# 1990 Cray supercomputer vers. my grandmother’s Dell **URL:** \ **Category:** Factual Questions\ **Created:** [October 28, 2010, 11:02am UTC](https://boards.straightdope.com/t/1990-cray-supercomputer-vers-my-grandmother-s-dell/558644 "2010-10-28T11:02:12Z")\ **Posts on this page:** 8\ **Page:** 4
**Author:** ![eschereal](https://sea3.discourse-cdn.com/straightdope/user_avatar/boards.straightdope.com/eschereal/32/18939_2.png) [@eschereal](https://boards.straightdope.com/u/eschereal)\ **Post date:** [October 24, 2012, 5:37pm UTC](https://boards.straightdope.com/t/1990-cray-supercomputer-vers-my-grandmother-s-dell/558644/61 "2012-10-24T17:37:59Z")
> [@Laggard](#): > > I’m curious about questions like does my cell phone have more computing power than the Apollo 13 capsule? Arguably, a contemporary smartphone will typically have [more processing power than the Space Shuttle originally did](http://en.wikipedia.org/wiki/Space_Shuttle#Flight_systems), though the later upgrades close the gap quite a bit. When first launched, the shuttle five guidance computers contained close to half a megabyte of _core_ memory each (those had to be enormous storage racks). Add in the GRiD laptop, you are getting kind of close (bubble memory? holy crap). Still, what the shuttle’s computers did was pretty highly specialized and relied heavily on redundancy: if your cell phone were running shuttle guidance and experienced a failure (crash), it might have trouble recovering in time to save your ass. Though, I suppose 5 phones working together would do the trick and still be less expensive. ---
**Author:** ![AndrewL](https://avatars.discourse-cdn.com/v4/letter/a/3d9bf3/32.png) [@AndrewL](https://boards.straightdope.com/u/AndrewL)\ **Post date:** [October 24, 2012, 8:20pm UTC](https://boards.straightdope.com/t/1990-cray-supercomputer-vers-my-grandmother-s-dell/558644/62 "2012-10-24T20:20:46Z")
Here’s a cycle-accurate recreation of a Cray-1A on a single FPGA chip: [http://www.chrisfenton.com/homebrew-cray-1a/](http://www.chrisfenton.com/homebrew-cray-1a/) Not quite the same thing as comparing it to a Dell, but it does show that modern computer hardware can fairly easily recreate the function of a Cray 1A. ---
**Author:** ![Blakeyrat](https://avatars.discourse-cdn.com/v4/letter/b/ecd19e/32.png) [@Blakeyrat](https://boards.straightdope.com/u/Blakeyrat)\ **Post date:** [October 24, 2012, 11:12pm UTC](https://boards.straightdope.com/t/1990-cray-supercomputer-vers-my-grandmother-s-dell/558644/63 "2012-10-24T23:12:07Z")
> [@Hari\_Seldon](#): > > In the early days of PCs, even older generations of mainframes had much greater I/O capacity than even high end PCs. The first PC hard drive I saw was just 10MB. Two days ago at Costco, I saw a 1TB drive on a PC! I’ve had dual 1.5-terabyte drives in my computer for almost 3 years now. [Now you can buy 4 TB in a single 3.5" enclosure.](http://www.newegg.com/Product/Product.aspx?Item=N82E16822145560) ---
**Author:** ![RaftPeople](https://avatars.discourse-cdn.com/v4/letter/r/6f9a4e/32.png) [@RaftPeople](https://boards.straightdope.com/u/RaftPeople)\ **Post date:** [October 25, 2012, 2:39am UTC](https://boards.straightdope.com/t/1990-cray-supercomputer-vers-my-grandmother-s-dell/558644/64 "2012-10-25T02:39:31Z")
I’m curious about the supers that aren’t on the top500 list, the ones at NSA or other agencies. Has anyone ever heard of any kind of performance from these? I assume they have ones that are more powerful than the top of the top500. ---
**Author:** ![Whack-a-Mole](https://sea3.discourse-cdn.com/straightdope/user_avatar/boards.straightdope.com/whack-a-mole/32/141_2.png) [@Whack-a-Mole](https://boards.straightdope.com/u/Whack-a-Mole)\ **Post date:** [October 25, 2012, 3:10am UTC](https://boards.straightdope.com/t/1990-cray-supercomputer-vers-my-grandmother-s-dell/558644/65 "2012-10-25T03:10:44Z")
There are great answers already in this thread but I think the following answer about why some video cards are better at Bitcoin mining than a CPU explains well how comparing different computer architectures can be apples and oranges (video cards in modern PCs work more akin to a super computer than a CPU in a modern PC does): > [@](#): > > One way to visualize it is a CPU works like a small group of very smart people who can quickly do any task given to them. A GPU is a large group of relatively dumb people who aren’t individually very fast or smart, but who can be trained to do repetitive tasks, and collectively can be more productive just due to the sheer number of people. > > It’s not that a CPU is fat, spoiled, or lazy. Both CPUs and GPUs are creations made from billions of microscopic transistors crammed on a small piece of silicon. On silicon chips, size is expensive. The structures that make CPUs good at what they do take up lots of space. When those structures are omitted, that leaves plenty of room for many “dumb” ALU’s, which individually are very small. > > The ALUs of a GPU are partitioned into groups, and each group of ALUs shares management, so members of the group cannot be made to work on separate tasks. They can either all work on nearly identical variations of one single task, in perfect sync with one another, or nothing at all. Trying different hashes repeatedly - the process behind Bitcoin mining - is a very repetitive task suitable for a GPU, with each attempt varying only by the changing of one number (called a “nonce”) in the data being hashed. > > The ATI Radeon 5970 is a popular video card for Bitcoin mining and, to date, offers the best known performance of any video card for this purpose. > > This particular card has 3,200 “Stream Processors”, which can be thought of as 3,200 very dumb execution units that can be trained to all do the same repetitive task, just so long as they don’t have to make any decisions that interrupts their flow. Those execution units are contained in blocks. The 5970 uses a VLIW-5 architecture, which means the 3,200 Stream Processors are actually 640 “Cores,” Each able to process 5 instruction per clock cycle. Nvidia would call these cores “Cuda Cores”, but as mentioned in this article, they are not VLIW, meaning they cannot do as much work per cycle. This is why comparing graphics cards by core count alone is not an accurate method of determining performance, and this is also why nVidia lags so far behind ATI in SHA-256 hashing. > > Since ALU’s are what do all the work of Bitcoin mining, the number of available ALU’s has a direct effect on the hash output. Compare that to a 4-core CPU that can switch tasks on a dime, but has ALU’s in some small multiple of four, if not just four ALU’s alone. Trying a single SHA256 hash in the context of Bitcoin mining requires around 1,000 simple mathematical steps that must be performed entirely by ALU’s. > > That, in a nutshell, is why GPU’s can mine Bitcoins so much faster than CPU’s. Bitcoin mining requires no decision making - it is repetitive mathematical work for a computer. The only decision making that must be made in Bitcoin mining is, “do I have a valid block” or “do I not”. That’s an excellent workload to run on a GPU. > > SOURCE: [Why a GPU mines faster than a CPU - Bitcoin Wiki](https://en.bitcoin.it/wiki/Why_a_GPU_mines_faster_than_a_CPU) ---
**Author:** ![Tim\_T-Bonham.net](https://avatars.discourse-cdn.com/v4/letter/t/46a35a/32.png) [@Tim\_T-Bonham.net](https://boards.straightdope.com/u/Tim_T-Bonham.net)\ **Post date:** [October 25, 2012, 4:32am UTC](https://boards.straightdope.com/t/1990-cray-supercomputer-vers-my-grandmother-s-dell/558644/66 "2012-10-25T04:32:13Z")
> [@RaftPeople](#): > > I’m curious about the supers that aren’t on the top500 list, the ones at NSA or other agencies. > > Has anyone ever heard of any kind of performance from these? I assume they have ones that are more powerful than the top of the top500. No, they don’t. The NSA etc. haven’t made their own supercomputers since the 1950’s. They discovered that the machines they designed & built cost much more than estimated, and ran slower. So in the early 1960’s they switched to buying the newest commercial machnes. Like the CDC 6600, 7600, and then the Cray machines. So by the time the Top 500 list was started, NSA was just using commercial machines (but often the 1st buyer of a new machine, and the most powerful version available). These machines appear in the upper range of the Top 500 list, with sites like Lawrence Livermore, Los Alamos, Oak Ridge, etc. – it’s likely that NSA had a similar machine operating, and might have even had it earlier8. But such machines weren’t public to be listed in the Top 500. - It’s commonly reported that there was a battle between Lawrence Livermore Labs and Los Alamos Labs to get the Cray-1 serial number 001 machine (won by LLNL). But a recently declassified report on NSA computers claims they had ‘the first’ Cray-1 produced. Was there a serial number 000 Cray machine? NSA had a close relationship with Seymour Cray. His machines had a very RISCy design (before the term RISC was even recognized). But while he was eliminating many instructions from his machines, he added one (PopCount) that seemed way too infrequently used to deserve a place in the machine’s instruction list. But that one just happened to be very important to NSA and cryptology work. So it was there. ---
**Author:** ![Francis\_Vaughan](https://sea3.discourse-cdn.com/straightdope/user_avatar/boards.straightdope.com/francis_vaughan/32/3093_2.png) [@Francis\_Vaughan](https://boards.straightdope.com/u/Francis_Vaughan)\ **Post date:** [October 25, 2012, 5:08am UTC](https://boards.straightdope.com/t/1990-cray-supercomputer-vers-my-grandmother-s-dell/558644/67 "2012-10-25T05:08:25Z")
An old college of mine (who did work for defence agencies) once observed that there was a “black” Top-500 equivalent list, and it looked mostly like the open Top-500. Another guy I knew was a hardware maintenance guy for Cray, and lived in a city where there were no known Cray machines installed. But there were lots of government departments. It isn’t just spooks decrypting communications. Classified work is going to occur in just about every scientific and engineering filed as well, and those projects will require access to similarly classified facilities - if only to maintain the secrecy of their own existence. ---
**Author:** ![RaftPeople](https://avatars.discourse-cdn.com/v4/letter/r/6f9a4e/32.png) [@RaftPeople](https://boards.straightdope.com/u/RaftPeople)\ **Post date:** [October 26, 2012, 2:31am UTC](https://boards.straightdope.com/t/1990-cray-supercomputer-vers-my-grandmother-s-dell/558644/68 "2012-10-26T02:31:45Z")
Thanks **[t-bonham@scc.net](mailto:t-bonham@scc.net)** and **Francis Vaughan** , good info. [Previous page](https://boards.straightdope.com/t/1990-cray-supercomputer-vers-my-grandmother-s-dell/558644.md?page=3)