came across this and thought other HNers might find it interesting, my favorite on this list has to be the "RCA COSMAC CDP 1802" for the 2001 quality alone not to mention radiation-hardening :)
One thing I noticed was that the article incorrectly claims that the RCA COSMAC CDP 1802 was used in Voyager and Viking missions, but it wasn't used until Galileo
Do we have anything like that in the works right now? Everything seems to be fairly straightforward evolutions of the x86 or ARM--though maybe the innovation is happening over in FPGAs or business-not-tech venues?
Well, if that sort of thing is indeed in the works, I doubt anyone would tell us- competitive advantage and all that- but it has been ten years since the Opteron 240. Maybe it will be time for the next one soon.
It could even be one of many technologies recently on the market. "Influence" is a legacy; you can't see it on launch day. Maybe one day we will look back on hUMA [0] and say it was one of those Things? The PS4 processor in particular, as the first processor with hUMA.
Although, it does look to me like innovation is more gradual now just as a matter of fact- the business cycle is much shorter now. The 4004 was released in '71, the 8088 in '79, but today every chip vendor releases a new chip every six months, so changes will naturally be spread across releases and it will be harder to point and say "There, right there, that is where the world changed"
I imagine in another few years the Intel Core Duo will make the list, because of its status as the first major multicore CPU on the consumer market.
Realize that's still x86. I'm not sure we'll see that change, though. Another hugely influential Intel chip is behind that story: Itanium marks the point at which it became clear that the market's no longer receptive to completely new ISAs in general-purpose CPUs.
I think the market would have embraced Itanium, if it had been significantly faster.
Also, markets change. Today, 'normal' people don't care about CPU architectures. Who cares what his phone runs on, as long as it runs with low power use?
I would add the P6 architecture to that list, I feel that it was the redemption of many of the ideas in the i960 as well as its designer.
It was the one that finally lifted intel in peoples viewpoint. I think that a lot of people fail to realise just how much of intel's product lineup in the last 14 years can be traced to the P6 microarchitecture.
> I was under the impression that they were munched by Intel
Nope, you must be thinking about something else. Transmeta started moving into IP in 2005, sued intel for patent infringement in 2006 (settled for a cool 250mil, Intel got a perpetual, non-exclusive license out of it), licensed tech to Nvidia in 2008 and died in 2009 (was acquired by Novafora in January, Novafora collapsed in July but not before Intellectual Vultures made off with the patent stash in Feb)
Now part of Intel's activity at the time (the PIII and Pentium M side which ended up with Core) may well have been inspired by Transmeta (as many allege), but at the same time Transmeta's activity best matches Intel's pursuit of the NetBurst (P4) shit-cake, which ran opposite to pretty much anything Transmeta looked for (unless Transmeta had patents on lofty promises they couldn't come close to deliver on, then year the P4 fits).
There's speculation that NVidia's Project Denver is an Efficeon reworked to target ARM code rather than x86. So there might be a live Transmeta descendant out in the real world again in a few months.
The Transmeta is a really fascinating CPU architecture based around "code morphing", modern CPUs use something at a bit of a lower level: micro-op translation.
Intel was doing micro-op translation way before 2005...it was something they introduced with the Pentium Pro. Their patent problems with transmeta was probably coincidental infringement (in that one can patent the obvious).
Transmeta's code morphing was quite different: they were going to VLIW instead of RISCy Pentium Pro operands. It never worked very well, but for the same reason Itanium/Merced failed: it is just really hard to transparently schedule VLIW instructions efficiently without programmer intervention.
I thought that was what I said, maybe I wasn't very clear.
Anyway, it's a really interesting range of problems, as is what's worked and what hasn't. Personally I think code morphing still has a lot of promise, but mostly in software level "emulation"/trans-coding.
Something interesting about Itanium is that eventually it's actually become pretty good. But it's now in a market niche that it's not going to be able to break out of. The big problem with IA64, in my opinion, was that they neglected IA32 performance with the first gen. They made the classic error of prematurely committing to a new design before it was proven, which contrasts greatly to the AMD64 example where they did everything possible to ease the transition and maintain, or even improve, performance with x86 only code.
I believe Intel eventually fixed Itanium with more support for dynamic instruction scheduling which sort of goes against the very concept of VLIW. SIMD (via GPUs) rather than MIMD then took the performance crown for HPC tasks and hasn't looked back.
VLIW still works very well in DSP-style applications, where static scheduling is quite feasible.
I would certainly agree that MIPS, at least as reference architecture, is an very important part of all modern architectures. The Patterson/Hennesey book [1] is absolutely require reading for many Computer Science/Electrical Engineering/Computer Engineering departments (even my state school required it) in undergrad, and most certainly required in graduate school when Computer Architecture turns to pipelining, cache structures and hierarchies, micro-architecture vs. macro-architecture, instruction set design, etc. Without MIPS, there isn't a baseline architecture to talk about in these courses as all other commercial architectures quickly begin to show their biases and optimization strategies.
I guess you can never make a list that satisfies everybody. I would like to see something with DEC Alpha there (not only) for the integrated memory controller. Or Nehalem.
To show the MOS 6502 without the Commodore 64 is a HUGE oversight. The C64 was the most prolific computer of the 80's. Thank you Chuck Peddle for the 6502. Thank you Bob Russell and Bob Yannes for the C64. Jack Tramiel, thank you for providing computers for the masses not the classes.
I was a C64 kid all the way, but the Apple II was released four or five years earlier than the C64. It very definitely blazed the way for the C64, and arguably deserves the place of honor in the list; I don't think the C64 would have been what it was without Apple going first. (Leaving C64 totally off the 6502 list is a travesty, though.)
But the Commodore PET was released the same year of the Apple II, and outsold it during the first years. The myth is that there was only the Apple II, and everyone else copied it - that's definitely not true.
The C64 was very clearly Commodore's attempt to use its technology to make an Apple II-style home computer.
Oh! I just checked on http://en.wikipedia.org/wiki/Commodore_PET#Origins_and_the_e... and here's something I didn't know: "In September 1976 Peddle got a demonstration of Jobs and Wozniak's Apple II prototype, when Jobs was offering to sell it to Commodore, but Commodore considered Jobs' offer too expensive." So it turns out even the PET was at least somewhat inspired by the Apple II.
Like I said, I loved my C64. But I remember when it came out, and everyone understood it was Commodore's answer to the Apple II. A very successful answer, mind you!
This is funny. Chuck Peddle had designed the first microcomputer design around the MOS 6502 - that's the MOS Technology KIM-1 (1975), which was a reference board and was sold as a kit. The Apple I was mostly inspired by that - which is normal, considering that it was the reference board. I seriously doubt that Peddle needed much inspiration from Apple for the PET.
I think that's pretty much out of date, as far as I can find only a total 17 million Commodore 64s were ever sold (even the most unrealistic estimates put it at 30 million), Apple sells about 15 million iPads per quarter, with models being sold for about a year.
Considering that an iPad can do everything that (as I recall) a C64 could do, yes. The exception of writing and executing user-entered code could be called out, but I don't view that as a requirement of a "personal computer" but rather a "general-purpose computer". Oh, sure, we geeks think they're the same thing. But most users of C64s that I knew didn't, at least judging from how they used their machines (i. e., not writing code).
Maybe not my phone, but I'd hand you my iPad. Oh, you wanted to pull some code of off github, compile it and FTP the binary to a remote server? My iPad has ssh, login into the remote server of your choice and knock yourself out. But you more likely just wanted to Google something, in which case the iPad is probably a better choice than the C64 anyway. "Wah, I want a real keyboard!" Here, use my BT keyboard. "Boo hoo, real screen, please." Connect to the Apple TV and use the 50" 1080p TV, I'm sure you'll find it more to your liking than the C64's video display options.
The C64 gets its sales record trounced by the iPad every year that iPads are for sale. Your original statement is no longer true, no matter how hard to try to narrowly define "personal computer". Best to just update your world view and move on.
My point is that a term that is too broad becomes meaningless. Would you call your 3g tablet a phone? And what if you don't have 3g, only wi-fi, but you can still call phones using skype? Then, even my desktop-PC-with-a-keyboard could be called a phone. Where do you put the line?
Not comparable, I would say that a computer is a broader term than telephone.
Nowadays, telephony is just another application not a device, so an iPhone is a computer that does telephony as one of its primary tasks and your desktop is a computer that does telephony via Skype.
I don't worry about where the lines are drawn because the lines are mostly arbitrary and imaginary.
And without lines the names lose their significance, that's all my point. They are arbitrary but not imaginary: they are a convention. A convention that is useful and necessary, if we want to communicate.
Technically the C64 had a 6510 in it, though of course the 6510 was essentially just a 6502 plus an extra I/O port and you're right that they really should have mentioned it somewhere in the "variants" section of the 6502 writeup.
I think they are correct in stating that the Apple 2 was the breakthrough application of the 6502. The C64 was a tsunami, but it came after the breakthrough.
That's also why they list the Mac for the 68000, not the Atari 400 or the Amiga, the Archimedes for ARM, even though it got way more popular later, and the Altair for the 8080 even though that probably sold less than even today's greatest flop.
I do find it weird that all the most influential microprocessors happened to have their breakthrough in a PC. Surely, there were influential embedded CPUs? For example, where's the 8051?
Had a lot of (slightly masochistic) fun programming the Z80 back in the day on my MSX2 machine.
I didn't have an assembler, so I wrote my code by taking the opcodes from a table, calculating offsets etc., then turning them into DATA-lines in an MSX-Basic program, which POKEd the code into RAM, then CALL into the starting address.
Same here! And i'm not sure was is masochistic about it; I still write software for the MSX2 like that now ;) I only knew about Hisoft assembler and that was too expensive so I never learned anything different than opcodes.
allowed, after some short time without even looking at the table, to type the binary code directly in (our preferred way of the Forth words implementation back then, on Russian 8080 clone of course :).
When I got my MSX from the attic after almost 30 years I still remembered almost all the opcodes. Took me few days to relearn the rest; I was 8 when I memorised them...
My first intro to microprocessors was the Z80 book published by Howard Sams. I never actually tried using one, but the book was so well written that it gave me an excellent foundation.
I'd probably recommend one of the older uP's for anybody who is just getting started, as they are so much simpler.
Ah yes, so much power going the assembly code route, it took me a while to shake it. Started entering opcodes in the z80, and thought that Masm was as good as it could get. Was still doing Windows x86 assembly programming, until I found another way.
Like the Z80, the M68k can still be found today inside of some TI graphing calculators (the 89 series, 92, and V200. The 80, 81, 82, 83 and 84 series, and the 85/86 have Z80's).
This list isn't very well balanced. The 386 revolutionized computing. It introduced an architecture that is still alive today and held market dominance for over 20 years (which is more than half the duration of the micro-computer age itself). And the P6 (Pentium Pro) architecture erased the old CISC/RISC boundary, enabling x86 code to run seamlessly on effectively state-of-the art RISC cores, extending the lifetime of the architecture tremendously.
The gameboy uses an LR35902 by Sharp, which is not exactly a Z80. It's kind of in the middle of the 8080 and Z80 chips IIR, so you could consider it a variant of either.
It was also the audio co-processor in the Genesis/Megadrive and the Neo-Geo alongside the M68k CPUs.
A friend's father, who works in embedded environmental control systems once showed me a control board for a heating and a/c system that was powered by a Z80. It had inputs for a dozen or so temperature sensors that were to be placed throughout a building and the CPU only needed to be fast enough to poll them every few seconds. The number of sensors was limited to the addressability of an 8-bit CPU, so under 256.
They should also mention the Japanese MSX standard which was Z80 centered for the first few generations and is the source of a great many very recognizable video game series (most of which were ported to the 6502 used by the NES). The last generation used a crazy variant called the R800, which I suppose would be like the 80286 was to the 8080.
Much of the 80s stereotypical synthesizer sound is due to the use of FM synthesis which can be thin sounding. There are a lot of classics from that era like the Yamaha DX7.
67 comments
[ 2.8 ms ] story [ 128 ms ] threadEDIT: (another link: http://history.nasa.gov/computers/Ch6-2.html)
Further, no love for Transmeta?
Poor show.
It could even be one of many technologies recently on the market. "Influence" is a legacy; you can't see it on launch day. Maybe one day we will look back on hUMA [0] and say it was one of those Things? The PS4 processor in particular, as the first processor with hUMA.
Although, it does look to me like innovation is more gradual now just as a matter of fact- the business cycle is much shorter now. The 4004 was released in '71, the 8088 in '79, but today every chip vendor releases a new chip every six months, so changes will naturally be spread across releases and it will be harder to point and say "There, right there, that is where the world changed"
[0]: http://en.wikipedia.org/wiki/Uniform_memory_access#hUMA
http://ootbcomp.com/
EDIT: They're releasing explanations as they submit patents, so not everything is public yet. I just submitted the most recent talk.
https://news.ycombinator.com/item?id=7027115
Realize that's still x86. I'm not sure we'll see that change, though. Another hugely influential Intel chip is behind that story: Itanium marks the point at which it became clear that the market's no longer receptive to completely new ISAs in general-purpose CPUs.
Also, markets change. Today, 'normal' people don't care about CPU architectures. Who cares what his phone runs on, as long as it runs with low power use?
It was the one that finally lifted intel in peoples viewpoint. I think that a lot of people fail to realise just how much of intel's product lineup in the last 14 years can be traced to the P6 microarchitecture.
Nope, you must be thinking about something else. Transmeta started moving into IP in 2005, sued intel for patent infringement in 2006 (settled for a cool 250mil, Intel got a perpetual, non-exclusive license out of it), licensed tech to Nvidia in 2008 and died in 2009 (was acquired by Novafora in January, Novafora collapsed in July but not before Intellectual Vultures made off with the patent stash in Feb)
Now part of Intel's activity at the time (the PIII and Pentium M side which ended up with Core) may well have been inspired by Transmeta (as many allege), but at the same time Transmeta's activity best matches Intel's pursuit of the NetBurst (P4) shit-cake, which ran opposite to pretty much anything Transmeta looked for (unless Transmeta had patents on lofty promises they couldn't come close to deliver on, then year the P4 fits).
Fun fact: TX/RX Labs (Houston Hackerspace) has a rack of old Transmeta blade servers that a former member donated.
http://anandtech.com/show/7622/nvidia-tegra-k1/2
http://en.wikipedia.org/wiki/Project_Denver
The Transmeta is a really fascinating CPU architecture based around "code morphing", modern CPUs use something at a bit of a lower level: micro-op translation.
Transmeta's code morphing was quite different: they were going to VLIW instead of RISCy Pentium Pro operands. It never worked very well, but for the same reason Itanium/Merced failed: it is just really hard to transparently schedule VLIW instructions efficiently without programmer intervention.
Anyway, it's a really interesting range of problems, as is what's worked and what hasn't. Personally I think code morphing still has a lot of promise, but mostly in software level "emulation"/trans-coding.
Something interesting about Itanium is that eventually it's actually become pretty good. But it's now in a market niche that it's not going to be able to break out of. The big problem with IA64, in my opinion, was that they neglected IA32 performance with the first gen. They made the classic error of prematurely committing to a new design before it was proven, which contrasts greatly to the AMD64 example where they did everything possible to ease the transition and maintain, or even improve, performance with x86 only code.
VLIW still works very well in DSP-style applications, where static scheduling is quite feasible.
[1] http://www.amazon.com/Computer-Architecture-Quantitative-App...
By the way, the C64 was not just the most prolific computer of the 80s - it remains the most sold computer model in history.
Oh! I just checked on http://en.wikipedia.org/wiki/Commodore_PET#Origins_and_the_e... and here's something I didn't know: "In September 1976 Peddle got a demonstration of Jobs and Wozniak's Apple II prototype, when Jobs was offering to sell it to Commodore, but Commodore considered Jobs' offer too expensive." So it turns out even the PET was at least somewhat inspired by the Apple II.
Like I said, I loved my C64. But I remember when it came out, and everyone understood it was Commodore's answer to the Apple II. A very successful answer, mind you!
source: http://www.c64-wiki.com/index.php/Commodore#Sales_numbers_.2...
The C64 gets its sales record trounced by the iPad every year that iPads are for sale. Your original statement is no longer true, no matter how hard to try to narrowly define "personal computer". Best to just update your world view and move on.
Nowadays, telephony is just another application not a device, so an iPhone is a computer that does telephony as one of its primary tasks and your desktop is a computer that does telephony via Skype.
I don't worry about where the lines are drawn because the lines are mostly arbitrary and imaginary.
https://itunes.apple.com/us/app/codea/id439571171?mt=8
https://itunes.apple.com/us/app/python-programming-language/...
That's also why they list the Mac for the 68000, not the Atari 400 or the Amiga, the Archimedes for ARM, even though it got way more popular later, and the Altair for the 8080 even though that probably sold less than even today's greatest flop.
I do find it weird that all the most influential microprocessors happened to have their breakthrough in a PC. Surely, there were influential embedded CPUs? For example, where's the 8051?
It's pretty long but well worth a listen, there's some really fascinating stuff in it.
I didn't have an assembler, so I wrote my code by taking the opcodes from a table, calculating offsets etc., then turning them into DATA-lines in an MSX-Basic program, which POKEd the code into RAM, then CALL into the starting address.
http://pastraiser.com/cpu/i8080/i8080_opcodes.html
allowed, after some short time without even looking at the table, to type the binary code directly in (our preferred way of the Forth words implementation back then, on Russian 8080 clone of course :).
I'd probably recommend one of the older uP's for anybody who is just getting started, as they are so much simpler.
This list isn't very well balanced. The 386 revolutionized computing. It introduced an architecture that is still alive today and held market dominance for over 20 years (which is more than half the duration of the micro-computer age itself). And the P6 (Pentium Pro) architecture erased the old CISC/RISC boundary, enabling x86 code to run seamlessly on effectively state-of-the art RISC cores, extending the lifetime of the architecture tremendously.
It was also the audio co-processor in the Genesis/Megadrive and the Neo-Geo alongside the M68k CPUs.
A friend's father, who works in embedded environmental control systems once showed me a control board for a heating and a/c system that was powered by a Z80. It had inputs for a dozen or so temperature sensors that were to be placed throughout a building and the CPU only needed to be fast enough to poll them every few seconds. The number of sensors was limited to the addressability of an 8-bit CPU, so under 256.
They should also mention the Japanese MSX standard which was Z80 centered for the first few generations and is the source of a great many very recognizable video game series (most of which were ported to the 6502 used by the NES). The last generation used a crazy variant called the R800, which I suppose would be like the 80286 was to the 8080.
What could be more influential than influencing how a decade of music sounded?
http://www.youtube.com/watch?v=iIpfWORQWhU
Much of the 80s stereotypical synthesizer sound is due to the use of FM synthesis which can be thin sounding. There are a lot of classics from that era like the Yamaha DX7.