Talk:History of general-purpose CPUs

summarizing

I think the section history of general purpose CPUs#Asynchronous CPUs is a bit long. I've copied all the details to asynchronous circuit#asynchronous CPU. (I suspect that section might grow into a clockless CPU article of its own). Help me reduce that section to a summary. --68.0.124.33 (talk) 01:40, 5 May 2008 (UTC)

history of cache and virtual memory

CPU cache briefly mentions: A historical note: the first virtual memory systems were very slow, because they required an access to the page table (held in main memory) before every programmed access to main memory. With no caches, this effectively cut the speed of the machine in half. The first hardware cache used in a computer system was not actually a data or instruction cache, but rather a TLB.

I think this "history" article should also mention this history of cache and virtual memory. Where to put it? --68.0.124.33 (talk) 01:39, 6 May 2008 (UTC)

2000-2010, 2010-

Suggestions:

• 2000-2010: Multithreading, multicore, integrating other units (SIMD units and memory management), heterogenous CPUs (Cell) and GPGPU
• 2010-: CPUs going full SoC with integrated graphics, sound, video, networking. Massively multicore. Emergence of ARM in the general CPU segment.

-- Henriok (talk) 14:03, 3 February 2010 (UTC)

External links modified

Hello fellow Wikipedians,

I have just modified one external link on History of general-purpose CPUs. Please take a moment to review my edit. If you have any questions, or need the bot to ignore the links, or the page altogether, please visit this simple FaQ for additional information. I made the following changes:

• Added archive https://web.archive.org/web/20080202055942/http://www.intellasys.net/index.php?option=com_content&task=view&id=21&Itemid=41 to http://www.intellasys.net/index.php?option=com_content&task=view&id=21&Itemid=41

When you have finished reviewing my changes, you may follow the instructions on the template below to fix any issues with the URLs.

This message was posted before February 2018. After February 2018, "External links modified" talk page sections are no longer generated or monitored by InternetArchiveBot. No special action is required regarding these talk page notices, other than regular verification using the archive tool instructions below. Editors have permission to delete these "External links modified" talk page sections if they want to de-clutter talk pages, but see the RfC before doing mass systematic removals. This message is updated dynamically through the template {{source check}} (last update: 18 January 2022).

• If you have discovered URLs which were erroneously considered dead by the bot, you can report them with this tool.
• If you found an error with any archives or the URLs themselves, you can fix them with this tool.

Cheers.—InternetArchiveBot (Report bug) 10:54, 3 April 2017 (UTC)

No PowerPC?

Wow.. not any mention of POWER or PowerPC anywhere.. fantastically skewed article. -- Henriok (talk) 09:36, 10 May 2017 (UTC)

…or PA-RISC and Alpha for that matter. And only one cursory mentions of SPARC and MIPS. -- Henriok (talk)

External links modified

Hello fellow Wikipedians,

I have just modified 4 external links on History of general-purpose CPUs. Please take a moment to review my edit. If you have any questions, or need the bot to ignore the links, or the page altogether, please visit this simple FaQ for additional information. I made the following changes:

• Added archive https://web.archive.org/web/20110719211222/http://www.hofstra.edu/pdf/CompHist_9812tla6.PDF to http://www.hofstra.edu/pdf/CompHist_9812tla6.PDF
• Corrected formatting/usage for http://www.ieee.org/portal/cms_docs_iportals/iportals/aboutus/history_center/oral_history/pdfs/Shima197.pdf
• Corrected formatting/usage for http://www.antiquetech.com/chips/NEC751.htm
• Added archive https://web.archive.org/web/20120415121639/http://jbayko.sasktelwebsite.net/cpu.html to http://jbayko.sasktelwebsite.net/cpu.html

When you have finished reviewing my changes, you may follow the instructions on the template below to fix any issues with the URLs.

This message was posted before February 2018. After February 2018, "External links modified" talk page sections are no longer generated or monitored by InternetArchiveBot. No special action is required regarding these talk page notices, other than regular verification using the archive tool instructions below. Editors have permission to delete these "External links modified" talk page sections if they want to de-clutter talk pages, but see the RfC before doing mass systematic removals. This message is updated dynamically through the template {{source check}} (last update: 18 January 2022).

• If you have discovered URLs which were erroneously considered dead by the bot, you can report them with this tool.
• If you found an error with any archives or the URLs themselves, you can fix them with this tool.

Cheers.—InternetArchiveBot (Report bug) 02:53, 5 November 2017 (UTC)

Busicom and Microprocessor

Hello @Ancheta Wis:, I would like to explain why I removed that information. The information I removed was added by sock puppet of Jagged 85, an infamous vandal, who was banned for misusing sources. It was originally reverted by @Indrian: [1], but then reinserted in October 2017. The information is extremely inaccurate and inflates the role of Busicom and Japanese engineers in invention of microprocessor.

For instance the claim that "Sharp engineer Tadashi Sasaki, who also became involved with its development, conceived of a single-chip microprocessor in 1968" citing this [2]. The source does not say that Sasaki conceived single-chip, that is, that it is his invention. Here what I found:"In 1968 the four-chip calculator was at its peak. So in that year Mr. Sasaki started to think of two years ahead. He needed a two-chip machine. This was the way he actually thought at that time. In 1968, he started to discuss what's coming after one chip". Later he simply states, as far as I see, that the Japanese woman was the first person he was aware of that articulated the general theory of a single-chip architecture.

Another claim is that " Intel wanted a single-chip CPU design,[5] influenced by Sharp's Tadashi Sasaki who presented the concept to Busicom and Intel in 1968.[6] The single-chip microprocessor design was then formulated by Intel's Marcian "Ted" Hoff in 1969,[3] simplifying Shima's initial design down to four chips, including a single-chip CPU. I checked [3], and not able to find anything about Hoff being influenced by Shima initial design, or in fact anything about Shima design.

Here is by the way history of microprocessor written by Faggin, and he does not say anything like this [4]. I think we should stick to mainstream sources, and not on misrepresentation of oral reports.

Here is another example of misuse of sources, in timeline it is stated that: ". Busicom's Masatoshi Shima begins designing three-chip CPU that would later evolve into the single-chip Intel 4004 microprocessor", citing this source [5]. I was not abled to find anything about Shima designing three-chip CPU, not that it would later evolve into Microprocessor. Here is what I found: "Starting in 1968 a young engineer at Busicom, Masatoshi Shima, worked on the design of Busicom's first calculator with printed output, the Busicom 141-PF."

Here is another questionable one from timeline: " Intel 4004's initial design led by Intel's Ted Hoff and Busicom's Masatoshi Shima." I checked [6], and I can't find it there. DMKR2005 (talk) 18:25, 11 January 2022 (UTC)

Shima is very clear that Intel was a memory manufacturer, not a logic shop at the time, and the logic was his contribution. Memory chips were Intel's business model at the time. Note that when Intel made an extensive survey of proposed applications of integrated circuits, the CPU was not among the hundreds of applications of ICs in the survey. The history notes that a calculator manufacturer, was the source of the chip-level concept, not Intel. The Intel history notes this fact. Sasaki is clear that the unmarried Nara Women's college alumna thought up the idea of the PMOS cpu, as an organic concept stemming from the application (calculators). After she married and changed her name, he lost track of her. She should step forward, if she still lives. --Ancheta Wis   (talk | contribs) 18:51, 11 January 2022 (UTC)

Faggin 2009 nicely corroborates Shima's oral history: "I came here to check, and there is nothing to check! This is just idea!"—(Faggin 2009 p.13). Shima was clearly senior to Faggin, who had only arrived at Intel the week before. Note that Busicom (meaning Shima) had already provided the data (timing diagrams, etc.), in an inversion of the "vendor/client" relationship. Clearly Busicom knew what it was doing. --Ancheta Wis   (talk | contribs) 19:45, 11 January 2022 (UTC)

Faggin 2009 p.12 states that Mazor (who reported to Hoff) (1970) showed him the "Busicom project", a proposal which included multiple chips, and that Faggin was to implement as the IC designer. (Sasaki having already presented the PMOS chip idea to Noyce in 1968)

There actually an accusation in Faggin 2009, namely that the silicon gate technology was taken to Intel. But rights are a murky area, aren't they. An inventor needs only disclose the specific practice in the invention itself, and not the idea. --Ancheta Wis   (talk | contribs) 20:09, 11 January 2022 (UTC)

I think we should stick to what mainstream sources say, and not try to do OR. The claim that same unnamed woman formulated single-ship architecture is stemming only from one resource, an interview with Sasaki. I suppose we can add something like "according to Sasaki a single-chip arhictecture was concivied by unnamed woman...", or something like this. What does Shima yelling at Faggin, or being senior to him has to do with microprocessor invention? And where does history notes that a calculator manufacturer, was the source of the chip-level concept and not Intel? Are you refering to this source [7]? I can't find anything here. Speaking of Sasaki claim about a woman conceiving single-chip architecture, I looked at some papers about history of microprocessor like [8], [9] and of cause Faggin article and they do not say anything about her. Seems to me quite a minority view.

You also did not responded to some of source misuse like "Busicom's Masatoshi Shima begins designing three-chip CPU that would later evolve into the single-chip Intel 4004 microprocessor", citing this source [10]. There is nothing there about designing three-chip CPU. Also take a look at this discussion [11] where @Indrian: explain whats wrong with Jagged-85 edits. DMKR2005 (talk) 22:20, 11 January 2022 (UTC)

Faggin 2009 is clear: he (as employee of Intel, the vendor), was assigned to design chips to perform functions in behalf of Busicom (the client, which was designing circuit boards which were to incorporate the Intel chips into the Busicom circuit boards). Busicom knew how to apply the chip outputs, even supplying Intel with chip-level circuit behavioral data. Shima arrived at Intel expecting to see the design work, and found that Intel had done nothing on their Busicom project (what was to become the 4001, 4002, 4003, 4004) in the interim. Since Shima was expecting chips, and found nothing, he became upset. Faggin (the newly-arrived employee) and Mazor (who introduced Faggin to the Busicom project) had to placate Shima -- it took a week for Shima to realize he had to step in and do the logic design himself, because logic designers were in short supply. Intel, as memory manufacturer, would have been interested in the 4001 and 4002 memory chips (supposedly higher profit), with much less interest in the shift register and cpu -- the 4003 and 4004. As it turned out, the market was interested.

ALU design had been public knowledge since the Von Neumann memo (1945), and the circuit-level implementation of ALU and associated electronics was called the cpu in the '50s going forward. By inverting the economics of implementation, what formerly took a room of electronics, now took a box. Even Fairchild could understand this. When Shima had to step in, the partitioning of the cpu was up in the air, and 1, 2, 3, or 4 chips as cpu would have been in play. An outsider's question "where is the cpu?" would be moot if there was no reduction to practice, which Shima was forced to provide. --Ancheta Wis   (talk | contribs) 08:26, 12 January 2022 (UTC)

Faggin et al (1996) p.16 states "At the peak of the project, Faggin and Shima worked simultaneously on all four chips at different stages of the development process. The 4004’s detailed logic design, which Shima undertook, took place during June and July. Shima also did the logic simulation, while Faggin ...". This proves my statement. --Ancheta Wis   (talk | contribs) 09:22, 12 January 2022 (UTC)

I am not sure what are we disputing here. Shima helped design the logic,as the project was behind schedule. I don't dispute this. Ted Hoff is the one who formulated the the architecture of single-chip computer CPU, see [12] p15 or this [13]. Faggin designed the chip and Shima helped with logic design. My problem is with statments like this "Tadashi Sasaki, who also became involved with its development, conceived of a single-chip microprocessor in 1968, when he discussed the concept at a brainstorming meeting that was held in Japan", this is supported only by one source, and interview with Sasaki. Moreover according to interview it was an unnamed woman who formulated the architecture, and not Sasaki. The other sources do not say anything like this. I think we should stick to mainstream version. DMKR2005 (talk) 05:26, 13 January 2022 (UTC)