Design Article
30 years of DSP: From a child's toy to 4G and beyond
Steve Taranovich
8/27/2012 2:19 PM EDT
As Texas Instruments principal fellow Gene Frantz tells it, the aha moment for the company’s DSP pioneers came in the late 1970s, shortly after TI’s seminal Speak & Spell learning toy hit retailers’ shelves. Frantz recalls that a customer asked, “If you can [use DSP to] add speech synthesis to a toy, what else can you use it for?”
This year, as TI celebrates its 30th year in the DSP market, that long-ago question has been answered many times over. Without DSP and the advances it has enabled in audio, graphics, and multimedia processing, there would be no “infotainment” content, no smartphones or tablets, no Internet or ecosystem of apps.
TI’s “toy” technology not only moved the company into a new business but set the stage for developments by TI, its competitors, and tool vendors that have pushed DSP technology into diverse applications and markets. At the same time, traditional DSP devices have seen competition from an array of alternative signal-processing platforms, including CPUs with DSP-oriented features; digital signal controllers, which pair a DSP core with an MCU; FPGAs, which can be used to design custom data paths for digital signal processing or even to create custom programmable processors; and, most recently, massively parallel processing graphics processors that can tackle data-parallel problems.
Figure 1: TI’s Speak & Spell team—from left, Gene Frantz, Richard Wiggins, Paul Breedlove, and Larry Brantingham, showing off the product at its introduction—went on to push DSP technology into diverse applications and markets.
The roots of DSP technology predate the Speak & Spell by several years. In the early 1970s, scientists began using off-the-shelf TTL discrete logic chips to implement specialized signal-processing “engines.” The early systems were relatively slow and consumed a lot of space. TRW shipped the first practical parallel multiplier design in 1973 and added bit-slice ALUs two years later. But at several hundred dollars just for the multiplier chip, the only customers that could afford such a product were research laboratories, medical-scanning equipment makers, and the military.
In 1978, American Microsystems Inc announced the first single-chip IC designed specifically for DSP: the 12-bit S2811. AMI devised a truly innovative circuit design but implemented its chip in a radical “V groove” MOS technology that never yielded volume commercial products.
The following year, Intel Corp introduced the Intel 2920 16-bit “analog signal processor,” so called because Intel had designed the chip as a drop-in analog-circuit replacement, complete with on-board A/D and D/A converters. The 2920 processed analog signals digitally, but it lacked a parallel multiplier; what’s more, its 600-nsec cycle time made it too slow to perform useful work in the audio spectrum, where the first high-volume DSP chip market would eventually materialize.
The first “true” single-chip DSPs—which market-analysis firm Forward Concepts defines as having parallel MAC (multiplier-accumulator) circuits—emerged in early 1980 from Bell Labs and NEC. The Bell Labs chip, the DSP-1, was a captive device used in AT&T and Western Electric equipment. NEC’s µPD7720 was the first true single-chip DSP shipped in volume to the merchant market. Although hampered by primitive development tools, the NEC chip offered sufficient speed—a 122-nsec cycle time with a two-cycle MAC—to perform useful work in the audio spectrum.
In the late 1980s, Hiromitsu Yagi of Ricoh redesigned the original AMI S2811 chip for a conventional NMOS process. Yagi’s work resulted in the Ricoh RD28211 and the AMI S28211.
Next: Title-1
|
|
|
|
|
delashmit
8/29/2012 2:14 PM EDT
My first use of DSP type chips was the Intel 2708 that was programmed in assembly language for a "Passive Sonar Signal Processor" at the Penn State University Applied Research Laboratory in the 70s-80s. A technical paper on this work was piblished in the IEEE AESS Transactions.
My 2nd use of DSP chips was the TI TMS320C10 for a digital version of the Anti Satellite Signal Processor. This was performed in 1985 for the LTV Corporation (Now Lockheed Martin). The initial chips that we used were labeled experimental parts. A technical paper on this work was published in the IEEE AESS Transactions.
I also have experience with the TI TMS320C30-40 series.
Sign in to Reply
forthprgrmr
10/1/2012 1:34 PM EDT
Did I miss the '80s?
I thought the hot application for the early DSP chips was audio. And Motorola had the best part - the 24bit DSP56 family. I see no mention of this important bit of history.
If I remember right it came out in the early '80s and dominated the high end audio market until 32bit parts took over.
Sign in to Reply
nGENEr
12/20/2012 11:50 AM EST
You didn't miss the '80s. Motorola did find it niche in the professional audio area. That lasted until ADI introduced the 21060 with extended precision floating point (32 bit mantissa). We, at TI, later realized we could only compete using double precision floating point (53 bit mantissa).
But do remember that the story above is about TI's 30th anniversary. By the way, next year (2013) will be the 35th anniversary of the Speak & Spell (TM) learning Aid.
Sign in to Reply
SYW
10/2/2012 1:22 AM EDT
Before IC DSP there were discrete transistor DSP fix wired for certain defense projects. It was about 1965 at Hughes Aircraft where I was refuge computer designer among bunch of radar experts. Someone gave me a paper by Cooley & Tucky about fast Fourier Transform if useful to replace banks of crystal filters. At von Neumann's Computer Project at Institute for Advanced Study in the early 1950s, Prof. Tukey of Princeton U. had his FT program running on the computer. Probably the slow kind because it ran so long that each night he gets a few hours with intermediate results punched out for next night run. Cooley was a graduate student from New York helping Prof. Tukey in programming. I did figured out FFT and even had several patents for simplifying it for implementation. It was my collegue Art Zukin that proposed the programmable version which I cannot remember whether was implemented or not. TI effort impementing on IC certainly is a great contribution. That gives me comfort because I am trying to revive a DOD language to unify software and hardware designs so that even K-12 students can learn to design ICs. That is if I can get some Defense agency to support such idea. I tried on an old IBM PC and am convinced it works. If anybody thinks that simplified IC design tool anybody can afford might promote entrepreneurs, please let me know. SYW
Sign in to Reply
TestGuy33
10/3/2012 11:46 AM EDT
I recall when TI people visited EDN magazine's editors and gave a presentation for the introduction of the TMS320C20. They gave me an experimental chip that I wired up on a breadboard for the PC ISA bus. The chip required external memories and some control logic, but it worked and I wrote routines in BASIC on the PC to load the DSP memories with values and instructions, and then reset the DSP chip to run my short programs. I wrote several DSP programs and got them to run, but debugging was quite a chore because I used 'C20 assembly language, translated instructions into hex, then loaded them into an array in my BASIC program, and finally sent them to the memories on the prototype board. But I enjoyed doing some DSP "stuff" with one of the first chips. When I told the TI people about my experiments, they said, "Gee, if we thought you were going to actually use the chip we gave you, we would have sent you one we knew worked." I guess I got lucky with what I had. --Jon Titus
Sign in to Reply
fiftyohm
12/21/2012 4:20 PM EST
Probably should mention Zilog here. Back in the early 90's, they introduced the Z8-C95 microcontroller. It was an extremely cheap part that targeted disk drive controllers to replace the analog stuff for servo control. It was a standard Z8 with a rudimentary DSP core that shared a small memory array.
We used it with great success doing FFTs in an industrial Doppler flow instrument. At the time, nothing could touch the performance/price ratio. It was pretty low-power as well.
Sign in to Reply
Tony Boom
3/2/2013 11:39 PM EST
Very long history, hope your business can develop more technology for every people.
http://www.odybed.com
Sign in to Reply