Computer memory (Несколько текстов для зачёта), страница 4

Cache Technology
One common question asked at this point is, "Why not make all of the computer's memory run at the same speed as the L1 cache, so no caching would be required?" That would work, but it would be incredibly expensive. The idea behind caching is to use a small amount of expensive memory to speed up a large amount of slower, less-expensive memory.

In designing a computer, the goal is to allow the microprocessor to run at its full speed as inexpensively as possible. A 500-MHz chip goes through 500 million cycles in one second (one cycle every two nanoseconds). Without L1 and L2 caches, an access to the main memory takes 60 nanoseconds, or about 30 wasted cycles accessing memory.

When you think about it, it is kind of incredible that such relatively tiny amounts of memory can maximize the use of much larger amounts of memory. Think about a 256-kilobyte L2 cache that caches 64 megabytes of RAM. In this case, 256,000 bytes efficiently caches 64,000,000 bytes. Why does that work?

In computer science, we have a theoretical concept called locality of reference. It means that in a fairly large program, only small portions are ever used at any one time. As strange as it may seem, locality of reference works for the huge majority of programs. Even if the executable is 10 megabytes in size, only a handful of bytes from that program are in use at any one time, and their rate of repetition is very high. Let's take a look at the following pseudo-code to see why locality of reference works (see How C Programming Works to really get into it):

Output to screen « Enter a number between 1 and 100 »

Read input from user

Put value from user in variable X

Put value 100 in variable Y

Put value 1 in variable Z

Loop Y number of time

Divide Z by X

If the remainder of the division = 0

then output « Z is a multiple of X »

Add 1 to Z

Return to loop

End

This small program asks the user to enter a number between 1 and 100. It reads the value entered by the user. Then, the program divides every number between 1 and 100 by the number entered by the user. It checks if the remainder is 0 (modulo division). If so, the program outputs "Z is a multiple of X" (for example, 12 is a multiple of 6), for every number between 1 and 100. Then the program ends.

Even if you don't know much about computer programming, it is easy to understand that in the 11 lines of this program, the loop part (lines 7 to 9) are executed 100 times. All of the other lines are executed only once. Lines 7 to 9 will run significantly faster because of caching.

This program is very small and can easily fit entirely in the smallest of L1 caches, but let's say this program is huge. The result remains the same. When you program, a lot of action takes place inside loops. A word processor spends 95 percent of the time waiting for your input and displaying it on the screen. This part of the word-processor program is in the cache.

This 95%-to-5% ratio (approximately) is what we call the locality of reference, and it's why a cache works so efficiently. This is also why such a small cache can efficiently cache such a large memory system. You can see why it's not worth it to construct a computer with the fastest memory everywhere. We can deliver 95 percent of this effectiveness for a fraction of the cost.

Removable Flash Memory Cards
While your computer's BIOS chip is the most common form of Flash memory, removable solid-state storage devices are becoming increasingly popular. SmartMedia and CompactFlash cards are both well-known, especially as "electronic film" for digital cameras. Other removable Flash memory products include Sony's Memory Stick, PCMCIA memory cards, and memory cards for video game systems such as Nintendo's N64, Sega's Dreamcast and Sony's PlayStation. We will focus on SmartMedia and CompactFlash, but the essential idea is the same for all of these products. Every one of them is simply a form of Flash memory.

There are several reasons to use Flash memory instead of a hard disk:

• Flash memory is noiseless.

• It allows faster access.

• It is smaller in size.

• It is lighter.

• It has no moving parts.

So why don't we just use Flash memory for everything? Because the cost per megabyte for a hard disk is drastically cheaper, and the capacity is substantially more.

SmartMedia
The solid-state floppy-disk card (SSFDC), better known as SmartMedia, was originally developed by Toshiba.

SmartMedia card

SmartMedia cards are available in capacities ranging from 2 MB to 128 MB. The card itself is quite small, approximately 45 mm long, 37 mm wide and less than 1 mm thick. This is amazing when you consider what is packed into such a tiny package!

As shown below, SmartMedia cards are elegant in their simplicity. A plane electrode is connected to the Flash-memory chip by bonding wires. The Flash-memory chip, plane electrode and bonding wires are embedded in a resin using a technique called over-molded thin package (OMTP). This allows everything to be integrated into a single package without the need for soldering.

The OMTP module is glued to a base card to create the actual card. Power and data is carried by the electrode to the Flash-memory chip when the card is inserted into a device. A notched corner indicates the power requirements of the SmartMedia card. Looking at the card with the electrode facing up, if the notch is on the left side, the card needs 5 volts. If the notch is on the right side, it requires 3.3 volts.

SmartMedia cards erase, write and read memory in small blocks (256- or 512-byte increments). This approach means that they are capable of fast, reliable performance while allowing you to specify which data you wish to keep. They are small, lightweight and easy to use. They are less rugged than other forms of removable solid-state storage, so you should be very careful when handling and storing them.

CompactFlash
CompactFlash cards were developed by Sandisk in 1994, and they are different from SmartMedia cards in two important ways:

• They are thicker.

• They utilize a controller chip.

CompactFlash consists of a small circuit board with Flash-memory chips and a dedicated controller chip, all encased in a rugged shell that is several times thicker than a SmartMedia card.

As shown below, CompactFlash cards are 43 mm wide and 36 mm long, and come in two thicknesses: Type I cards are 3.3 mm thick, and Type II cards are 5.5 mm thick.

CompactFlash card

CompactFlash cards support dual voltage and will operate at either 3.3 volts or 5 volts.

The increased thickness of the card allows for greater storage capacity than SmartMedia cards. CompactFlash sizes range from 8 MB to 192 MB. The onboard controller can increase performance, particularly on devices that have slow processors. The case and controller chip add size, weight and complexity to the CompactFlash card when compared to the SmartMedia card.

Both of these types of removable storage, as well as PCMCIA Type I and Type II memory cards, adhere to standards developed by the Personal Computer Memory Card International Association (PCMCIA). Because of these standards, it is easy to use CompactFlash and SmartMedia products in a variety of devices. You can also buy adapters that allow you to access these cards through a standard floppy drive, USB port or PCMCIA card slot (like the one you find on a laptop computer). Sony's Memory Stick is available in a large array of products offered by Sony, and is now showing up in products from other manufacturers as well.

Although standards are flourishing, there are many Flash-memory products that are completely proprietary in nature, such as the memory cards in video game systems. But it is good to know that as electronic components become increasingly interchangeable and learn to communicate with each other (by way of technologies such as Bluetooth), standardized removable memory will allow you to keep your world close at hand.

Virtual memory

Virtual memory is a common part of most operating systems on desktop computers. It has become so common because it provides a big benefit for users at a very low cost.

What is Virtual Memory?
Most computers today have something like 32 or 64 megabytes of RAM available for the CPU to use (see How RAM Works for details on RAM). Unfortunately, that amount of RAM is not enough to run all of the programs that most users expect to run at once.

For example, if you load the operating system, an e-mail program, a Web browser and word processor into RAM simultaneously, 32 megabytes is not enough to hold it all. If there were no such thing as virtual memory, then once you filled up the available RAM your computer would have to say, "Sorry, you can not load any more applications. Please close another application to load a new one." With virtual memory, what the computer can do is look at RAM for areas that have not been used recently and copy them onto the hard disk. This frees up space in RAM to load the new application.

Because this copying happens automatically, you don't even know it is happening, and it makes your computer feel like is has unlimited RAM space even though it only has 32 megabytes installed. Because hard disk space is so much cheaper than RAM chips, it also has a nice economic benefit.

Speed Concerns
The read/write speed of a hard drive is much slower than RAM, and the technology of a hard drive is not geared toward accessing small pieces of data at a time. If your system has to rely too heavily on virtual memory, you will notice a significant performance drop. The key is to have enough RAM to handle everything you tend to work on simultaneously -- then, the only time you "feel" the slowness of virtual memory is is when there's a slight pause when you're changing tasks. When that's the case, virtual memory is perfect.

When it is not the case, the operating system has to constantly swap information back and forth between RAM and the hard disk. This is called thrashing, and it can make your computer feel incredibly slow.

The area of the hard disk that stores the RAM image is called a page file. It holds pages of RAM on the hard disk, and the operating system moves data back and forth between the page file and RAM. On a Windows machine, page files have a .SWP extension.

Configuring Virtual Memory
Take Windows 98 as an example of a typical operating system that has virtual memory. Windows 98 has an intelligent virtual memory manager that uses a default setting to help Windows allocate hard drive space for virtual memory as needed. For most circumstances, this should meet your needs, but you may want to manually configure virtual memory, especially if you have more than one physical hard drive or speed-critical applications.

To do this, open the "Control Panel" window and double-click on the "System" icon. The system dialog window will open. Click on the "Performance" tab and then click on the "Virtual Memory" button.

Click on the option that says, "Let me specify my own virtual memory settings." This will make the options below that statement become active. Click on the drop-down list beside "Hard disk:" to select the hard drive that you wish to configure virtual memory for. Remember that a good rule of thumb is to equally split virtual memory between the physical hard disks you have.

In the "Minimum:" box, enter the smallest amount of hard drive space you wish to use for virtual memory on the hard disk specified. The amounts are in megabytes. For the "C:" drive, the minimum should be 2 megabytes. The "Maximum:" figure can be anything you like, but one possible upper limit is twice physical RAM space. Windows default is normally 12 megabytes above the amount of physical RAM in your computer. To put the new settings into effect, close the dialog box and restart your computer.

The amount of hard drive space you allocate for virtual memory is important. If you allocate too little, you will get "Out of Memory" errors. If you find that you need to keep increasing the size of the virtual memory, you probably are also finding that your system is sluggish and accesses the hard drive constantly. In that case, you should consider buying more RAM to keep the ratio between RAM and virtual memory about 2:1. Some applications enjoy having lots of virtual memory space but do not access it very much. In that case, large paging files work well.