Anda di halaman 1dari 31

A Complete History Of

Mainframe Computing
Harvard Mark I

Our trip down mainframe lane starts and ends, not so surprisingly, with IBM. Back in the 1930s, when
a computer was actually a fellow with a slide rule who did computations for you, IBM was mainly
known for its punched-card machines. However, the transformation of IBM from one of the many
sellers of business machines to the company that later became a computer monopoly was due in
large part to forward-looking leadership, at that time going by the name of Thomas Watson, Sr.

The Harvard machine was a manifestation of his vision, although in practical terms, was not a
technological starting point for what followed. Still, it is worth looking at, just so we can see how far
things have come.

It all began in 1936, when Howard Aiken, a Harvard researcher, was trying to work through a
problem relating to the design of vacuum tubes (a little ironic, as you will see). In order to make
progress, he needed to solve a set of non-linear equations, and there was nothing available that
could do it for him. Aiken proposed to Harvard researchers there that they build a large-scale
calculator that could solve these problems. His request was not well-received.

Aiken then approached Monroe Calculating Company, which declined the proposal. So Aiken took it
to IBM. Aiken's proposal was essentially a requirement document, not a true design, and it was up to
IBM to figure out how to fulfill these requirements. The initial cost was estimated at $15,000, but
that quickly ballooned up to $100,000 by the time the proposal was formally accepted in 1939. It
eventually cost IBM roughly $200,000 to make.

It was not until 1943 that the five-ton, 51-ft. long, mechanical beast ran its first calculation. Because
the computer needed mechanical synchronization between its different calculating units, there was a
shaft driven by a five-horsepower motor running its entire length. The computer "program" was
created by inserting wire links into a plug board. The data was read by punched cards and the results
were printed on punched cards or by electric typewriters. Even by the standards of the day, it was
slow. It was only capable of doing three additions or subtractions per second and the machine took a
rather ponderous six seconds to do a single multiplication. Logarithms and trigonometric calculations
took over a minute each.

As mentioned, the Harvard Mark I was a technological dead-end, and did not do much important
work during the 15 years it was used. Still, it represented the first fully-automated computing
machine ever made. While it was very slow, mechanical, and lacked necessities like conditional
branches, it was a computer, and represented a tiny glimpse at what was yet to come.

ABC (Atanasoff-Berry Computer)

Although only recognized as such many years later, the ABC (Atanasoff-Berry Computer) was really
the first electronic computer. You might think "electronic computer" is redundant, but as we just saw
with the Harvard Mark I, there really were computers that had no electronic components, and
instead used mechanical switches, variable toothed gears, relays, and hand cranks. The ABC, by
contrast, did all of its computing using electronics, and thus represents a very important milestone
for computing.

Although it was electronic, the computer's parts were very different than what is used today. In fact,
transistors and integrated circuits are required just to have the same building blocks. They did not
exist in 1939 when John Atanasoff received funding to build a prototype, so he used what was
available at the time: vacuum tubes. Vacuum tubes could amplify signals and act as switches, so they
could thus be used to create logic circuits. However, they used a lot of power, got very hot, and were
very unreliable. These were tradeoffs he and others had to live with and were unfortunate
characteristics of the computers built from them.

The logic circuits he created with the vacuum tubes were fast, and could do addition and subtraction
calculations at 30 operations per second. While it would be normal today, it was rare for a computer
to use a binary system, since it was not a number system with which many were familiar at that time.
Another important technology was the use of capacitors for memory, and "jogging" them with
electricity to keep their contents (similar to a DRAM refresh used today). Memory was not truly
random though, as it was actually contained in a spinning drum that rotated fully once per second.
Specific memory locations could only be read from when the section of the drum they were in was
over the reader. This obviously had serious latency issues. Later, he added a punched-card machine
(punched cards were very extensively used by businesses at that time to store records and perform
computations on them) to hold data that could not fit in the drum memory.

In retrospect, this computer wasn't terribly useful. It wasn't even programmable. But it was, at least
on a conceptual level, a very important milestone for computers, and a progenitor to computers of
the future. While working on this machine, Mr. Atanasoff invited a man named John W. Mauchly to
view his creation. Let's find out why that was significant.

ENIAC

On December 7, 1941, Japan attacked Pearl Harbor, drawing the United States into the conflagration
known as World War II. One problem every country at war had was creating artillery ballistic tables
for each type of artillery they produced. This was a huge undertaking, being both a very slow and
tedious process. So, the U.S. army granted funds to the Moore School of Electrical Engineering at the
University of Pennsylvania to build an electronic computer to facilitate this work. You might have
guessed from the last page that our friend John Mauchly just happened to be there, and he then took
on this project with a gifted graduate student named J. Presper Eckert.

However, World War II ended before the machine was completed. When finished in 1946, this 30-ton
monstrosity consisted of 49-ft. high cabinets, 18,000 vacuum tubes, 1,500 relays, 70,000 resistors,
10,000 capacitors, and 6,000 manual switches, and it consumed 200 kilowatts. Although finished
after the war, it hardly proved useless. Capable of 5,000 additions, 357 multiplications, or 38
divisions per second, the performance of this machine was incredible. Problems that took a human
mathematician 20 hours to solve, took only 30 seconds for the ENIAC.

The main problem with the machine, aside from the unreliability inherent in all vacuum tube
machines, was that it was not programmable in the conventional sense. "Programs" were entered by
the "ENIAC girls" working on plug boards and banks of switches. This generally took from a few hours
to a few days. Also, in a backward step from the ABC computer, the ENIAC worked with decimal and
not binary numbers.
Nevertheless, the ENIAC was an extremely useful machine for the U.S., particularly with the
enhancements that were later added on, until it was retired in 1955. During its lifetime, it worked on
problems ranging from weather forecasts, random-number studies, thermal ignition, wind-tunnel
design, artillery trajectory calculations, and even development of the hydrogen bomb. In fact, by the
time it was retired in 1955, it was estimated that the ENIAC by itself did more calculations than all of
humankind did up to 1945.

While the story of the ENIAC trails off in 1955, our two heroes, Mauchly and Eckert, still have much
to accomplish before their stories end.

EDVAC

Even before the ENIAC ran its first test, Mauchly and Presper were very aware of its shortcomings. So
was John Von Neumann, whom many of you have heard about from the expression "Von Neumann
Architecture" (although he received too much personal credit for what was a group effort). At any
rate, the EDVAC was the first expression of this architecture, although Mauchly and Presper left the
University of Pennsylvania where it was being built in 1946, before the computer was finished.

At that time, there were several major issues with the ENIAC. Sure, it was fast. But it had very little
storage. More than that, it had to be reprogrammed by re-wiring it, which could take hours or even
days, and it was inherently unreliable because the computer used so many vacuum tubes. In addition
to being unreliable, vacuum tubes also used a lot of power, required a lot of space, and generated a
lot of heat. Clearly, minimizing their use would have multiple advantages.

There were two important conceptual changes (one of which was revolutionary) on the EDVAC that
seem very obvious today. For one, it was binary rather than decimal, like the ENIAC, and this was
much more efficient. Also, rather than rewiring the machine every time you wanted to change the
"program," the EDVAC introduced the idea of storing the program in memory, just as if it were data.
This is what we do today. We do not, after all, have separate RAM areas for applications and for their
data (although L1 caches typically operate this way). The processor knows, based on the context in
which the memory was accessed, whether it is data or an executable.

In addition, memory no longer consisted of vacuum tubes, but was stored as electrical impulses in
mercury. The mercury delay line was 100 times more efficient in terms of the electronics necessary
to store data and made much larger amounts of memory feasible and more reliable.

The EDVAC was a major advance, and proved very useful until it was retired in 1960. It was a binary
stored-program computer, which could be programmed much more quickly than the ENIAC could. It
was also much smaller, weighing less than nine tons, and consumed "only" 56 kilowatts of power.
Even still, our two heroes were not done yet.

UNIVAC

As mentioned, Eckert and Mauchly left the University of Pennsylvania in 1946 to form the Electronic
Control Co. They incorporated their company in 1947, calling it the Eckert-Mauchly Computer Corp.,
or EMCC. Their departure delayed the completion the EDVAC to the extent that the EDSAC, based on
the EDVAC design, was actually completed before it. The dynamic duo, however, wanted to explore
the commercial opportunities that this new technology offered, which was not possible with
university-sponsored research, so they developed a computer based on their ideas for the EDVAC
and even superseded them. Along the way, they created the BINAC for financial purposes, but the
Universal Automatic Computer (UNIVAC) is really the more interesting machine.

The UNIVAC was the first-ever commercial computer, 46 units of which were sold to businesses and
government after its 1951 introduction. All machines before it were unique, meaning they only made
one of them. The difference for the UNIVAC was there were multiple UNIVACS (meaning many of the
same design). Eckert and Mauchly correctly concluded that a computer could be used not only for
computations, but also for data processing, while many of their contemporaries found the idea of
using the same machine for solving differential equations and paying bills to be absurd. At any rate,
this observation was critical in the design and success of the UNIVAC.

On a lower level, the UNIVAC consisted of 5,200 vacuum tubes (almost all in the processor), weighed
29,000 pounds, consumed 125 KW, and ran at a whopping 2.25 MHz clock speed. It was capable of
doing 455 multiplications per second and could hold 1,000 words in its mercury delay-line memory.
Each word of memory could contain two instructions, an 11-digit number and sign, or 12 alphabetical
characters. The processing speed was roughly equivalent to the amount of time it took the ENIAC to
complete the tasks that it could perform. But in virtually every other way, it was better.

Perhaps most importantly, the UNIVAC was much more reliable (mainly due to its use of much fewer
vacuum tubes) than the ENIAC. On top of this, the "Automatic" in its name alluded to how it required
no human effort to run. All the data was stored and read from a metal tape drive (as opposed to
having to manually load the programs each time they were to be run with paper tapes or punched
cards). Using tapes made actual processing much faster than the ENIAC, since the I/O bottleneck was
mitigated. And of course, setup time re-wiring the ENIAC for the next "program" was eliminated.
There were other niceties that made their appearance on the UNIVAC as well, like buffers (similar to
a cache) between the relatively fast delay lines and relatively slow tape drives, extra bits for data
checking, and the aforementioned ability to operate on both numbers and alphabetical characters.

The UNIVAC gained additional fame by correctly predicting the landslide presidential victory of
Dwight Eisenhower in 1952 on national TV. This and the fact it was the first commercially available
computer gave Remington Rand (which had bought EMCC) a very strong position in the burgeoning
electronic computer industry. They had thrown down the gauntlet with UNIVAC. But what was IBM
doing at this time?

IBM 701

While most of our esteemed readers have a good idea of IBM's dominance in the world of computing
from the mid to late 20th century, what may be less-known is where it starts, how and why it
happened, and how it progressed. Let's start with one of the two computers it developed at the
same time as the UNIVAC.
We'll begin with the IBM 701, which was a direct competitor to the esteemed UNIVAC. Announced in
1952, there were many similarities between the 701 and the UNIVAC, but many differences as well.
Memory was not stored in a mercury-delay line, but in 3" vacuum tubes referred to as "William's
Tubes," in deference to their inventor. Although they were more reliable than normal vacuum tubes,
they still proved to be the greatest source of unreliability for the computer. However, one benefit
was that all bits of a word could be retrieved at once, as opposed to the UNIVAC's mercury delay
lines, where memory was read bit by bit. The CPU was also considerably faster than the UNIVAC's,
which could almost perform 2,200 multiplications per second, compared to 455 for the UNIVAC. It
could also execute almost 17,000 additions and subtractions, as well as most other instructions, per
second. This was remarkable for that time. IBM's eight million byte tape drive was also very good and
could stop and start much faster than the UNIVAC's and was capable of reading or writing 12,500
digits per second. However, unlike the UNIVAC with its elegant buffers, the processor had to handle
all I/O operations, which could severely impact performance on heavily I/O-based applications.

In 1956, IBM introduced a technology known as RAMAC, which was the first magnetic disk system for
computers. It allowed data to be quickly read from anywhere on the disk and could be attached not
just to the 701, but to IBM's other computers, including the 650, which we will look at next. As most
of you no doubt realize, this technology is the progenitor to the hard disks that are very much with us
today.

IBM produced 19 701 units, which were fewer than the number of UNIVACs made, but still enough to
prevent Remington Rand from dominating the field. The cost was a serious inhibitor to more
widespread use, setting the user back over $16,000 a month. Also, as mentioned, the 701 was only
part of IBM's response. The 650 was the other.

650 Magnetic Drum Data Processing Machine

While IBM's more direct response to the UNIVAC was the 701 (and later the 702), it also was working
on a lower-end machine known as the 650 Magnetic Drum Data Processing Machine (so named
because it employed a rotating drum that spun at 12,500 revolutions per minute and could store
2,500 10-digit numbers). It was positioned somewhere between the big mainframes like the 701 and
UNIVAC and the punched-card machines used at the time, the latter of which were still dominating
the market.

While the 701 generated most of the excitement, the 650 earned most of the money and did much
more to establish IBM as a player in the electronic computer industry. Costing $3,250 per month
(IBM didn't sell computers at that time, but only leased them), it was much less expensive than the
701 and UNIVAC, but was still considerably more expensive than the punched-card machines so
prevalent at that time. In total, over 2,000 of these machines were built and leased. While this
greatly exceeded the 701's and UNIVAC's deployment, it was paltry compared to the number of
punched-card accounting machines that IBM sold during the same period. Although very reliable by
computer standards, it still used vacuum tubes and thus was inherently less reliable than IBM's
electromechanical accounting machines. On top of this, it was considerably more expensive. Finally,
the peripherals for the machine were mediocre at best. So, right up to the end of the 1950s, IBM's
dominant machine was the punched-card Accounting Machine 407.

To be able to usurp the IBM Accounting Machine 407, a whirlwind of changes were needed. The
computer would need better peripherals and had to become more reliable and faster, while costing
less. Our next machine is not the computer that finally banished the 407 into obsolescence--at least
not directly--but many of the technologies that were developed for it did.

Whirlwind project

The Whirlwind project was ironic. It went way over budget, took much longer than intended, and was
never used in its intended role, but was arguably one of the most important technological
achievements in the computer field.

In 1943, when the US Air Force gave MIT's Jay Forrester the Whirlwind project, he was told to create
a simulator to train aircraft pilots rather than have them learn by actually being in a plane. This
intended use was very significant in that it required what we now call a "real-time system," as the
simulator had to react quickly enough to simulate reality. While other engineers were developing
machines that could process 1,000 to 10,000 instructions per second, Forrester had to create a
machine capable of a minimum of 100,000 instructions per second. On top of this, because it was a
real-time system, reliability had to be significantly higher than other systems of that time.

The project dragged on for many years, long after World War II had ended. By that time, the idea of
using it for a flight simulator disappeared, and for a while, they weren't quite sure what this machine
was being developed to do. That is, until the Soviets detonated their first nuclear bomb and the U.S.
government decided to upgrade its antiquated and ineffective existing air defense system. One part
of this was to develop computer-based command-and-control centers. The Whirlwind had a new life,
and with so much at stake, funding would never be a problem.

Memory, however, was a problem. The mercury-delay line that others were using was far too slow,
so Forrester decided to try a promising technology: electrostatic storage tubes. One problem he
faced was that they did not yet exist, so a lot of development work had to be put into this before he
would have a working product. But once it was completed, electrostatic storage tubes were deemed
unreliable and their storage capacity was very disappointing. Consequently, Forrester, who was
always looking for better technology, started work on what would later be called "core memory." He
passed his work on to a graduate student also working on the project, called Bill Papian, who had a
prototype ready by 1951 and a working product that replaced the electrostatic memory in 1953. It
was very fast, very reliable, and did not even require electrical refreshes to hold its values. We'll talk
more about core memory later, but suffice it to say, it was an extremely important breakthrough that
quickly became the standard for well over a decade.

Core memory was the final piece of the puzzle. The computer was effectively complete in 1953 and
first deployed in Cape Cod. Although it failed to reach the intended performance level, it was still
capable of 75,000 instructions per second. This far exceeded anything available back then. The
technology was transferred by MIT to IBM, where the production version was re-christened the IBM
AN/FSQ-7 and saw production in 1956. These monsters had over 50,000 vacuum tubes, and weighed
over 250 tons, which made them the largest computers ever built. It also consumed over a megawatt
of power, not including the necessary air conditioning.

SAGE (Semi-Automatic Ground Environment), the bomber-tracking application for which the
Whirlwind was now intended, became fully operational by 1963. Ironically, this was past the time
when the Whirlwind was truly useful, since it was designed to track bombers, and by then, ICBMs
had made their appearance a few years earlier. Nonetheless, while the actual uses for the Whirlwind
were dubious, the technologies either created or accelerated by it were extremely important. These
include not only the aforementioned core memory, but the development of printed circuits, mass-
storage devices, computer graphics systems (for plotting the aircraft), CRTS, and even the light pen.
Connecting these computers together gave the United States a big advantage in networking
expertise and digital communications technologies. It even had a feature we lack in modern
computers: a built-in cigarette lighter and ashtray. Clearly, it was worth the $8 billion that it cost to
fully install SAGE, even though SAGE never helped intercept a single bomber.
IBM 704

Announced in 1954, the IBM 704 was the first large-scale commercially-available computer system to
employ fully automatic floating-point arithmetic commands and the first to use the magnetic core
memory developed for the Whirlwind.

Core memory consisted of tiny doughnut-shaped metal pieces that were roughly the size of a pin-
head with wires running through them, which could be magnetized in either direction, giving a logical
value of zero or one. Core memory had a lot of important advantages, not the least of which was that
it did not need power to maintain its contents (an advantage it holds over modern memory). It also
allowed truly random access, where any memory location was accessed as quickly as any other
(except when interleaving was used, of course). This was not the case with prior forms of memory. It
was considerably faster than other memory technologies used, having an access time of 12
microseconds. Perhaps most importantly, however, was the much greater reliability that the IBM 704
offered.

For longer-term storage, the 704 used a magnetic drum storage unit. For additional storage, tapes
capable of holding five million characters each were used.

The 704 was quite fast, being able to perform 4,000 integer multiplications or divides per second.
However, as mentioned, it was also capable of doing floating point arithmetic natively and could
perform almost 12,000 floating-point additions or subtractions per second. More than this, the 704
added index registers, which not only dramatically sped up branches, but also reduced program
development time (since this was handled in hardware now).

The 704 pioneered two major technologies we have today: the index registers and floating-point
arithmetic. Magnetic core memory was also extremely useful, offering far greater speed and
reliability, but it was a transient technology.
IBM 1401 Data Processing System

While the 650 put IBM on the map, its replacement, the IBM 1401 Data Processing System, was the
computer that made punched-card machines obsolete. It is considered to be the "Model T" of the
computer industry, since its combination of functionality and relative low cost allowed many
businesses to start using computer technology. Its popularity helped IBM become the dominant
computer company of the era. Ironically, its success was not entirely good for IBM, and this machine
was surely not its biggest or most profitable. In fact, in some cases, it was just used as an adjunct to
its bigger brothers to transfer data on punched cards to tape and to print.

However, for the first time, the cost, reliability, and functionality made computers very attractive to
many customers. Compared to the 650 it replaced, the 1401 was roughly seven times faster, more
reliable, and better-supported. Perhaps most importantly, it had better I/O. IBM had the perspicacity
to develop a machine that actually did what its customers really needed and at a cost that made
sense to them. In some ways it was too good, as it was problematic when customer after customer
returned their rented accounting machines to IBM for these new wonders. This caused a lot of short-
term problems for IBM, but it was farsighted enough to bear the pain. And history has recorded how
well the new computing business model later paid off.

So, what made this computer resonate so well with customers? Core memory, transistors, software,
and a printer were all tremendous advances, any one of which would have made the computer a big
advance over the 650. Put them all together, and the machine outsold IBM's expectations by over 12
to one.

We have already been introduced to core memory in the description of the 704. Its virtues of speed,
reliability, high capacity, and lower power use made this a very important technology. The 704 was a
very expensive machine, however, and was not affordable for many businesses. The 1401 moved this
technology to a much larger market.

By now we all know what transistors are, but the improvement over existing technologies at the time
included reliability, power use, heat dissipation, and cost.
The holistic approach IBM took also included software. For the first time, free of charge, IBM
included software packages for most of the needs of its customers rather than make its customers
develop their own. This was critically important, since it saved considerable time and money on in-
house development and allowed businesses that did not have programmers to finally derive the
benefits of computers.

And strangely, one of the biggest advantages of the 1401 was its printer. The 1403 "chain" printer
had a rated speed of 600 lines per minute, which was four times the speed of the 407 accounting
machine. It was also very reliable. In fact, for many, the 1403 was a salient characteristic of the
system and often sold the computer that went with it.

All of these contributed to a machine that transformed the computer industry. It was extremely
successful not only thanks to its excellent technical characteristics, but also due to its low starting
price of only $2,500 per month. In fact, after the release of the 1401, the computer industry became
known as IBM and the seven dwarfs. The 1401 was that good.

IBM 7090

Announced in late 1958, IBM replaced the aging 709 (the last of the 700 line we saw a few pages ago)
with the 7090. In fact, in many ways, the 7090 was essentially a 709 made with 50,000 transistors
rather than vacuum tubes. However, there were many benefits because of it, including both speed
and reliability.

The 7090 and its later upgraded form, the 7094, were classic, powerful, and very large mainframe
computers--and they were very expensive. The 7090 cost around $63,500 a month to rent in a typical
configuration, and that did not include electricity.

Despite its cost, the speed of this machine could still make it very appealing. It was roughly five to six
times faster than the 709 it had replaced, and was capable of 229,000 additions or subtractions,
39,500 multiplications, or 32,700 divisions in one second. The 7094, announced in 1962, was capable
of 250,000 additions or subtractions, 100,000 multiplications, and 62,500 divisions per second. It
could use 32,768 36-bit words of core storage.

However, outside of implementing the newest technologies (core memory, RAMAC, transistors, etc.)
and the consequent improvement in speed, power use, and reliability, it was not functionally very
different from its predecessor. Jobs were executed by collecting them on reels of tape and were run
in batches, and the results were given back to the programmer when done.

While the performance, capacity, and reliability of these machines were impressive (mainly due to
the move to transistors and other new technologies), it would be a stretch to call this a
groundbreaking machine that pushed the boundaries of computing.

IBM 7030 Stretch

IBM's 7030, or Stretch, is something of a paradox. It introduced new technologies, many of which are
still in use today, and was the fastest computer in the world for three years after it was introduced.
However, it was considered a failure to such an extent that IBM reduced its price before
discontinuing it very quickly with a loss of around $20 million. How could this be?

In 1956, Los Alamos Scientific Laboratory awarded IBM a contract to build a supercomputer. The goal
of this computer was to offer a hundred-fold improvement over the IBM 704's performance. This was
a very ambitious goal indeed. And in fact, the 7030 outperformed the 704 by a factor of up to 38
when it was released in 1961. Due to this "disappointing" performance, IBM was forced to lower the
price of the machine from $13.7 million to a paltry $7.78 million, which meant IBM lost money on
every machine. This being the case, after meeting its contractual obligations, IBM withdrew the 7030
from the market, which was a major disappointment and failure. Or was it?

Not only was the performance of this machine far ahead of its time (0.5 MIPS), but the technologies
it introduced read like a who's who list of modern computing. Does instruction prefetching sound
familiar? Operand prefetching? How about parallel arithmetic processing? There was also a 7619 unit
that channeled data from the core memory to external units, like magnetic tapes, console printers,
card punches, and card readers. This is an expensive version of the DMA functionality we use today,
although mainframe channels were actual processors themselves and far more capable than DMA. It
also added interrupts, memory protection, memory interleaving, memory write buffers, result
forwarding, and even speculative execution. The computer even offered a limited form of out-of-
order execution called instruction pre-execution. You probably already surmised that the processor
was pipelined.

The applications are almost equally impressive. The 7030 was used for nuclear bomb development,
meteorology, national security, and the development of the Apollo missions. This became feasible
only with the Stretch due to the enormous amount of memory (256,000 64-bit words) and incredible
processing speed. In fact, it could perform over 650,000 floating point adds in a second and over
350,000 multiplications. Up to six instructions could be in flight within the indexing unit and up to
five instructions could be in flight within the look-ahead and parallel arithmetic unit. Thus, up to 11
instructions could be in some stage of execution within Stretch at any one time. Even compared to
the excellent 7090 released at that time, the 7030 was anywhere from .8 to 10 times the speed,
depending upon the instruction stream.

So, while the 7030 had a short, but very useful life, its technology is still with us today, and had a very
important impact on the legendary System/360 family. This could easily be the most important
computer in the history of mainframes. Yet, it was a failure. Who says life makes sense?

B 5000

By now, at least a few of you would probably like to remind me that IBM was not the only company
to make a computer since the UNIVAC. Your point is well taken, so let us take a look at a machine
from Burroughs, the B 5000. This is a really interesting machine, especially considering that it was
announced in 1961. In fact, to this day, UNISYS still supports the software.
The B 5000 was developed for high-level languages, namely COBOL and ALGOL. By this I mean the
machine language was created mainly for easy translation from higher-level languages. It contained a
hardware stack, segmentation, and many descriptors for data access.

The descriptors had many uses, which included allowing bound checking in hardware, distinguishing
between character strings and arrays of words, easing dynamic array allocation, indicating the size of
characters, and even whether something was in core memory or not. Why would we need that? In
two words, virtual memory. The B 5000 was the first commercial computer with this technology. It
also supported multiprocessing and multiprogramming, even with ALGOL and COBOL. In fact, the
Master Control Program (MCP), as the operating system was called, handled memory and
input/output unit assignments, segmentation of programs, subroutine linkages, and scheduling,
which freed the programmer from all these tedious and time-consuming tasks.

Another aspect Burroughs was proud of was the modular nature of the computer. It could be
increased or decreased, without costly "reprogramming" of the entire machine.

The B 5000 was not the commercial success IBM mainframes were. In fact, it was sometimes referred
to as the machine everyone loves but no one buys. However, its design was nothing less than elegant
and efficient. It focused on solving problems within the context of how humans interacted with and
related to computers, as opposed to speed for the sake of speed. Perhaps more importantly, some of
the technologies it introduced, like virtual memory and multiprocessing, are necessities in present
computers, some of which still support this magnificent architecture 48 years after it was introduced.

UNIVAC 1107 Thin Film Memory Computer

While IBM deserves much praise for the innovations first expressed in the Stretch, Remington Rand,
the number-two computer company in the world at the time, was busy conjuring up some of its own
magic with the UNIVAC 1107 Thin Film Memory Computer.

As you no doubt guessed from its name, the main technological accomplishment was the use of thin-
film memory. It had an access time of 300 nanoseconds and a complete cycle time of 600
nanoseconds, making it extremely fast for 1962, when the machine was released. However, this did
not replace core memory, which had a cycle time of roughly two microseconds, but rather was used
to provide multiple accumulators, multiple index registers, and multiple input-out control registers.
This allowed for greater parallelism, with increased speed as the end result. In total, there were 128,
36-bit words of thin-film memory (alternatively called "control memory" because of its function). By
today's standards, this would not be considered memory at all, but part of the processor, much like
registers. Although, in both cases, they are really very fast internal memory. One difference is that
the control-memory registers were actually accessed by using a memory address as opposed to
register name, but only when using special instruction designators or when referred to by an
execution address. If not accessed this way, the addresses were mapped to core memory. So, rather
strangely, the memory map for the first 128 bytes was different depending upon the context.

While the thin-film memory was certainly the biggest splash in the pool, there were other interesting
features of this enduring line worth mentioning. For one, it had usable word sizes of 36-bits.
Characters were expressed in six bits. Memory banks were interleaved so that if reads were done
from different banks in successive reads, the access time was only 1.8 microseconds. If the word was
in the same bank, it was four microseconds. As mentioned, this averaged out to two microseconds
since it was more likely to access a different bank. The 1107 also contained 16 input and 16 output
channels, all of which could be used concurrently to support a maximum of 250,000 words per
second.

The main storage of the machine consisted of one to eight magnetic drums, each capable of storing
from 262,144 to 6,291,456 words, giving this machine an enormous capacity of over 94 million 36-bit
words (or over half a billion characters of storage).

Although the UNIVAC 1107 was without question a fine machine in its own right, its more important
significance was the family of computers it started. While never approaching the sales of a series of
computers that IBM would soon introduce, UNIVAC's 1100-series made the company the second-
largest in the world for many years and is still supported by UNISYS today. But enough of the horse
that placed. Let's head back to Big Blue.
IBM System/360

When most people think of a mainframe, they think of the System/360 family of computers from
IBM, arguably the most important computer architecture created. In many ways, it is similar to 8086
processors in that it created the standard for an industry and spawned a long line of descendants
that are still alive and thriving to this day. One big difference is that IBM actually intended the
System/360 to be important, unlike the 8086, which gained an importance its creator could never
have foreseen. In fact, as many of you know, Intel even tried to kill off this instruction set with the
Itanium.

But let's get back to the matter at hand. Prior to the System/360, IBM had something of a mess on its
hands, having created many systems that were incompatible with each other. Not only did this make
it more difficult for its customers to upgrade, but it also was a logistical nightmare for IBM to support
all these different operating systems on different hardware. So, IBM decided to create what we
almost take for granted today: a compatible line of computers, with differing speeds and capacities,
but all capable of running the same software. In fact, in April 1964, IBM announced six computers in
the line, with performance varying by a factor of 50 between the highest- and the lowest-end
machines. This actually doubled the design goal of 25, which in itself posed many problems for IBM.
Scalability of this magnitude was said to be impossible even by the infamous and brilliant Gene
Amdahl. It was never a simple matter of just making something 25 times "bigger" than the smallest
part and it really had to be completely re-implemented.

Today, it is common to disable parts of a processor, or underclock it to somehow compromise the


performance. But back then, it was not economically feasible to create a high-end processor and
artificially lower its performance for marketing purposes. So, IBM decided on the idea of adding
"microprogramming" to the System/360, so that all members of the family used the same instruction
set (except for the lowest-end, Model 20, which could execute a subset). These instructions were
then broken down into a series of "micro-operations," which were specific to that system
implementation. By doing this, the underlying processor could be very different, and this allowed
scalability of the magnitude IBM wanted, and as mentioned, even exceeded it by two times.

This probably sounds familiar to you, since something similar has been implemented on x86
processors since the Pentium Pro (or really, NexGen Nx586). As mentioned, however, IBM planned
this. The x86 designers did this because the instruction set was so poor, it could not be directly
executed effectively. There was one very important advantage of this micro-programming that could
not be easily implemented on a microprocessor. By creating new micro-programming modules, the
System/360 could be made compatible with the very popular 1401, for the lower end machines, and
even the 7070 and 7090 for the higher end System/360s. Since this was done in hardware, it was
much faster than any software emulation, and in fact generally ran older software much faster on
the System/360 than on the native machine, due to the machine being more advanced.

Some of these advances are still with us today. For one, the System/360 standardized the byte at
eight bits, and used a word length of 32-bits, both of which helped simplify the design since they
were powers of two. All but the lowest-end Model 20 had 16 general-purpose registers (the same as
x86-64), whereas most previous computers had an accumulator, possibly an index register, and
perhaps other special-function registers. The System/360 could also address an enormous amount of
memory of 16 MB, although at that time this amount of memory was not available. The highest-end
processor could run at a very respectable 5 MHz (recall that is the speed the 8086 was introduced at
14 years later), while the low-end processors ran at 1 MHz. Models introduced later in 1966 also had
pipelined processors.

While the System/360 did break a lot of new ground, in other ways it failed to implement important
technologies. The most glaring deficiency was that there was no dynamic address translation (except
in the later model 67). This not only made virtual memory impossible, but it made the machine
poorly suited for proper time-sharing, which was now becoming a possibility with the increasing
performance and resources of computers. Also, IBM eschewed the integrated circuit, and instead
used "solid-logic technology," which could roughly be considered somewhere between the
integrated circuit and simple transistor technology. Conversely, on the software side of things, IBM
was perhaps a bit too ambitious with OS/360, one of the operating systems designed for the
System/360. It was late, used a lot of memory, was very buggy, lacked some promised features, and
more than that, continued to be buggy long after it was released. It was a well known, high visibility,
and dramatic failure, although IBM eventually did get it right and it spawned very important
descendants.

Despite these issues, the System/360 was incredibly well-received and over 1,100 units were ordered
in the first month, far exceeding even IBM's goals and capacity. Not only was it initially successful,
but it proved enduring and spawned a large clone market. Clones were even made in what was then
the Soviet Union. It was designed to be a very flexible and adaptable line, and was used extensively in
all types of endeavors, perhaps most famously the Apollo program.

More importantly, the System/360 started a line that has been the backbone of computing for
almost 50 years, and represents one of the most commercially important and enduring designs in the
history of computing.
CDC 6600

While IBM was busy focusing on a wide swath of compatible systems with its System/360 line, a
company called CDC had a different design goal for its next computer: fast and really fast.

Unshackled by any other considerations, such as compatibility or cost, Seymour Cray was free to use
his legendary talents to focus on raw speed. He succeeded, as the roughly $7 million machine was
the fastest computer from 1964 to 1969 by employing a unique design that relied on what would
now be called an asymmetric multiprocessor design.

The main CPU ran at a blazing 10 MHz, but was very limited in the instructions it could perform, since
it was in a very real sense a RISC processor long before the term was coined. It was capable of only
very simple ALU functions, but was complemented by 10 logical peripheral processors that could do
what the CPU could not, and kept it fed with data, while unfettering it from retiring data. The ability
to make the processor more specialized and the parallelism by using the 10 "barrel" processors were
key components in the exceptional performance of this machine. With an enormous amount of
memory (128 K words), this 60-bit computer could trade off larger executable size for the additional
performance that a simple instruction set could offer.

Although the CDC 6600 was a profitable machine, it was never a threat to the System/360’s market
share–nor was it ever intended to be. Like our next machine, sometimes it was better to compete
where IBM was not, rather than where it had targeted. The 6600 targeted a market higher than even
the System/360 Model 75 could reach, while the next computer we look at targeted a market below
where the System/360 Model 20 could.
DEC PDP-8

While IBM was busy releasing its magnificent System/360 line, Digital Equipment Corp. (DEC) was
about to release a computer that would have a major impact on the future of computing as well, the
PDP-8. Although the different computers in System/360 had an enormous range of performance
characteristics and capacities, they were still mainframes, and even the lowest-end models were still
too expensive for many businesses. This opportunity was not lost on DEC's founder, Ken Olsen.

Although DEC had released computers as early as 1960, these models were only modestly successful
and had little impact on the industry. However, the steady advance of technology, mainly in the form
of integrated circuits, allowed DEC to sell a much smaller and much less expensive computer than its
predecessors. Integrated circuits also allowed for much lower power use, and consequent to that,
much less heat dissipation. This freed computers from purpose-built air-conditioned rooms. When
released in 1965, the PDP-8 sold for an astonishingly low price of $18,000, which, with the
aforementioned housing requirements, put computers within the reach of many companies that
previously found them to be prohibitively expensive.

One unique feature of the PDP-1, DEC's first product, was the use of true direct memory access
(DMA), which was much cheaper and less complicated than the channels mainframes used, and
without much negative impact on the processor performance. In fact, a single mainframe channel
cost more than the entire PDP-1. DMA was used on every successive computer DEC made, including
the PDP-8. However, not all the cost-cutting comprises made for the PDP-8 were so benign. The 12-
bit word length dramatically limited the amount of directly addressable memory, while only 7-bits of
the word comprised the address field, allowing only 128 bytes to be directly addressed. There were
ways around this drawback, one of which was to use indirect addressing, where the 7-bits pointed to
a memory location that contained the actual address that you wanted to access, which was slower,
but allowed a full 12-bit access. The other way was to divide memory into segments of 128 bytes,
and change segments when necessary (and people thought the 64 K segments of 16-bit x86
processors were bad). Neither solution was desirable, and they severely limited the usefulness of the
PDP-8 with high-level languages. The PDP-8 was also no speed demon, and was capable of only
35,000 additions per second.

Despite these compromises, the PDP-8 was remarkably successful, selling over 50,000 machines
before it was discontinued. The low purchase price, low continuing costs, and ease of housing it all
were more compelling than its deficits were damning. In fact, this modest machine sparked a whole
new type of computer, called the mini-computer, which became very successful for over two
decades and made DEC the second-largest computer company in the world. Perhaps sadly, the mini-
computer did not survive the march of the micro-computer, and is now an extinct species, and thus is
more applicably called a dinosaur than the normal recipient of that unflattering term, the mainframe.
The mainframe still sits on top of the food chain, capable of things far beyond desktop computers.

IBM System/370

Although the System/360 was very successful, and in some ways, revolutionary and innovative, it
also eschewed leading-edge technologies that left opportunities for other companies to exploit. To
its credit, however, it was still selling well even six years after its announcement, and it laid a
foundation for generations that followed it, of which the System/370 was first.

The initial launch of the System/370 in 1970 consisted of just two machines, the charismatically
named 155 (running at almost 8.70 MHz) and 165 (running at 12.5 MHz). Naturally, both machines
were compatible with programs written for the System/360 and could even use the same
peripherals. Additionally, the performance was greatly improved, with the System/370 165 offering
close to five times the performance of the System/360 65, the fastest machine available from that
line when it was released in November 1965.

There were also several new technologies for the System/370, compared to the System/360. IBM
finally moved to the integrated circuit, a change many people thought long overdue. Most models in
the line had transistor memory rather than core memory. The System/370 also finally supported
dynamic address translation (on all but the initial two models), which was an important technology
for time sharing and virtual memory. There was also a very high-speed memory cache (80 ns for the
165), which IBM called a buffer. This was used by the processor to mitigate the relatively slow (two
microsecond or 2,000 ns) main memory access time. Another important consideration was that the
System/370 was built from the beginning with dual processors and multiprogramming in mind.

So, while the System/370 was not a spectacular announcement, it did plug up some glaring holes in
the System/360, improved speed considerably, expanded the instruction set, and maintained a high
degree of compatibility. It was a solid step forward and maintained IBM's dominance in the
mainframe world.

IBM 3033 – The Big One

While the System/370 line dominated mainframe computing for many years by introducing new
models with new features and performance characteristics, IBM announced in March 1977 the
successor to this very successful family of computers, the 3033, or "The Big One."

Although IBM mainly stressed the additional speed (1.6 to 1.8 times the speed of the System/370
168-3) and its much smaller size, ironically for "The Big One," this machine's technical merits would
not look out of place on a modern computer. Running at 17.24 MHz, the processor sported an eight-
stage pipeline, branch prediction, and even speculative execution. It contained several logical units
and 12 channels. The units of 3033 processor were the instruction preprocessing function (IPPF),
execution function (E-function), processor storage control function (PSCF), maintenance and retry
function, and the well-known channels indigenous to all IBM mainframes. The IPPF fetched
instructions and prepared them for the execution by the E-function, determined priority, and made
fetch requests for the operand. It not only used branch prediction, but it could buffer three
instruction streams at once, so in the event it "guessed" wrong, it was likely to have the other
instruction sequence ready and preprocessed for the E-Function. The E-Function, not surprisingly,
was the execution engine of the processor, boasting a very large 64 K cache (with a 64 byte line size)
for the first time, to speed up memory accesses. Memory itself was eight-way interleaved, allowing
refreshes to occur in the seven banks it was not accessing when it did a read, which sped up read
time if the next access was in one of those seven banks (DRAM requires a refresh after a read to be
accessed again).

The processor storage control function handled all requests for storing or fetching data from
processor storage, and translated virtual address to absolute storage addresses using a technology
we previously mentioned as dynamic address translation. Like modern processors, it used translation
lookaside buffers to speed this up. Essentially, this is a cache of addresses already translated from
virtual to absolute, so if the processor can find them there, conversion is unnecessary. On the 3033, if
an address could be found, it would take one clock cycle to resolve it, or if not, it could take
anywhere from 10 to 40, which is quite a difference.

The maintenance and retry function provided the data path between the operator console and the
3033 processor for manual and service operations.

So, while ostensibly the 3033 was just a very fast successor to the powerful System/370 168-3, when
we look closer we see it has almost all the technologies of a modern processor and even some that
are lacking in a portion of today's modern CPUs. However, it was still a scalar design, and despite its
impressive characteristics, was replaced relatively quickly by the 3081. While I know you are just
brimming with curiosity about the 3081 (who could blame you?), and I can assure we will get very
familiar with it, let us first take a short interlude by looking at what DEC, the second largest computer
company of the world at that time, had to offer.

DEC VAX-11/780

While most of our readers know that the x86 instruction set originated in 1978 with the 8086,
perhaps a more important development happened a year earlier when Digital released the infamous
VAX-11/780. But how could anything possibly be more important than the x86 instruction set?
When most people think of DEC, they remember a large mini-computer maker that failed and was
bought by Compaq when the micro-computer usurped DEC’s key market. But what happened in 1977
that was so important? DEC’s VAX and its very comely wife, VMS, the latter of which still has much
relevance today.

The VAX-11/780 was ostensibly released to address the shortcomings of the highly successful and
very well liked PDP-11. DEC downplayed many of the changes and instead focused on the ability to
finally break the 16-bit (64 K) addressable memory limitation of the PDP-11 with the VAX-11/780’s
32-bit address. However, there was much more to it than that.

The VAX is considered by most to be the finest of all CISC instruction sets, rivaled only by those
influenced by it. It was a highly orthogonal instruction set, with 243 instructions on several basic data
types and with 16 different addressing modes. This elegant architecture was a strong influence in the
Motorola 68000 family, which became the platform for Apple Lisa and MacIntosh until it was
replaced by the PowerPC in the 1990s. Incidentally, the performance of the VAX-11/780 was adopted
as a standard measurement when “VAX MIPS,” or later just “one MIPS,” became a measure of
computer performance.

However, perhaps the most important contribution of the VAX was VMS. Windows NT was
developed by none other than Dave Cutler, the designer for VMS. He was one of many VMS
developers who went over to Microsoft to work on the development of Windows NT. Despite the
controversy surrounding Windows, Windows NT is still the dominant operating system in use today,
and will remain so for the foreseeable future, particularly since Windows 7 is being far better
received than Vista. This is not to denigrate the VMS operating system as insignificant other than its
impact on Windows NT as it was a much respected design that was especially user friendly.

Many showered accolades on this easy-to-use operating system, which was very much ahead of its
time. In fact, although the VAX is dead, OpenVMS is clearly not, and is currently running on Intel's
Itanium processors and HP's archaic Alpha processors, with a new release due out later this year.
Thus, since its release 32 years ago, the operating system is still going strong.

As delightful as the VAX and VMS were, and the latter still is, they never challenged the Big Blue
beast in any real economic way and instead probably helped IBM in its fight with the government,
which was not too fond of what they considered IBM's monopoly. In 1981, President Ronald Reagan
dropped the anti-monopoly suit against IBM, and that same year, Big Blue released the 3081, which
incidentally, was the first mainframe with which I had experience. And what an experience it was.
IBM 3081

I still remember it like it was yesterday, that spring day in 1988 when I got a call from IBM telling me
to come in to interview for a computer operator position. I was ecstatic when what was considered
to be the greatest company in the world, the only one I wished to work for, was going to be my
employer. It was a different time then, when IBM represented everything good about American
business, and represented the pinnacle of success.

During my first day of work, I was introduced to a machine that was released in 1981, the 3081. I had
some experience with an old Univac 1100/63 in college, but until then, I was more familiar with
micro-computers, which were best represented by the still fairly-new 80386 and 68030. My first
impression of the mainframes was unfavorable. Even by the microcomputers standards of the day,
the interface was primitive and far less intuitive than that of PCs. I was not impressed.

The scale of things was shocking. The air-conditioned, raised-floor room was hundreds of feet wide
and long, with almost a dozen 3081s and an enormous number of DASDs. We had six printers, which
were enormous and almost the same size as the mainframe. There were three sets of consoles, one
for the print area and one for the tape area, while the computers were monitored closely in the main
console area.

We had three interfaces to MVS, as the operating system was called, which stood for multiple virtual
storages, but we derisively referred to it as “man versus system.” There were the system consoles,
which were essentially only available in operations: time share option (TSO) and operations planning
and control (OPC). TSO was what many people used to do their work, while OPC was mainly for
scheduling batch jobs that were going to run on the system. Many programmers preferred to work
on VM, which was another operating system IBM offered for the 3081, before transferring their work
to the MVS machine.

Our site had responsibility for the customer master record (CMR), which was used by many
applications and sometimes directly by people. This ran on an IBM internal application called AAS,
which was never sold. There were also some applications on CICS, which was the product IBM sold
and is still widely used today by many companies. Many of these applications were critical, and any
down time was extremely expensive during normal working hours. In fact, we were told that it cost
IBM a million dollars every minute the system was down, which I never believed and still do not.
Anyway, after these online applications would go down (usually at around 8:00 PM), the batch
processing would begin. Jobs were scheduled in OPC and were submitted in kind of a "wrapper"
called job control language (JCL). JCL could run several executables in one job and it specified the
resources and order for the executables. You did not tell it explicitly in the executable which DASD to
access, as the JCL defined where the input and output were. As mentioned, jobs were tracked in OPC,
and were released based on time and/or dependencies. They were sent to the job entry system (JES)
and from there were executed.

As mentioned, interfaces were poor compared to PCs of that time, but the reliability of the operating
system was far greater than the Windows NT derivatives that we use today. It's something I learned
to appreciate over time, and I still marvel at it. The 3081 was a "dyadic" design, meaning it had two
processors that even shared the same cache. They could not be split into two computers, as they
were inseparable. However, the sophistication of this operating system was such that even if one of
the processors died, the system would stay up and continue to execute. The application that was
using the failed processor would crash, but it would do so fairly gracefully as the operating system
would recognize the failure and send it into the proper place for crashed applications (we'd track
them in OPC, and either fix them ourselves or get their support team to take care of the problem).
This is not to imply the 3081 CPUs were always crashing, as it was rare when they did so.

DASDs did fail fairly often, although most of the time failures happened when we had to power them
down and then back up periodically. This was expected behavior and we always had CEs there for
scheduled downtimes to repair those that were especially problematic. Normally, only one or two
would fail out of the few hundred on the floor during each power down.

Each 3081 processor ran at a blistering clock speed of almost 38.5 MHz. By IBM's somewhat
optimistic measurements, the base 3081 (model D) was up to 21 times faster than the 3033UP, while
the higher-end model K was almost 30 times faster. Some of this, of course, came from the extra
processor, although sharing the cache did create some overhead. The uniprocessor 3083, for
example, actually ran 15% faster than the 3081 when the workload could not engage the 3081’s
second processor. The 3084 was another extension of this line, and actually had a pair of dyadic
processors. Unlike the 3081, it could be divided into two separate machines. Another improvement
of the 3081 was that it could address more than 16 MB and used 31-bit addressing rather than the
3033’s 24-bit addressing. All in all, considering it was released only four years later than the 3033, it
was a substantially improved machine. The hardware was good and the stability of the software was
just incredible.

I hope the personal tone of this entry does not bore or irritate the reader, but I wanted to give a view
of what working with these machines was really like. In many ways they were amazing machines.
Still, as amazing as the 3081, 3083, and 3084 were, we were envious of sites that had the 3090, and
we had heard the stories of how incredible the performance was.
IBM 3090

Although not one of the more well-known mainframes, when the IBM 3090 was announced in 1985
it offered a solid advancement on the System/370 architecture that not only continued the
improvements in speed, but also increased the number of processors while giving them vector
processing options.

Initially only available as Model 200 and Model 400 (the first number denoted the number of
processors), the line was expanded dramatically in its short four years of existence. A uniprocessor
version (1xx series) and a 600 series of processors were added, as well as an enhanced version of
each model (denoted with an "E" after the model; for example, 600E). Even the original models were
formidable, running at over 54 MHz, and executing instructions almost twice as fast as the 3081s
they replaced.

The next year the 3090 was expanded to include the vector processing feature, which added 171 new
instructions and sped up computation-intensive programs by a factor of 1.5 to three times. The "E"
version of the 3090 ran at a brisk 69 MHz, and was capable of roughly 25 MIPs per processor. By
comparison, the x86 processor at that time, the 80386, ran at 20 MHz, was capable of roughly 4
MIPs, was uniprocessor only, and had no vector instructions.

The 3090 was replaced after four short years by the ES/9000 line. With local area networks (LANs)
gaining popularity and powerful new processors like the 80486 and the many RISC designs (including
IBM's own POWER), it was becoming increasingly clear that these technologies would soon render
the mainframe obsolete and extinct, as they were doing to the mini-computer. The handwriting was
on the wall for anyone that wanted to read it. Or was it?
IBM ES/9000

In late 1990, IBM replaced the illustrious 3090 with the ES/9000 line, which ushered in the era of
fiber optics with a technology IBM called ESCON or Enterprise Systems Connection. Naturally, this
was not the only new thing about these systems. In fact, Thomas J. Watson Jr. considered the
ES/9000 as the most important release in the company's history. Even more important than the
System/360, you ask? Well, Mr. Watson thought so.

So let us assume he was lucid and not simply issuing hyperbole. Certainly ESCON was an important
technology. It was a serial, fiber optic channel that could transmit data at 10 MB/s and up to nine
kilometers apart when it was released. Or maybe he was referring to the massive amounts of 9 GB of
memory it could use? Or perhaps it was the ability to use eight processors in one sysplex, which
allowed it to be treated as one logical unit? Then again, for the first time, one could create multiple
partitions and allocate processor resources to each logical partition, and run any of the new (and
compatible) Enterprise System Architecture/390 operating systems on them. Maybe that was it.

I doubt it was the performance, which was roughly 1.7 to 1.9 times the speed of the 3090/600J (the
previous fastest mainframe from IBM) in commercial applications, 2.0 to 2.7 in scalar, and 2.0 to 2.8
in vector performance. Although impressive, we've seen similar jumps before between generations.
None of this sounds so earth shattering that it should be the most important release in the most
important computer company's history does it? Yes, by today's standards 9 GB is a lot and 10 MB/s
over nine kilometers is faster than the Internet speeds to which most of us have access. Serial
transmission has been around for a few years now, and virtualization is becoming more common all
the time. Eight processors is a good amount, but dual-socket quad-core processors are not that rare
anymore. And we'll soon have processors with that many cores. So, I just don't know.

Maybe it had something to do with it being released in 1990. You know, when the 486 was hot and
George H.W. Bush was in the first part of his term. Before Yahoo! existed and about six years before
the first article appeared on Tom's Hardware about Softmenu BIOS features for Socket 7
motherboards. Taken in that time context, it was a monumental achievement, with so many
important advances in so many aspects of the systems. All in all, it's very hard to disagree with Mr.
Watson. Would you have expected otherwise from such a distinguished and accomplished person?

But, although this marvel has technology that hardly seems old even by today's standards, our story
is surely not done. But, what can top the ES/9000? It's hard to imagine, but then again, it's even
harder to imagine a computer line staying the same for 19 years. So, let's take a look at the latest and
greatest from Big Blue.

IBM eServer zSeries E64

While this article is supposed to be a history of big computers, this last entry is about a computer
that is still being sold today. But it was sold yesterday too, and that's history, right? So, let's and take
a look at IBM's biggest and baddest computer on the planet, the eServer zSeries E64.

In this day and age, it's hard to imagine a physically large computer, but IBM did manage to create a
30 square ft. beast that weighed in at over 5,000 pounds and consumed 27,500 watts of power. Still
not impressed? How about 1,520 GB of memory? Yes, that's a bit more than the 6 GB of most Core
i7-based enthusiast boxes. Well, actually, that's a bit more than the average hard disk of a PC with
the Nehalem. It can also have 1,024 ESCON, 336 FICON Express4, 336 FICON Express2, 120 FICON
Express, 96 OSA-Express3, and 48 OSA-Express2 channels. That's more I/O than the X58, wouldn't
you agree? Maybe several orders of magnitude more? This amazing machine can even host up to 16
virtual LANs in one machine.

Needless to say, these computers far exceed your normal server and, in fact, consolidate many
smaller x86-processor machines. Rather than fading into oblivion, mainframes are finding customers
that never used them before and wish to consolidate their x86 servers for space and energy savings.
The flexibility of these servers are truly impressive, as one can stock them with up to 16 integrated
facility for Linux (IFL) processors if Linux is the choice of operating systems or add up to 32 zAAP
processors to assist with integration of Web apps using Java or XML with backend databases. There
also can be up to 32 zIIP processors for data and transaction processing and network workloads,
which are often used for ERP, CRM, and XML applications and IPSec data encryption.

The main processor, the z10 processor unit chip, has a rich CISC design that can execute 894
instructions, 668 of which are hardwired. The processor, in a nod to the ENIAC, even supports
hardware decimal floating point operations, which can limit rounding errors and is much faster than
using binary and converting. On top of all this, it can still run software written for the System/360,
which is now 45 years old, and the amazingly solid MVS operating system, although it's now called
z/OS. One can have up to 64 of these 4.4 GHz quad-core monsters running, designed for 99.999%
uptime. It is no wonder these machines are selling well, as they offer incredible reliability, excellent
and flexible performance, capacity that is hard to imagine, and very advanced, yet rock-solid
software.

As suggested, virtualization capabilities on these machines are far beyond those of mere mortal
servers. Naturally, they can run multiple operating systems, including Linux, z/OS, z/VM, AIX, and
OpenSolaris, but more than that, they are capable of hot-swapping capacity non-disruptively and on
the fly when one partition needs more capacity. One can even bring extra processors online for short
periods of burst activity, and schedule them for certain times of the day, if there are known peaks.

These remarkable machines have capabilities that are so advanced that it might be difficult to get
your mind around it. Forgetting for a moment the remarkable performance and flexibility of these
machines, it is still dumbfounding how reliable they are. They feature, for example, something called
"lock-stepping," when each result-oriented instruction is run twice and the results are compared to
make sure they are the same. If they are not, the instruction is re-executed and the computer
attempts to locate where the error occurred. It can even switch in-flight instructions to other
processors, thus eliminating any negative effects of the error from the user’s perspective. More than
this, when used in a parallel sysplex (clustering up to 32 mainframes into one logical image), one can
update all the software and hardware on any mainframe without any downtime or disruption at all.

Only in the sense that these magnificent machines make the average desktop machine look small by
comparison are they dinosaurs. They are far more advanced, powerful, flexible, capacious, and useful
than the PCs we all know and love, not only in hardware, but in the incredible stability of the system
software. They still are very much part of the backbone of computing and show absolutely no signs of
death. On the contrary, their sales increase every year. In fact, how could it be any other way?

Mainframes arguably express man's highest achievement, not only in the amazing amount of thought
and intelligence invested in them, but also in the sublime role they have had, and still have, on
human life, and the endeavors of our kind. Perhaps rather than dinosaurs, they are like something
even older. Like diamonds, they are a combination of many ordinary parts, that when combined in a
certain way, through nature or extraordinary thought, become something far greater than the sum of
ordinary.

Source: http://www.tomshardware.com/picturestory/508-24-mainframe-computer-history.html

Anda mungkin juga menyukai