fastest ones on the market were 3ns or higher, meaning 333MHz or less in speed. Because the processor was being driven in speed above that, in the Pentium II and initial Pentium III processors Intel had to run the L2 cache at half the processor speed since that is all the commercially available cache memory could handle. AMD followed suit with the Athlon processor, which had to drop L2 cache speed even further in some models to two-fifths or one-third the main CPU speed to keep the cache memory speed less than the 333MHz commercially available chips.

Then there was a breakthrough, which first appeared in the Celeron processor 300A and above. These had 128KB of L2 cache, but there were no external chips used. Instead the L2 cache had been integrated directly into the processor core just like the L1. This meant that now both the L1 and L2 caches would run at full processor speed, and more importantly scale up in speed as the processor speeds increased in the future. In the newer Pentium III, as well as all the Xeon and Celeron processors, the L2 cache runs at full processor core speed, which means there is no waiting or slowing down after an L1 cache miss. AMD also achieved full-core speed on-die cache in its later Athlon and Duron chips. Using on-die cache improves performance dramatically, because the nine percent of the time the system would be using the L2 it would now remain at full speed instead of slowing down to one-half or less the processor speed or, even worse, slow down to motherboard speed as in Socket 7 designs. Another benefit of on-die L2 cache is cost, which is less because there are now fewer parts involved.

Let's revisit the restaurant analogy using a modern Pentium III 1GHz. You would now be taking a bite every one second (1GHz = 1ns cycling). The L1 cache would also be running at that speed, so you could eat anything on your table at that same rate (the table = L1 cache). The real jump in speed comes when you want something that isn't already on the table (L1 cache miss), in which case the waiter runs to the cart, and returns nine out of 10 times with the food you want in only one second (L2 speed = 1GHz or 1ns cycling). In this more modern system, you would run at 1GHz 99 percent of the time (L1 and L2 hit ratios combined), and only slow down to RAM speed (wait for the kitchen) 1 percent of the time as before. With faster memory running at 133MHz (7.5ns), you would only have to wait 7.5 seconds for the food to come from the kitchen. If only restaurant performance increased at the same rate processor performance has!

Cache Organization

The organization of the cache memory in the 486 and Pentium family is called a four-way set associative cache, which means that the cache memory is split into four blocks. Each block also is organized as 128 or 256 lines of 16 bytes each.

To understand how a four-way set associative cache works, consider a simple example. In the simplest cache design, the cache is set up as a single block into which you can load the contents of a corresponding block of main memory. This procedure is similar to using a bookmark to locate the current page of a book that you are reading. If main memory equates to all the pages in the book, the bookmark indicates which pages are held in cache memory. This procedure works if the required data is located within the pages marked with the bookmark, but it does not work if you need to refer to a previously read page. In that case, the bookmark is of no use.

An alternative approach is to maintain multiple bookmarks to mark several parts of the book simultaneously. Additional hardware overhead is associated with having multiple bookmarks, and you also have to take time to check all the bookmarks to see which one marks the pages of data you need. Each additional bookmark adds to the overhead, but also increases your chance of finding the desired pages.

If you settle on marking four areas in the book, you have essentially constructed a four-way set associative cache. This technique splits the available cache memory into four blocks, each of which stores different lines of main memory. Multitasking environments, such as Windows, are good examples of environments in which the processor needs to operate on different areas of memory simultaneously and in which a four-way cache would improve performance greatly.

The contents of the cache must always be in sync with the contents of main memory to ensure that the processor is working with current data. For this reason, the internal cache in the 486 family is a write-through cache. Write-through means that when the processor writes information out to the cache, that information is automatically written through to main memory as well.

By comparison, the Pentium and later chips have an internal write-back cache, which means that both reads and writes are cached, further improving performance. Even though the internal 486 cache is write-through, the system can employ an external write-back cache for increased performance. In addition, the 486 can buffer up to four bytes before actually storing the data in RAM, improving efficiency in case the memory bus is busy.

Another feature of improved cache designs is that they are non-blocking. This is a technique for reducing or hiding memory delays by exploiting the overlap of processor operations with data accesses. A non-blocking cache allows program execution to proceed concurrently with cache misses as long as certain dependency constraints are observed. In other words, the cache can handle a cache miss much better and allow the processor to continue doing something non-dependent on the missing data.

The cache controller built into the processor also is responsible for watching the memory bus when alternative processors, known as busmasters, are in control of the system. This process of watching the bus is referred to as bus snooping. If a busmaster device writes to an area of memory that also is stored in the processor cache currently, the cache contents and memory no longer agree. The cache controller then marks this data as invalid and reloads the cache during the next memory access, preserving the integrity of the system.

A secondary external L2 cache of extremely fast static RAM (SRAM) chips also is used in most 486 and Pentium-based systems. It further reduces the amount of time that the CPU must spend waiting for data from system memory. The function of the secondary processor cache is similar to that of the onboard cache. The secondary processor cache holds information that is moving to the CPU, thereby reducing the time that the CPU spends waiting and increasing the time that the CPU spends performing calculations. Fetching information from the secondary processor cache rather than from system memory is much faster because of the SRAM chips' extremely fast speed—15 nanoseconds (ns) or less.

Pentium systems incorporate the secondary cache on the motherboard, while Pentium Pro and Pentium II systems have the secondary cache inside the processor package. By moving the L2 cache into the processor, systems are capable of running at speeds higher than the motherboard—up to as fast as the processor core.

As clock speeds increase, cycle time decreases. Most SIMM memory used in Pentium and earlier systems was 60ns, which works out to be only about 16MHz! Standard motherboard speeds are now 66MHz, 100MHz, or 133MHz, and processors are available at 600MHz or more. Newer systems don't use cache on the motherboard any longer, as the faster SDRAM or RDRAM used in modern Pentium Celeron/II/III systems can keep up with the motherboard speed. The trend today is toward integrating the L2 cache into the processor die just like the L1 cache. This allows the L2 to run at full-core speed because it is now a part of the core. Cache speed is always more important than size. The rule is that a smaller but faster cache is always better than a slower but bigger cache. Table 3.11 illustrates the need for and function of L1 (internal) and L2 (external) caches in modern systems.

Table 3.11 CPU Speeds Relative to Cache, SIMM/DIMM, and Motherboard

The Celeron processors at 300MHz and faster as well as the Pentium III processors at 600MHz and faster have on-die L2 cache which runs at the full-core speed of the processor. Newer Athlon processors and all Duron processors have full-core speed on-die cache as well. The older Pentium II and III processors, as well as the older Athlons, use external L2 and run the cache at either one-half, two-fifths, or one-third of the core processor speed. As you can see, having two levels of cache between the very fast CPU and the much slower main memory helps minimize any wait states the processor might have to endure, especially those with the on-die L2. This allows the processor to keep working closer to its true speed.

Processor Modes

All Intel 32-bit and later processors, from the 386 on up, can run in several modes. Processor modes refer to the various operating environments and affect the instructions and capabilities of the chip. The processor mode controls how the processor sees and manages the system memory and the tasks that use it.

Three different modes of operation possible are

• Real mode (16-bit software)

• Protected mode (32-bit software)

• Virtual Real mode (16-bit programs within a 32-bit environment)

Real Mode

The original IBM PC included an 8088 processor that could execute 16-bit instructions using 16-bit internal registers and could address only 1MB of memory using 20 address lines. All original PC software was created to work with this chip and was designed around the 16-bit instruction set and 1MB memory model. For example, DOS and all DOS software, Windows 1.x through 3.x, and all Windows 1.x through 3.x applications are written using 16-bit instructions. These 16-bit operating systems and applications are designed to run on an original 8088 processor.

See "Internal Registers."

See "Address Bus."

Later processors such as the 286 could also run the same 16-bit instructions as the original 8088, but much faster. In other words, the 286 was fully compatible with the original 8088 and could run all 16-bit software just the same as an 8088, but, of course, that software would run faster. The 16-bit instruction mode of the 8088 and 286 processors has become known as real mode. All software running in real mode must use only 16-bit instructions and live within the 20-bit (1MB) memory architecture it supports. Software of this type is normally single-tasking, which means that only one program can run at a time. There is no built-in protection to keep one program from overwriting another program or even the operating system in memory, which means that if more than one program is running, it is possible for one of them to bring the entire system to a crashing halt.

Protected (32-bit) Mode

Then came the 386, which was the PC industry's first 32-bit processor. This chip could run an entirely new 32-bit instruction set. To take full advantage of the 32-bit instruction set, you needed a 32-bit operating system and a 32-bit application. This new 32-bit mode was referred to as protected mode, which alludes to the fact that software programs running in that mode are protected from overwriting one another in memory. Such protection helps make the system much more crash-proof, as an errant program cannot very easily damage other programs or the operating system. In addition, a crashed program can be terminated, while the rest of the system continues to run unaffected.

Knowing that new operating systems and applications—which take advantage of the 32-bit protected mode—would take some time to develop, Intel wisely built in a backward-compatible real mode into the 386. That allowed it to run unmodified 16-bit operating systems and applications. It ran them quite well—much faster than any previous chip. For most people, that was enough; they did not necessarily want any new 32-bit software—they just wanted their existing 16-bit software to run faster. Unfortunately, that meant the chip was never running in the 32-bit protected mode, and all the features of that capability were being ignored.

When a high-powered processor such as a Pentium III is running DOS (real mode), it acts like a "Turbo 8088." Turbo 8088 means that the processor has the advantage of speed in running any 16-bit programs; it otherwise can use only the 16-bit instructions and access memory within the same 1MB memory map of the original 8088. This means if you have a 128MB Pentium III system running Windows 3.x or DOS, you are effectively using only the first megabyte of memory, leaving the other 127MB largely unused!

New operating systems and applications that ran in the 32-bit protected mode of the modern processors were needed. Being stubborn, we resisted all the initial attempts at getting switched over to a 32-bit environment. It seems that as a user community, we are very resistant to change and would be content with our older software running faster rather than adopting new software with new features. I'll be the first one to admit that I was one of those stubborn users myself!

Because of this resistance, 32-bit operating systems such as UNIX or variants (such as Linux), OS/2, and even Windows NT and Windows 2000 have had a very hard time getting any mainstream share in the PC marketplace. Out of those, Windows 2000 is the only one that will likely become a true mainstream product, and that is mainly because Microsoft has coerced us in that direction with Windows 95 through 98 and Me. Windows 3.x was the last full 16-bit operating system. In fact, it was not a complete operating system because it ran on top of DOS.

Microsoft realized how stubborn the installed base of PC users was so it developed Windows 95 through the current Windows Me as a bridge to a full 32-bit world. Windows 95, 98, Me are mostly 32-bit operating systems but retain enough 16-bit capability to fully run old 16-bit applications. Windows 95 came out in August 1995, a full 10 years later than the introduction of the first 32-bit PC processor! It has taken us only 10 years to migrate to software that can fully use the processors we have in front of us.

Virtual Real Mode

The key to the backward compatibility of the Windows 32-bit environment is the third mode in the processor: virtual real mode. Virtual real is essentially a virtual real mode 16-bit environment that runs inside 32-bit protected mode. When you run a DOS prompt window inside Windows, you have created a virtual real mode session. Because protected mode allows true multitasking, you can actually have several real mode sessions running, each with its own software running on a virtual PC. This can all run simultaneously, even while other 32-bit applications are running.

Note that any program running in a virtual real mode window can access up to only 1MB of memory, which that program will believe is the first and only megabyte of memory in the system. In other words, if you run a DOS application in a virtual real window, it will have a 640KB limitation on memory usage. That is because there is only 1MB of total RAM in a 16-bit environment, and the upper 384KB is reserved for system use. The virtual real window fully emulates an 8088 environment, so that aside from speed, the software runs as if it were on an original real mode-only PC. Each virtual machine gets its own 1MB address space, an image of the real hardware BIOS routines, and emulation of all other registers and features found in real mode.

Virtual real mode is used when you use a DOS window to run a DOS or Windows 3.x 16-bit program. When you start a DOS application, Windows creates a virtual DOS machine under which it can run.

One interesting thing to note is that all Intel and Intel-compatible (such as AMD and Cyrix) processors power up in real mode. If you load a 32-bit operating system, it will automatically switch the processor into 32-bit mode and take control from there.

Some 16-bit (DOS and Windows 3.x) applications misbehave, which means they do things that even virtual real mode will not support. Diagnostics software is a perfect example of this. Such software will not run properly in a real mode (virtual real) window under Windows. In that case, you can still run your Pentium III in the original no-frills real mode by either booting to a DOS floppy or in the case of Windows 9x, interrupting the boot process and commanding the system to boot plain DOS. This is accomplished on Windows 9x systems by pressing the F8 key when you see the prompt Starting Windows... on the screen or immediately after the beep when the POST (power on self test) is completed. In the latter case it helps to hit the F8 key multiple times as it is hard to get the timing just right and Windows 9x will only look for the key during a short two-second time window. If successful you will then see the Startup Menu; you can select one of the command prompt choices, which tell the system to boot plain 16-bit real mode DOS. The choice of Safe Mode Command Prompt is best if you are going to run true hardware diagnostics, which do not normally run in protected mode and should be run with a minimum of drivers and other software loaded.

Note that even though Windows Me (Millennium Edition) is based on Windows 98, Microsoft removed the Startup Menu option in an attempt to further wean us from any 16-bit operation. Windows NT and 2000 also lack the ability to interrupt the startup in this manner. For these operating systems, you'll need a Startup Disk (floppy), which you can create and then use to boot the system in real mode. Normally you would do this to perform certain maintenance procedures, especially such as running hardware diagnostics or doing direct disk sector editing.

Although real mode is used by 16-bit DOS and "standard" DOS applications, special programs were available that "extended" DOS and allow access to extended memory (over 1MB). These are sometimes called DOS extenders and are usually included as a part of any DOS or Windows 3.x software that uses them. The protocol that describes how to make DOS work in protected mode is called DPMI (DOS protected mode interface). DPMI was used by Windows 3.x to access extended memory for use with Windows 3.x applications. It allowed them to use more memory even though they were still 16-bit programs. DOS extenders are especially popular in DOS games, because they allow them to access much more of the system memory than the standard 1MB most real mode programs can address. These DOS extenders work by switching the processor in and out of real mode, or in the case of those that run under Windows, they use the DPMI interface built in to Windows, allowing them to share a portion of the system's extended memory.

Another exception in real mode is that the first 64KB of extended memory is actually accessible to the PC in real mode, despite the fact that it's not supposed to be possible. This is the result of a bug in the original IBM AT with respect to the 21st memory address line, known as A20 (A0 is the first address line). By manipulating the A20 line, real mode software can gain access to the first 64KB of extended memory—the first 64KB of memory past the first megabyte. This area of memory is called the high memory area (HMA).