lol...just seen ya edit..... peace :D
Printable View
lol...just seen ya edit..... peace :D
A word of warning re overheated AMD cpu's - AMD are now VERY picky about replacing overheated cpu's - my supplier will not replace them if there is the slightest sign that the cpu has been overheated because they know that AMD will NOT replace them. I think this policy has been in place since the advent of the Thoroughbred series, and is being particularly enforced with the Barton series of chips.
I am told that if they are in any doubt whether the processor has been overheated they will run extra tests and will not replace the processor if overheating is proved. So anyone thinking of trying to get away with using minimal cooling should think again - AMD are trying hard to get away from the image that their processors run hot, and I think justifiably so with their latest offerings.
omg...most people that buy computers dont know squat about a cpu, ram, or whatever...and you seem to say that AMD is only being sold to the "advanced user" that could buy a cooling system to USE the computer? for crying out loud man.... get the things str8 b4 u post this...Quote:
Originally posted by lynx@7 September 2003 - 10:38
So poor cooling is to blame.
DWk
i dont think p4 is gonna go higher than 4 or 4.5 since they are putting out these new processors...well not soooo new.... but newest from Intel (Itanium and Xeon)...Quote:
Originally posted by 3RA1N1AC@7 September 2003 - 10:16
i don't know how high P4 clock frequencies are supposed to eventually go, but it appears to be a design that will end up dealing very well with extremely high clock speeds.
good thing bout p4 is the 800mhz fsb, but i bet getting some ram sticks like that must be reaaaaaaaaly expensive :D
EDIT: i forgot to mention Centrino :D
DWk
this topic needs some serious water cooling me thinks! or has it got to much? its either a tad frosty or overheating in here depending on how you look at it ;)
keke :D
DWk
nice shot... :PQuote:
Originally posted by SnnY@7 September 2003 - 13:41
http://img.villagephotos.com/p/2003-9/367722/oc.jpg
:D :lol:
I'm just happy it isn't my own comp. :lol:
Poor guy.
The problem here is that there are a lot of people in here spouting bullshit about stuff they have no idea about.Quote:
Originally posted by boyzeee@7 September 2003 - 13:32
this topic needs some serious water cooling me thinks! or has it got to much? its either a tad frosty or overheating in here depending on how you look at it ;)
Some examples:
Wrong. You can't generalise like this, it's all dependent on which chips you're talking about and which conditions they're operating in. It has been proved that the highest-end P4s are marginally faster than their Athlon equivalents.Quote:
in my experience, AMD out performs P4 in the real world, under everyday conditions, which is what realy counts
:lol: :lol: :lol: :lol: :lol:Quote:
in my opinion, amd's r for experienced overclockers
You'll find that they do. AMD are not stupid enough to believe that clock speed defines the processing power of a chip, so they do not encourage this point of view.Quote:
yea they are cheaper, but you may be disappointed by the results because AMD doesnt put the actual speed on the cpu box
:lol: :lol: :lol: :lol: :lol:Quote:
like i said, intels r fast straight out of the box. amd's have to be overclocked, and u have to get all these cooling systems.......
i think intels can be overclocked 2, but there won't be much of a point to do that......
Procedure for installing an AMD CPU:Quote:
amds r good, but they r for more advanced users. p4's r for the hardware nowledge deprived.
- lift lever on CPU socket
- gently place CPU into socket, taking care to align pins properly
- lower lever after checking the CPU is seated correctly
- apply thermal paste to die of processor
- place cooler on CPU, taking care to align it properly
- engage clip on cooler
- plug in cooler's power cable
Procedure for correctly installing an Intel CPU:
- lift lever on CPU socket
- gently place CPU into socket, taking care to align pins properly
- lower lever after checking the CPU is seated correctly
- apply thermal paste to die of processor
- place cooler on CPU, taking care to align it properly
- engage clip on cooler
- plug in cooler's power cable
:lol: :lol: :lol: :lol: :lol:Quote:
AMD Athlon Processors run hotter than intels because they are just ALL overclocked to begin with coz AMD Couldnt or just cant be arsed to make a processor from scratch that will compete with the P4's speed.
AMD's Athlon line is one of the longest evolution chains in the CPU world, and they have progressed through many cores along the way, from Thunderbird to Palomino through the three revisions of Thouroughbred up until the Bartons.Quote:
I know what you are saying but what i meant was instead of amd designing new processors they basically increase the clock speed of the ones they got already with the exception of barton, the design of the xp2.0 is basically the same as the 1400 but amd themselves have just overclocked it
So in actual fact they have been revising their CPU architecture a lot.
For maximum effieciency, most experts agree that your FSB frequency should match your RAM frequency. Thus, the 800MHz FSB does not deliver twice the performance of a 400MHz FSB, since they'll both have to work on 400MHz DDR RAM.Quote:
good thing bout p4 is the 800mhz fsb, but i bet getting some ram sticks like that must be reaaaaaaaaly expensive
:blink: What on earth does Centrino have to do with it?Quote:
EDIT: i forgot to mention Centrino
If you have no idea what you're talking about, that is cool; ask questions and we will happily answer. But don't start spouting crap, 'cos anyone with any knowledge will just tear you apart, and with good reason.
If you want to learn more about hardware, have a look at some hardware sites such as Tom's Hardware Guide, AnandTech or better still Ars Technica.
One of the biggest reasons for Intel's continued dominance of the CPU market is due to people being misinformed. If everyone knew how much better value AMD's processors are, Intel would be a dead company.
This thread is a good example of that.
http://www.ml20.nowinbeta.org/thumbsup.gif Nice one lamsey, I'm glad someone cleared up all the crap that was being sprouted in this thread
Is it really such a good thing ?Quote:
Originally posted by DWk@7 September 2003 - 14:30
good thing bout p4 is the 800mhz fsb, but i bet getting some ram sticks like that must be reaaaaaaaaly expensive :D
Once again, you have to remember that higher frequencies means higher temperatures, so it is a far better idea if you can find a way of increasing memory speed without raising frequency. This is the reason for ddr memory - twice the data throughput for the same frequency (DDR400 ram actually only runs at 200MHz). Power consumption rises in proportion to the square of the frequency, so (everything else being equal) memory on an 800MHz bus would generate 4 times the heat of the same memory on a 400MHz bus.
Of course, everything else is not equal, the core memory voltage is lowered in order to reduce the power consumption, this would make lower performance memory unstable so higher performance (and therefore, as you have suggested, more expensive) memory has to be used.
The solution is multi-channel memory transfers, so that more than one memory bank is transferring data at the same time. For example 4 banks of memory each running at 200 MHz (DDR400) could be configured to supply data simultaneously giving an aggregate data rate of 1600 MHz. Power consumption would be exactly the same as a single memory bank of 4 times the size running at 200MHz. Conversely, a single bank running at 800MHz (to give a data rate of 1600MHz) would consume 16 times as much power.
This sort of technology is already in use on high-power mainframe comps, and is now starting to appear in pc chipsets (eg Nvidia NForce2). The real way to progress is to do much more within existing frequencies rather that constantly attempt to produce higher and higher frequencies with all the associated problems.
AMD is showing the way in processor design, it's latest 400MHz FSB XP3000+ processor typically uses less power than the 266MHz FSB XP2000+, and only slightly more power consumption when running flat out - you are certainly not going to get those sort of improvements by constantly raising clock speeds.
Edit: and I wish I had seen Lamsey's piece before I wrote all of that.
And I learned the above while doing a project in high school for Advanced Higher Computing; it's not difficult.Quote:
Nice one lamsey, I'm glad someone cleared up all the crap that was being sprouted in this thread
Even the more complex stuff I've learned since then like the differences between the caching methods, the ins and outs of Hyperthreading, etc., are not difficult to understand.
edit: @lynx, the latest AMD Athlon XP is actually the Barton-cored 3200+.
@Lamsey, yes, I know the 3200 is the latest processor, when I refered to the 3000 I was meaning 400MHz FSB was the latest offering. The 3200 processor actually uses more power which is why I didn't quote that one, and there have also been mutterings about the performance of the 3200.
Ah, sorry, misread you there.Quote:
Originally posted by lynx@7 September 2003 - 21:45
@Lamsey, yes, I know the 3200 is the latest processor, when I refered to the 3000 I was meaning 400MHz FSB was the latest offering. The 3200 processor actually uses more power which is why I didn't quote that one, and there have also been mutterings about the performance of the 3200.
The 3200+ is probably over-agressively named; I think 3100+ would be more accurate.
What many people don't realise is that the model numbers are based on the original Athlon's performance. The model number reflects the speed in MHz of an original Athlon.
However, the Intel P4 architecture is developing, while the original Athlon is the same as it always was; the Athlon model ratings, which started out better than equivalent P4 clock ratings, are now falling behind their equivalents.
This is because P4s were originally less efficient clock-for-clock than the original Athlon, but the newer P4s are now more efficent clock-for-clock, hence the apparent inequalties in the model rating system.
However, even taking this into account, 3200+ seems overly agressive for that chip, possibly a product of AMD's problems with matching Intel, due of course to the massively late launch of Hammer, or Athlon64.
Hopefully, model numbers will be less of a problem with Athlon64; I think they're planning on moving to a new rating system.
i meant the thing about the cpu speed on the box as if they dont say that 1800+ is 1.53ghz.... in the box my processor came it didnt say 1.53ghz...only 1800+... didnt mean that they were "cheating" hehe...
DWk
It says the the rating and the clock speed on the box.
Digging.Quote:
Originally posted by DWk@7 September 2003 - 23:21
i meant the thing about the cpu speed on the box as if they dont say that 1800+ is 1.53ghz.... in the box my processor came it didnt say 1.53ghz...only 1800+... didnt mean that they were "cheating" hehe...
DWk
Hole.
Deeper.
Clock speed alone tells you nothing about the speed of a CPU.
An AMD Athlon XP 3000+ runs at only 2.167 GHz, but it kicks the crap out of an Intel P4 running the same clock speed.
Lose your fascination with clock speed, the frequency of the CPU clock is misleading when comparing two different processor architectures.
Okay, one last time, FOR EVERYONE WHO SAYS AMD DOESNT SHOW THEIR CLOCK SPEED ON THE FREAKING BOX.
http://www.angelfire.com/ex/beatle/Pict0004.JPG
I took that off my 2500 Box.
Now guys, look, my point in this post is this, and its a small one. (All prices from www.newegg.com, great place to buy parts. and great prices)
AMD 1700+ XP = 60 dollars.
AMD 1800+ XP = 62 dollars.
Now, thats if you go AMD, if you got Intel, here are your options, for SIMILAR AMOUNT OF MONEY.
Intel Celeron 1.7 Ghz = 59 Dollars.
Intel Celeron 1.8 Ghz = 61 Dollars.
Pentium III 1 Ghz = 96 Dollars.
Pentium IV 1.8A Ghz = 127 Dollars.
And if you guys doubt this, here is a link
http://www.newegg.com/app/ListProduct.asp?...rtby=22&order=0
Should work, I think all the queries are saved. And I hope to god none of you Intel fan boys dont try and say, "well there you go, you just proved yourself wrong, that celeron is just as much as the AMD XP." For those of you who are thinking about it, Celerons are the cheap pieces that are in all the really, REALLY low end systems. www.emachines.com
AMD = Best bang for the buck. Like I just did, in your supposed 'real world' situations, dont compare performance, COMPARE THE FREAKING PRICE. I dont know about you guys, but I things get pretty simple in deciding on my proessor if I DONT HAVE THE MONEY FOR ONE OF THE OPTIONS.
I mean honestly guys, first you say, oh well, the 1.8Ghz P4 out performs the 1800+ XP. But, FOR THE 127 DOLLARS, YOU COULD BE AN AMD 2600+ XP. But of course then, you guys try and say "oh, well, you have to pay 80 dollars more than an 1800+. HORRIBLE LOGIC!
well, even then, if the P4 stops at 4ghz or 4.5ghz, that would mean that the final P4s ended up being 2ghz+ faster than the very first P4s. i would call that a successful design, if they're able to get so much mileage out of it. and the same goes for the Athlon, imho.Quote:
Originally posted by DWk@7 September 2003 - 05:30
i dont think p4 is gonna go higher than 4 or 4.5 since they are putting out these new processors...
Architecture Architecture Architecture
Its all about the Architecture
Can someone give me the temp for a p4 3.06HT Cpu at full maxed out CPU%?
Take a look at the size of the die for the p4 and for the amd athlon line, the p4 has a huge die (ergo muchos more $/£ since u get less outta the wafer and therfore less chips per wafer = more money)
The p4 also has a metal casing to the die, area to transmit heat is greater on a intel than a amd, so amd's do run hotter, they have a smaller die and less area to transmit the heat. i have to have my case opened (since new chip) cos i got a poor case and cooling, and ive got shitty silver thermal paste, if i where to shove my old thunderbird copper base heatsink with some artic silver 3 instead of the oem ( cos the old brace on the copper heatsink is just a bitch to equip) i would lower the temp from 51C to 40 odd C. case closed also.
but as it stands my amd2000+ operates at 44C base and 51C full 100% cpu case open. case closed 51 base and 60C full 100%. 60C for an amd is a stable temp, people are just used to overclockers temps where they try to get their chip as cool as poss'. amds can go as high as 90C b4 they burn out. my mobo has settings to shut it down at certain temps, and the lowest temp is 75C . (chaintech 7njs Ultra 400) which i think has to be one of the best amd mob's around right now.
my old amd t-bird ran at 37C full wack with 100% cpu load and that same old copper based bitch to fit heatsink and artic silver 2 case closed. !!!!!!
and then p4's only stay cooler cos they de-clock themselves when they get hot.
Leave an amd on over nite and it still has the same performance in the morning. leave a p4 overnite and its prolly' dropped the closk by 200mhz to lower the cpu temp to what the manufacturer has deemed "cool"
my 2p
Xan
Depends solely on the cooling, there is no figure for this. What u want is the rate of heat output (or consumption) in watts, which i dunno offhandQuote:
Can someone give me the temp for a p4 3.06HT Cpu at full maxed out CPU%?
If the heatsink and thermal paste is set up properly then the metal casing makes for poorer cooling not better. but it is true that the smaller die size means lower rate of heat dissipationQuote:
The p4 also has a metal casing to the die, area to transmit heat is greater on a intel than a amd, so amd's do run hotter,
they only lower their operating frequency when the temperature becomes dangerous to the chip (ie 80 degrees or something like that) . A p4 adequately cooled will be the same speed in the morning. If it was reallly poorly cooled it would slow down as u say, an AMD left poorly cooled would simply shut off. (I think the old thing about AMD chips burning out has been addressed and all recent chips shouldn't do that)Quote:
and then p4's only stay cooler cos they de-clock themselves when they get hot.
Leave an amd on over nite and it still has the same performance in the morning. leave a p4 overnite and its prolly' dropped the closk by 200mhz to lower the cpu temp to what the manufacturer has deemed "cool"
Ok u guys can debate "clock time" :lol: and all that other stuff but the hardcore fact is that Intel's stock kicks amd's stock's ass the only reason amd's iz above the 10 dollar mark rite now cuz they announced opteron 64 bit that also runs 32 bit. BTW INTEL HAD 64 BIT BEFORE AMD JUSS THAT THEY DUN RUN 32 BIT LIKE AMD(THere called XEON)
Did you see that bit about not posting if you don't know what you're talking about?Quote:
Originally posted by Secret Squirrel@8 September 2003 - 23:43
Ok u guys can debate "clock time" :lol: and all that other stuff but the hardcore fact is that Intel's stock kicks amd's stock's ass the only reason amd's iz above the 10 dollar mark rite now cuz they announced opteron 64 bit that also runs 32 bit. BTW INTEL HAD 64 BIT BEFORE AMD JUSS THAT THEY DUN RUN 32 BIT LIKE AMD(THere called XEON)
No?
Oh well...
Just about to correct a couple of errors, then saw Lamsey's post, so never mind.Quote:
Originally posted by Secret Squirrel@9 September 2003 - 00:43
Ok u guys can debate "clock time" :lol: and all that other stuff but the hardcore fact is that Intel's stock kicks amd's stock's ass the only reason amd's iz above the 10 dollar mark rite now cuz they announced opteron 64 bit that also runs 32 bit. BTW INTEL HAD 64 BIT BEFORE AMD JUSS THAT THEY DUN RUN 32 BIT LIKE AMD(THere called XEON)
I've seen this exact debate on several forums that I visit and it always seems to degenerate into throwing statistics and test numbers back and forth.
What is the real world difference?
I have to assume that this argument is mostly of interest to gamers, as most users aren't pushing their CPUs at 100% for hours on end.
So, is there a real difference between comparable chips when actually playing a game?
a lot of the people who get worked up about CPU comparisons are video game players. that is true. sure, if you just check your email, surf the web, download a bit of pr0nz, listen to some mp3s, you're not going to make a modern CPU break a sweat.Quote:
Originally posted by clocker@8 September 2003 - 17:41
I've seen this exact debate on several forums that I visit and it always seems to degenerate into throwing statistics and test numbers back and forth.
What is the real world difference?
I have to assume that this argument is mostly of interest to gamers, as most users aren't pushing their CPUs at 100% for hours on end.
So, is there a real difference between comparable chips when actually playing a game?
but games are not the only things that push CPUs to 100% of their abilities. there are plenty of people who get paid to use computers all day, who would be concerned about CPU comparisons. editing audio, video, creating multimedia/internet content, using photoshop or illustrator, running scientific programs (i admit, this is a bit more rare than the other professional types)... any of that can and will easily use 100% of a CPU's cycles and CPU speed can make a huge difference in how long it takes you to complete your tasks. a lot of people do some of those more creative things at home as part-time work, or just for their own amusement-- faster CPUs do benefit their activities.
as for the effect of CPU speed on games, it depends. the results vary wildly from one game to the next because any modern 3D game depends on the combined speeds of the CPU and the 3D-accelerated video card (designed to remove much of the burden from the CPU, of rendering 3D graphics). some games rely more heavily on the speed of the CPU, some rely more heavily on the speed of the video card. two classic examples are Quake 3 Arena and Unreal Tournament. in these reflex-intensive games, displaying a high rate of frames per second benefits the player by presenting a more accurate, smoothly animated representation of the action, so the player can respond more confidently based on more reliable visual information. Quake 3 Arena's frame rate flies when you play it with a high-end video card and a lower-end CPU-- it is not especially dependent on CPU speed. Unreal Tournament on the other hand benefits to some extent from video card upgrades, but fast CPUs are what really make its frame rate improve.
of course, those two games are a few years old... so there is such a thing as "more than enough computer power" for older games. after you pass a certain threshold, there's really no discernible difference between 110 frames per second or 210 frames per second. but then the next generation of games is released, following the same pattern of hardware-dependence but wanting MORE, rendering last year's best-PC-on-the-block into an outdated piece of junk because it doesn't have enough speed.
Brainiac,
Thanks for the reply.
Well written.
I realize that there are other apps that can intensively use a CPUs cycles.
I guess my point is that so far all I read here are number comparisons.
Or theoretical debates about the advantages about different archetectures etc.
I think it would be more informative if someone could post something like: " I've played Quake with both setups and I like AMD because..." .
Most of this discussion seems to be pretty blue-sky.
When I was building my first system a couple of weeks ago, I asked the guys at my local comp shop this same question.
They didn't launch into a dissertation about stats or theoretical advantages.
Their reply: "How much money ya got?".
The very high frame rates of some of the modern games are ridiculous - above about 100 fps (about 50fps for lcd) the refresh rate of the phosphor on the monitor (or lcd pixel) cannot keep up with the frame rate, so anything above that is totally wasted. And in any case, the human eye cannot react at anything like those speeds (actually only about 8 fps), although the frame rate needs to be much faster than the eye to avoid strobing effects.
Game developers should concentrate on getting more detail rather than higher frame rates, or better still make better games based on current processor speeds rather than trying to produce games that stretch pc's further and further. I suspect we are getting past the limit of what is required in terms of frame rate, and getting near to the limit of what is required in terms of picture detail.
I often have periods where my processor is running at 100%, but not so much that I can justify spending a lot of money on the top processor chips. I set myself a budget and find out what sort of performance I can get for that money. I don't care whose tests you use, the answer is always AMD. I've currently got a XP1700+, Sandra tells me that the performance is bettter than a 1.6GHz Pentium and worse than a 1.8Ghz Pentium, but it cost me a lot less than any Intel chip. I'm currently looking to upgrade, the XP2400+ beckons (I think that's the fastest chip I can get for my current M'board), and £63.43 seems a very reasonable price, far better than £132.92 for a 2.4GHz P4.
I think someone was quoting stock prices earlier - all I can say is that if so many people are foolish enough to pay excessive prices for their processor chips, it is hardly surprising that Intel has a high stock valuation.
well, the effect of a CPU's brand on games is relatively intangible. upgrading your CPU may or may not contribute to an increase in frames-per-second, it may or may not make the game run more smoothly. i would not expect a person to be able to identify Intel or AMD (like a Coke vs Pepsi taste test) if they were given a chance to play the same game on two unmarked computers.
in contrast, you upgrade a 3D video card, and you get more frames per second, you can turn up the detail levels, you may be able to enable more special effects that your older card couldn't produce, etc. some people can pretty easily tell which picture is produced by which card, because of certain quirks or characteristics of each brand's display methods. the characteristics and features of the video card are obvious.
but CPUs? i would be incredibly surprised if someone could identify the two brands in a "blind" test, to the point where a preference is justified on performance or stability alone. their brand-exclusive features are entirely speed-related (aside from throttling/idling behavior). both brands perform well, both brands make 100% stable CPUs. CPUs either work or don't work, period-- improper cooling, shoddy motherboards & RAM, etc are completely separate issues. there just is no obvious difference to identify the CPU brand, if you haven't already been told which one you're using. "i play Quake on AMD because AMD makes Quake look better, sound better, feel better." anyone who claims such a thing (about Intel or AMD) is just fooling themselves.
So would that make Lamsey's assertion that "it all comes down to money"* valid then?Quote:
Originally posted by 3RA1N1AC@8 September 2003 - 23:42
well, the effect of a CPU's brand on games is relatively intangible. upgrading your CPU may or may not contribute to an increase in frames-per-second, it may or may not make the game run more smoothly. i would not expect a person to be able to identify Intel or AMD (like a Coke vs Pepsi taste test) if they were given a chance to play the same game on two unmarked computers.
in contrast, you upgrade a 3D video card, and you get more frames per second, you can turn up the detail levels, you may be able to enable more special effects that your older card couldn't produce, etc. some people can pretty easily tell which picture is produced by which card, because of certain quirks or characteristics of each brand's display methods. the characteristics and features of the video card are obvious.
but CPUs? i would be incredibly surprised if someone could identify the two brands in a "blind" test, to the point where a preference is justified on performance or stability alone. their brand-exclusive features are entirely speed-related (aside from throttling/idling behavior). both brands perform well, both brands make 100% stable CPUs. CPUs either work or don't work, period-- improper cooling, shoddy motherboards & RAM, etc are completely separate issues. there just is no obvious difference to identify the CPU brand, if you haven't already been told which one you're using. "i play Quake on AMD because AMD makes Quake look better, sound better, feel better." anyone who claims such a thing (about Intel or AMD) is just fooling themselves.
* paraphrase
Of course when choosing a chip the money is all important. If youve got tons of money to spare and are just looking to buy the very best and latest system then its all about the top spec chip, otherwise you will want the best chip you can afford (without sacrificing the quality of the other components). Also the point about discussing which chip is faster is not only looking at what could use 100% cpu now, but also how long the chip will be able to cope before its obsolete/can't play hte games being released.
Thankyou for that really nice post I enjoyed reading it =)Quote:
Originally posted by ilw@8 September 2003 - 09:31
Quote:
Depends solely on the cooling, there is no figure for this. What u want is the rate of heat output (or consumption) in watts, which i dunno offhand
To clarify: Intel P4 3.06HT with the OEM cooling.
Basically a prebuild that you would buy from any major suckage retail shop eg PC world etc
Thanks
AMD ownz all
Assumtions: "Intel" = P4 3.06GHz; "AMD" = AthlonXP 3000+ (2.1GHz)
Cost (from NewEgg.com)
Intel: $379.00
AMD: $269.00
AMD is cheaper. (Intel - 0; AMD - 1)
Intel = $0.12/MHz
AMD = $0.13/MHz
Intel squeezes by AMD at $0.01 cheaper per MHz. (Intel - 1; AMD - 1)
(Following info gather from Tom's Hardware Guide: "Benchmark Marathon: 65 CPUs from 100 MHz to 3066 MHz")
OpenGL Benchmarks (1024x768 / 32 bit / 85Hz)
Intel: 351.3 FPS
AMD: 311.2 FPS
Intel gives you more FPS. (Intel - 2; AMD - 1)
Intel = $0.92/FPS;
AMD = $0.86/FPS;
AMD offers better price/FPS than Intel. (Intel - 2; AMD - 2)
Intel = 0.11 FPS/MHz
AMD = 0.14 FPS/MHz
AMD offers better FPS per MHz than Intel. (Intel - 2; AMD - 3)
Direct3D Benchmarks (1024x768 / 32 bit / 85Hz)
Intel: 15878
AMD: 15655
Intel squeaks by with a higher score. (Intel - 3; AMD - 3)
Intel = 41.89 pts/$
AMD = 58.20 pts/$
AMD offers more points per dollar. (Intel - 3; AMD - 4)
Intel = 5.07 pts/MHz
AMD = 7.28 pts/MHz
AMD also offers more points per MHz. (Intel - 3; AMD - 5)
Audio/Video Benchmarks (1178 MB Wave / VBR)
Intel: 72 seconds
AMD: 110 seconds
Intel beats AMD when it comes to encoding. (Intel - 4; AMD - 5)
Intel = 0.043 (MB/sec)/dollar
AMD = 0.039 (MB/sec)/dollar
Intel offers slightly faster encoding per dollar (Intel - 5; AMD - 5)
Intel = 0.0052 (MB/sec)/MHz
AMD = 0.0050 (MB/sec)/MHz
Intel also offers slighltly faster encoding per MHz. (Intel - 6; AMD - 5)
Synthetic Benchmarks - CPU (PC Mark 2002) (1280x1024 / 32 bit / 85Hz)
Intel: 7571
AMD: 6646
Intel gives you a higher score. (Intel - 7; AMD - 5)
Intel = 19.98 pts/$
AMD = 24.71 pts/$
AMD offers more points per dollar, however. (Intel - 7; AMD - 6)
Intel = 2.42 pts/MHz
AMD = 3.09 pts/MHz
AMD also offers more pts per MHz. (Intel - 7; AMD - 7)
Synthetic Benchmarks - Memory (PC Mark 2002)
Intel: 8120
AMD: 6853
Again, Intel gives you a higher score. (Intel - 8; AMD - 7)
Intel = 21.42 pts/$
AMD = 21.76 pts/$
Wow, a close one, but again, AMD offers more points per dollar. (Intel - 8; AMD - 8)
Intel = 2.59 pts/MHz
AMD = 3.19 pts/MHz
AMD offers more points per MHz, also. (Intel - 8; AMD - 9)
Applications Benchmarks (File Compression: WinRAR 3.1) (178 MB)
Intel: 53 seconds
AMD: 69 seconds
Intel beats AMD in file compression. (Intel - 9; AMD - 9)
Intel = 0.0087 (MB/sec)/dollar
AMD = 0.0096 (MB/sec)/dollar
AMD offers faster file compression per dollar (Intel - 9; AMD - 10)
Intel = 0.0011 (MB/sec)/MHz
AMD = 0.0012 (MB/sec)/MHz
AMD also offers slightly faster file compression per MHz. (Intel - 9; AMD - 11)
Conclusion:
Overall, AMD just barely beats out Intel. However, if you like big numbers, Intel is the way to go (Intel - 6; AMD - 1). If you're more concerned about bang-for-your-buck, AMD is a must (Intel - 3; AMD - 10).
There you have it...
Oh great, another person who's obessed with clock rates.
That's a very nice post and well thought out, but you really need to lose the clock rate fascination.
It's not just about clock speed. It's the performance per advertised clock speed, which AMD clearly wins at. If it was about clock speed, Intel would win hands down.
So, how do you suggest comparing these processors without getting into their clock speeds? I don't see anyone else actually trying figure anything out. Just a lot of meaningless "you're wrong," "no, you're wrong," "you're all wrong" bullshit...
Hey, I'm not saying that Intel's perfect. In term of Front Side Bus Frequency, they are beaten, by IBM, with their G5 processer which has a 1GHz FSB.
AMD have a rather useful thing called a model rating. If you actually read my posts above on the subject, you'd see why clock speed is often irrelevant.Quote:
Originally posted by Cl1mh4224rd@21 September 2003 - 11:43
So, how do you suggest comparing these processors without getting into their clock speeds? I don't see anyone else actually trying figure anything out. Just a lot of meaningless "you're wrong," "no, you're wrong," "you're all wrong" bullshit...
I prefer AMD myself, but the model rating is useless. I know you know it's just the comparative clock speed of what an earlier AMD chip design would've been capable of. If Intel also used a model rating like AMD, I'm sure the P4 3.06GHz would be the "Intel 4000+", which means clock speeds are just obfuscated even more, and no other choice but to look at the actual clock speed of the chip.Quote:
Originally posted by Lamsey@21 September 2003 - 14:46
AMD have a rather useful thing called a model rating. If you actually read my posts above on the subject, you'd see why clock speed is often irrelevant.
Seems as though you're trying to say that comparing CPUs is like arguing the existence of God. So, I ask you once again... how do you propose showing comparative CPU performance, without involving clock speed?
I'm not trying to say, "OMG!!11 INteL sPEed > AMd SpeED! iNTEl Win!!111!!" and that a 2GHz Intel chip = a 2GHz AMD chip. If I had done that, then you say I was obsessed with clock speed. Look over my numbers and you'll realize that this about how much performance each chip squeezes out. Granted, FSB is a factor, too, but I wasn't sure how to add that into the comparison (although Intel's 533MHz FSB may have helped in the breakdown, it still wasn't enough to beat out AMD, with only a 400MHz FSB, in most areas).
If you can figure out a way to include FSB, L1 cache, L2 chache, and any other aspect of each chip into the comparisions, I'll gladly redo everything.