AMD vs Intel CPU question...

Dragon41673

Senior member
Jun 15, 2005
898
0
0
Ok...dumb question I know...but...

How is it that the AMD cpu's can beat out Intel seeing as how Intel uses a better memory setup (ddr2 vs ddr) and so forth, and AMD is at a slower clock speed???

I'm begining to lean twords the AMD X2 4800+ but it just doesn't seem to make sense how a slower cpu and slower memory speed, can lead to a CPU being faster...
 

Markfw

Moderator Emeritus, Elite Member
May 16, 2002
26,910
15,884
136
This has been answered a zillion times, but since you are new here, the AMD has an internal memory controller, and a smaller pipline, and it gets more work done each clock cycle. Look at the temps, and the current draw, and the benchmarks, and it becomes a nobrainer, get the AMD. Like Zebo say "X2 has no competition"

And BTW, at the moments DDR and DDR2 are almost equal on performance due to latency. DDR2 is just more exspensive.
 

Dragon41673

Senior member
Jun 15, 2005
898
0
0
K, thanks...I did look around...but it still didn't make sense...that's why I asked. Guess I just didn't look har enough...sorry to those that I made pissed or "walked" out. Just trying to get answers before I go and plop down a grand for something I might regret...which it doesn't sound like I will...
 

SrGuapo

Golden Member
Nov 27, 2004
1,035
0
0
IIRC, Intel prescotts do about 6 instructtions per clock cycle. AMD A64s do about 9... Overall, the clock speed really means nothing. AMD does more per clock cycle and that more than makes up in performance.

As for DDR2, DDR2 has higher speeds, but has much higher latencies as well, making it not much faster than DDR (if any). It is also much more expensive.

BTW - that title looks like a serious flamewar starter, I was al ready to post my flameproof suit pics :p!
 

Markfw

Moderator Emeritus, Elite Member
May 16, 2002
26,910
15,884
136
Yup once you see the post count, and the question, I really think he just wanted info. And new members are used to searching. And I have searched before and not found what I was looking for.
 

Dragon41673

Senior member
Jun 15, 2005
898
0
0
Thank you Mark...I appreciate you having my back on this one. Basically I'm torn on what to get. I started one thread and got a lot of answers there...but I can't simply get a grip on why AMD would be so much better given that it runs slower and uses lower speed memory...

Thanks to SrGuapo and yourself...I understand a little better now.

Thanks
D
 

GuitarDaddy

Lifer
Nov 9, 2004
11,465
1
0
MHZ speed is only a component of performance.

Basically Performance (Calcs per second)= CPU MHZ x IPC(Instructions per Cycle). AMD has higher IPC's so they can win in performance with lower MHZ.
 

Zebo

Elite Member
Jul 29, 2001
39,398
19
81
its staggeringly-long pipeline was a gimmick ? a poor design choice made for reasons of marketing and not performance and scalability. Intel knew that the public naively equated higher MHz numbers with higher performance, or so the argument went, so they designed the P4 to run at stratospheric clock speeds and in the process made design tradeoffs that would prove detrimental to real-world performance.

http://arstechnica.com/articles/paedia/cpu/pentium-2.ars
 

Kevatl

Junior Member
Jun 16, 2005
18
0
0
Easy way to expalin it -

If my CPU can add 1+1+1=3 in one step
but it takes yours 2 steps i.e. 1+1=2 then +1=3
your CPU has to run twice a fast as mine to keep up.

case 1 - 1+1+1=3 (one step)
case 2 - 1+1=2 then +1=3 (two steps)

Now lets say you wanted to make both carry out the complete instruction in 1 sec.
Case 2 has to run twice as fast as Case 1 to do this.

AMD would be case 1, it does more per cycle, therefore requires less Ghz to equal or out perform a P4 for example.


DDR v DDR2
DDR2 high bandwidth but horrible latency.
DDR lower bandwidth much better latency.

Think of latency as delay.
Which is better -
A 4 lane highway where cars are released every 4 secs (DDR2)
or
a 3 lane highway where cars are released every 2 secs (DDR)

Both examples crude, but gives you an idea.

 

Dragon41673

Senior member
Jun 15, 2005
898
0
0
Thank you Zebo!

Well...I was gonna ask between the FX-57 and the X2 4800+ which one to get...but I see a thread is already started on that one...so I'm off to delve even more into the hell I call finding what I want! LOL
 

Aenslead

Golden Member
Sep 9, 2001
1,256
0
0
FX-57 or 4800+ cost too much for the performance bennefits you actually get compared to the model behind.

I would consider a 4400+ and invest more in RAM or storage.
 
May 30, 2005
142
0
0
Originally posted by: Kevatl
Easy way to expalin it -

If my CPU can add 1+1+1=3 in one step
but it takes yours 2 steps i.e. 1+1=2 then +1=3
your CPU has to run twice a fast as mine to keep up.

case 1 - 1+1+1=3 (one step)
case 2 - 1+1=2 then +1=3 (two steps)

Now lets say you wanted to make both carry out the complete instruction in 1 sec.
Case 2 has to run twice as fast as Case 1 to do this.

AMD would be case 1, it does more per cycle, therefore requires less Ghz to equal or out perform a P4 for example.


DDR v DDR2
DDR2 high bandwidth but horrible latency.
DDR lower bandwidth much better latency.

Think of latency as delay.
Which is better -
A 4 lane highway where cars are released every 4 secs (DDR2)
or
a 3 lane highway where cars are released every 2 secs (DDR)

Both examples crude, but gives you an idea.


That's not my understanding of what happens.

Instruction-level computations are theoretical maximums; AMD's max is 9, Intel's is 6.

AMD chips are more efficient in parallelizing instruction-level calculations than Intel chips, so use a greater portion of their 9 per clock than Intel with their 6 per clock. As an example, let's say AMD averages use of 6 instructions for 66% efficiency; Intel uses maybe 3, 50% efficiency.

AMD chips excel for applications and programs with parallelized instructions. Intel chips excel best with serial, that is, instructions that must be performed one at a time and/or where instructions are dependant upon the previous instruction, such as certain types of data compression and encryption. Best-case scenario, one might expect Intel to have a 33% improvement over AMD in this area; however it's much closer to about 10-15% due to pipeline inefficiencies. This inefficiency similarly lets AMD chips to perform parallelized operations much better than the Intel chips.

EDIT:

I have no idea how some compression mechanisms are employed; however I suspect that while many are serial-heavy, there may be parallel isntruction components within this set of data manipulation that gives the AMD dual-cores a noticeable, in many cases significant improvements over their single-core counter-parts.
 

Gamingphreek

Lifer
Mar 31, 2003
11,679
0
81
Originally posted by: Kevatl
Easy way to expalin it -

If my CPU can add 1+1+1=3 in one step
but it takes yours 2 steps i.e. 1+1=2 then +1=3
your CPU has to run twice a fast as mine to keep up.

case 1 - 1+1+1=3 (one step)
case 2 - 1+1=2 then +1=3 (two steps)

Now lets say you wanted to make both carry out the complete instruction in 1 sec.
Case 2 has to run twice as fast as Case 1 to do this.

AMD would be case 1, it does more per cycle, therefore requires less Ghz to equal or out perform a P4 for example.


DDR v DDR2
DDR2 high bandwidth but horrible latency.
DDR lower bandwidth much better latency.

Think of latency as delay.
Which is better -
A 4 lane highway where cars are released every 4 secs (DDR2)
or
a 3 lane highway where cars are released every 2 secs (DDR)

Both examples crude, but gives you an idea.

That is an excellent example :thumbsup:

-Kevin
 

Lonyo

Lifer
Aug 10, 2002
21,938
6
81
We need a sticky for "Why AMD can keep up with Intel" questions.
Someone make a thread, C&P the above explanation, then get Mods to sticky.
 

SVT Cobra

Lifer
Mar 29, 2005
13,264
2
0
Originally posted by: Lonyo
We need a sticky for "Why AMD can keep up with Intel" questions.
Someone make a thread, C&P the above explanation, then get Mods to sticky.


zebo should do it:thumbsup:
 

BitByBit

Senior member
Jan 2, 2005
474
2
81
We really need some sort of official thread to preemptively answer this question.

Edit:
As I've stated atleast twice on these forums, the difference in IPC has far less to do with pipeline depth, and far more to do with execution width.

Edit 2:
Damn, didn't see Lonyo's post.
 

mircea

Member
Dec 24, 2004
123
0
0
Originally posted by: Acanthus
searching for Intel vs AMD only gave me 163 results, i see how you couldve missed it.

Be nice!! Give him a break. He's actually looking for actual information. Now how many of those threads have that ;)