Free Essay

Pentium Flaw

Submitted By Ebereuguru
Words 872
Pages 4
Name: Ebere Uguru Student ID: 16389756
Course: NT1110T Computer Structure and Logic
Unit 5 Analysis

THE FLAW IN THE INTEL PROCESSOR CHIP
Since computer evolution, various computer companies have made their marks on the shores of revolutionizing computer as we know it. Hence, Intel, one of the world’s computer company giants, is not an exception to the zeal of making computers more efficient as the world evolves with time.
However in 1994, Intel was hit by a major setback related to a flaw in its P5 Pentium Floating Point Unit (FPU) rolled out that year. This defect was first discovered by Professor Thomas R. Nicely, a professor of Mathematics at Lynchburg College in Virginia. According to the chronology, Professor Nicely in his quest to perfecting codes to enumerate primes, twin primes, and prime quadruplets unraveled the incoherence in his calculation. This abnormally occurred only after he had added a collection of computers manufactured by Intel to his group of computers. At first, he was unable to eliminate this flaw due to other factors such as: motherboard, programming errors and chiplets.
After series of attempts to bring the attention of Intel to this error proved abortive, Professor Nicely then went public with it, and his claim was concurred by other internet users using Intel computers. Out of concern for the ripple effects of admitting to this error as it is, Intel flagrantly rebuffed the assertions. The reality slowly started to dawn on them after various media outlets picked up the story. This was first broadcast on November 7, 1994, in an article in Electronic Engineering Times, "Intel fixes a Pentium FPU glitch" by Alexander Wolfe; then CNN, LA Times and so many others.
A standard test was widely published to determine whether a user’s microprocessor was flawed. Using spreadsheet software, the user was able to take the number 4,195,835, multiply it by 3,145,727, and then divide that result by 3,145,727. As we all know from elementary math, when a number is multiplied and then divided by the same number, the result should be the original number. In this example, the result should be 4,195,835. However with the flawed FPU, the result of the calculation was 4,195,579.
When it became conspicuous that the bubble had burst, Intel rescinded its initial stance and admitted that although there was indeed a defect in the chip, however, the defect was insignificant and the vast majority of users would not even be cognizant of it. In its attempts to curtail the surge of outcry by Users of Intel computers, the company declared the chip would be supplanted with an unflawed version for free only if users could demonstrate that indeed their computer gives erroneous results. Vividly, this approach didn’t sit well with most Pentium owners since no one can predict whether the flaw might be significant in a future application. Following this imbroglio, IBM, a major Pentium user, canceled the sales of all IBM computers containing the flawed chip. As the public outcry and media publicity on this flaw became insurmountable for Intel, it agreed to replace the flawed microprocessor with an unflawed version for any customer who asked to have it replaced.
It is pertinent to disclose that prior to the news of the flaw surfaced in the press; Intel was cognizant of the problem and had already corrected it on subsequent versions, the P6 Pentium core which was first used in Pentium Pro. It did, however, continue to sell the flawed chip with the assertion the flawed chip would be exhausted before the errors would be identified. But with their clandestine plan hitting rock bottom, Intel ultimately had a write-off of \$475 million to solve this problem.
After passing through the ordeal, Intel’s approach to chip flaws has since turned a new leaf. They now believe flawed chips should be replaced upon request, irrespective of how minute the flaw is.
It is incontrovertible, therefore, that this error tented the public perception of Intel. In addition, some interesting ethical issues can be elicited from this and are as follows: * Should defects be revealed to consumers? Are there times when it is ethical not to reveal defects? Is it an ethics problem only if safety is involved? * Suppose a manufacturer places a warning in the literature that comes with a product such as “This product may contain unexpected flaws and might not operate correctly under all conditions.” Does this solve the ethical problems for the company? * How can an engineer be sure that there are no defects in a product? If it is impossible to eliminate all defects in a product, what level of defects is acceptable? Does this depend on what the product is? * What do codes of ethics of professional engineering organizations such as the IEEE say about selling products that are known to be defective? * What were the responsibilities of the engineers working on the Pentium chip once they became aware of the flaw?

REFRENCE
Pentium FDIV bug. (May 12, 2014.ed). In Wikipedia, the free Encyclopedia. http://en.wikipedia.org/wiki/Pentium_FDIV_bug Fleddermann, C. B. (2004). The Flaw in the Intel Pentium Chip. Engineering ethics
[Microsoft word document].
www.engr.sjsu.edu/.../Flaw_Intel_Pentium_Chip…...

Similar Documents

Pentium Flaw

Words: 374 - Pages: 2

Pentium Flaw

...Pentium Flaw The Pentium Microprocessor is the widest selling personal computers on the market. Intel created the 486DX and the Pentium chip that included Floating point unit (FPU). This FPU was known as a math co-processor. The problem arose in the fall of 1994, all the new Pentium chips were manufactured with an error in the FPU system. This error was in the FPU instructions for the division. This caused the chip to divide certain numbers incorrectly. Intel engineers discovered a flaw in the floating-point math subsection of the Pentium processor. But instead of assessing this problem they simply ignored it and thought that the customers would not ever notice the flaw. Thomas Nicely discovered this problem also when he was computing the sum of large reciprocals of prime numbers on his Pentium base computer. Later on Thomas emailed Intel and told them that there was a flaw in the co-processor. Intel never responded back so he took it to his own hands and posted the flaw online, asking other people to check for the flaw also on other users computers. Many people responded back and the news got involved sooner or later Intel started receiving more and more emails about the flaw. A common Known error was 4195825/3145727 dividing those numbers gave an incorrect answer to the problem. Intel’s response to this flaw was to replace Pentium chip microprocessor to whoever could explain the flaw to them. This angered man of the customers so Intel responded by replacing......

Words: 410 - Pages: 2

Pentium Flaw

...Intel’s famed technical prowess was not without mishaps. Its greatest mistake was the so-called “Pentium flaw,” in which an obscure segment among the Pentium CPU’s 3.1 million transistors performed division incorrectly. Company engineers discovered the problem after the product’s release in 1993 but decided to keep quiet and fix the problem in updates to the chip. However, In 1994 American mathematician Thomas Nicely was using a personal computer equipped with the then new Pentium chip from the Intel Corporation when he discovered a flaw in the chip that was producing inconsistent results in his calculations of Brun’s constant. Negative publicity from the mathematics community led Intel to offer free replacement chips that cost them millions of dollars in revenue. My analysis of the way the Intel Corporation handled the Pentium flaw of the 90's was irresponsible. They seemed to basically dismiss that there would be noticeable problems that could affect the user with their computer. Although in most cases this assumption is correct, it still shows a great deal of dishonestly from the company because it seemed as if Intel tried to cover it up. I feel that Intel was lazy and simply not willing to fix the problem that they created due to cost concerns. If I were to sell a bicycle to someone knowing the breaks were faulty, causing occasional break failure, I think people would be pretty upset and I would most likely be sued for sub sequential harm caused. On December 20, 1994,...

Words: 371 - Pages: 2

The Pentium Flaw

...The Pentium Flaw Unit 5 Analasyis 1 The Pentium flaw is that on certain input data, the floating point divide instructions on the Pentium processor produce inaccurate results. Intel quoted an error rate of about 1 in 8.77*10^9 random divisions. The exact frequency depends on the type and precision of the operands; single-precision reciprocals, for example, are always returned correctly. (Nicely, 2011) This was first reported by Professor Thomas Nicely in October of 1994 by computing the sum of the reciprocals of a large collection of prime numbers on his Pentium-based computer. (Nicely, 2011) Checking his computation, he found the result differed significantly from theoretical values. He got correct results by running the same program on a computer with a 486 CPU, and finally he tracked the error to the Pentium itself. (Janeba, 1995) Pentium originally refused to replace the faulty chips unless the user proved a need for high end computations as the flaw is rare and data-dependent. Although they did eventually agree to replace the product for any who requested it. (Janeba, 1995) I believe that Intel made several mistakes with the handling of this first, releasing a the product that was not 100% accurate all of the time into the market, secondly not heeding Professor Nicely when he advised them of the issue, and third by refusing at least initially to replace the faulty processors. The combination of these injured Intel, both in their reputation in the......

Words: 339 - Pages: 2

The Pentium Flaw

...The Pentium Flaw The Pentium Flaw is a prime example of what happens when a company ignores the users they sell their product to. The Flaw was in the 486DX processor chip, with the Floating point unit. The error in the unit would occur very rarely, when dividing non-integers. Intel’s testers knew of this issue before it was released, but they decided not to tell anyone outside of the company, this was their first and largest mistake. After the release of the chip, it was several months before Dr. Thomas Nicely noticed the flaw. He conducted several tests on multiple computers and processor units before he was convinced of the flaw and decided to alert Intel of what he had discovered. Dr. Nicely contacted Intel technical support, who ran his test and confirmed the flaw, however said that the issue had not been reported before. After six days, Dr. Nicely had heard nothing back from Intel; he then emailed a few people about this bug. It took less than two weeks for things to get out of control for Intel; already their stock had dropped a little more than a dollar. Intel initially ignored this problem, and when they did acknowledge it, it was much too late. The internet was chaotic with unhappy customers and newsgroups hoping to get a good scoop. It wasn’t until November 24th that Intel had offered their first Offer to effected customers. This offer was insignificant; to only replace the chips when a person could prove they needed absolute accuracy in their use of the......

Words: 477 - Pages: 2

Free Essay

The Pentium Flaw

...Collin Pannell Warwick NT 1110 October 22, 2013 The Pentium Flaw During the year of 1994 one of Intel’s processors called the Pentium microprocessor chip had a small flaw inside the chip. These Pentium processors included something new called a floating-point unit, which is also know as a math coprocessor. These Pentium processors had this floating-point unit built into the processors, which makes them much faster. These chips that were made had errors on the floating-point unit that corrupted instructions for division. This cased the Floating-point unit to divide certain floating-point numbers incorrectly. This Pentium flaw was most know from an equation solved by Tim Coe of Vitesse Semiconductors. The number he tried to divide was 4195835 by 3145727. The value that was outputted by the computer was incorrect by 0.006%. Thomas Nicely, a math professor at Lynchburg College was computing the sum of the reciprocals of a large collection of prime numbers on one of Intel’s Pentium-based computers. He calculated the same equation on a different program and then traced the problem back to the Pentium itself. Nicely contacted Intel and didn’t get any real response to the problem. He then posted on the Internet asking others to confirm the problem he had found. Nicely was interviewed with a magazine and CNN aired a story about by his findings. After Nicely’s findings, Intel publicly announced “an error is only likely to occur [about] once in nine billion random floating...

Words: 462 - Pages: 2

Free Essay

Pentium Flaw

...Analysis 1: Pentium Flaw Intel Corporation discovered a design flaw in June of 1994 in its flagship Pentium Processor. For divisions involving a few specific numbers, the chip's floating point unit gave the wrong answer. Intel's tests showed that the error only appeared in the ninth significant digit of the answer and affected only a minuscule percentage of the possible division combinations. Intel did not handle the problem correctly, they consider the flaw to be “minor” .They said that it wasn’t the first time a flaw of this nature happened so Intel continued to sell hundreds of thousands of chips that were already made. Intel pretty much ignored the flaw and did nothing to satisfy its consumer. Dr. Thomas contacted Intel’s technical support in October of the same year and had no luck, so he decided to post the problem in a blog, which brought immediate attention to Intel. At the beginning Intel said that that they will only replace the flawed chip only for those users that work with heavy duty scientific/floating point calculations since the problem did not affected everyone else using simple mathematics. Later that year after the increased coverage by worldwide print and electronic media, Intel fear and decided to recall the chip on December 20, 1994. Intel decided to offer a replacement chip to all of its end-users—"no questions asked." Intel took a \$475 million loss for the replacement program. In today’s society I think it would be mostly impossible for a......

Words: 353 - Pages: 2

Free Essay

Pentium Flaw

...The Pentium flaw was discovered in June 1994. The Pentium floating point flaw occurred in some models of the original Pentium microprocessor chip. Pentium processors with a clock speed of 120 MHz or higher are not affected by the flaw. The Intel Processor Frequency ID Utility checks for the floating point flaw on the affected microprocessors. Professor Thomas Nicely discovered the Pentium floating point unit flaw and emailed various contacts describing the flaw. Professor Nicely requested testing for the flaw on the 486-DX4s, and the Pentium clones. The flaw in in the Pentium floating point unit was verified and became known as the FDIV bug. The issue was a mathematical problem in the Floating Point (FPU), the math coprocessor. The Pentium chip had glitches when calculation large divisions. Testing on the 486 pin pointed the error to the Pentium Chip. Intel confirmed the error but said they had no other reports of it. Intel the considered the flaw as a minor problem and did not let the industry know about the flaw. However word of the flaw got out through the internet and articles and Intel started getting negative publicly. Intel handled did not handle the problem with the flaw correctly. By considering the flaw minor to avoid fixing the problem and negative publicly, Intel showed poor judgment and integrity as a company. Intel only attempted to fix the flaw after receiving negative publicly. To satisfy customers concerned about the flaw Intel fix the......

Words: 353 - Pages: 2

Pentium Flaw

...Pentium Flaw The Pentium flaw was a bug within the Pentium CPU’s 3.1 million transistors that caused the transistors to perform division incorrectly. Intel’s engineers discovered the flaw after the product’s release in 1993 but chose to keep silent and attempt to correct the flaw in future updates to the processor chip. The flaw was discovered in 1994 by American mathematician Thomas Nicely. Nicely was using a personal computer equipped with Intel’s Pentium chip when he discovered a flaw in the chip that was producing inconsistent results in his calculations of Brun’s constant. Nicely informed Intel of the flaw, but after receiving no response he posted his finding on the internet. News of the bug spread quickly on the internet and then to the industry press. Intel’s statement that the bug was minor was not accepted by many computer users. After a spotlight of the flaw ran by The New York Times, Intel changed its postion and offered to replace every chip. Only a fraction of Pentium users bothered to have their chips replaced. I believe Intel handled the situation in a professional manner and gave customers reasonable options to have their chips replaced. I do not think the flaw in the chip affected most customers and had little effect to the common user. If the flaw was a major problem more people would have had issues and more chips would have been replaced. Intel did everything necessary to satisfy their customers. I believe if the same situation was to occur......

Words: 305 - Pages: 2

Free Essay

Pentium Flaw

...arithmetic-logic unit, and the control unit. The CPU is connected to the other various equipment is the computer system which include input/output devices, storage units and other peripheral equipment. Essentially the CPU is the brains of a computers system. In 1968 Gordon Moore and Robert Noyce created the company giant, Intel which is now the largest CPU manufacturer in the world. In 1993 Intel introduced the Pentium series CPU. The Pentium architecture became the most successful processor of all time. As successful as the Pentium was it had issues. Most can and could not be seen by the typical user but in 1994 it had a flaw that was noticed by a mathematician from Lynchburg collage in West Virginia by the name of Thomas Nicely while doing some calculations on his PC. The Pentium flaw was the flaw in the Float-point unit would cause incorrect answers when preforming double precision arithmetic, which is a common operation. Intel’s first response to the problem was to deny that the problem did not exist. Then would later acknowledge the flaw. However state that the flaw was insignificant and most users would not notice. Intel would replace the defected processor if a user could demonstrate the need for a processor that was not flawed. After IBM cancelled sales of its computers that had the flawed processer in it and lots of negative publicity Intel replaced the flawed processor with an unflawed processor to any customer who asked for it. In......

Words: 402 - Pages: 2

Free Essay

Pentium Flaw

...College discovered a flaw with the new Intel Pentium processor while he was trying to perform calculations. He had noticed that the answers to his calculations were coming back wrong. One example of the flaw was found where the division result returned by the Pentium was off by about 61 parts per million. He initially contacted Intel in which he would find out later that they were aware that there was a problem. At first Intel denied there being a problem but after several reports they said that there was a problem but it was so minor that most computer users wouldn’t notice it. Intel then told its customers that if they could prove that they received a defective chip then they would replace it for free. IBM, who used the Pentium in their computers, cancelled their sales of their computers that had the flawed chip. But finally after a lot of negative press and decreasing sales, Intel finally decided to replace all the flawed chips. It seems to me that at first Intel did a horrible job of addressing the issue. Ii seemed as if they wanted to hide the problem because they didn’t want it to affect their profit margins. It also seemed that they were worried about losing their customer base over the issue. But in the end they seemed to have admitted their fault and tried to do the right thing and replace the defective chips. I would hope and imagine that any company, including Intel, would try to be more proactive in the future if they were to encounter any flaws in their......

Words: 302 - Pages: 2

Free Essay

Pentium Flaw

...Tiffany M Shamlee Unit 5 Analysis 1 NT1110 Pentium Flaw The Pentium flaw was discovered where the division result returned by the Pentium microprocessor was off by about sixty-one parts per million. When Intel discovered the flaw, their solution was to keep the information within the company. They did not want to disclose any of the information to the public, because of the negative publicity it would bring to the company. The flaw did not affect all microprocessors, only a very small number of customers. I feel that Intel should have openly acknowledged the problem despite the small number of customers affected. Intel determined if customers were affected by the flaw when they called in to report a problem. They did this by inputting a certain code into their system. Once they identified the problem, Intel would then implement a solution. However, if feel if Intel had openly accepted and informed the clients about the issue, it would have most likely saved them money. Their reputation between the company and their existing clients would have also been protected. Intel’s decision and way of handling the flaw caused a lot of their customers to be very unhappy. If this type of flaw was to be found in a new CPU today, the company would surely fail. With a problem in the floating-point math subsection with an error of approximately sixty-one parts per million, this would cause too many problems for the clients today. Especially considering that Intel......

Words: 310 - Pages: 2

Free Essay

Pentium Flaw

...Pentium Flaw The Pentium Flaw, also known as the Pentium FDIV bug, was a bug located in the FPU, and certain floating point division operations performed would produce incorrect results, which includes decimals, addition and subtraction. These are mostly used in math and some science work. Intel was heavily criticized for the flaw, and the handling of this flaw, which caused them to recall every one of the processors. Dr. Thomas Nicely discovered the bug in 1994. After emailing Intel and receiving no response, Dr. Nicely went ahead and posted a message on the internet. Word of the bug quickly spread to industry press. Intel responded by saying it was a minor issue, this was not accepted by computer users. Intel later changed its position and offered to replace every chip, which resulted in a \$500 million dollar loss for the company. This also actually propelled the company from being a tech supplier to now becoming a house hold name. Next, they in turn used the negative publicity to change business practices and become an overall better company. The Pentium Flaw made Intel into the most successful processor making company that it is today. Intel achieved a position of dominance in the market as a supplier. While the Pentium Flaw hurt the company short term, it actually helped the company in the long run. Gaining popularity and ensuring consistency within its products. Without the Pentium Flaw no one knows if Intel would be as successful as they are today, or if any of...

Words: 266 - Pages: 2

Free Essay

Pentium Flaw

...The Intel Pentium microprocessor had a design flaw in the mathematical division groupings. An internet blog site states, “Under certain data dependent conditions, low order bits of the result of floating-point division operations would be incorrect, an error that can compound in floating-point operations to much larger errors in subsequent calculations” (http://intelcorporation4uinfo.blogspot.com/2008/12/pentium-flaw.html). Due to not receiving a response from Intel on his findings, Professor Thomas Nicely from Lynchburg College, posted his findings on the internet on October 30, 1994. Nicely quoted that “he was computing the sum of the reciprocals of a large collection of prime numbers on his Pentium-based computer and found the error. Checking his computation, he found the result differed significantly from theoretical values. He got correct results by running the same program on a computer with a 486 CPU, and finally he tracked the error to the Pentium itself” (Janeba.Mark.The Pentium Problem.1995). News of calculations error spread like a wildfire. Intel publicly announced that "an error is only likely to occur [about] once in nine billion random floating point divide situations”. This did not sit very well with companies and individuals alike. The Food and Drug Administration stated its concerns for the drug-testing data that had been produced using the Pentium processor. They did not tell the companies to redo all their testing, but firmly represented hesitation......

Words: 674 - Pages: 3

Free Essay

Pentium Flaw

...Pentium Flaw The Pentium microprocessor flaw was basically that the CPU didn’t know how to do arithmetic or math calculations, so it failed at calculating any type of math. The Pentium flaw was found in the summer/fall of 1994 by Thomas Nicely according to Mark Janeba from the article I read. Mark Janeba stated that Thomas Nicely was a math professor at Lynchburg College and that Thomas was computing the sum of the reciprocals of a large collection of prime numbers on his Pentium-based computer. That’s when the problem started showing up, the CPU gave Thomas different results from his theoretical values so Thomas did the same problem on a different computer, the computer gave Thomas the same answer he got theoretically. He finally tracked the problem to the Pentium chip itself. According to the article by Mark Janeba, Intel admitted the problem publically around November of 1994. Intel was going to replace the Pentium chips but only for the people that could explain their need for complicated calculations. In the end of December Intel stated that a free replacement Pentium CPU would be given for anyone that asks for one. Basically Intel was going to do a total recall, replacement and they were going to destroy any of the flawed Pentium microprocessors. I honestly don’t think Intel handled the problem very well because at first they ignored it and said that it wasn’t happening to every Pentium CPU but people were saying that the Pentium CPU was not giving them the right......

Words: 452 - Pages: 2