Talk:Cray-1

speed

The problem citing the 800 MFLOPS number for the X-MP (the Cray-1's lineage successor) is that this performance figure does NOT correspond to 1982 performance for a 2 processor (then available) X-MP; it more closely corresponds to 4 processor X-MPs on a "good" day which was not until a couple of years later. The text has an impediance mismatch between machine performance and chronology.

--enm 26 Apr 2006 18:00 GMT

The problem I see with this artical is that thier seems to be inconsistences in the speeds given for the cray-1 and apparently also thiers an accidental use of the acronym MIPS rather then MFLOPS (or megaflops). This article states that In 1975 Cray clammed that the speed was 80 MFLOPS and then give an un-named sorce credit for placed the speed of the Cray-1 at "138–250 MFLOPS". I visited Cray inc's web site and Cray inc claims today that the Cray-1's speed was 160 megaflops (not MIPS).[[ http://www.cray.com/about_cray/history.html]]

Now I have nrver read of seen any banchmarks for the Cray-1 giving speeds in MIPS and Cray inc. claims it's speed was 160 megaflops, and this artical says 160 MIPS so I think maybe the acronym MIPS was used by accident and ether MFLOPS or megaflops should of bin used instead. Using MIPS may confuse people in to thinking that MIPS and MFLOPS (or megaflops) mean the samething.

But the article is quite clear on the difference: the theoretical performance was 2 instructions at 80 MHz which is 160 million instructions, or MIPS. Floating point operations were not one-cycle, nor could they be dispatched on any cycle, so the FP performance was slower, the 136 MFLOPs number. I don't know where the 80 MFLOPs number came from, it's wrong and I'm removing it. Maury 21:39, 28 November 2006 (UTC)

You say, "Floating point operations were not one-cycle, nor could they be dispatched on any cycle, so the FP performance was slower...." Oh yeah??? That was the whole point of Cray's pipelined vector processors. They yielded a result every clock cycle. Why don't you stick to changing stuff you actually know about or understand! Just because idiots designed the junk from the Intel 4004 family that is in your PC doesn't mean that all computer architects are idiots!!! Doesn't anyone review changes that people make in Wikipedia anymore??? —Preceding unsigned comment added by 98.212.132.146 (talk) 15:48, 12 December 2010 (UTC)

@98.212.132.146: I think you missed my point. The Cray had vector startup overhead, albeit much shorter than the STAR. That overhead means that single units could not retire one instruction per cycle, on average. But don't take my word for it, take Crays - look at Table III of their report on the machine. Note that a single FP multiply takes 60 clock cycles, and at 10,000 elements you're down to 3.7. That means overall performance will be significantly slower than the potential peak. Do you have a source from Cray that says otherwise? Maury Markowitz (talk) 02:57, 8 December 2017 (UTC)

OS history

Another topic which needs real elaboration is the history of the first planned operating system for the Cray-1 at LANL. This was supposed to be Deimos. An academic paper was written about Deimos, but apparently the message-passing and its Unix-like favor for years put the fear of God in anything smelling like UNIX at LASL (later LANL) and LLL (later LLNL). Why this was and what happened is a lesson for technologists.

--enm 26 April 2006 18:30 GMT

comparison to 2006 ipod shuffle

Gjvo: That's really interesting. Can you provide more details? Mmernex 17:38, 22 May 2007 (UTC)

Comparison with modern pc prosessors

http://www.tomshardware.com/2007/07/16/cpu_charts_2007/page36.html i think the second table shows relevant Mflops?--Teveten 07:07, 3 October 2007 (UTC)

History

The first sentence of the history states:

In the early 1974 Cray was working at Control Data on a new machine known as the CDC 8600, the logical successor to his earlier CDC 6600 and CDC 7600 designs.

I think that in [1974]] Cray was working at Cray Research and not at Control Data. Later the history states:

In 1972 the 8600 had reached a dead end.

and a little bit later (without stating a date):

Cray left.

The article about the CDC 8600 states that:

In 1972 Cray decided that he couldn't work under such conditions, and left CDC to form Cray Research.

The article about Cray Research states that:

Cray Research, Inc. (CRI), was founded in 1972 by computer designer Seymour Cray.

So I guess the history should begin with:

In the years 1968 to 1972 Cray was working at Control Data on a new machine known as the CDC 8600, the logical successor to his earlier CDC 6600 and CDC 7600 designs.

since the article about CDC 8600 states that:

Development started in 1968

Therefore I will do the change. Glass Tomato 08:47, 2 November 2007 (UTC)

Background notes (STAR)

From the article,

... something that might have been obvious had the designers considered Amdahl's Law.

Implying that the designers simply failed to take into account Amdahl's law is a vast over-simplification of the underlying causes of disappointing real-world performance. Amdahl's law is a simple back-of-the-envelope calculation that any idiot can do. I think the STAR's problem may have been an inaccurate estimate of typical workloads. It is all to easy to come up with corner cases that would show a huge speedup with vector processing that are not likely to be found in the real world. For good examples of such toy problems, refer to just about every microbenchmark ever written.

And it's probably likely that any advertised speedups came from inflated or misinterpreted claims spewed by the marketing department of the company, not directly from the designers themselves.

In any case, the claim that the designers were able to engineer a complex piece of technology without understanding one of the simplest principles of parallel programming is laughable. —Preceding unsigned comment added by 24.136.36.147 (talk) 11:43, 9 January 2008 (UTC)

How is the Amdahl's Law argument different today than it was in regard to the STAR-100? If forecasting the efficacy of computing architectures were that simple, it would have been obvious that none of the fine-grained parallel processors in the Top500.org list should have been built, and they wouldn't have.

Furthermore, it seems obvious that whoever made the original criticism has never worked in teams or committees on large engineering projects. Inertia and conformance to human social systems are paramount. No one can tell the king he has no clothes and survive. Cray got the (very small) "A Team" in Chippewa. The entire rest of the thousands of employees at CDC were emotionally and financially invested in producing "their" machine. Cognitive dissonance set in. Recall that the main reason they were building the STAR was that someone had published that the content of all the phonebooks (the spy's convenient cryptographic table of the time) in the US could be loaded into the STAR's virtual memory. Someone behind the "black curtain" thought that was important. Introduce the "spooky" need-to-know behavior into the company, and soon it becomes the dominant behavior in the corporate culture. There was no way that most people could find out how the STAR was actually intended to work, let alone how that would map onto commercial computing mixes. There is no evidence that the commercial market was the target market, anyway. The world, and especially the world of the US govt. behind the scenes, is more complicated than you imagine. It's amazing, nay miraculous, that Seymour was able to accomplish what he did while interacting with that theatre of operations.

Let's remove the impertinent "Amdahl's Law" remark. 98.212.138.123 (talk) 19:56, 24 December 2010 (UTC)

I spoke with Neil Lincoln, the final architect of the STAR-100, shortly after it was completed. It turns out the original design team FORGOT to design in a way for I/O to put data in/out of memory. They relied on an old concept which had always worked before called "cycle-stealing," wherein the buffered I/O uses "background" memory cycles which are unused by the CPU. Unfortunately in a vector-processing memory-to-memory architecture, there ARE NO MEMORY CYCLES UNUSED during a vector operation. Hence there had to be a whole redesign after-the-fact with kludges inserted into the completed hardware just so the STAR could do I/O. Don't tell me that the same people responsible for that fiasco couldn't have overlooked Amdahl's Law! They were the "B" team; Cray had the "A" team. The company gave these B-team Bozos a significant chunk of Cray's funding which was intended to be used in the 8600 development project, too. It should be obvious why Seymour left CDC. It had begun to die the death of all bloated bureaucracies, and it finished dying shortly after Cray left. 98.212.132.146 (talk) 16:09, 12 December 2010 (UTC)

Addressing

I have my doubts about this sentence: "Addressing was 24-bit, for a maximum of 1 megaword (8 MB) of main memory."

According to my references, data addressing was 22-bit and operated at the word level, allowing a maximum of 4 Mwords (64-bit words). Instruction addressing was also 22-bit, but operated at the instruction parcel level (16-bit parcels). Early models could have a maximum of 1 Mword, but this was later raised to four. Am I wrong? Philip Trueman (talk) 13:30, 3 April 2008 (UTC)

I think you're basically right. There some info in the Cray-1 hardware reference manual [1] which describes the original 1 MW max setup. The memory reference instructions have a 22 bit address field of which the top two bits are said to be unused (that's presumably the original 1 MW physical memory limit). Branches take a 25 bit address (top 3 bits unused); the bottom 2 bits are the parcel address. Finally, the exchange package specifies 22 bit base and limit addresses. So I'd say 4 MW is the max, both for data and for instructions. Paul Koning (talk) 20:23, 3 April 2008 (UTC)

The address registers were 24 bits wide. However, since each of the 4 instruction parcels in a word were addressable (e.g., via a branch instruction), this gave 22 bits of word address for 4 mwords. The early Cray-1 machines were limited by the memory technology of the day - only 1k bits/chip! The Cray-1S used denser technology (4k bits/chip), so could be configured with 4 mwords in the same 12-column footprint of a 1 mword Cray-1. --Wws (talk) 21:45, 4 April 2008 (UTC)

The sentence is quite illogical without this explanation. And 1MW limit due too available memory chips seems reasonable, if that's the case or not, the manual clearly states that Cray-1 had a 1MW maximum memory. Because right now 24-bit addressing is mixed with information about maximum memory you could get with a Cray-1, not the maximum memory a Cray-1 could address.

I tried to understand it all by looking in the manual, in the section about Instructions at page 4-3 and 4-4, the memory transfer instructions are explanied. They have a 22-bit memory word address consisting of a bank address (16-bits) and bank select (4-bits for the 16 banks) and the extra 2-bits (from the 24-bit address integer) are not used (in this instruction). With this information I would like to purpose a rewrite of the memory information, by including bank information and 24-bit addressing into a larger description of the memory, and include notice about different memory sized available with Cray-1 and later models. And an explanation on what the 2-bits are used for? Adrianjcc (talk) 14:15, 29 December 2009 (UTC)

It currently says, "Addressing was 24-bit, for a maximum of 1,048,571 72 bit words..." The Cray-1 was WORD, not BYTE, addressable. Since when does 2^24 equal 1 million??? 98.212.132.146 (talk) 15:40, 12 December 2010 (UTC)

Not only that, since when does 2^20 == 1,048,571 ??? Why isn't this 1,048,576 ? Someone with authoritative knowledge should rework the entire addressing writeup. SJGooch (talk) 22:47, 24 December 2010 (UTC)

References

"High Power" should be "ECL"

I think the section on the Cray-1's circuitry, which always refers to the IC's and signals as "high power", should probably mostly be talking in terms of "ECL" or "differential" or "ECL differential" levels.

It is true that ECL and its differential signaling are a specific design point chosen to allow high speed, high noise immunity, and they happen to use comparatively high power and twisted pair wiring. And these are all important details the article currently brings out. But calling it "high power" logic throughout is not right. It should be called ECL and MECL logic, with references to the Wikipedia pages about ECL. —Preceding unsigned comment added by N3QE (talk • contribs) 17:32, 1 November 2009 (UTC)

Absolutely true that it was ECL. Under the "Description" section, it says that the logic was constructed from 4/5 NAND gates. I am fairly certain that it was constructed from all one part, which was a combination of two ECL NOR gates, one 4-input, and one 5-input made by Fairchild. I believe I even have an audio tape of Seymour saying this at home. In searching archives, I believe the chip may be Fairchild part number 11C01 ( refer to: http://doc.chipfind.ru/fairchild/11c01.htm ). Yes, I know we could talk about majority functions, and DeMorgan's laws, etc., and even negative-true logic. But this is not the 6600. And the point is that this documentation is historically incorrect. Please fix it. There are many people you could ask: Les Davis, Dave Cahlander, and all the other guys who were there. 98.212.138.123 (talk) 00:15, 20 December 2010 (UTC)

naming -- 9600

While it was being developed, there were people internally who called the Cray-1 the 9600, since it followed very much in the 6600-7600-8600 design path. The main reason that name was not used was that nobody could agree on what to call the next machine after it, and Seymour was already looking toward the next machine. T-bonham (talk) 04:23, 28 March 2010 (UTC)

Additionally, Steve Chen told me that the Cray-{1,2,3...N} numeric designations were reserved for machines for which Seymour was the Chief Architect, while the Cray-(X,Y,Z} designations were for projects led by others. SJGooch (talk) 07:28, 24 December 2010 (UTC)

Yep. All the way up to N=7. Have never heard of 9600 used. 8600 bares a little resemblence to the 2. 198.123.49.48 (talk) 18:47, 20 January 2011 (UTC)

After the CTO went to NYC for an IOU

"The CTO went..." Wow! That's incredible! I didn't know CTOs traveled! But apparently this one did! What the **** is a CTO? Hello! Spell out the acronyms! More exclamation points!!!!! 65.199.232.66 (talk) 15:35, 14 May 2011 (UTC)

 Done --Kvng (talk) 17:29, 16 May 2011 (UTC)

8600

the 8600 was as different from the 7600 as that was from the 6600 — Preceding unsigned comment added by 72.193.24.148 (talk) 19:07, 27 April 2012 (UTC)

Cray OS

• The search for the lost Cray supercomputer OS, By Signe Brewster, Gigaom, Jan. 14, 2014, chrisfenton.com/cray-1-digital-archeology — Preceding unsigned comment added by So-retro-it-hurts (talk • contribs) 05:09, 1 May 2015 (UTC)

80 MFLOPS or 160 MFLOPS?

The box at the upper right says 160 MFLOPS whereas sub section "History" says 80 MFLOPS. What is correct?

--Mortense (talk) 21:13, 24 September 2016 (UTC)

External links modified

Hello fellow Wikipedians,

I have just modified one external link on Cray-1. 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/20121227164249/http://www.ucar.edu/educ_outreach/vtour/cray.html to http://www.ucar.edu/educ_outreach/vtour/cray.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) 06:55, 14 August 2017 (UTC)

Umm, that seems wrong

"The Data General minicomputers were optionally replaced with an in-house 16-bit design running at 80 MIPS"

The DG was about 0.25 MIPS, and a VAX 11/780 was 1. It is extremely unlikely that the front-end computer ran at 80, especially 16-bit one. Maury Markowitz (talk) 02:36, 8 December 2017 (UTC)

When was the last Cray 1 shut down?

I can't find a reference. I assume they aren't pouring 115KW into something this slow anywhere anymore? - Immigrant laborer (talk) 18:04, 7 July 2022 (UTC)

Shorten background section

The background section appears to be confusing instruction pipeline with data prefetching/memory-memory architecture. I'm not familiar with the STAR and Cray-1 architectures to know if there's a reason to do so, but if there is, the current wording doesn't communicate this sufficiently.

I think most of the section can be shortened to a concise summary as it's ultimately not about the article's subject and duplicates content of the Vector_processor#Supercomputers and CDC_STAR-100#Real-world_performance,_users_and_impact sections, which seem to explain the background better. PaulT2022 (talk) 05:29, 19 April 2023 (UTC)