Comparative CPU Benchmarks From 1995 to 2004

Lux writes "The guys over at Tom's Hardware Guide have been busy recently! They've compared over a hundred different architectures dating all the way back to the Pentium 1 in one huge benchmarking effort. Looking to upgrade an older system? Unlike most benchmarks, which compare modern systems to other modern systems, these charts can help you figure out if the cost of upgrading is worth the speedup or if you should hold off for a bit longer."

Comments

Upgrade

[Anonymous Coward]

I currently have a 486 with an (upgraded) 900MB hard drive, cdrom drive, and a whopping 32MB of ram. And windows 3.1 + dos. What are my upgrade options?

Re:Upgrade

[stratjakt]

A 487 math co-processor will turn it into (almost) an equivelant pentium.

Actually a 486+487 still has enough juice for a homebrewed linux firewall/router, and you can get boards with chips for a buck in the throwaway bin at my local computer shop.

Re:Upgrade

[Anonymous Coward]

486DX had built in co-proc. The 486SX had the co-proc disabled. There is no co-proc chip for the 486's to my knowledge.

Re:Upgrade

[Anonymous Coward]

Go SMP then.

Re:Upgrade

[Zerbey]

Put Linux on it, it'll make a perfectly decent home firewall, dns server, web server and mail server. It'll still have plenty of horsepower left over as well.

Re:Upgrade

[daniil]

I fail to see how installing linux on it is an upgrade.

Re:Upgrade

[the unbeliever]

Because megahertz is not totally where it's at, contrary to Intel's marketing hype. I'm currently running an Athlon XP-M 2500+ overclocked to 2.4ghz, and it performs faster than a 3.2ghz Pentium 4. An Athlon 64 3200+ runs at 2.2ghz iirc, and outperforms a 3.2ghz p4 by an even larger margin.

With multi-core chips and on-die memory controllers, the benefits of performance will be felt, even if the clock speed is constrained to 4ghz for now.

Re:Upgrade

[Slime-dogg]

Another one of those people who think that clock speed equates to performance. :sigh:

I'd take a 1 Ghz proc that executes 5 ops/clock over a 3 Ghz proc that executes 1.5 ops/clock, if I were given a choice. Price is also a major determinating factor for me.

Re:Upgrade

[jejones]

Clock speed != performance, no matter what the Blue Man Group might want you to think.

Re:Upgrade

[ahsile]

If they can't pump up the MHz they'll get you with everything else:

"Anti-Virus Projection" - AMD & NX Flag (Earlier today)
"Multi-Core chips"
"Dual processors"

etc, etc. The industry will continually find another reason for you to upgrade. And I'll keep doing it, because I like to be on the Bleeding Edge (TM).

Re:Upgrade

[stratjakt]

This site says different, it lists:

80487 Intel 487 SX CPGA SZ494, USA

Another forum I found has this to say, which is interesting (take it with a grain of salt, I don't vouch for what "RatBoy" says)

Intel created an inferior version of the CPU in the SX, but remember they did the same thing with the 386 SX and DX. There was a nasty rumour that the 486 SX was created only because a batch of 486 chips had faulty FPUs and this was a way for Intel to sell damaged goods and still make some money on them. This rumour was helped out when Intel introduced the 487 math co-processor for the 486 SX. It turned out the 487 was really a 486 DX with one extra pin whose job it was to completely shutdown the 486 SX when you plugged the 487 into your motherboard next to the 486 SX!

Either way, there was (is) a 487.

Re:Upgrade

[mrak and swepe]

Dude; you've just said something Not Good about Linux.

The only question now remaining is do you end up as -1:Flamebait, or -1:Troll?

Re:Upgrade

[barzok]

As others have pointed out, MHz isn't the only factor in speed. I don't understand the obsession with speed in the first place - if the box works, use it. If it's too slow to do what you need, upgrade it.

I went from a 486-66 to a P133 to a P2-266 (doubling clock each time), then a 1.33GHz. I don't use any "rule" based on performance gain - I just upgrade when I have the money, and I have a need. That 1.33GHz is going on 4 years old and does everything I ask of it (thankfully I spec'd it out well enough that it's never run short on RAM), but it'd sure be nice to be able to play HL2 or Doom 3. I've put exactly $100 into it for upgrades - a second hard drive, because I needed space (the 3 failed motherboards are another story, however).

Re:Upgrade

[wfberg]

Dual processor is very, very useful. Even for lowly non-server use.

You see, I have a dual cpu system, and for the longest time I thought XP must be the most stable windows OS evar!

Turns out the OS never really crashes because there's always a cpu left to bring up the ctrl-alt-del screen with, so you can kill all the OS processes on the other CPU that DID crash..

Re:Upgrade

[Boronx]

When we got our first Athlon 1 GHz a few years ago, it was about 3 times faster at floating point operations than the P-3 500Mhz that had been our top number cruncher.

Re:Upgrade

[BinLadenMyHero]

A 486+487 is still far away from a Pentium.
Anyway, how will a math coprocessor help firewall or router software? It will help you to play Quake I, but will make no diference for a program that is not intensive on floating point math.

Re:Upgrade

[rainman_bc]

The reason that we're all obsessed with Mhz is that it's the only performance guage offered.

If for example, processor makers started guaging their performance in MIPS (or BIPS) or something, it would make more sense I guess.

(someone will correct me if I'm wrong anyway lol)

Re:Upgrade

[secretsquirel]

Cool it with liquid nitrogen and overclock the hell out of it!

Re:Upgrade

[noyren]

I fail to see how installing linux on it is an upgrade.

your obviusly new to slashdot

Re:Upgrade

[Dysan2k]

Well, it is if you're running DOS 6.xx + Win3.x or 95. Namely full 32-bit support, native multitasking, better VM; over all, far better tools to work with under Linux than older offerings. Just comes down to what you are wanting to do.

I still use an old P5-133 w/ 80MB just to do general doc writing and such. I've got it working plenty fast with Mandrake 9.

Re:Upgrade

[peragrin]

I see you got a dell as well. Congradulations on buying the cheap side of motherboards.

Actually my Dell never had a probelm. Of course i didn't spec out enoguh RAM, and can't seem to part with the $200 for RDRAM needed to run Doom 3. That and the $75 for the video card upgrade. Ah well, I heard it sucks anyway.

the trick with MHZ is that Intel reinforced that more mHZ is more speed. Look how many people laughd at Apple for years when the G4 running at 400mhz was out performing 1 ghz intel chips.

Simple fact is that you can do more things if you get out of the one op per clock routine.

Re:Upgrade

[stratjakt]

IIRC, the TTL of an entry in iptables is a time_t value which is floating point, so an iptables based router would be doing a lot of trivial floating point work to decide which connections to keep.

I dunno, I got that from the coyotelinux (and other LRP based distros) minimum requirements, where it says you need an FPU (486DX/25 minimum requirement). I suppose that's just how they compiled their kernel.

Someone recompile and try it out on an SX and let me know.

Re:Upgrade

[GlassHeart]

If for example, processor makers started guaging their performance in MIPS (or BIPS) or something, it would make more sense I guess.

It would make about as little sense. On many CPUs (particularly the CISC CPUs), instructions take wildly different amounts of time to complete. A NOP might complete in one clock cycle, while an obscure legacy instruction might take twenty. Running only NOPs, the CPU would be 1 BIPS if driven at 1 GHz. Running the other instruction, it'd be 50 MIPS. Somewhere in the middle would be the truth.

The fact is, it is next to impossible to accurately digest CPU performance down to a single number that can be comparable across architectures and across the variety of actual usage. Even something as obvious as instruction cache size has a different real world effect depending on the sizes of your instructions!

Re:Upgrade

[daniil]

It's probably an urban legend, but i've heard of a guy who overclocked a 386 to run at 300 MHz. For a few seconds before the meltdown.

Re:Upgrade

[upsidedown_duck]

I tried digging out an old 80MHz 486 and put Linux on it...it was soooooo slooooowwwww. 4200RPM (or was it 3600?) hard drive didn't help.

The thing is, at the time a 486 was current, so was FVWM. Our expectations just aren't backwards compatible.

Re:Upgrade

[upsidedown_duck]

Okay...but my credit limit isn't high enouth for a Sun Fire 4900.

Re:Upgrade

[Anonymous Coward]

...do they have blue penises, too? How do they share Smurfette?

Re:Upgrade

[Zerbey]

Are you sure? A 486-80Mhz will run slow with a modern GUI such as KDE or GNOME. However, as a server it will run very fast. Never underestimate the power of a 486 :)

Re:Upgrade

[upsidedown_duck]

Are games currently multi-threaded enough for multi-core to have any effect? Do games developers even want that debugging headache?

Re:Upgrade

[the unbeliever]

No, but games aren't currently *that* CPU dependant. If you have enough memory bandwidth and video card power, you can run almost any game now.

Best example is Sims 2. If you have a T&L Video card, you can run the game with a 900mhz processor. If you don't, you need a 2.4ghz processor.

Re:Upgrade

[all about the loo]

I'm running a fanless, diskless 486/33 w/ 12MB RAM as fw/router, serving dhcp, ntp, printservice and dns for 2 separate internal networks, routing to my companys broadband connection. Another one (with disk and a little more memory) serves NIS/NFS. Works like a charm, reliable, quiet and fast.

Re:Upgrade

[alex_ware]

Does the -M- part of the XP2500+ matter as I just have that and how do you overclock it???

Re:Upgrade

[the unbeliever]

The "M" designates "Mobile" which means the multiplier isn't locked in the chip. I'm running at 12x200mhz, the default is 11x166. To overclock a standard athlon xp, you're stuck with nudging up the bus speed or using an unlock kit.

Re:Upgrade

[alex_ware]

Does overclocking the -m- break the warranty and does unlocking the non m break the warrenty.

Re:Upgrade

[the unbeliever]

Yes to both questions.

Overclocking breaks warranties on all chips.

Re:Upgrade

[alex_ware]

Thanks.

Re:Upgrade

[timeOday]

Because megahertz is not totally where it's at, contrary to Intel's marketing hype.

Somewhat true, but historically most cpu improvement was due to clock speed increases, which have slowed way down.

CPUs just aren't getting faster like they used to. We've hit something of a wall. It would be interesting to seem Tom's benchmark charts plotted against release dates.

The move to multiple cores is a white flag waving. Two cpus aren't in any was as good as one that's twice as fast.

Re:Upgrade

[Surt]

Most games are multi-threaded just a little bit, but not enough for multicore to help rather than hurt. They'll certainly consider multicore in next generation titles, but most titles today aren't anything like cpu bound (they're all GPU bound).

Re:Upgrade

[Zork the Almighty]

I put Gentoo on my 486 DX 50 w/ 8MB of RAM. It actually worked pretty good as a terminal. My wife won't let me keep it :(

Re:Upgrade

[isecore]

And I'll keep doing it, because I like to be on the Bleeding Edge

I personally feel that it's more a matter of "I like being Intel/AMD's bitch"

Note though that I say this in the most humorous sense I can muster. I'm a sucker for faster/cooler/flashier computer stuff, and I suppose most of /. is the same way.

(although I've tired long since of Intels bullshit, these days I'm an AMD-only bitch.)

Re:Upgrade

[tylernt]

I wouldn't advise a GUI on an older machine like that. I used to run a 486DX2 66MHz (I think) with 24MB of RAM and an old 512MB hard drive as a web/ftp server. Web pages were served up pretty quick but ftp was a little slow when a client first connected because Linux had to swap some things out to disk. Other than that, it did just fine.

On the other hand, my current Pentium 166 with 32MB of RAM is an absolute dog when I load up X and Blackbox. I think it's a combination of swap thrashing and slow video (pre-AGP vintage). Moral of the story, a GUI is way too demanding for these older, slower machines unless you trick them out with lots of upgrades.

Re:Upgrade

[Anonymous Coward]

historically most cpu improvement was due to clock speed increases

Define "improvement".

If you're measuring CPU horsepower, increasing the CPU clock won't give you a linear increase in performance, but will result in shorter lifespan, and more heat.

Look at the benchmarks - a P4 whose clock speed is 380 times that of a P100 only affords a 74 times performance increase.. that's a 500% drop in performance per tick.

Two cpus aren't in any was as good as one that's twice as fast.

Define "twice as fast" - if you're talking Mhz, then you're just full of shit.

Engineers need to look at making the pipe deeper, rather than simply trying to up the MHz.

Re:Upgrade

[Anonymous Coward]

I stuck my dick in your mother.

Oh, and by the way, you're a fucking moron. Never post here again you unfunny faggot.

Re:Upgrade

[tetsuji]

That looks like my webserver. Except, of course, that mine's running Linux.

Re:Upgrade

[WMD_88]

You're thinking of the 247MHz guy. It was definately fake; he put the motherboard in a freezer (wouldn't work), and he claimed to be able to play Quake and Half-Life on it, which also isn't possible because the 386 lacks an FPU.

Never mind that the multipliers would be through the roof, on a box from the days where multipliers weren't even needed at all sometimes.

Re:Upgrade

[Vaystrem]

That's kind of a flawed logic because your linking performance directly to MHZ.

I myself went from a 386 SX 20 -> 486 dx2 50 -> Pentium 233 MMX -> Pentium II 300 -> Athlon 850 -> Athlon XP 1800+ -> Centrino (Pentium M) 1.4ghz.

The 486 -> 233 had the level of performance boost you are describing. The Pentium II 300 -> Athlon XP 1800+ Also did.

It wasn't just the mhz. The improvements in architecture (RAM/FSB/Hard Drives themselves, Video Cards, etc)

Myeslf I'm incredibly happy with my little Thinkpad, its quiet, runs forever on batteries, and performs abit better than the Athlon XP 1800+.

You are right in stating that for 'web browsing' and the like a 3ghz+ CPU is not required. But to have a quiet computing environment that runs cool, I'm willing to pay more for that. Making the Pentium M the only Intel chip I'll consider, can't wait for the proper desktop boards with PCI-E to come out.

Either way you must look at all the system variables not simply the MHZ. I'm sure that going to a Dual CPU Athlon64 or even next generation pentium @ 2.5->3.0ghz will provide that significant boost in performance you're looking for. The question really is, whether the apps you are going to use will show it - or whether the apps you use need it.

Re:Upgrade

[Anonymous Coward]

And I'll keep doing it, because I like to be on the Bleeding Edge (TM).

Geek penis envy?

Okay, enough trolling for the day.

Re:Upgrade

[C0vardeAn0nim0]

'twas a i486 with a fully functional FPU and a Voodoo video card, so running half-life wouldn't be so dificult if it was really at 247 mhz.

the project, of course, was a joke. it was called E.U.N.U.C.H. for "The Extreme Use of Nearly Universal Cooling Hardware", the page is here. enjoy.

Re:Upgrade

[Anonymous Coward]

Because Linux makes Ketchup better, apparently.

Re:Upgrade

[ksheff]

so what about those of us that were running X11 on those machines when they were new? (FWIW, I have a P166 w/80M running Gnome 1.4 just fine).

Re:Upgrade

[Anonymous Coward]

Look how many people laughd at Apple for years when the G4 running at 400mhz was out performing 1 ghz intel chips

Yeah, in certain obscure PhotoShop filters, but certainly not significantly elsewhere, otherwise the Athlon wouldn't have spanked the G4/G5 silly clock-for-clock.

Re:Upgrade

[plover]

The obsession with speed is based on what you're doing with it. I have done three upgrades recently that were strictly speed based.

1. At work, the project we're working on took 45 minutes to perform a full compile on our two-year-old 1500GHz P4s. 12 developers, each chewing up a substantial fraction of the day waiting for compiles, is not a great use of money. Replacing them with dual 3.6GHz P4s dropped compile times to 9 minutes. Even at Dell's price for those machines, the ROI will be taken care of in months.

2. At home, I've been playing America's Army for a couple of years now. It's the only graphics intensive game I play, but I really enjoy it. I had an Athlon 1200 that was just on the cusp of "OK" performance. But then my monitor blew out, and I replaced it with a large LCD flat panel. The change from a 1024x768 to 1280x1024 screen resolution meant that the game was no longer playable, unless I dropped back to 1024x768.

Having my cake without eating it was leaving me hungry. So, I upgraded to an AthlonXP 2400+. The frame rate came up somewhat, but the graphics quality was still quite poor. About this same time, the next version of the game came out with vastly improved graphics (and vastly heightened minimum system requirements.) I stuck a Radeon 9800 on it and it's now able to play at a frame rate that doesn't suck. Now I'm happy, and have no firm plans to upgrade it (until AA 4.0 is released and requires a 4GHz machine.)

3. On the other hand, last year my kid upgraded that old hand-me-down Athlon 1200 to an Athlon 3000+ and added a Radeon 9800. He then proceeded to become a serious gamer. Six months later he wanted to sell or trade his almost-new card to get an ATI X850 because some website published a framerate improvement in Halo from like 24 to 48 FPS. It took a lot of convincing to get him to understand that would be a really poor use of his finite supply of money. It finally sunk in that he should at least wait a year or two to upgrade. In the mean time, he's amusing himself by adding watercooling and overclocking what he's got.

So, most speed-driven upgrades have their basis in some kind of reality. Did I need to upgrade the machines at work? Yes. Did I need to play America's Army at home at a higher resolution? Of course not -- but I wanted to, and I could afford it. Did my son need to up his frame rate from "definitely sweet and playable" to "buttery-smooth and ultra playable?" I obviously didn't think the payback was worth it, and I've convinced him to delay a decision (mostly based on the assumption of future price drops.)

Re:Upgrade

[tylernt]

Well, I suspect the 80MB vs. 32MB makes a big difference. The real question is though, are you running the versions of X and Gnome that came out the same time as your P166? Newer versions tend to add a lot of cruft.

Re:Upgrade

[Anonymous Coward]

AFAIK floating point is forbidden in kernel space.
But a FPU makes a big difference if you try to run Squid.
Every second it is calculating an exponential function for every cached file to determine if it is expired.

Re:Upgrade

[SmittyTheBold]

380? Have you even considered doing the math here?

3.8 GHz is equal to 3800 MHz. So that's 38 times the clock rate for a 74x performance gain.

Unless there's a secret 38 GHz P4 out there that I didn't know about...damn overclockers.

And making the pipe deeper is exactly what you DON'T want. A shallow pipeline is good because it makes the penalty for errant branch prediction. A long pipeline means you have to throw away a LOT fo work when the processor guesses wrong. You may have fourteen instructions that are executing, but since they were predicated on the code branching a certain way all the work must be re-done. That's why people complained about the longer pipeline when the P4 was initially introduced - it allowed the clock rate to be cranked, but such things are always a tradeoff.

Re:Upgrade

[SmittyTheBold]

Are you sure HL2 won't run? This is just me being uninformed, probably - but unless there's a software limit, I think your CPU should be able to do it. My Athlon XP 1800+ (a 1533 MH CPU) does a good-enough job of it. Of course, you'll need a decent video card, but my GeForce 4 does the trick.

Re:Upgrade

[barzok]

I see you got a dell as well. Congradulations on buying the cheap side of motherboards.

Actually, it's a "beige box special" (well, silver) from a local shop. The first 2 boards he put in it had a transistor fry after a year or so each, then I replaced it with a different make/model board altogether, and that one similarly cooked. I got a used PSU (thinking my PSU was overvolting the motherboard) and board that met my specs from a friend and have been stable since.

Re:Upgrade

[barzok]

I'm pretty sure my GeForce2 MX can't pull it off.

I have downloaded the demo and intend to give it a shot though.

Re:Upgrade

[Anonymous Coward]

Yeah, as long as you don't actually use it as a file server or have a fast broadband connection. ISA bandwidth and interrupt servicing overhead can become a bottleneck very quickly.

But for light usage it'd be fine.

Re:Upgrade

[mattyrobinson69]

setup a framebuffer console with the boot logo penuin - she wont let you get rid of it then

Re:Upgrade

[Lehk228]

depending on your Video card you can probably play Half Life 2, I run my CPU (athlon 2200+) at 1.33 Ghz rather than the spec'd 1.8 to keep heat and fan noise down, and my system handled HL2 just fine.

Re:Upgrade

[SmittyTheBold]

Yeah; the video card will very likely hold you back. It's pretty easy to get a GF4-era card inexpensively now, though.

Re:Upgrade

[Anonymous Coward]

I got to admit that I found those charts very interresting. I have a bunch of boxes and the latest I bought like 5 years ago. Like, I have 2 Celeron (600 and 700) and a P3 550.

No doubt that buying the brand new lowest speed P4 available will give me a Weeehaa! impression, but lately I was wondering if I could upgrade the Celeron boxes to a 1.x Ghz cpu and get that same impression.

The chart showed me that I would get about a 20 to 30% boost. I think I'd rather speend a little more and get a 1000% boost. I'm due anyway.

Thanks for the chart.

Re:Upgrade

[robnauta]

I finished Half-Life 2 on my XP 1700+ (1.43 GHz) with a radeon 8500. That's good enough to play reasonably smooth and it looks pretty enough.

CPU wise you're ok. The 8500 is old but the 9000/9200 cards are essentially the same chip, only faster and those can be had for $30-$40. Spend a little more for something like a 9550 or 9600SE and you're in business.

Re:Upgrade

[ksheff]

It's a P166 laptop that used to have a 'designed for Windows 95' sticker on it. Gnome hadn't even started when this thing was built and unfortunately, because of the video chipset, it's stuck on whatever the last version of the XFree86 3.x was. The 80M helped a lot mainly for any mozilla based browser. Ximian GNOME 1.4 still worked ok w/ 32M as I recall.

Heat Output

[eln]

It's easy...if the room is getting a little too chilly for my liking, I upgrade to a faster processor. Problem solved.

Re:Heat Output

[deathazre]

I guess you must be a pentium 4 fan then?

I too use my computer as a spaceheater, usually `emerge -auD world`. Shame it only puts out about 250w total.

Re:Heat Output

[mOoZik]

Imagine a Beowulf cluster of those! ;)

Re:Heat Output

[operagost]

My circa-1994 Alphaserver is the hottest computer in the house.

Re:Heat Output

[Anonymous Coward]

This is actually a serious problem for me being in Phoenix Arizona. It can get a little toasty in here, and as CPUs get faster and hotter (at least Intel chips anyways, AMD doesn't have as bad of a problem) theres nothing you can do as cooling solutions don't eliminate the heat, rather they just move it elsewhere. The worst part is theres nothing I can do about it.

Re:Heat Output

[secretsquirel]

You could get an air condioner.

Re:Heat Output

[spitefulcrow]

My Athlon 2600+ is good at being a space heater when I run emerge -uD world! But the Thermaltake fan I have on there doubles as a jet engine. 5000 RPM. Does a great job of moving the heat out to the room though.

Re:Heat Output

[heresy_fnord]

Just use a new P4 and you can not only warm you room up, you can catch it on fire.

Re:Heat Output

[Anonymous Coward]

Everyone is a fan of the Pentium 4. They are yelling over the noise of the fan too.

Re:Heat Output

[utlemming]

In my college apt in Idaho (brr...South Eastern Idaho can get quite chilly) my room mate and I leave the heat off during the winter. My P4 and Athlon system do a great job of heating the bedroom. Through in his P4 laptop and it is comfortable. During the summer we need to put in an air conditioner, otherwise it gets unbearable in the room.

Re:Heat Output

[WMD_88]

Happened to me...I had a Pentium Classic 166 in my room, with the A/C vents mostly closed. I upgraded to a P4/2.8e (damn me...i want a P-M), and I had to open most of the vents to get the room back to the same temperature. And this is with the CPU fan running at only 3,000RPM. :/

Re:Heat Output

[Entropius]

I use SpeedswitchXP as an adjustable space heater on my Athlon 64 laptop. At 800MHz it puts out very little heat at all (underclocked and undervolted), but at 2.2GHz it generates a fair bit of heat.

Re:Heat Output

[mysticwhiskey]

What?!?! I can't hear you over my 11 fans that keep my processor cool. You'll have to speak... WHOOOOOSH

Tom's slashdotted?

[dreamchaser]

A /.'ing that I can actually cheer for!

Re:Tom's slashdotted?

[mOoZik]

No...I can still see it fine. It's actually pretty fast, too.

Benchmarks, shmenchmarks

[stratjakt]

Artificial benchmarks tend to exaggerate minor differences in speed that aren't noticable or relevant in human time.

The best analysis of whether you should upgrade is a subjective one. Sit down at the computer. Does it do what you want or not?

Benchmarks tell me my Radeon 9800 is horribly out of date and imply its too weak to play any modern games. But I know from experience, that's bullshit.

Re:Benchmarks, shmenchmarks

[JustinXB]

*sits at his Macintosh from 1984*

I can honestly say I don't want to upgrade.

Re:Benchmarks, shmenchmarks

[araemo]

Benchmarks tell me my Radeon 9800 is horribly out of date and imply its too weak to play any modern games. But I know from experience, that's bullshit.

I'm somewhat curious what benchmarks tell you that, since the benchmarks I read(Most on www.anandtech.com) tell me my Radeon 9700 Pro is still capable of chugging out a playable FPS in most current games, and my personal experience says it's more than capable(Since I run at a slightly lower resolution than their current 'low res' benchmark. ;P)

Benchmarks are usefull tools, if they are presented and read right.

Re:Benchmarks, shmenchmarks

[adam31]

Totally.

I didn't see the Doom3 benchmark anywhere!

Re:Benchmarks, shmenchmarks

[Anonymous Coward]

Benchmarks tell me *my* Radeon 9800 pro is out of date and too weak to play modern games.
Based on my Doom3 high-detail performance, I'd tend to agree...

Re:Benchmarks, shmenchmarks

[tigeba]

"Benchmarks tell me my Radeon 9800 is horribly out of date and imply its too weak to play any modern games. But I know from experience, that's bullshit."

Freecell is not a modern game.

Re:Benchmarks, shmenchmarks

[MicroBerto]

Agreed. My CPU just turned 5 years old.

That's right, I'm a slashdotter with an AMD Athlon 550mhz, 384MB ram, and 80gb hard drive (the latter 2 were obviously some small upgrades).

This does everything I need, why should I spend money on it? It plays music, is fine for my homework, IM, web browsing, and plays *cough* videos *cough* just fine. In the meantime, it's also my server running SSH, Samba, Apache, ProFTPD, etc...

I'm now at the point where I refuse to upgrade until it melts down on me. It's been this good to me, so I'm going to keep using it until forced out. I obviously don't play new games.

Re:Benchmarks, shmenchmarks

[MicroBerto]

Another theory of mine - Most people getting new computers don't NEED new computers - they need new operating system installations (haha sometimes a completely different operating system).

So, in order to combat a cyclical chip/semiconductor market, I propose that chip and PC companies artificially prop up the demand for their products - by riddling the world with slow-you-down spyware/adware/etc programs!

Joe Sixpack doesn't know it's his software. He just knows that his 2 year old computer is slow as hell right now and that he needs a new one! It doesn't matter that all he does is e-mail and web browsing...

User unawareness keeps the PC market chugging, and I see no reason to believe why some PC and chip manufacturers don't absolutely love all the crap that clogs Joe's system.

Re:Benchmarks, shmenchmarks

[rxmd]

*sits at his Macintosh from 1984*

I can honestly say I don't want to upgrade.
--
For as long as I can remember, I've had memories.

I believe you.

Re:Benchmarks, shmenchmarks

[doublem]

Your computer.

It does everything you need, at a speed you are happy with.

As long as your data is backed up and safe and security issues are taken care of, I see no reason to upgrade.

Re:Benchmarks, shmenchmarks

[Anonymous Coward]

"Another theory of mine...Most people getting new computers don't NEED new computers...I propose that chip and PC companies artificially prop up the demand for their products"

How insightful... i dont think anybody has ever thought of this before

Re:Benchmarks, shmenchmarks

[doublem]

And if it does everything you want it to, you shouldn't upgrade.

Re:Benchmarks, shmenchmarks

[Anonymous Coward]

Or have 1/2 moderation and display it. Half of the guys argument is actually thought out...the other half is bullshit.

Re:Benchmarks, shmenchmarks

[Anonymous Coward]

Hey,

I setup a Dell L400c (400 Celeron and 810 chipset) with 128MB of RAM. It surpriseningly has successfully run VCDs, SVCDs, XviD, and DivX, full screen, with no problems under the latest OpenBSD running KDE. No DVD drive so I was not able to test that. Considering the Windows drivers for the 810 video are probably better accelerated for video than X Windows I'm sure this machine could do even better. I was not able to test 64MB as the OpenBSD gart driver seams to be finiky in its ability to allocated the needed 4 or 6 MB for X Windows. Even on 128MB I have to usually start X Windows right after boot up.

Re:Benchmarks, shmenchmarks

[angle_slam]

The best analysis of whether you should upgrade is a subjective one. Sit down at the computer. Does it do what you want or not?

OK, you sit down at your computer and it does not do what you want. What do you do? Buy every video card until you find one that "does what you want"? Or do you go to Tom's Hardware or Anandtech and use their benchmarks as a guide to what to get?

Benchmarks are not the end-all of buying computer products, but they are certainly useful

Re:Benchmarks, shmenchmarks

[fontkick]

I agree, my GeForce Ti4200 plays Half-Life2 extremely well.

Re:Benchmarks, shmenchmarks

[Lehk228]

you are the only other person i have ever seen postin that they have a Radeon 9700 Pro, I have not tested it on doom 3 but I know it does just fine with Half Life 2 and UT2004.

Re:Benchmarks, shmenchmarks

[aardwolf204]

Got a radeon 9500 pro here, been playing doom3, ut2k4, and hl2 and it works great. had to tweak just a *bit* to get doom3 smoother but for the most part I cant complain when your still getting 50-60 fps in a 2 year old card. I'm still getting my $200 worth. Maybe I'll upgrade in a year to whatever they got for $200. I'm sure my bench marks and yours are VERY similar :)

Re:Benchmarks, shmenchmarks

[Anonymous Coward]

The best analysis to decide when to upgrade is when the minimum requirements of most new games or software describes the system that u have...

Well

[0racle]

I went from a 486 to a Sempron 2500+. Unfortunatly the artical doesn't go back far enough so I can't tell if it was worth it.

Re:Well

[SillySnake]

It depends heavily on if it was a DX or SX chip.

Re:Well

[0racle]

486/33 DX. Nothing but the best man.

Re:Well

[SillySnake]

It ran wing commander, what's all that mattered :)

Re:Well

[red_dragon]

You could do a bit better and get a 486DX-50. The problem was finding a motherboard and memory that could run fast enough for the processor's front side bus. They were also quite a bit more expensive.

Re:Well

[Anonymous Coward]

Well you'll finally have the CPU to run a spellchecker so you will write ARTICLE instead of ARE-TEE-KAL.

Re:Well

[Anonymous Coward]

I don't understand why you are so obsessed with 486, I have only a 386 (damn those rich kids with their sound cards!!) and I can play every LucasArts adventure game or X-Wing, Tie Fighter... I don't need more than 20MHz for this.

Re:Well

[IamNotWitchboy]

That's why you bought a Sempron, right?

Re:Well

[Omestes]

Man I remember sitting around LUSTING for one of those when they came out, and I was still running my 286, which was a big upgrade from my poor or 8086. My freind got one, and I was in awe of how responsive it was with win3.11. It was quite a gaming machine. It played that silly pipe game like a dream!

Then I got a P1 60 (66?), and laughed at him for hours, putting his manhood to shame.

Re:Well

[Zorilla]

Ahh, what fun.

286/13MHz + Wing Commander = Too slow (and no control stick sprite drawn)

386DX/40MHz + Wing Commander = Way too fast (but control stick was drawn)

Re:Well

[C0vardeAn0nim0]

until the moment he found that your CPU had that horrible division bug...

Re:Well

[higuita]

well, i'm still using a 486 as my main computer...

not joking, its a pet computer, with more than 10 years:

amd 486dx5 (aka 5x86) @133, overclocked to 160Mhz, bus 40Mhz
64Mb EDO ram (max for the motherboard and chipset)
1 80G IDE HD, 2 SCSI HD (20Gb and 4Gb)
1 SCSI CDRW
matrox millenium PCI graphic card
3Com PCI network card

it is running a slackware 10.0, kernel 2.6.9, X11 with fluxbox, dillo, sylpheed, xfe, alot rxvt
running in background samba, cups, apache, ssh, mysql, privoxy, spambayes,nfs and postfix

it have some users and its also my main server

it have many tuneup so its dont waste cpu cycles

for normal using (web, mail, system manager, etc) is still very good, not that diferent than a moderm machine

now if i try to compile anything, well... i have to wait, so i only compile things during when i'm sleeping or before leaving for work
some times i turn on distcc and my duron 700 and laptop at 700Mhz give a help
algo, gpg trustdb checks also take long time, and anything that last more than 10 seconds in a moderm machine

by the way, the 2.6.9 kernel took about 8 hours (or more, can tell for sure) to compile

i'm using about 400Mb of swap, in the scsi drive, so the low memory is not that much a problem unless if i try to use too much things at same time
also, i search and test alot of apps to see the lighters and fasters, check all options in programs and servers to see the effect (i found that some little options eat ALOT of CPU, while others make almost no diference)
its great to test server daemons in higher load, i can see that some daemons are junk, but with moderm machines people cant see that, while others are still very complete and alot faster

it still very stable, very usable and its my favorite computer... that is why i still use it as may main machine, and not the others near it that are fasters with more memory
i also like to recover old computers to use for what ever people around me need

Re:Well

[0racle]

The only reason that I had to replace the 486 was that the disk controller failed on it, otherwise it would still be working away.

Slashdotted

[lgbarker]

I wonder what hardware they're using to run Tom's site?

Re:Slashdotted

[The Snowman]

I wonder what hardware they're using to run Tom's site?

Tom uses several of these. He has multiple dedicated boxes with this company (the same one I use, but I am on shared hosting). This host uses FreeBSD, so maybe his site died along with BSD? :-)

Re:Slashdotted

[adeydas]

whatever it is, it sure isn't /. proof.

Re:Slashdotted

[Anonymous Coward]

Linux, that's why it's slow.

This is only covers 1999-2004

[Anonymous Coward]

This seems to be the second part of a 2-part article. Does anyone have a link with the first part (1994-1999?)
I just can't find it.

Re:This is only covers 1999-2004

[Lux]

Sure. I had the exact opposite problem... I went looking for the graphs, and couldn't find them because I wound up in part 1. :)

http://www.tomshardware.com/cpu/20041220/index.h tm l

Isn't this getting a little absurd?

[tom1974]

The articles not even up 3 minutes and its slashdotted already!

3 minutes, as i'm writing there're 2 comments. This ain't right.

No Apples?

[WormholeFiend]

They must've dropped them on the road on the way to the benchmarking lab. :(

would be nice

[ID000001]

If they incluce Cryix, VIA C3, Trans processor. Possibly event a G3 G4 or Alpha and Sun system as references to see how far Processors development have gone instead of making it strictly x86. Then again. Tom's hardware is usually just x86 site.

Re:would be nice

[oberondarksoul]

Then again, if the article's intention is to help you decide how to upgrade an older system, then it's x86 all the way. AFAIK, you can't slap an Alpha into an old and tired 486 and expect it to work - best to show where someone could reasonably expect to upgrade whilst keeping current hardware.

Re:would be nice

[Anonymous Coward]

Then again, they have a chart of (sic) ALL CPUs, which is strictly x86. Amazing how some folks can't see outside their own parochial little worlds. Mother of all, indeed!

Re:would be nice

[LuSiDe]

Exactly. They claim this is 'the mother of all CPU charts' and on page 2 they say they have a complete chart from year X to Y yet they evaded other x86 processors which are not from AMD and Intel such as Transmeta's Crusoe, RISC processors (MIPS, POWER, ALPHA, SPARC, PA-RISC). These processors were still popular in the 90s. Some still are, although not in consumer market. They're perfectly aware of at least the ALPHA given they state that in page 1.

I sended a similar message as here above as feedback and asked wether they'd made their statements more clear or graph more complete, but i'm not holding my breath. Not to say its not a useful article, its a useful article to compare the 2 market leaders; Intel and AMD.

No Response

[Anonymous Coward]

Looks like Tom needs to upgrade!

Fixed link

[Anonymous Coward]

Whoops, pasted the wrong wikipedia link. The correct one is Intel 486

Re:Fixed link

[spac3manspiff]

Well the clock speed of ketchup could be comparable to the 486.

Re:Fixed link

[LiquidMind]

"Well the clock speed of ketchup..."

African or European?

Re:Fixed link

[mOoZik]

African ketchup is non-migratory.

Re:Wow

[Anonymous Coward]

With the amazing technology of "subscriptions," links can now come to you pre-slashdotted. Truly, a major advance in modern science.

I see how this fits

[Wrexs0ul]

So YOU'RE the one hosting that site. Fastest slashdot effect ever.

-Matt

Upgrade

[FiReaNGeL]

Back when I upgraded my 386 16 Mhz, I told myself that I'd upgrade every 10x in performance gain. I upgraded to a Pentium 90 Mhz, then to an Athlon 900 Mhz. It seems that with the recent troubles of AMD/Intel at breaking the 4 Ghz barrier that I won't keep my 'promise' anytime soon, sadly.

How will they keep their market alive if they can't upgrade the performance? Its not like CPU chips are burning easily anyhow... so why get a replacement if the performance gain is not worth it? (Especially for web browsing / text editing only folks who upgrade based on marketing ONLY... yes! 3 Ghz more will make your internet go faster! Heh)

turns out

[2MuchC0ffeeMan]

turns out they left the pentium 1 in the server, so it's dead now... they'll figure out the cost of upgrading it later.

Already done

[Anonymous Coward]

You can get this kind of info elsewhere

100 architectures?!

[Jhan]

Actually, they only benchmark one architecture, x86. A real shame, I would love to see a thorough comparison of *multiple* processor architectures over a long period of time.

Re:100 architectures?!

[Kaellenn]

While it might be an interesting exercise, I think it's well beyond the scope of this article. The focus is clearly on personal computers, and the (by-far) dominant architecture we've had on our desks over the past 10 years.

While the slashdot crowd might find such a benchmark informative, the general Tom's HWG user probably would not.

Re:100 architectures?!

[kaisyain]

x86 is an instruction set architecture which is separate from a micro-architecture. They have certainly benchmarked more than one micro-architecture.

Re:100 architectures?!

[LiquidCoooled]

Its a real shame.

I went from a 68020 14mhz upto a p90.
I felt for a good long time that it was a step down (upgrade was through necessity rather than want).

It wasn't until I got a Duron 650 (and win98) that I felt the playing field was almost level.

I still miss my Amiga, and occasionally hammer fists at things I could do then which are still inpractical now.

Re:100 architectures?!

[tomstdenis]

Um, clock for clock a Duron is a heck of a lot more capable than a 68020.

Maybe you just long for the days of the happy mac on the screen during boot up?

Tom

Re:100 architectures?!

[Xzzy]

>Maybe you just long for the days of the happy mac on the screen during boot up?

Who doesn't?

Admit it. You felt happy every time that little icon showed up. The world was a better place, because the computer was starting up and it was happy doing it.

Re:100 architectures?!

[LiquidCoooled]

It was an Amiga actually, and I know the 650 could do a LOT more than the 020, thats why I said "felt".

Day to day computing has never been about mhz, its responsiveness and getting things when you expect them, the Amiga was always there for me :)

Re:100 architectures?!

[LiquidCoooled]

One other point worth making.

Nowadays, we think nothing of opening an mp3. Back then, music was supplied with short samples and tracker files. An old Amiga now would collapse trying to decode one nowadays, and video would just be totally out.
Things do change, and I'm now reasonably happy with the x86 platform, purely because of hardware support - I can buy pretty much anything for it and get it working.
I will always miss my Amiga though :)

Re:100 architectures?!

[Rebar]

Okay, since Tom's is completely dead at the moment, I'll share the results of my own useless benchmark. I ran the very same single-threaded stupid command on several different machines and recorded user time. Users enter stupid commands anyway, so I figure this is as good as any other test.

I did say this is useless, right? Good. Note that most of these machines are multi-cpu machines, and it looks like I only did this on Power4, PPC, Intel and AMD, and Alpha systems.

My stupid command is:
dd if=/dev/zero bs=32768 count=3200 | time gzip > /dev/null

Here are the machines and the USER-time result in seconds:

MHz Secs CPU Arch
3185 1.04 Intel Xeon CPU 3.20GHz
3057 1.08 Intel Xeon CPU 3.06GHz
2795 1.22 Intel Xeon MP CPU 2.80GHz
2786 1.22 Intel Xeon CPU 2.80GHz
2395 1.39 Intel Xeon CPU 2.40GHz
1800 2.00 AMD Athlon 64 Processor
1533 2.44 AMD Athlon MP 1800+
1300 3.18 IBM Power4
1108 3.69 IBM P690 Power4
1108 3.71 IBM P690 Power4
1000 4.36 EV6.8CB
1150 4.4 EV7 21364
1000 4.79 AMD Duron OC 133FSB
1000 5.1 EV6.8CB 21264C
1000 5.37 PIII Xeon Coppermine core
1000 5.5 PowerPC RS64-IV
866 5.76 PIII Coppermine core
700 6.1 EV6.7 21264A
500 12.36 PIII Katmai core
600 14.9 EV5
400 14.99 AMD K6
350 17.23 Pentium 2
532 19 EV5.6 21164A
300 27.14 Pentium MMX
300 34 EV5

Due to the Lameness Filter, I can't make the above data any prettier, but I'd bet you can figure it out.

Of course with differences in OS, compilers, memory speeds, etc. you can't really draw any conclusions from this, EXCEPT this is how fast this particular command runs on these exact systems, AND you can run it on yours to compare how fast a stupid command will finish, which is good to know.

--rebar

Re:100 architectures?!

[tomstdenis]

That's why I wrote it. Old school macs were cool. I did a load of pascal/C coding in high school on them [well and on my 486SX with TurboC but that macs were funner]

Tom

Re:100 architectures?!

[tomstdenis]

My only serious power boost was from a 60Mhz 486 [with no FPU] to a 133Mhz MI [or MII can't recall now, think it was a MI]. I could now play mp3s while doing other shit at the same time. It was insane! After that it was just cream.

Tom

Re:100 architectures?!

[System.out.println()]

Did you not test IBM's 970 (better known as Apple's G5), or am I just blind? I'd like to know where it stacks up....

Re:100 architectures?!

[Rebar]

No, I only tested systems available to me for either evaluation or that were production somewhere; the G5 had not made it to the big-iron world at the time (has it yet?), but feel free to run that simple command on your G5 and compare. These numbers are anywhere from several years old to 1 year old, and I don't have access to all the latest-and-greatest hardware.

Oh, and the AMD64 is running in 32 bit mode; IIRC it was about 20% faster when running Gentoo in 64 bit mode.

Re:100 architectures?!

[upsidedown_duck]

Hate to break it to you, but gzip is actually a useful benchmark. I spend more time waiting on file compression commands on my old computer than anything else, because I tend to like to tar and compress infrequently used directories. I also re-do gzipped downloads in bzip to save space.

Re:100 architectures?!

[Anonymous Coward]

On a 296MHz UltraSPARC II, averaged over five runs, I get 13.96 seconds! Take that EV5! You suck!!!

Re:100 architectures?!

[Rebar]

I agree, but I figured someone would point out that compressing a stream of zeros is not quite like compressing real data - but at least the stream of zeros is available on (nearly) all platforms, and it is very nearly CPU bound and so a pretty good relative test, for what that is worth.

I hate waiting on gzip so much that I wrote a multi-threaded program to make gzip files faster on machines with >1 CPU; see http://lemley.net/smp.html if you have more than one CPU and hate to wait on compression programs.

Re:100 architectures?!

[incom]

1.64user athlon64 2000mhz , with some typical desktop apps open(but idle) simultaniously.

Re:100 architectures?!

[Anonymous Coward]

With an O2 with R12k 400MHz I get 7.67s (take that, UltraSPARC II!), 13.13s with a R7k/350, 34.03 with R5k/200, and a rather dissapointing 39.95s with an indy R5k/180,

Re:100 architectures?!

[Anonymous Coward]

For Fun:
602 5.7 Fujitsu Sparc64 (GPUS)
900 5.3 Sun UltraSPARC III (Sun V480)
1002 6.5 Sun UltraSPARC IIIi (Sun V210)
2100 1.72 AMD Athlon XP 2800+

Re:100 architectures?!

[Zork the Almighty]

Ok, here's what I have access to.

MHz Sec CPU
2800 1.33 P4 Xeon
1991 1.8 Opteron 246
1400 3.3 Athlon Thunderbird
1000 4.6 iBook G4
1000 9.3 iBook G4 (Reduced CPU)
800 5.8 PowerMac G4
700 6.0 Pentium III Cascades
250 13 MIPS R10000 (SGI Origin?)
195 20 MIPS R10000 (SGI O2)
133 65 Pentium 133 (LONG LIVE SLACKWARE!)

Re:100 architectures?!

[Saiyine]

15.3 seconds in a K6 350

104857600 bytes transferred in 18,960594 seconds (5530291 bytes/sec)

real 0m19.127s
user 0m15.338s
sys 0m2.057s

vendor_id : AuthenticAMD
cpu family : 5
model : 8
model name : AMD-K6(tm) 3D processor
stepping : 12
cpu MHz : 350.712

Re:100 architectures?!

[sean23007]

2795 1.19 Intel P4 HT 2.80 GHz

I was running Debian, with Gnome and several userland apps open as well as Apache & Postgresql ... out of curiosity, what was running on your systems, that a normal P4 outperformed (barely) some Xeons with the same clockspeed?

Re:100 architectures?!

[Rebar]

Nothing much; Redhat AS 2.1 and Oracle on most of the Xeon systems, but idle at time of benchmark. Most likely gzip fits well into the cache of both your CPU and the Xeons, and it could be that your gzip is more optimized than Redhat AS 2.1's gzip. From the numbers it looks to measure clock speed more than anything else, but it's still fun to compare.

Re:100 architectures?!

[kbahey]

Add this to your list:

7.61 user seconds on an Intel Pentium III (Katmai) stepping 03, 550 MHz.

Re:100 architectures?!

[multiOSfreak]

Motorolla G4 533Mhz/dual
User-time: 8.04 seconds

I wonder if both procs are used in this kind of process?

Re:100 architectures?!

[Anonymous Coward]

4.18secs on an iMac 1.8 G5 and 14.38secs on an iBook G3 500Mhz

Re:100 architectures?!

[Anonymous Coward]

Nope, but you should be able to start two simultaneously and have them run close to the runtime of a single process; maybe 20% longer but not 100% longer as you would expect with a single CPU. Some of the machines I tested had 16 cpus so I picked a process that I knew would peg a single CPU.

Re:100 architectures?!

[Anonymous Coward]

850 4.07 AMD Athlon
333 17.90 Intel Pentium 2
206 40.88 Intel StrongARM 1110
50 276.91 Intel 486SX/2
25 417.44 Intel 486SL

I wonder how long gzip takes on my 8MHz Atari ST...

Re:100 architectures?!

[Anonymous Coward]

Intel P4 2.8/800, Linux 2.6.8: 1.10
Intel Pentium 100, NetBSD2.0: 94.0

Re:100 architectures?!

[Dominatus]

1600 2.263 Pentium M

Re:100 architectures?!

[Just Some Guy]

275 73.5 EV45 21064A

Recently?

[jargoone]

They haven't been busy recently. They just updated the guide they did quite some time ago. Not very much new to see here...

Slashdotting TomsHardware, yey!

[Man in Spandex]

I feel a great joy for this event.

Interesting

[SillySnake]

It seems the server that hosts the /cpu/(stuff) died.. the main site is accessable, as are other parts of it.. Maybe /. should have posted motherboard reviews instead!

linux on 486 :-)

[Crass Spektakel]

The last time I looked there where more distributions available for 68030 than for 486. Just take a look, most distribution except Linux-from-Scratch and variations like Linux-nearly-from-Scratch are build to run on a minimum of Pentium.

Re:linux on 486 :-)

[nkh]

I installed Linux on a 386, you just need a boot floppy, and an ethernet card to pump the programs from another computer. It's pretty useless for me but it installed without problem.

The title of this newspiece is misleading!

[chaoskitty]

"Comparative CPU Benchmarks From 1995 to 2004"

I only see x86 CPUs. What about the PowerPCs, SPARCs, MIPS, Alphas, ARMs, and so on?

For instance, the m68060 was the first consumer level processor with branch prediction and branch folding, superscalar dispatch, and real-world throughput of more than one instruction per clock cycle. Except for floating point where it performed only modestly, the m68060 seriously outperformed the Pentium in spite of only having a 32 bit data bus as compared with the Pentium's 64 bit bus. Isn't this significant in illustrating the influences in processor architecture?

http://www.sixgirls.org/ is an m68060 Amiga running NetBSD 2.0. Still very useful after all this time. Where are all those Pentium 60 machines?

Re:The title of this newspiece is misleading!

[Anonymous Coward]

Text of sixgirls.org:

reva.sixgirls.org is back online! Now running NetBSD 2.0!

Seems amazingly useful to me! :P

Re:The title of this newspiece is misleading!

[LiquidCoooled]

Not to sound offish (I'm an Amiga man), but plenty of people run their webservers from old home machines, 486s and low spec pentiums are very common. Its only big business that pays for new servers.

They perform really well, and most can even survive a slashdotting (usually more because bandwidth tops out before the cpu). Don't knock the dark net.

Re:The title of this newspiece is misleading!

[NitroWolf]

The reasons those CPUs didn't get benchmarked (aside from the time and effort it would take) is because they really aren't that relevant to the article. No one used those CPUs for any gaming, and gaming is what drives the CPU market. Not business apps, not scientific apps, and certainly not Mom and Dad word processing or desktop publishing their way to fame and fortune.

Games drive consumer CPU advances, plain and simple, and the CPUs you mentioned had virtually nothing (comparitively) to offer in terms of games, and thus they are really irrelevant to the comparison.

Are they nice CPUs? Yes. Are they innovative? Yes. Are they for niche markets? Yes. I know Mac, Amiga, or anything but x86 people don't like to be relegated to a "niche" market, but in terms of $$ expenditure and mindshare, the x86 is (obviously) the primary game platform for computers, far, far, FAR outstripping EVERY OTHER CPU EVER MADE COMBINED. You could put the dollar value of non x86 games together from the beginning of time (that was a Tuesday in 1970, wasn't it? :) ) and it still wouldn't add up to one year of the dollar value of the x86 game market.

Re:The title of this newspiece is misleading!

[rainman_bc]

Not business apps, not scientific apps, and certainly not Mom and Dad word processing or desktop publishing their way to fame and fortune.

I'm sure IBM and Motorola would disagree with that. I'd bet Apple (who buys from IBM) would disagree with you. I'd bet Sun disagrees with you.

In fact, maybe the only business that would agree with you would perhaps be HP with their now defunct Alpha product (Started by Digital and destroyed by Compaq).

This is the problem with /. - pimply faced school-children that think they are the only consumers of processors out there.

Repeat after me: Games are not the only driving force behind processor performance.

Re:The title of this newspiece is misleading!

[Control Group]

No, but they are the driving force between CPUs marketed (and hence priced) for consumers.

You're absolutely right that gaming hasn't driven CPU advancement, but it has certainly drive CPU pricing, which is arguably just as important.

Re:The title of this newspiece is misleading!

[upsidedown_duck]

Where are all those Pentium 60 machines?

Well the best place for them is as a firewall between the broadband modem and the new PC. People are using separate hardware firewalls, right? No? Oh dear...

Re:The title of this newspiece is misleading!

[rainman_bc]

Actually competition and innovation keeps CPU pricing down.

The bleeding edge will always be expensive, be it for servers or desktops.

Re:The title of this newspiece is misleading!

[Anonymous Coward]

> No one used those CPUs for any gaming, and gaming is what drives the CPU market.

What????

Back in the time of the 68040, most of the serious gamers, as well as the best games, were on the Amiga or Atari ST, because PC graphics completely sucked ass at the time, and their sound ability also sucked ass.

I agree that nobody uses those CPUs for gaming _any more_, but if you go back a ways, there was a thriving and very large gaming market on non-intel CPUs. Early PCs were a joke for gaming.

Re:The title of this newspiece is misleading!

[Abattoir]

I only see x86 CPUs. What about the PowerPCs, SPARCs, MIPS, Alphas, ARMs, and so on?

Because Tom's Hardware Guide is a site aimed at users of the Wintel Platform. I don't read the site on a regular basis, but they certainly don't review the latest in other architectures.

Particularly because many people who read Tom's are looking for information for Windows gaming.

Re:The title of this newspiece is misleading!

[NitroWolf]

Did you just not bother to read what I wrote, are you intetionally obtuse or is it just your natural state of beign? I normally can tell when someone is being obtuse intentionally, but it appears you have a knack for making it look like it's a natural function of your daily activity.

Your obtusness aside, though... Let me restate what I said in perhaps simpler terms that you might be able to comprehend.

Lets start with your statements about IBM, Motorola, Apple and SUN. They do not sell fast chips to businesses. Their primary sale are of the middle of the road chips. The high end processors are sold by those companies in startlingly limited quantities when compared to "yesterdays" processors. The fastest CPUs are not needed for 95% of the markets those companies you mention sell to. The ones that DO need the fastest/latest/greatest/highest power chips do NOT buy in quantities approaching anything NEAR what the gaming market buys.

See, the problem with Slashdot is indeed pimply faced school-children... but you are a shining example of why even those not in school are complete degenerates who have no idea, not even the vaguest shred of a clue, as to what drives the industry you think you're so into. I've been working in this industry for over 20 years now, and I started with building my own Hazeltine computer. I certainly don't need a fallicious lecture from a pimply-faced schoolkid like yourself to tell me what actually drives the industry.

You have NO idea what you are talking about. It's painfully clear to anyone with even a few years experience in this industry that you are a snot nosed brat who likes to talk a lot of crap, but has nothing to back it up. Please stop posting on /. so that the adults can have reasonable conversations with you interjecting your ill-informed opinions that you pull out of your ass.

Thank you, and please drive through.

Re:The title of this newspiece is misleading!

[rainman_bc]

If you think for a second that games drive processor speeds, I'm afraid you don't know what you're talking about.

It might have a part of it, but it isn't the sole driving force.

Rendering farms, video editing, scientific applications, geoligical applications, and bioinformatics also play a very large role. As does the next killer app whatever it is.

And there's just as much money selling a high end rendering farm as there is selling faster procs to school children.

Otherwise, why would Intel bother to push the Xeon, and not shift their business to the consumer desktop market?

This comment here shows you don't have a clue:

BM, Motorola, Apple and SUN. They do not sell fast chips to businesses. Their primary sale are of the middle of the road chips.

You've been in the industry too long. Move aside for people who know what they are talking about. That's a pretty bold absolute statement you've just made.

I know some graphic designers who would beg to differ with you. And I also know some video editors who'd argue with you too.

If businesses only needed middle of the road stuff, why not just abandon the xeon line all together?

Re:The title of this newspiece is misleading!

[NitroWolf]

I love how you use the Xeon as the lynchpin in your whole arguement. It makes it so easy to bring your whole house of cards down.

The Xeon processor IS a middle of the road processor. It's not the speeds of Xeon that make it a desirable processor for business, it's the stability and large cache. The Xeon processor is SLOWER, or at best exactly the same as the fastest P4's. The Xeon offers absolutely nothing in terms of processor speeds that can't be achieved at a signifigantly lower price point by buying a "non" Xeon version of the same processor. The only gains realized (and they are valid gains for a limited set of applications) is the L1 cache.

As for Intel pushing the Xeon line... haha, are you serious? They push the Xeon line because it's a cash cow. Offer the same processor with a bit more L1 cache for two or three times the price. What's not to like about that? I'd be pushing the hell out of that, too... when in reality 99.8% of the people buying Xeon's wouldn't know the difference between a Xeon and a stock P4 at the same clock speed.

I have no idea how you can say that "high end rendering farms" et al is the majority of the sales of Apple and x86 vendors. That's just plain ludicrous. Go do some research... the lions share of processor sales goes towards middle of the road CPUs... Why do you think the Celeron line is so popular?

I make a "bold, absolute" statment becaus that's what the yearly sales figures for the companies you mention show... It's a pretty cut and dried set of statistics that you perhaps need to research a bit before you make claims to the contrary.

I never said there aren't legitimate businesses that need the fastest CPUs for something other than games... I said they are a limited market, and compared to the consumer CPU market, they pale in comparison. You just can't ship tens of millions of processors to render farms around the world... there aren't enough of them.

Why Jesus... Why not force Coralization on /.?

[Mike626]

Part 1: http://www.tomshardware.com.nyud.net:8090/cpu/2004 1220/index.html
Part 2: http://www.tomshardware.com.nyud.net:8090/cpu/2004 1221/index.html

mirrored on Coral

[atlaz]

the article

another article killed by slashdot instead of linking to the coral version, or creating their own mirror.

how many more times does this have to happen?

Am I the only one who thinks this is crazy that this site built a backbone for itself and then uses its traffic to kill sites it links to?

"All AMD CPUs ever made"

[SteeldrivingJon]

ever.

So says the title of a chart they post.

Note that the CPUs in the chart start at 600MHz. Who knew the old AMD 286's ran so fast!

Re:"All AMD CPUs ever made"

[WMD_88]

AMD only made co-processors until Intel started putting them on-chip with the 486. There are no 286 AMDs.

Standard Benchmarks?

[basscomm]

I can't get to the article, so I have to wonder what kind of benchmarks they used that were consistant on all those platforms. Old benchmarks tend to freak out on newer hardware, and I can't imagine newer benchmarks running properly on older hardware.

Toms hardware site is staggering under load

[sundru]

I think toms site is going under with all the traffic from /.

takes a couple of minutes for a page to load ..
I was first there peeps :) lemme read ..

software anyone

[Anonymous Coward]

Would be nice if they included what software was available at each level. For example, I had XENIX (from Microsoft and SCO) on an early 386 and it rocked (full 32-bits), but Microsoft didn't do 32-bits on the desktop until Win95 (10 years later), and didn't migrate to a full 32-bit O/S until Win2K and XP (nearly 15 years after the 386 came out).

8mb card for PCI?

[jensen404]

Why did they use an 8mb video card for the older motherboards that don't support AGP?

Matrox Mystique G170
Memory: 8 MB SD-G-RAM

They should use the fastest availible video card if they are testing CPU speed. My 200mhz pentium pro with a 16mb TNT card ran Quake 3.

Re:8mb card for PCI?

[chaoskitty]

Yeah, you know how a slow CPU can be sped up to insane speeds by putting in a fast video card!

Sarcasm aside, why would they put in a >2000 year card in a 2000 year computer? That's not representative.

Re:8mb card for PCI?

[caino59]

what?!?!

please pass me some of what you're smoking.

graphics cards dont do shit for CPU speeds tests.

Re:8mb card for PCI?

[icebones]

but they sure can help / kill the results when your measuring the FPS in openGL. I'm running a K6-2/533 w. 32mb geforce2 and it ran QIII and RTCW. but their's didn't. hmm..

Re:8mb card for PCI?

[DuncMan]

I have little experience of all this, but it seems to me that choice of video card will only noticeably affect a CPU benchmark if drivers are being used which offload some of the CPU work onto the video card.

If 3D or video work is being done in software on the CPU, then isn't the video card little more than the place to put bits you want to see on a monitor?

Re:8mb card for PCI?

[jensen404]

If you want to use the Frames Per Second in a game to test a CPU, the video card has to be able to render frames at least as fast as the cpu can send them.

If the CPU can push 20 FPS, but the graphics card can only render 10 FPS, it becomes a graphics card benchmark, not a CPU benchmark.

Re:8mb card for PCI?

[jensen404]

They have some quite old cpus(down to 600mhz) on there that they are testing with a 6800 GT. This is supposed to be a cpu benchmark, not a full system benchmark.

Re:8mb card for PCI?

[caino59]

well - if you want to test the cpu - you probably shouldn't be using something relies on the processing capability of your gpu.

btw tom's hw sucks.

if someone is publishing an article and says: "Hey, lookee here at these cpu performance numbers!" and they're using benchmarks that tie in graphics performance - that just makes the tester look like a dumbass.

Not a very good job.

If benchmarks perform worse than subjectivity

[PhysicsGenius]

that doesn't mean that subjective judgement is "the best analysis", it just means that current benchmarks suck. Subjective judgement is what built the cathedrals of yore. That's because they didn't have a real "best analysis" back then. (And sure a lot of them held up, but most of the crumbled within a few years and in any case they are vastly overengineered, however aesthetic.)

Re:If benchmarks perform worse than subjectivity

[Anonymous Coward]

Truth be told running performance benchmarks like Olog(n) routines is
tantamount to a perfectly subjectable measurement. If the analysis was done
in a level and proportional environment then the results will be mathmatically
demonstratable to be stastically substanative. Granted, the results can also
be subject to human bias, but this would require the application of determined
opinion to counter-balance the measurement methods to begin with.

My results

[freelunch]

The article is a bit slashdotted but it looks like it doesn't go back all that far.

Just a teaser, I have been running a collection of benchmarks since the Pentium 90.

At the time, I was involved in a huge UNIX engineering workstation benchmark. I felt we needed something more constant than the applications to compare performance (the engineering apps constantly change). So I quickly assembled everything I could find that could be easily run. These are mostly 'toy' benchmarks, but the results are still interesting.

For these int benchmarks, higher is better:

c4.s c4.64 dhry21 hanoi heapsort nsieve nsieve TOTAL
Kpos/sec Kpos/sec MIPS mvs/sec high High Low
MIPS MIPS MIPS
P 90 92.7 94.2 68.6 51.2 43.55 111.0 33.3 494.6
md64b 4050.1 4167.8 4914.3 2708.8 3333.7 3333.7 610.4 21782

Float: Higher is better, except for the fft's.
flops20 fft tfftdp
MFLOPS MFLOPS MFLOPS MFLOPS TOTAL time time
(1) (2) (3) (4)
P 90 13.3 12.8 18.1 23.8 68.0 3.07 16.81
amd64 1120.9 1004.3 1480.9 1834.7 5440.8 0.04 0.42

The P90 was running RedHat. The AMD64 is my new desktop, a 90nm 3000 OC'd to 2430 Mhz. My data also includes systems from DEC, HP, IBM, Sun and SGI. I also ran 10 matrix multiply benchmarks as part of the effort.

I have never gotten around to publishing the results or the collection of benchmarks.. Maybe it is time.

Re:My results

[Anonymous Coward]

So is it cooler to post in code font now days on slashdot?

Re:My results

[Anonymous Coward]

The lameness filter won't allow that type of posting as plain text.

But...

[Junior J. Junior III]

I bought my computer in 1982... how will I know if it's worth upgrading if the data only goes back to 1995?

Re:But...

[shadowsurfr1]

Aftre 22 years, I would hope you upgrade.

Exciting?

[SpinningAround]

As I recall, they claimed that part one of the article took something like 300 hours to put together. Seems like a lot of work to tell me that processors have become a lot faster in the last 10 years.

Actually I shouldn't give Tom's Hardware a hard time (like everyone else seems to). As articles go, the reviews of high-end ink-jets, the 8-channel RAID6 card and the Viewsonic media center were quite interesting (and a lot more recent than the CPU round-up too).

These days though, my favourite reviewer is Dan (who posts here now and then). Dan seems to understand that a million graphs showing you the statistically insignificant difference between the latest mobos / graphic cards / processors / ram sinks don't really make a great site.

Re:Exciting?

[imsabbel]

well, i agree that tom isnt very hot regarding reviews (anand is better, for special stuff of course storagereview or beyond3d rule), but i wouldnt say dan is a reviewer.
He just takes every shit he gets for free and tells something about it, which is either "its cool" or "it sucks", only with more words.
Every 2nd article is eiter a beggin for money (he actually posts news items "please send me money via paypal") or a blatant product placement ("click here to get those GREAT photon lights for so much cheaper").
He is nice to read because he CAN write (not like anand, where every 2nd review is 90%graphs, 10% text), so i read every article by him, but i wouldnt trust him for any purchase.

Re:Exciting?

[D. Book]

Dan seems to understand that a million graphs showing you the statistically insignificant difference between the latest mobos / graphic cards / processors / ram sinks don't really make a great site.

On the other hand, cliche-ridden vebiage isn't much help either. Usually it serves as a mere extension of the manufacturer's marketing and product literature; it almost always leaves you feeling like you ought to buy something. And have you ever noticed how few reviews conclude with a score of less than, say, 8/10 or 80%? It's like a school that gives practically every student an "A". That suggests an inherent corruption exists regardless of the intentions of the reviewer.

I find the most useful research tool before purchasing a product is downloading and reading the product manuals. These take about as long to read through as your typical review, and provide a much clearer and more realistic picture of what the product is and does rather than selling you on some UltraHyperWhizzBang technology that becomes irrelevant once you've handed over your hard-earned dollars.

Re:Exciting?

[Anonymous Coward]

The problem with TomsHardware is that Tom has broken the journalist ethic too many times in the past to be taken seriously. There have been several cases of falsified or completely fabricated data in his reviews. Whether this was to land a particular advertising contract or drum up controversy and readership, I don't know and don't care.

One or two incidents I can forgive and forget. Multiple times, I cannot.

Re:Exciting?

[Anonymous Coward]

"300 hours"...

Those were Scotty hours, not Kirk hours...

not exactly fair to older systems

[icebones]

Alot of the benchmarks have the bottom 4 or 5 at zero, ie quake III and RTCW. What specifically got my attention was the K6-2+ 500. This is almost exactly what I'm running (don't laugh) and I've played both of these games on it quite well. They may not be at max graphics settings, but they look pretty good to me. and yes I am planning on upgrading, but I'm waiting on the nforce 4 mb'sso I won't have to upgrade the next time I want a new graphics card.

Re:not exactly fair to older systems

[BorgHunter]

nForce 4 motherboards are out. I backordered the Asus A8N-SLI Deluxe on Sunday, and the site I ordered it from says "In Stock" for it now. I assume it'll ship soon. Unlike you, I'm upgrading a 2.4 GHz P4 system. :-P

Here

Re:not exactly fair to older systems

[icebones]

thanks for the info, I had been checking newegg and they were out as of a few days ago.

Re:not exactly fair to older systems

[trongey]

...so I won't have to upgrade the next time I want a new graphics card...

You're dreamin dude. By the time you get your nforce running we'll be hearing about the new gee-whiz-super-slot graphic hyper bus on mobos with the ultra-sphere cpu interface. Happens every time.

Not necessarily a dup,

[nbert]

but I'm sure that I read a similar article at tom's this year comparing x86 CPUs from ~386 to recent systems.

IIRC they decompressed zip files and encoded video stuff among other things. It's quite impressive to see a fairly modern CPU performing the same task in minutes which used to take several hours on one of those 'antiques'.

The 487 would disable the 486sx

[Anonymous Coward]

It was actually a complete replacement. The rumor was that Intel would test the 486's and if the math co-didn't work they would be modified and sold as 486sx's.
However, beware of the 486DX50 vs the 486DX250. The 486DX 50 was a true 50Mhz part whereas the DX2 were only 50Mhz internal to the chip with the bus running at 25Mhz. Same thing for 486DX2 66's. Most programs ran slower on them than a trus 486DX50 due to the slower (33Mhz) bus speed.

Re:The 487 would disable the 486sx

[i41Overlord]

However, beware of the 486DX50 vs the 486DX250. The 486DX 50 was a true 50Mhz part whereas the DX2 were only 50Mhz internal to the chip with the bus running at 25Mhz. Same thing for 486DX2 66's. Most programs ran slower on them than a trus 486DX50 due to the slower (33Mhz) bus speed.

Yup. Then Intel had to confuse the issue by releasing the 486DX4. Just as the DX2-50 had a 2x multiplier with a 25 mhz bus and a 50 mhz core speed, you'd think the DX4-100 would have a 4x multiplier with a 25 mhz bus and 100 mhz core speed. But it was actually a 3x multiplier, with a 33 mhz bus speed. They should have caused it a DX3

Re:The 487 would disable the 486sx

[foxtrot]

However, beware of the 486DX50 vs the 486DX250. The 486DX 50 was a true 50Mhz part whereas the DX2 were only 50Mhz internal to the chip with the bus running at 25Mhz.

Of course, then there's the other side of this issue, which was VLB: Vesa Local Bus (which is what we used for fast access to graphics cards [and sometimes IDE disk] before PCI/AGP) was only spec'd to run at 33MHz tops, and many VLB cards wouldn't run at 50 MHz. So you often had a choice: buy the 50 MHZ 486 DX to get the full 50MHz bus speed, but use an ISA graphics card, or buy the DX2/50 and use a VLB graphics card a 25MHz. The usual answer (once it came out) was the 486 DX2/66, which was a 66 MHz processor on a 33 MHz bus, topping out the local bus clock. Some things still ran faster on the 486DX/50, but games usually ran better on the DX2/66 due to the higher graphics card throughput.

Of course, the highest end graphics cards (Diamond's Viper, ferinstance) could generally handle a 50MHz clock. But most of us didn't have that kind of scratch lying around at the time.

-JDF

Re:The 487 would disable the 486sx

[phsdv]

yep, I was lucky back then, my vesa local bus graphics card (sorry forgot which one) did work at 50 MHz. So I had the fastest computer of the whole lab, runing 50MHz all over, Yes! It was running OS/2 with a Gopher server and later my first web server. With all pages handcoded in HTML 1.0.

Re:The 487 would disable the 486sx

[Anonymous Coward]

They should have caused it a DX3

You mean like the 486SLC3 and DLC3?

We're talking about intel math where 33*3=100.

Did they recompile?

[Anonymous Coward]

You know you get much better results if your CFLAGS are matching your hardware.

THG Upgrade

[Dacmot]

I think Tom's Hardware servers need an upgrade...

Re:Wow

[ePhil_One]

I think its a measure of the true utility of the article. People are actually reading the article BEFORE posting, a rarity on Slashdot...

486's had the coprocessor built in.

[i41Overlord]

The 486 has had a built-in math coprocessor ever since it debuted. After the 486 was around for a while, they made a stripped down version without a coprocessor called the 486SX. The plain 486's were called 486DX.

You could get a coprocessor for the 486SX, but not the DX. From what I've heard, the original 486SX's were actually re-badged 486DX's whose math coprocessor unit was either not functional or just disabled. When you bought the 487SX "co-processor" you were actually buying a fully functional 486DX that disabled the other CPU on the board.

Re:486's had the coprocessor built in.

[vasqzr]

When you bought the 487SX "co-processor" you were actually buying a fully functional 486DX that disabled the other CPU on the board.

Correct.

And for the 386, the 386SX was like a 386DX but it was crippled by a 16-bit bus instead of a 32-bit bus. Which made them the same speed as a fast 286.

Neither 386SX or 386DX had math-coprocessors. You had to add them on later.

Re:486's had the coprocessor built in.

[dhwebb]

IIRC, the 487 coprocessor chip was the same as the SX chip just reversed. So a SX was a DX with coprocessor disconnected, and the 487 was a DX with the main CPU disconnected. I remember this from one of my old NetWare study guides.

Re:486's had the coprocessor built in.

[DarkMantle]

IIRC you're correct. Had to brush up on older technology when I broke down to get my A+ a short while back. (Like I remember IRQs anymore)

Geeky Urges

[Ryan Huddleston]

Does anyone else have the sudden urge to run off to Kinko's and get the giant master benchmark charts printed off as posters?

...Or is that just me? : - )

Re:Geeky Urges

[Anonymous Coward]

It's just you!

Re:Why Jesus... Why not force Coralization on /.?

[Anonymous Coward]

What happens when Coral can't get in either ?

Error: 503 Service Unavailable

www6.tomshardware.com: Connection refused

Server CoralWebPrx/0.1 (See http://www.scs.cs.nyu.edu/coral/) at 192.170.103.21:8090

Stock Intel PPro CPUs did not have MMX!

[Richard Steiner]

If you installed Intel's PII Overdrive for Socket 8 mommyboard you could obtain MMX, but that was the only way.

Re:Stock Intel PPro CPUs did not have MMX!

[Anonymous Coward]

bs, my old pc is a stock ppro 166mhz and it has mmx

Re:Stock Intel PPro CPUs did not have MMX!

[stratjakt]

The PPro didn't, but there was a Socket 7 CPU that did have MMX:

January 1997 saw the first major processor release from Intel since the Pentium Pro in 1995. The processor in question was the Intel Pentium MMX (or P55C to the technicaly minded). This was heralded by a loud advertising campaign which introduced us to the now imfamous dancing "Bunny People".

Re:Stock Intel PPro CPUs did not have MMX!

[Anonymous Coward]

BS?

Same press release on a faster server.

Maybe time to upgrade the server?

[seafortn]

Looks like they should look at the chart themselves and decide whether to upgrade the 8086 they have running the webserver...

Answer is simple. Upgrade to WfW 3.11

[Anonymous Coward]

You're welcome.

Re:Boring.

[zev1983]

In the meantime the model in the holiday buying guide is hot.
http://www.tomshardware.com/consumer/2004111 5/inde x.html

AMD made 286 processors?

[gotr00t]

I'm not too clear on this, but given that I have in my hands a 286sx processor labeled "(c) Intel/AMD 1982", and it follows logically that AMD and Intel were at some point in history combined in some way.

Though that was before my time, I do know for sure that AMD made processors way before they got the clock speed to 600MHz, so you're right about that.

Re:AMD made 286 processors?

[Entropius]

Well, I have an AMD K6-2 @ 400 sitting in my bedroom, all lonely, plugged into a dusty motherboard that hasn't seen voltage for years.

Anyone know a good place to get ancient RAM?

Re:AMD made 286 processors?

[Mr Z]

AMD was a second-source for Intel CPUs up through the 286 era. I believe this arose out of IBM's requirement to have a second source for whatever CPU it picked for its PC. It appears Wikipedia corroborates my story.

--Joe

Re:AMD made 286 processors?

[greenegg77]

Got some sitting in my desk at home. Do you need 72-pin or whatever the thirty something pin was?

Hell, send me a SASE and I'll mail ya some.

DAV

Re:AMD made 286 processors?

[archen]

Dude, a K6-2 probably uses SDRAM, and that's not ancient (dated yes). You can probably find old computers that people are going to throw away and just tear it out. Personally I've got SDRAM,EDO, and whatever the hell came before that comming out of my ears because I refuse to throw it out even if I can't use it. You can probably get stuff off of ebay to suppliment the machine save nothing else.

Re:AMD made 286 processors?

[The FooMiester]

Email me and we'll talk. I'm always looking for legacy hardware.

Re:AMD made 286 processors?

[SteeldrivingJon]

Apparently, AMD at first made 286 chips under license from Intel.

Later, they came out with a non-licensed clone 286, which they imaginatively called the "286A".

Re:AMD made 286 processors?

[bryanp]

Yes, they did. My first x86 box (prior to that I was running an Apple //e) had an AMD 80286 running at 16Mhz. Intel 286's topped out at 12Mhz. That extra 4Mhz made a noticeable difference when playing Wing Commander. If anyone cares, the stats on that box were -

286-16
Trident VGA card with 512KB of RAM.
1MB of RAM socketed on the motherboard with DIP chips. (Upgradeable via SIPPS, if anyone remembers those.)
Seagate ST157A 40MB hard drive
3.5" 1.44MB FDD
5.25" 1.2MB FDD
14" Samtron VGA monitor
Kraft KC-3 joystick (I still have that in a box somewhere ...)
2400bps internal modem.
Panasonic 24pin dot matrix printer

For which I seem to recall paying about $1200.

Rule of thumb

[howlingmoki]

When you see better computers than the one you're using at Goodwill/Salvation Army/St. Vincents .. it's time to upgrade.

Re:Rule of thumb

[Anonymous Coward]

When you see better computers than the one you're using at Goodwill/Salvation Army/St. Vincents .. it's time to upgrade.

My rule of thumb was that whenever the new main stream video card had a faster processor or more memory, it was time to upgrade.

Several years ago, my video card flaked out. At the store, the Creative Labs Banshee was on sale cheap, so I bought it. Got it home and realized the 250MHz RAMDAC was more powerful than my 133MHz Pentium with 32M RAM, so I upgraded to a Celeron 333 and 64M. A couple years later it flaked out, and I replaced it with an Annihilator 2 (350MHz, 64M), so I upgraded to an Athlon 1200 and 128M, then ATI Radeon 8500LE (128M), so Athlon XP 2500+ with 1GB. Should last me awhile, I hope.

Heh.

[Renraku]

I've got a Duron 1200 and am trying desperately to upgrade to an nForce2 / XP 3200+.

After a bad board and bad processor (from partspc!) blew a RAM chip I had bought for it, I ended up RMAing all three of them, likely with little or no compensation coming my way.

So here I am, after Christmas, stuck with one functional 512 stick of PC3200 Corsair after have spent $400 or more on my upgrade fest.

That's why I don't upgrade very often, besides the lack of money. Because I know that there's a good chance whatever I get isn't going to work as well as the old parts, thus stability is a good thing for me.

Re:Heh.

[Blakey Rat]

Tip: It's stupid to buy PC parts online because of the high rate of failure. Find a nice local PC parts store and become a customer... that way when you have a defective part, it's easy to return and they might even be nice enough to test it for you. PCClub is great if you live near one.

Re:Heh.

[Anonymous Coward]

"Tip: It's stupid to buy PC parts online because of the high rate of failure."

I wonder if this is a different experience from mine due to shopping for the lowest price. I've purchased (literally) tons of consumer-grade hardware, and there's always been the odd DOA component, the only consistent problems have been failing drives (usually after a respectable service life though), and failing fans (which can lead to any number of bizarre problems and other failures related to overheating.)

Thousands of hosts configured, from the 80s, 90s, and current, a bad motherboard here and there, the occasional DOA CPU, but nothing to justify your claim of a "high rate of failure" that would steer me away from mail order.

Har

[Anonymous Coward]

Why do so many people assume that a benchmark is only made by some program like 3DMark?

The Weather 13090

[zoloto]

It's actually below freezing, heavily overcast and dull as hell. Now I know why everyone with an IQ under 150 is irritable and gloomy. What is it with people and the weather that their moods are totally dependant on sunshine for "feeling" good?

these people depress me, not the weather!

Re:The Weather 13090

[zoloto]

crap...

my boss is watching me.

Yes

[Anonymous Coward]

I believe that Albert Brooks covered this in his seminal Mythical Man Month.

Re:Yes

[Anonymous Coward]

Personally my favorite one is "Spaceballs".

Why cthulhu... Why not force automatic links?

[zoloto]

First Link
Second Link

24% performance increase = zero value

[gelfling]

People don't really detect a perceivable performance boost for less than 25% more actual performace. And the perception of that 25% varies wildly from 'fneh' to 'wowieeeee'.

But I'm talking to a bunch of gamers for whom that last 0.4% performance boost is worth more than a hot cheerleader full of X.

Re:24% performance increase = zero value

[dh003i]

Actually, a worthy performance boost should be an order of magnitude (10x).

I don't upgrade until there's a computer 10x better than the one I have right now, and available at a good value.

Mod parent up please

[Anonymous Coward]

It's important to note the subjectivity factor in benchmark measurements. Too much focus is put the raw numbers, though that's easy for the marketing folks. There's a good column by economist Alfonzo Wallings that covers this kind of thing (Forbes I think, don't have the URL on me at the moment).

Re:Wow

[nolife]

Dude, the article is mostly pictures, very little reading going on.

Hardware Makes Expensive Software Obsolete

[was_ms_now_linux]

The primary end-result of the evolution of this commodity hardware is the fact that expensive software is now just obsolete - plain and simple. Ten years ago, there was a justified price premium associated with state of the art software algorithms. I still see these zealots for the DB companies raising these red-herring issues as to why every organization should still spend hundreds of thousands of dollars on expensive DB software. With the evolution of hardware the way it is, any credible SQL DB Engine could run almost any company. Same thing for web and application servers. How can anyone justify paying for these things when the hosting companies prove everyday for thousands of tech-savvy companies that the free solution is just as scalable and more secure. I used to maintain several Windwos servers and finally ported them to a hosted Apache solution - for about 5% of the cost. The sites are always available and the admin tools are web-based and better. And I don't have to hire these guys that want to go to the MS Marketing summit for a week every year so they can continue to administer the "low-cost MS solution approach". If you have any hesitation, make the switch. This stuff is now public domain, don't pay for this stuff. Those days are long gone. In the new model, it only makes sense to pay for software that solves industry-specific problems - not for tools that cost a fortune to maintain and invite tech companies into your business to meddle and start religous wars among the employees. www.SoftwareObjectz.com

Re:Why Jesus... Why not force Coralization on /.?

[Anonymous Coward]

Because there a people at work behind a firewall that drops ALL except dst port 80 and 21.
So, no coral for me.

Now this is useful

[eno2001]

I'd have to say this qualifies as "News for nerds. Stuff that matters". In fact, it's the first front page article in a little while I've seen that qualifies. Thanks guys, for doing your job right at least once. ;P

Some gamers have skewed perceptions

[sczimme]

But I'm talking to a bunch of gamers for whom that last 0.4% performance boost is worth more than a hot cheerleader full of X.

These are the same people that get into squabbles over which display adapter is better when A gets 150FPS (frames per second) and B gets 140FPS but with better double-dodecahedron rendering or whatever. It makes no difference to them that most human eyes cannot distinguish between 40FPS and 80FPS, let alone anything above 100. However, if the [abstract and wholly meaningless number] is higher then the product must be better. Oh, well - at least the cheerleaders are safe.

Re:Some gamers have skewed perceptions

[Destructo-Bot]

I must disagree with you on the "most human eyes can't distinguish the difference between 40 and 80fps." This may be somewhat more true of movies which are made with motion blur that blends the frames together. But you can certainly still tell the difference for the better when a movie is captured at 60fps rather than 30. Its not as big a difference as changing the framerate in a game is due to the motion blur but its certainly more visually pleasing when a video is captured and played at a higher framerate.

Back on track though, games have no motion blur... each frame is sharp and leads into the next with no blur. So in order to get a smooth look to it the framerate must be much higher in order to trick the brain into seeing a smoothly transitioning scene. I can easily tell the difference between framerates up to about 120fps, after which it becomes very difficult to discerne the changes.

Of course if you are playing a game and bump up your framerate without increasing your refresh rate as well, you are basically wasting rendering power as the monitor is only drawing the same number of frames as the current refresh rate. Keeping your refresh at or higher than your average framerate will make for a much more pleasant gaming experience.

Here is an ancient but still very much valid write-up on Framerate and Refresh Rate in regards to gaming:
Framerate and refresh rate write up

Why did they use Quake III?

[vasqzr]

You can't even run it on the lowest CPU's they tested.

Why not use GLQuake or even *gasp* software Quake?

Re:Why did they use Quake III?

[Prophet of Nixon]

Quake 3 will run fairly well at 640x480 on a Pentium 1 233 with a Voodoo card in it... but good luck getting it to work with the awful pci video card they used in those tests...

My wife...

[Belial6]

My wife responded to my description of the SX, DX situation with "So, you want the 486DX, not the 486 Sucks, right?"

MOD PARENT UP

[Anonymous Coward]

Words of true wisdom...

Not fully correct. Windows NT is 32-bit.

[Anonymous Coward]

...and didn't migrate to a full 32-bit O/S until Win2K and XP (nearly 15 years after the 386 came out).

You forgot Windows NT, which is fully 32-bit.

1333 4.02 PowerPC (1.5year old 17" powerbook G4)

[morcheeba]

1333 4.02 PowerPC 7457 (1.5 year old 17" powerbook G4)

Question about FSB speeds...

[The Master Control P]

If you take a look at the big chart, why is it that the clock speeds have increased by ~10 fold from start to end, but the front side busses have only increased ~5 fold?

Re:Question about FSB speeds...

[AvitarX]

Because it is easier to make a very small chip fast then it is to make all the other stuff that is spread out.

Something about the speed of electricity not being infinate or something.

Re:Question about FSB speeds...

[Detritus]

It's hard to increase the clock rate on busses. On a chip, clock rates generally increase as transistor size decreases. The physical size of external busses is more of a constant. This makes it difficult to increase the clock rate of signals on the bus. When working with wires or traces on a printed circuit board, the choice is usually "short and fast" or "long and slow". As clock rates increase, wires behave more like RF transmission lines. Simple things like pins on an integrated circuit package or connectors for plug-in I/O adapters can introduce impedance bumps that can disrupt the transmission of signals. That's part of the reason why it's easy to design a motherboard with lots of ISA slots but a motherboard with PCI slots has to limit the number of PCI slots to 3 or 4. When dealing with front-side busses running at hundreds of MHz, the electrical design gets very critical.

Good info on upgrade CPU or GPU

[Anonymous Coward]

I have a P3 933 coppermine, running an AGP MX440SEN 64MB. I get around 15-30fps in UT2004 at 800x600 with low graphic settings. If there are 20+ players on the screen with a lot of background, this drops to 4-7fps.

I have wondered if upgrading my video card would make any difference on my FPS since my CPU is so old.

What I am seeing is that P3 800 and 1000 with the newer 6800GT card are getting much better FPS at much higher resolutions. If I could get a minimum of 30fps at 800x600 from my system at ALL TIMES then I would be happy. These reviews show me this is possible.

Since the 6800GT is about $400, give or take, the question then becomes - would I see the same FPS increase from my current video card if I spent the same $400 on a MOBO/CPU/MEMORY upgrade? I would venture not.

Edwin

Re:Good info on upgrade CPU or GPU

[Goalie_Ca]

What i find a really snazzy card would allow me to do is run with ANISO and FSAA up really high, maxed out textures, etc. No guarantees but i think upgrading your mobo/cpu/memory would have a greater effect. Just as you said, when you increase players it drops like hell. This is obviously not video card related.

That crap was marked +3 insightful?

[Anonymous Coward]

> Clock speed != performance

And he never claimed it did. The very first upgrade was from 16MHz to 90MHz. Either you didn't read the first sentence or you're really bad at math. That was a 5.6x faster clock speed for 10x the performance. He obviously understand it.

Re:That crap was marked +3 insightful?

[Anonymous Coward]

That was a 5.6x faster clock speed for 10x the performance.

Please provide some reference that a 386 is 10x as fast as a P90.

Re:That crap was marked +3 insightful?

[SmittyTheBold]

1/10 th as fast. Please comprehend what you're reading before you pick nits.

Re:That crap was marked +3 insightful?

[Anonymous Coward]

Please comprehend what you're reading before you pick nits.

Hey asswipe, *YOU'RE* the only one picking nits here.

I asked for *PROOF* that product X has 10x the performance of product Y. That's not nit picking.

Perhaps you should heed your own advice?

Re:That crap was marked +3 insightful?

[SmittyTheBold]

Yet you were wanting him to show proof that a 386 is 10x as fast as P90, showing a startling lack of comprehension.

Any proof he would likely give would result in your further confusion.

I'm very sceptical about anything Tom's Hardware

[Digital Dharma]

Has to say about benchmarks. Especially considering that they only accept advertising money from AMD.

Not in hardware it doesn't.... Not without an OD.

[Richard Steiner]

Unless there's a late-release unit that I'm unaware of, in which case I will sit corrected, no Socket 8 Pentium Pro supported the MMX instruction set at all. Their release predated MMX.

I own seven PPro boxes myself, most of them with stepping level 7 or 9 CPUs, and one with a PII/333 OverDrive chip installed.

It's fairly trivial to demonstrate that MMX instructions are not present -- almost any CPU identification software will test for that, and the one Linux game I've been interested in which has a hard MMX requirement will fail to run on all of my PPro boxes except the one with the OverDrive.

I suspect you either misunderstand the issue being talked about or are actually using a chip which is not a Pentium Pro CPU. An older PII, perhaps?

amiga playing MP3 files

[Anonymous Coward]

> Nowadays, we think nothing of opening an mp3. ... An old Amiga now would collapse trying to decode one nowadays, and video would just be totally out.

Alas I'm posting as AC, so probably nobody will ever see this :)

But: I still have a working A4000 with cybergraphics, an 040, and 64 Mb. It's old, and I don't really use it any more, but it still boots. You might be surprised: it does better than you think it would, although it's no match for modern HW. It definately does not "collapse" playing mp3 files.

It will play MP3s with no troubles at all - in fact the system is quite responsive while doing so. I doubt an early 68000 amiga would be, but the later ones do just fine at this.

Video is more dicey, and depends on various factors. I can play 320x200 clips without any issue in mp3 format. Even 640x400 kinda-sorta works OK, although at that res you're starting to run into horsepower issues unless you use a fast-to-decode format. Past that, and it won't match a modern PC, which thinks nothing of full motion video at 10x7 or even 12x10.

But still, the machine is better than your post asserts. Not bad considering it's multiple orders of magnitude slower than modern hardware. Would I go back to using it? No way. But for its day, it kicked ass.

Re:amiga playing MP3 files

[Anonymous Coward]

Sorry, I meant video in mpg format, not mp3.

No need, you can ignore the benchmarks...

[msauve]

which are fundamentally flawed for real user needs. They compare different systems running the same software (can you believe?) That might be relevant in academia, but in the real world, it's much more useful to compare complete systems: processor, disk, OS and applications. When you do that, you'll find that for the bulk of common user applications (web browsing being a notable exception), today's systems simply aren't much faster than older ones. Compare a system running Windoze XP / Office XP running on a 3 GHz machine today with a Windoze 98 / Office 98 machine running on a Pentium II. Not much difference in usable speed (which I define as time to boot, time to launch an application, time to do a common task like write a letter or create a spreadsheet, etc.) Sure, recalc on a zillion cell spreadsheet will be faster, but two things work against improvement: 1) both machines spend most of their time waiting for the user to do something, and 2) bloatware.

Re:No need, you can ignore the benchmarks...

[mrbcs]

That's exactly why I have win 98 on my Athlon64 3000.

This thing is incredibly fast. I can load Photoshop 6 from a cold boot in about 3 or 4 seconds.

I hate wating.

whetstone

[Clay Pigeon -TPF-VS-]

Its so nice to see that the sse2 results were used instead of the raw x87 scores for the intel p4 cored chips http://www.tomshardware.com/cpu/20041221/images/ch art_007.png

athlon 2700 times

[Anonymous Coward]

Athlon 2700:

1.63user 0.05system 0:01.75elapsed 95%CPU

Pentium M 1500:

1.98user 0.04system 0:02.09elapsed 97%CPU

2x 2000 2.37 PowerPC G5

[Meneudo]

2x 2000 2.37 PowerPC G5 I think the parent's observations about this being misleading and varying system to system, OS to OS are very true.

Here is a benchmark I did from 386 to P4

[John Sokol]

benchmark

This is just looking at core cpu performance, not bus and external cache issues.

Re:I'm very sceptical about anything Tom's Hardwar

[stupidkiwi]

Well he may or may not take AMD advertising, but he has weighted the results at least in part toward Intel CPUs. I have not built a machine in some time so I can't say for all the results, but when AMD was shipping the first of the 1.3 Ghz Athlons the standard ram was DDR266. I still use the ram I bought at that time (Over 5 gig for various machines) and at that time Rambus ram was twice the price and as rare as hens teeth. Why does Tom use SD ram on the AMD chips in this test for some time after DDR was standard? And why does he use Rambus memory on the Intel chips as soon as they support it? I get more reliable charts by staring at the streaks I leave on my used toilet tisssue.`

quasi 5 awfulyears without Merced & Alpha kill

[Anonymous Coward]

Since year 2000 until now before the next week, year 2005.

Merced's speculative-execution appeared in the 1995-1999 magazines didn't work until never.
Alpha 21364 was killed by the unexistent HP-Intel's Merced.
Digital DEC was sold ...

open4free ©

Corrected link to Part 1

[Lux]

Doah! Sorry about the skanky link in my last response. Here's a correct one.

What a delightful walk down memory lane.

[interstellar_donkey]

Been an AMD man (not counting laptops), and have had the same main computer now since 1991...much in the same way a lumberjack can claim he's had the same axe for 13 years but replaced the handle 9 times and the head 14 times.

~1989: Intel? 8086, 640k ram, ?video
~1991: AMD 386 DX 40, 4 megs ram, 1meg video
~1994: AMD 386 DX-2 66, 5 megs ram, 1 meg video
~1996: AMD 486 DX-4 133, 5 megs ram, 2 meg video
~1997: AMD K-5 166, 16 megs ram, 2 meg video
~1999: AMD K-6 300, 16 megs ram, 4 meg video
~2001: AMD Duron 600, 128 megs ram, 16 meg video
~2003: AMD Athelon 1900+, 512 megs ram, 64 meg video

Still have the 1900+, but added a new video card with a quarter gig of ram on it. It simply amazes me how much things have changed. I have a laptop now that theoretically should outperform my desktop (except with games). Though looking at that time schedule, I think it's probably time to upgrade my main PC.

Is Socket 940 really dead...

[f1rb]

... as claimed here (presumably as viewed from the desktop)?

I can just imagine PHBs cancelling orders for Opteron servers because "Tom says they don't make them any more".

BULLSHIT.

[Anonymous Coward]

"Turns out the OS never really crashes because there's always a cpu left to bring up the ctrl-alt-del screen with, so you can kill all the OS processes on the other CPU that DID crash.."

I call bullshit.

a.) Processes don't crash on a per-processor basis.

b.) There is no "alt+ctrl+delete" screen in XP. Instead, it brings task-manager right up. It's possible you could have meant that, but I doubt it.

c.) You're the first to mention it.

This is exactly the sort of stupid story that the anti-MS pro-Linux users here would believe. Pity it isn't true.

Re:BULLSHIT.

[Anonymous Coward]

a) Processes crash on a per-process basis, and since most of them are single-threaded, on a dual-CPU PC, there's a second processor that's free to perform the work other processes require if one process suddenly wants 100% CPU. ie. a high-priority process can't hog 100% of processing time unless it's multithreaded and at least 2 threads both go rogue.

b) That's exactly what he was referring to.

c) He's the first to mention it because everyone else with half a clue already knows this and considers that knowledge to be so fundamental that it's not worth mentioning. "oh btw, the sky is blue"

Re:BULLSHIT.

[FatherOfONe]

I don't want to start a flame war, but I belive you are referring to threads. One processor can handle multiple threads just fine, and two or more usually better. By adding one or more processors to Windows, it will by no way "fix" the lock up issue. It might make the system perform better under certain loads, but if you have a bad video driver (ATI), it will still take down the entire system. If you have a bad network task (something trying to map a drive to a bogus address) then your system will still crawl down. Very Very Very Very (~Very) seldom does one thread/process take up 100% CPU and STOP you from killing it in Windows or Linux. However even in that case, it would still be possible for someone to write a bad app that spawned a bunch of threads that did the same to all your processors.

"There are no 286 AMDs." Here's one.

[SteeldrivingJon]

Here's a picture of an AMD 286. Real close up.

http://micro.magnet.fsu.edu/chipshots/amd/286.ht ml

"The Advanced Micro Devices (AMD) 286 microprocessor, fabricated and distributed under license from Intel, utilizes identical architecture and the source code developed for the i80286 chip. AMD boosted Intel's original 6, 10, and 12 megahertz clock speed versions, which are powered at 5 volts, to standard models featuring higher speeds ranging up to 20 megahertz. During the mid-1980s, AMD launched the microprocessor clone market with their 286A processor, which followed their in-house version of the 287 math coprocessor. Released in 12 and 16 megahertz clock speeds, the 286A model did not break new ground, but did feature expanded memory specifications (EMS) and the ability to reassume protected mode, neither which was supported by the Intel 286."

Accuracy?

[c_spencer100]

Are the temperature specs posted in this picture really accurate ? That's interesting, because I'm about to upgrade an old pc. The currect case is ok, but it has mediocre ventilation, so I was going with a slower processer (say an Athlon 1800+) to reduce heat. By these specs, I'd be better off with the Athlon 2800+ (which was the one I wanted anyways...)

The funny thing is

[Freeman-Jo]

Pentium 233 MMX can convert MPEG2>DivX in 113 minutes while converting to XviD only take 59 minutes. cut it down nearly by half.
On the other hand P4 570 (3.8GHz) take 1:40 minutes for a DivX and 2:23 minutes for XviD. Almost double.

What is that mean? Is the CPU architechture very improving?

Uh, it can use SDRAM

[lidocaineus]

Any K6 can use SDRAM, ie anything a Pentium 3 can use, so can a K6-2. It may be limited to a 66 or 100 mhz fsb, but that doesn't mean a standard PC133 stick won't work perfectly in it. I still use a K6-2/300 as a very decent file server - 3 simulataneous users pulling / putting files on it + serving media files from a raid array (the regular linux software kernel one!) works fine.

uhhh, guys???

[Anonymous Coward]

http://www.spec.org/ :(

How slow? (was Re:100 architectures?!)

[imroy]

1919 2.18 AMD Athlon-XP 2600+
266 24.15 AMD K6-II 266
25 200.22 TI MicroSparc (Sparcstation LX)

Unfair comparison?

[mcbevin]

Most of the benchmarks are gaming and thus more dependant on the graphics card. Given that not all computers are using the same graphics card, that makes them somewhat unfair.

More interesting are thus the non-synthetic non-graphics application benchmarks, but unfortunately theres just four of these.

What might be interesting with the graphics benchmarks would be to outfit each computer with the state-of-the-art graphics card of its release date. Also unfair, but given that the graphics card used in the test is not uniform anyway (having a somewhat sudden cut-off for computers with only PCI and not PCIe or AGP) it might be a slightly more interesting setup.

SIMD Programming vs General Purpose Programming.

[Anonymous Coward]

What is that mean? Is the CPU architechture very improving?

NO, it's a trap.

DivX uses P4's SIMD instructions like SSE2 while than XviD uses general purpose instructions.

The only overloaded performance of P4 is not the P4 itself, it's otherwise, many programs are hardfully programmed in SIMD-assembly instead of i686-assembly to beat the P4 performance.

open4free © : hardful packed instructions vs easyful general purpose instructions.

Re:I'm very sceptical about anything Tom's Hardwar

[Anonymous Coward]

wow your criticism is so useful. please, don't just stop there at shitting on all the work they did. why not tell us either a) how to find a better benchmark page or b) that there's a dicrepancy in the benchmark that indicates some kind of bias.
or you could realise that you're the asshole with an agenda here and sod off.

Re:SIMD Programming vs General Purpose Programming

[Freeman-Jo]

Good point, but why can't the improvement be done at the hardware level that's transparent to the users and developers.

I actually use a K5/166.

[ponos]

The differences are not that dramatic if you are reasonably efficient. I use a (heavily) upgraded K5/166 with 48MB RAM, 40GB drive (BIOS won't see it correctly, but hda=x,y,z solved this issue with linux), PCI TNT2 with 32MB, SB Live! and a Plextor Ultra-SCSI CDROM on an adaptec controller. I also added a 3com 10/100 Ethernet and this thing rox0rz.

I use it to run linux and it is quite adequate for latex text editing. The system is snappy enough for emacs and xfce. Only when you start an MP3 player do you realise that media decoding can eat up ~30% CPU (there are huge differences between various players, of course). I also record some 44.1/16b music from analog and use it as a multimedia box. It can play VCDs too.

As for network use, well, rsync (encrypted) and ssh are really heavy but plain ftp runs pretty well either as a client or server. This machine will easily saturate a 10MBps line with unencrypted static content so it is not that bad for home use as a backup server/multimedia box. Network throughput peaks at about 70MBps if the machine is idle.

P.

P.S. For comparison, my other system is Athlon64 3200+ with 1GB CL2 RAM, 9800Pro and 160GB SATA.

Don't believe the Hype

[MasTRE]

While this is certainly interesting to see, what I like the most about it is that it actually proves the insanity of the Megahertz race. Using the P3/600Mhz as my low end and P4EE/3460 as my high end, I am not noticing any significant instance where the expensive whore is faster by at least an order of magnitude.

Let us not forget that it's not just the CPU but the whole supporting cast that has vastly improved over the years. Even with all the improvements in non-CPU technologies such as RAM, chipset and FSB, a P4 Gallatin CPU running at 3460 MHz does not perform 6x (3460/600=6.06) faster than a P3 Coppermine CPU running at 600Mhz in most cases (not counting the SIMD benchmarks that rely primarily on SSE2, etc.).

So what does this mean? It pretty much means that the great majority of us are buying marketing hype. At retail.