Slashdot Mirror
The History Of Pentium
yootje writes "ArsTechnica is running a story about the history of the Pentium processor. It starts with the original Pentium back in 1993, but it also handles the Pentium II and III. The article goes deep about how the processors are designed and work."
F00FC7C8 ?
I remember exploding many systems running many OSes with that...
Trolling using another account since 2005.
Really, who came up with the name "Pentium"?
It makes me feel old that they now have a histroy for things I was around for the beginning of.
I remember back in the day when my family got a brand new computer with this strange device called a Pentium...And it had Windows 95 installed! This was huge, considering our previous computer had a version of Windows from the mid-80's...Anyway, excuse the rant, it's what I think of when I hear "Pentium 1"
Here are some other cool CPU reference sites:
www.sandpile.org
Sandpile lists electrical specs for lots of CPUs and has links to lots of CPU documents.
http://users.erols.com/chare/elec.htm
Lots of info here about pinouts and electrical specs. I like this one because it lists the initial selling price for the CPUs as well.
--------
It's OK to be social, just don't tell anyone about it.
Got this from the 'Link of the Day' from "The Inquirer". A good comparison of various architectures.
# AL PHA
http://www.microprocessor.sscc.ru/great/s5.html
putting the 'B' in LGBTQ+
The reason Intel broke with tradition and gave this chip a non-numeric name is because numbers cannot be copyrighted/trademarked.
Anyone could sell a "586 Chip": competitive chip makers like AMD and Doritos.
They switched to Pentium so nobody else could use the name.
Ahhh, ArsTechnica ... what a refreshing way to start a Monday than to relive my geek heritage. I still have my first Pentium computer in my closet at home. Large paperweight, I presume, but it may still run Linux. I've been thinking of making a wall-mounted collection of all my used processors for posterity.
I could stand to forget about Win95 though ... (shudders). Nothing worse than having to reformat one's hard drive every 3-6 months!
Author also seems to believe that the P1 went up to 300Mhz, maybe with N2 cooling but I was under the impression it stopped at 233Mhz, with AMD taking SuperSocket 7 speeds to the 500Mhz mark
Music is everybody's possession.
It's only publishers who think that people own it.
Fuck Beta
~John Lenno
the article doesn't tell us when we should expect the Hexium.
Although I grew up on an Atari ST520, later upgraded to a 1040 (eleet) a Packard Bell-produced P60 with 8MB of RAM and a 420MB HD was my first computer, obtained in late 1993. Windows 3.11. Lotta fond memories, even if some of them involve a lot of cursing and head-scratching, most at Windows. Occasionally some weird piece of proprietary Packard Bell technology would rear its head but on the whole it wasn't too bad of a computer.
That computer was eventually donated to FreeGeek - I still have the Atari, though.
Exocet Industries - Taking over the world, one computer at a
Back in 1993
Was that sooooo long ago? I never had an original pentium, as I usually find the cost/performance not usually worth the upgrade and I therefore usually skip a processor generation or so.
- 8086 or was it 8088
- Mac II (i know, it's not a PC, but it kicked ass, and even though I don't have an apple now, I still believe that they are some very nice machines)
- 486 dx-2 66 (now that was a cool sounding name)
- Pentium II (300 mhz)
- Pentium 4 (1.7 & 3.2 Ghz)
Thing is, why do most of us need all of this power? The only thing that has really driven my upgrades has been the ability to play games. Excel worked fine on a PII (even usuing features most 'business' users don't like regression analysis, formulas, etc)Word processors worked fine as well, in fact I miss some of the older processors that didn't try to autoformat every damned thing
Web browsers as well
I know there are security issues with alot of older softwares, etc, but can't they produce a fast low cost computer, w/o all of the bloat. Then everyone could afford a decent computer to do 99.9% of the things they wan't to.
My cousin just bought a $2000 computer and all he want's to do is occasionally surf, rip mp3's and DVD's - could this be done on a pentium or pentium II platform.
Did, I go way offtopic, it's monday.
It's not a complete history as it didn't mentioned:
/. article about MS employee cracking AltaVista computers.
- How Intel handle the Pentium bug. When the FP bug surfaced, Intel grudgingly agreed to replace Pentium chips if it affected a user significantly. My fellow grad student found out the hard way that his Pentium 90MHz he bragged about yielded wrong results in Matlab for his project. He complained to Intel and Intel wouldn't replace it since it was not important. He was a grad student in an engineering school... how was it NOT important to get accurate results? It took a long time and persistence and a threat to complain to BBB to get it replaced. I never trust Intel since.
- Intel v. DEC. The article made it sound as all the architectural "innovations" in Pentium were the result of Intel's brilliance. What about the 10 patent infringements from Alpha that prompted DEC to sue Intel? There was a thread of this in another
I work with a lot of old Intel machines and my general rule of thumb is:
You need something running at 75Mhz to play an MP3
You need something running at 100Mhz to encode an MP3 in less time than it takes to play it.
You need something running at 500Mhz to play a DVD
You need something running at 1Ghz to encode video on the fly.
(note: I know I've played a DVD on a 466Mhz machine, but there are some "complicated" DVDs that take just a little bit more horsepower, so that's why I chose 500Mhz as the cutoff point)
My gut feel is that Mac's can probably do these things with a little bit less (10%?) Mhz since their processor arch. seems to be a bit more efficient.
Is there any way of "easily" understanding how a chip handles out of order dependcies? I've done some 6502 programming (Atari 2600) but the idea seems pretty amazing to me...I guess each instruction can only affect a certain # of registers and memory locations, and if another instruction doesn't rely on those, it's ok to run it prematurely, before the the first instruction...
Well, maybe I've answered my own question, but it seems pretty amazing that you can get improved performance with that, and not having to rollback all the time.
SO YOU'RE GOING TO DIE: The Comic for Dealing with Death
Intel brought us ...the deliberately misleading "the P-III makes your Internet faster!!"
God I remember the hype and FUD those B******ds stirred up with that bloddy ad campaign. I can still hear people walking up to me and asking: "Do you have a PC? What's your pentium?". Calm, calm, think happy... "Two OK!! It's two! And tell all your friends you need a pentium or your computer won't work! BEGONE EWES!!" It hurt to hear that again and again. I just gave up correcting people. They looked at me like I was crazy. Geeze listen to this guy, he dosen't know what a pentium is.
If Intel learned anything in those last few years of the P6 core's life, it learned that clock speed sells
It certainly does, and that's still the one thing that keeps me from buying AMD. When I configure a PC I can choose between a Pentium 2.2GHz, or an AMD 2400. Now how fast is the 2400? I don't know, It didn't say, and that's why AMD is No. 2. That and Intels hugely successful campaign of intel inside, making consumers believe that if hasn't got an intel chip, it won't work. They expect it, like they expect a monitor. Let them pay for their ignorence.
May the Maths Be with you!
[nostalgia]
... when I used to lust, in equal measures, for the hottest girl in my class and the soon-to-be-launched Pentium!!
[/nostalgia]
*sigh*
I had only been in the PC-building business for a few months when the Pentiums came out. I was always really nonchalant when it came to building computers and was certainly not gentle. However, everything I had built up to that point either had the CPU soldered onto the motherboard or someone else had done it because I had never seen a separate CPU.
When the first Pentium-based system arrived at my workstation to build I mounted the motherboard to the case and then put the CPU in place, but it didn't go in very well. I pulled it out and bent the pins back into place and put it in again. It felt like it went in okay.
I took the little arm thing and pulled down to secure it in place and heard a sound, but I thought it was okay... I had never done this before.
I put in the cards, drives and memory and fired the system up... blank screen and then... POP!!! and some smoke.
I didn't realize the CPU had a dot that corresponded with a notched corner indicating how to put the thing into place. From then on I started paying attention to things like that.
The Pentium made me mature as a technician... for about a week; then it was a contest to see how far we could launch them in the air. (kidding)
"I'm a karate man. Karate mans bleed on the inside."
You need something running at 75Mhz to play an MP3
I've found this highly dependant on the input bit rate. With a 120MHz processor, I used to be able to play up to 160kb/s flawlessly, but anything over that would occasionally stutter, and 256kb/s was unplayable.
You need something running at 100Mhz to encode an MP3 in less time than it takes to play it.
What encoder are you using? I use LAME, and that seems to need ~200MHz to encode in real time.
You need something running at 1Ghz to encode video on the fly.
Again: what encoder are you using? With TMPGEnc Plus encoding mpeg2 with the default setting for the motion search precision, performance on the aforementioned celeron suggests I'd need about 1.6 - 2GHz to get it up to real time (for high quality PAL DVD -- should be about the same for NTSC DVD, which has lower resolution but higher frame rate).
1978: 8086 processor is released
1979-Present: Regret
I think many of you will know exactly what I mean.
Rich.
libguestfs - tools for accessing and modifying virtual machine disk images
I don't need to read it, I've lived it.... :)
-m
http://www.invisik.com
My firewall/nat/webserver/voice chat server is comprised of an AMD K6 166 running SuSE 7.2, and has been merrily running disklessly since it was installed more than a year ago.
"The dew has clearly fallen with a particularly sickening thud this morning"
This is the part of hell where one has to use Java products....
I have a 800MHz Pentium based T20 running Websphere Studio Application Developer. 512 MB of RAM. I'm using 1GB of virtual memory when I run my programs. My CPU regularly spikes through to 100%. Its hell on earth. Wait a minute. Maybe I'm dead and in hell, since this misery seems to be constant....
So the answer to your question about why we need all this power is ...Java.
There is no such thing as luck. Luck is nothing but an absence of bad luck.
And to think... my uncle is still using his 75MHz Pentium every day. The funny thing is it still fits his needs and sees no reason to upgrade. It takes forever to boot up and get into his AOL account, but he just leaves the room for a while... watches tv... grabs a snac... and by then it should be there for him. I have been trying to convince him to upgrade for years, but I guess you could say he is getting his moneys worth.
I can think about a few reasons
... but this is what I know from reading various sources
- Expensive
- Intergrated Cache = Expensive Updating
- Too Fucking Hot (I run a Dual PPro and I can't keep this fucker cool even with 5 80mm Case Fans)
Although it did have some good things
- Intergrated Cache = Speedy
- 60 - 66MHz Bus
- Full Speed Bus (unlike the PII)
- Able to run the PII Overdrive and 533MHz Celery's if you got the kit
- Able to run Dual CPU and Quad CPU easy
There is prolly more reasons
Solosoft.org - Your Online Resource to Nothing
The P1 did go up to 300MHz, but it was only sold in mobile forms, for laptops and what-not.
All hail Weird Al Yankovic
SO YOU'RE GOING TO DIE: The Comic for Dealing with Death
I grew up on an Atari ST520, later upgraded to a 1040 (eleet)
;)
Funny, My first PC was the Atari 1040ST with the PC-Ditto hardware mod. Yup, I soldered that NEC V20 daughter board right on top of the 68000 CPU. Funny thing, since the ST didn't have the same hardware limitation the PC had, My Atari turned PC had 704K base memory free... (704K should be enough for anybody, right?
The difference between the 486DX and 486SX was that the SX didn't have a coprocessor. The difference between the 386DX and 386SX was that the SX had a narrower (slower) 16-bit external data path.
The upgrade to the 486SX was called the 487SX, which was actually a full 486DX in a different package. The 387 was just a floating-point processor.
<OT>
I had a friend who bought a Compaq 386 in 1988 to use as a Netware print server for his business. I think it cost $15k, but of course it had 2 full-height 1 GB SCSI disks, 16 MB of RAM, 3 expensive parallel ports and ethernet with a built-in 10base2 transceiver. Also a 387 for some reason. Bought it from him for $10 ten years later.
</OT>
Hands in my pocket
I know it's not nice to want people to die... but I want those people to die.
Does it make you happy you're so strange?
The article lacks a lot of detail, especially about the Pentium I. It makes it look like the "addition of MMX" was to only enhancement of the Pentium I. Instead it went through at least two redesigns and shrinks. First from a BiCMOS based P60 and P66 to the later P75-P200 design. The "addition" of MMX brought many additional tweaks as a far improved branch prediction.
The article does also claim that the Pentium I FPU was sub par. This is not true, in fact the design gets the most out of a stack-based FPU without resorting to out-of-order exucution. The FPU of the much praised contender at that time, the 68060 was as much as three times slower due to lack of pipelining.
Some flaws in the Pentium I designs: Waste of resources for a dual read data cache, which is rarely utilized. Dog slow shift and integer multiplication as compared to motorolas offerings, but intel kept the strategy also in later CPUs.
1. P-Pro wasn't just 256/512 there were 1mb and 2mb versions.
2. P-3 was initially off-chip L2 but later went to on-chip L2.
3. P-2 was available up to 333MHz on the desktop end and 400MHz on the laptop end.
4. It was implied that the SECC cartridge was just on the P-2, the P-3 also used a SECC cartridge and continued even after Socket 370 was standardized.
5. The author said that the P-3 brought the Bunny Suits, no that was the P-2. The P-3 brought us the sock monkey, robot, and even the blue man group.