How Ted Hoff Invented the First Microprocessor

But for Hoff, the microprocessor was merely one blip amongst many alongside the tracing of his lengthy fascination with electronics. His ardour for the sphere led him from New York City’s used electronics shops to elite college laboratories, via the extreme early years of the microprocessor revolution and the tumult of the online game trade, and finally to his job at the moment: high-tech non-public eye.

Fairly early in his childhood Hoff discovered that one of the best ways to really feel much less like a child—and slightly extra highly effective—was to grasp how issues work. He began his explorations with chemistry. By the age of 12 he had moved on to electronics, constructing issues with elements ordered from an Allied Radio Catalog, a shortwave radio package, and surplus relays and motors salvaged from the rubbish at his father’s employer, General Railway Signal Co., in Rochester, NY. Then in highschool, working largely with second­hand parts, he constructed an oscilloscope, an achievement he parlayed right into a technician’s job at General Railway Signal.

Hoff returned to that job throughout breaks from his undergraduate research at Rensselaer Polytechnic Institute, Troy, N.Y. Several summers started with Hoff coming into the General Railway laboratory to seek out the researchers’ two greatest oscilloscopes damaged. He would restore the state-of-the-art Tektronix 545s, then transfer on to extra fascinating stuff, like inventing an audio frequency railroad­prepare monitoring circuit and a lightning safety unit that gave him two patents earlier than he was out of his teenagers.

The smartest thing concerning the job, Hoff recalled, was the entry it gave him to parts that had been past the budgets of most engineering college students within the l950s—transistors, for example, and even the just-introduced energy transistor. He did an undergraduate thesis on transistors used as switches, and the money prize he received for it shortly went for a Heathkit scope of his personal.

Early Neural Networks

Hoff appreciated the engineering programs at Rensselaer, however not the slim focus of the school itself. He needed to broaden his perspective, each intellectually and geographically (he had by no means been various miles west of Niagara Falls), so selected California’s Stanford University for graduate college. While working towards his Ph.D. there, he did analysis in adaptive programs (which at the moment are known as neural networks) and, together with his thesis advisor Bernard Widrow, racked up two extra patents.

“He had a toy train moving back and forth under computer control, balancing a broom­ stick. I saw him as a kooky inventor, a mad scientist.”
—Stanley Mazor

His Intel colleague Mazor, now coaching supervisor at Synopsys Inc., Mountain View, Calif., recalled assembly Hoff in his Stanford laboratory.

“He had a toy train moving back and forth under computer control, balancing a broomstick,” Mazor mentioned. “I saw him as a kooky inventor, a mad scientist.”

After getting his diploma, Hoff stayed at Stanford for six extra years as a postdoctoral researcher, persevering with the work on neural networks. At first, his group made the networks trainable through the use of a tool whose resistance modified with the quantity and route of present utilized. It consisted of a pencil lead and a chunk of copper wire sitting in a copper sulfate and sulfuric acid resolution, they usually known as it a memistor.

“One result of all our work on microprocessors that has always pleased me is that we got computers away from those [computer center] people.”
—Ted Hoff

The group quickly acquired an IBM 1620 pc, and Hoff had his first expertise in programming—and in bucking the system. He needed to take care of officers on the campus pc middle who thought all computer systems needs to be in a single place, run by specialists who dealt with the packing containers of punched playing cards delivered by researchers. The concept {that a} researcher ought to program pc programs interactively was anathema to them.

“One result of all our work on microprocessors that has always pleased me,” Hoff instructed IEEE Spectrum, “is that we got computers away from those people.”

By 1968 pupil hostility to the federal government over the Vietnam War was rising and life for researchers on campus who, like Hoff, relied on authorities funding was wanting as if it would get uncomfortable. Hoff had already been considering the probabilities of commercial jobs when he obtained a phone name from Robert Noyce, who instructed him he was beginning a brand new firm, Intel Corp., and had heard Hoff may be taken with a job. He requested Hoff the place the semiconductor built-in circuit enterprise would discover its subsequent progress space. “Memories,” Hoff replied.

That was the reply Noyce had in thoughts (Intel was launched as a reminiscence producer), and that yr he employed Hoff as a member of the technical employees, Intel’s twelfth worker. Working on reminiscence know-how, Hoff quickly obtained a patent for a cell to be used in MOS random-access built-in circuit reminiscence. Moving on to grow to be supervisor of purposes analysis, he had the primary buyer contact of his profession.

“Engineering people tend to have a very haughty attitude toward marketing, but I discovered you learn a tremendous amount if you keep your eyes and ears open in the field.”
—Hoff

“Engineering people tend to have a very haughty attitude toward marketing,” Hoff mentioned, “but I discovered you learn a tremendous amount if you keep your eyes and ears open in the field. Trying to understand what problems people are trying to solve is very helpful. People back in the lab who don’t have that contact are working at a disadvantage.”

From 12 Chips to One Microprocessor

One group of consumers with whom Hoff made contact had been from Busicom Corp., Tokyo. Busicom had employed Intel to develop a set of customized chips for a low-cost calculator and had despatched three engineers to Santa Clara to work on the chip designs. Hoff was assigned to take care of them, getting them pencils and paper, exhibiting them the place the lunchroom was—nothing technical.

But the technical a part of Hoff’s thoughts has no off-switch, and he shortly concluded that the engineers had been going within the unsuitable route. Twelve chips, every with greater than 3000 transistors and 36 leads, had been to deal with completely different parts of the calculator logic and controls, and he surmised the packaging alone would value greater than the focused retail value of the calculator. Hoff was struck by the complexity of this tiny calculator, in contrast with the simplicity of the PDP-8 minicomputer he was presently utilizing in one other venture, and he concluded {that a} easy pc that would deal with the capabilities of a calculator might be designed with about 1900 transistors. Given Intel’s superior MOS course of, all these, he felt, may match on a single chip.

Marcian E. “Ted” Hoff

The Busicom engineers had little interest in dumping their design in favor of Hoff’s unproved proposal. But Hoff, with Noyce’s blessing, began engaged on the venture. Soon Mazor, then a analysis engineer at Intel, joined him, and the 2 pursued Hoff’s concepts, creating a easy instruction set that might be applied with about 2000 transistors. They confirmed that the one set of directions may deal with decimal addition, scan a keyboard, keep a show, and carry out different capabilities that had been allotted to separate chips within the Busicom design.

In October 1969, Hoff, Mazor, and the three Japanese engineers met with Busicom administration, visiting from Japan, and described their divergent approaches. Busicom’s managers selected Hoff’s method, partly, Hoff mentioned, as a result of they understood that the chip may have various purposes past that of a calculator. The venture was given the interior moniker “4004.”

Federico Faggin, now president and chief govt officer of Synaptics Inc., San Jose, Calif., was assigned to design the chip, and in 9 months got here up with working prototypes of a 4-bit, 2300-transistor “microprogrammable computer on a chip.” Busicom obtained its first cargo of the gadgets in February 1971.

Faggin recalled that when he started implementing the microprocessor, Hoff appeared to have misplaced curiosity within the venture, and infrequently interacted with him. Hoff was already engaged on his subsequent venture, the preliminary design of an 8-bit microprogrammable pc for Computer Terminals Corp., San Antonio, Texas, which, architected by Computer Terminals, was named the 8008. Hoff at all times “had to do very cutting-edge work,” Faggin instructed Spectrum. “I could see a tension in him to always be at the forefront of what was happening.”

In these early Intel days, Mazor recalled that Hoff had numerous concepts for initiatives, lots of which, although not commercially profitable, proved prescient: a RAM chip that may act like a digital digital camera and seize a picture in reminiscence, a online game with transferring spaceships, a tool for programming erasable programmable ROMs, and computer-aided design instruments supposed for logic simulation.

The Intel advertising and marketing division they estimated that gross sales [of microprocessors] would possibly whole solely 2000 chips a yr.

Meanwhile, the microprocessor revolution was gearing up, albeit slowly. Hoff joined Faggin as a microprocessor evangelist, attempting to persuade those that general-purpose one chip computer systems made sense. Hoff mentioned his hardest promote was to the Intel advertising and marketing division.

“They were rather hostile to the idea,” he recalled, for a number of causes. First, they felt that every one the chips Intel may make would go for a number of years to at least one firm, so there was little level in advertising and marketing them to others. Second, they instructed Hoff, ‘‘We have diode salesman out there struggling like crazy to sell memories, and you want them to sell computers? You’re loopy.” And lastly, they estimated that gross sales would possibly whole solely 2000 chips a yr.

But phrase went out. In May 1971 an article in Datamation journal talked about the product, and the next November Intel produced its first advert for the 4004 CPU and positioned it in Electronic News. By 1972 tales concerning the miracle of what started being known as the microprocessor began showing recurrently within the press, and Intel’s rivals adopted its lead by launching microprocessor merchandise of their very own.

Hoff by no means even thought-about patenting the microprocessor. To him the invention gave the impression to be apparent.

One step Hoff didn’t take at the moment was apply for a patent, though he had already efficiently patented a number of innovations. (Later, with Mazor and Faggin he filed for and was granted a patent for a “memory system for a multi-chip digital computer.”)

Looking again, Hoff recalled that he by no means even thought-about patenting the microprocessor in these days. To him the invention gave the impression to be apparent, and obviousness was thought-about grounds for rejecting a patent software (although, Hoff mentioned bitterly, the patent workplace presently appears to disregard that rule). It was apparent to Hoff that if in a single yr a pc might be constructed with 1000 circuits on100 chips, and if within the following yr these 1000 circuits might be put onto10 chips, finally these 1000 circuits might be con­ structed on one chip.

Instead of patenting, Hoff in March 1970 printed an article within the proceedings of the 1970 IEEE International Convention that acknowledged: “An entirely new approach to design of very small computers is made possible by the vast circuit complexity possible with MOS technology. With from 1000 to 6000 MOS devices per chip, an entire central processor may be fabricated on a single chip.”

But in December 1970, an unbiased inventor outdoors the cliquish semiconductor trade, Gilbert Hyatt, filed for a patent on a processor and talked about that it was to be made on a single chip. In 1990, after quite a few appeals and extensions, Hyatt was granted that patent and commenced amassing royalties from many microprocessor producers. Currently, although historical past traces at the moment’s microprocessor again to Hoff, Mazor, and Faggin, the authorized rights to the invention belong to Hyatt.

The Invention of the Codec

While the microprocessor has proved to be his most celebrated achievement, Hoff doesn’t view it as his largest technical breakthrough. That designation he reserves for the single-chip analog-to-digital/ digital-to-analog coder/decoder (codec).

“Now that work was an exciting technical challenge,” Hoff recollected with some glee, “because there were so many who said it couldn’t be done.”

The venture was kicked off by Noyce, who noticed the phone trade as ripe for brand new know-how, and urged Hoff to seek out an vital product for that market. Studying phone communications, Hoff and a number of other different researchers noticed that digitized voice transmission, then getting used between central places of work, relied on the usage of complicated costly codecs that tied into electromechanical switches.

”We thought,” Hoff instructed Spectrum, “we could integrate this, the analog-to-digital conversion, on a chip, and then use these circuits as the basis for switching.”

Besides decreasing the price of the programs to the phone firm, such chips would allow corporations to construct small department exchanges that dealt with switching electronically.

Hoff and his group developed a multiplexed method to conversion wherein a single converter is shared by the transmit and obtain channels. They additionally established numerous different methods for conversion and decoding that Hoff noticed as not being apparent and for which he obtained patents.

With that venture’s completion in 1980, after six years of effort, and its switch to Intel’s manufacturing facility in Chandler, Ariz., Hoff grew to become an Intel Fellow, free to pursue no matter know-how him. What him was returning to his work on adaptive buildings, combining the ideas he had wrestled with at Stanford with the ability of the microprocessor within the service of speech recognition. After a yr he constructed a recognition system that Intel marketed for a number of years.

A first-rate buyer for the system was the automotive trade. Its inspectors used the programs to assist them take a look at a automobile because it lastly left the meeting line. When an inspector famous out loud varied issues that wanted fixing, the system would immediate him for additional info, and log his responses in a pc.

From Intel to Atari

Though his place as an Intel Fellow gave Hoff a good quantity of freedom, he discovered himself becoming bored. Intel’s success in microprocessors by 1983 had turned it right into a chip provider, and different corporations had been designing the chips into programs.

“I had always been more interested in systems than in chips,” Hoff mentioned, “and I had been at Intel for 14 years, at a time when the average stay at a company in Silicon Valley was three years. I was overdue for a move.”

Again, Hoff had not gone past occupied with leaving Intel when a brand new job got here to him. Atari Inc., Sunnyvale, Calif., then a booming online game firm owned by Warner Communications Inc. and a significant consumer of microprocessors, was searching for a vice chairman of company know-how. In February 1983, after discussing the scope of the concepts that Atari researchers had been pursuing, Hoff latched onto the chance.

Intel from the beginning had a structured, extremely managed tradition. At Atari, chaos reigned.

Intel from the beginning had a structured, extremely managed tradition. At Atari, chaos reigned. Under Hoff had been analysis laboratories in Sunnyvale, Los Angeles, and Grass Valley, Calif.; Cambridge, Mass.; and New York City. Researchers had been engaged on image telephones, digital aids for joggers, pc controls that gave tactile suggestions, graphical environments akin to at the moment’s digital actuality, digital sound synthesis, superior private computer systems, and software program distribution through FM sidebands.

But Hoff had barely had time to find out about all of the analysis initiatives underneath manner earlier than the online game enterprise took a well-publicized plunge. Without stable inside controls, Atari was unable to find out how effectively its video games had been promoting on the retail level, and distributors had been returning tons of of hundreds of cartridges and sport machines. Hoff started receiving orders for workers cuts month-to-month.

“It would have been one thing if I had known I had to cut back to, say, one-quarter the size of my group,” he instructed Spectrum. “But when every month you find you have to cut another chunk, morale really drops.”

In July 1984, whereas Hoff was at his thirtieth highschool reunion, Warner bought Atari to Jack Tramiel. Hoff then had to decide on between convincing Tramiel that he may play a task in a narrowly centered firm bored with funding futuristic analysis, and permitting Warner to purchase out his contract. He selected the latter.

Looking again, most people who had been at Atari in these days now view them darkly. But Hoff remembers his yr there as an pleasant and finally helpful expertise. “Maybe I look at it more positively than I should,” he mentioned, “but it turned out to be a good transition for me, and the life I have now is a very nice one.”

“Whenever you are working on one problem, there is always another problem over here that seems more interesting.”
—Hoff

He now spends half his time as a guide and half pursuing technical initiatives of his personal devising—a learn­out system for machine instruments, varied kinds of body grabbers, sample recognition, and methods for analog-to-digital conversion. This variegated schedule is ideal for him. He has at all times felt himself to be a generalist, and has had hassle specializing in only one know-how.

“It’s easy for me to get distracted,” he mentioned. “Whenever you are working on one problem, there is always another problem over here that seems more interesting. But now it is more likely that my own projects get delayed, rather than things critical to other people and their employment.”

Faggin for one will not be stunned that such unbiased work appeals to Hoff. “He never was the gregarious type,” Faggin mentioned. “He liked introverted work, the thinking, the figuring out of new things. That is what he is good at. I always was impressed how he was able to visualize an architecture for a new IC, practically on the spot.”

“He comes up with idea after idea, situation after situation. I think if he wanted to, Ted could sit down and crank out a patent a month.”
—Gary Summers

Said Gary Summers, president and chief govt officer of Teklicon Inc., Mountain View, the consulting agency that employs Hoff at the moment: “He comes up with idea after idea, situation after situation. I think if he wanted to, Ted could sit down and crank out a patent a month.”

“There is no doubt in my mind that he is a genius,” Mazor acknowledged. Summers readily concurred.

Hoff’s first venture after Atari was a voice­managed music synthesizer, which gave off the sound of a specific instrument when somebody sang into it. Hoff’s largest contribution to the venture was a system that ensured that the rising notes can be in tune, or not less than harmonically complement the tune, even when the singer strayed off key. He scored one other patent for this technique, and the gadget was bought briefly via the Sharper Image catalog, however by no means grew to become a giant success.

Hoff nonetheless contributes often to product designs. At Teklicon, nonetheless, the place he’s vice chairman and chief technical officer, most of his consulting is finished for legal professionals. Hoff has a singular mixture of lengthy expertise with digital design and long-standing pack rat habits. His house workshop accommodates about eight private computer systems of various makes and vintages, 5 oscilloscopes, together with a classic Tektronix 545 scope, 15000 ICs inventoried and filed, and cabinets loaded with IC knowledge books relationship proper again to the Sixties.

“If my washing machine breaks down, I call the repairman. Most clever engineers would buy the replacement gear and install it. Ted is capable of analyzing the reason the gear failed in the first place, redesigning a better gear from basic principles, carving it out of wood, casting it at his home, and dynamically balancing it on his lathe before installing it.”
—Mazor

When a lawyer exhibits him a patent disclosure, even one many years outdated, he can decide whether or not or not it may then have been “reduced to practice” and whether or not it offered ample info to permit “one of ordinary skill in the art” to apply the invention. Then he can construct a mannequin proving his conclusion, utilizing classic parts from his assortment, and reveal the mannequin in courtroom as an skilled witness. This model-building can get very fundamental. On Spectrum’s go to, Rochelle salt crystals that Hoff tried to develop for a latest courtroom demonstration littered his workshop ground, subsequent to metal-working tools that he makes use of to construct instances for his fashions.

Hoff sees this capacity to get all the way down to fundamentals as certainly one of his strengths. “I relate things to fundamental principles,” he mentioned. “People who don’t question the assumptions made going into a problem often end up solving the wrong problem.”

Mazor mentioned, “If my washing machine breaks down, I call the repairman. Most clever engineers would buy the replacement gear and install it. Ted is capable of analyzing the reason the gear failed in the first place, redesigning a better gear from basic principles, carving it out of wood, casting it at his home, and dynamically balancing it on his lathe before installing it.”

Doing authorized detective work appeals to Hoff for one more motive: it offers him an excuse to hunt for fascinating “antique” parts at flea markets and electronics shops.

Hoff can’t talk about the specifics of patent instances he has been concerned with. Several just lately had been within the online game space; others have concerned varied IC corporations. In numerous instances, Hoff was assured that his facet was proper, and his facet nonetheless misplaced, so he felt little shock when the microprocessor patent was granted to Hyatt. (After the award was made, although, he did sit down with Hyatt’s patent software and tried to design a working microprocessor based mostly on Hyatt’s disclosures. He discovered a number of incongruities—like a clock price solely suited to bipolar know-how with logic that would solely be rendered in MOS know-how, and logic that required far too many transistors to placed on a chip, proving in his thoughts that the award was incorrect.)

Seeing another person get credit score for the microprocessor, notably in latest media experiences, “is irritating,” Hoff instructed Spectrum, “but I’m not going to let it bother me, because I know what I did, I know what all the other people on our project did, and I know what kind of company Intel is. And I know that I was where the action was.”

Editor’s observe: Hoff retired from Teklicon in 2007. He presently serves as a choose for the Collegiate Inventors Competition, held yearly by the National Inventors Hall of Fame. These days, his fundamental technical pursuits encompass vitality, water, and local weather change.