Clarify this for me, please

[akaBruno]

I've heard this on countless forums, and here, " AMD runs games and Windows smoother."

Is this just an excuse for AMD lacking in benchmarking, fps, etc... ???

What's behind these claims?

[Jakko]

Good question, I heard many people say this as well, and I wonder what this claim is all about.
Can anyone elaborate?

[biohead]

it isn't quantifiable, but i'm guessing the IMC plays a role. Users who own both platforms often say the AMD (K8/K10) feels snappier and the C2D feels kinda skippy in comparison, be it at 2.4ghz or at 4ghz.

horse power vs elegance i guess.

[Extelleron]

I don't have two systems to compare with side by side, I have only owned AMD systems for the last few years. A theoretical advantage for AMD makes some sense (because of IMC and lower latency) but I can't see this making enough of a deal in real world usage that it would be noticeable. With the newer, faster FSB's plus Phenoms having high latency relative to the A64's (because of slow L3/NB) AMD doesn't actually have much of an advantage in memory latency anyway.

If you look under memory access latency, E8500 is equal to Phenoms: http://www.techreport.com/articles.x/14424/3

[duploxxx]

All i can say is that during first c2d hype i also bought conroe e6600 and it sure felt fast in the beginning and some benches during test phase, but once all sw installations were done and lots off background apps were there and running the system started to slow down allot, even my wife started to complain about the speed .... and she questioned why i updated the main rig. old Rig was by that time am2 x2 5600 btw, for the rest same os, mem, psu, gpu etc only board+cpu was shifted

can't say that games are smoother, since i play only older games, but indeed you hear a lot of reviewers talking about this smoothness.

[Brother Esau]

Yes games are smoother on Phenom vs C2D & C2Q

[biohead]

I don't have two systems to compare with side by side, I have only owned AMD systems for the last few years. A theoretical advantage for AMD makes some sense (because of IMC and lower latency) but I can't see this making enough of a deal in real world usage that it would be noticeable. With the newer, faster FSB's plus Phenoms having high latency relative to the A64's (because of slow L3/NB) AMD doesn't actually have much of an advantage in memory latency anyway.

If you look under memory access latency, E8500 is equal to Phenoms: http://www.techreport.com/articles.x/14424/3

it isn't quantifiable. just an experience thing.

[stocius]

I have both an AMD 9850BE and Intel Q6600 quads with extremely similiar hardware. My AMD does in fact run smoother. Slower but smoother and I enjoy my AMD much more than my Intel atm. I love quality of picture in gaming, movies etc. over pure speed. For example, I prefer lower FPS with no jaggies than high FPS with more jaggies. You really don't see a noticeably huge difference from 60 FPS to 200+ FPS. 35 FPS and up is playable for me as long as pic quality is spectacular.

I believe that Intel FSB is outdated (which they are discontinuing with Nehalem etc.), in fact they are moving the NB to the CPU, if I understand Blauhung correctly. The FSB bottleneck shows up mostly in gaming real world stuff and not synthetic benchmarks. So yeah, you got 3.5+ GHz but unfortunatley its just not as good quality (smooth). AMD can take better advantage of RAM speed with HTT than Intel atm, i just saw an article about that yesterday, I hope I can remeber where I found it.

Remember, this is my opinion and in no way trolling or flaming Intel but rather stating why I'm happier with AMD. AMD is giving me what I want which is snappiness and smoothness. I will look for a reputable lab to back this up. In the meantime, Tony here on XS forums has also stated that his Phenom runs smoother as well.

EDIT: Here are the articles I quoted with regards to DDR2 memory and phenom

http://www.digit-life.com/articles3/...nom-page1.html

http://www.digit-life.com/articles3/...ma-phenom.html

[akaBruno]

Great feedback. I didn't expect such a quick response.

Another question...

Did intel get the cart in front the horse? Or is the horse just to fast for the software and OS?

[stocius]

Great feedback. I didn't expect such a quick response.

Another question...

Did intel get the cart in front the horse? Or is the horse just to fast for the software and OS?

IMHO, Intel got the cart in front of the horse. Amazing horspower, but crappy drivetrain and tires. That' how I would describe it. All the parts must be at amx or you get bottlenecks (limiting factors). FSB in my opinion is like a speed governor on an auto. Sure the car can go 200+mph but the governor won't let it go past 130 mph.

I've had so many lackluster Intel setups (including my current Intel quad, its good but not spectacular) that my AMDs consistently blew away that I don't get hot and bothered by anything Intel puts out, hype did not equal performance. Intel will 100% give you higher benchmarks and possibly better folding (I have yet to test my AMD on WCG, I do not speak unless I have tested).

I'm not trolling its just that in my opinion AMD has served me better in what I want my computer to do. That may change. That's why its called a Personal Computer, the user experience is personal and will vary depending on what you are into.

[Oldguy932]

I think this might be a better comparison...

Say you have 2 different cars. On has a 7 speed transmission that has close ratios, the other is your standard 4 speed. Now imagine pushing the pedal to the floor like in a drag race. AMD is like the 7 speed tranny, very smooth acceleration because of the close ratios. Intel is like the 4 speed, it still goes fast, but its jerky because of having less gears.

Another example that probably makes about as much sense as the last one. Take two runners, a distance runner and a sprinter. AMD is like the distance runner because it keeps going pretty fast but doesn't have bursts. Sure some stuff is slightly better optimized, kind of like running down a hill, but its only because its optimized. Intel is a sprinter. Feed them lots of sugar and they go fast, but they still need that recovery time. Sugar is like the massive L2 cache on C2's, recovery time is how long it takes to retrieve more stuff from memory. AMD doesn't need that recovery time because of its IMC.
Putting this into better perspective, Intels bench better because its monotonous and repetitive, meaning there's alot less to go to and from the memory. The "jerkyness" in games is because of all the information that changes that's stored in memory. That's why having the higher front bus speed makes such a difference, its that much closer to having the actual throughput to the memory as AMD, but it can't because its not an IMC.

Please don't flame me on this, I'm just posting my interpretation of what other people have said. I did have a Core 2 system before, I had the B2 rev of both the E6600 and the E6700. I burnt out the E6700 at 3.82ghz on air, I burnt out the Asus Striker I was using the E6600 with, didn't have the money to replace it, and my T2500 is now in the hands of my older brother. And my laptop has the Pentium-M.

[accord99]

Probably either:

a) The A64/Phenom uses a lot more power and therefore cause the fan to speed up more compared to a C2D/C2Q. And as we know from car culture, a louder car is a faster car.

b) In games, the C2D/C2Q goes up to higher fps when in CPU limited situations and therefore the delta between CPU limited and GPU limited situations is greater on the C2D, which results in a possibly "less smooth" experience, even if the C2D/C2Q has higher maximum and minimum frame rates.

IMHO, Intel got the cart in front of the horse. Amazing horspower, but crappy drivetrain and tires. That' how I would describe it. All the parts must be at amx or you get bottlenecks (limiting factors). FSB in my opinion is like a speed governor on an auto. Sure the car can go 200+mph but the governor won't let it go past 130 mph.

A F1 car is less smooth than a mid-size sedan, but it'll still take less time to complete a lap of a track. Just like a C2D and C2Q clearly finish tasks faster or do more work in the same amount of time as compared to their AMD competition.

[stocius]

As you can tell I'm not much of an auto buff so thanks for taking the time to explain it better. I've only recently returned to performance PCs in the last few months, I feel good that at least my thoughts are validated

[keithlm]

it isn't quantifiable. just an experience thing.

That is True.

On the other hand HISTORICALLY Intel has been known for doing just about anything they can to get higher benchmark scores. Since most people will accept that fact based on available past evidence, then it should not be difficult to believe that they might also sacrifice something that is non-quantifiable for better benchmarks. And that they might continue this trend on their current crop of processors.

Probably either:

a) The A64/Phenom uses a lot more power and therefore cause the fan to speed up more compared to a C2D/C2Q. And as we know from car culture, a louder car is a faster car.

b) In games, the C2D/C2Q goes up to higher fps when in CPU limited situations and therefore the delta between CPU limited and GPU limited situations is greater on the C2D, which results in a possibly "less smooth" experience, even if the C2D/C2Q has higher maximum and minimum frame rates.

1. If you have a super silent fan you'd have to base your opinion on what you actually experience. (I can't hear my CPU's fan over the case fans.)

2. What if you have higher max but lower min speeds? (Which happens on many benchmarks.)

[Calmatory]

My older brother also said that his old S754 New Castle 3000+ felt way smoother win WinXP and in WinVista than his new E6320. Guess the IMC makes the difference or something.

[Rammsteiner]

I think the HT link actually makes everything a lot better. It's basicly a HUGE highway what's connected to everyting in the whole system.

IMC surely helps, but not due to the latency tests you see from for example Everest but latency's we can't test (I think). I mean, if you'd run DDR800 5-5-5 (giving crap latency) or DDR1200 4-4-4 (superior latency), I wonder if this would make a whole lot of difference in your 24/7 usage experience. It's more the IMC being architectural wise good located and, as already said, gives untestable good latency.

But only the IMC isnt cutting it, I think it's more the whole connection with the whole system, the HT link.

[SkullCracka]

i have been testing over the weekend. while not very scientific tests. still tests.

rather then overclocking the cpu. instead running the ram at higher speeds along with getting the HT and NB higher and upping the pcie. i am seeing better fps and over all faster boots ect. going this route rather then trying to Oc the cpu speed itself. when i OC just the CPU i have to of course run lower ram sppeds and lower HT and NB.

so it seems going this other route is matching up the bandwidth pipe better with the whole system.


as far the thread here. i can say the home ati/amd machine does seem faster amd smoother then the work intel quads. not sure why since the work intels are rated at a higher stock speeds and benchmarks everywere say the intels should be faster.

[Max Spain]

My thoughts on why people are seeing this is because Phenoms have the ability to SHARE data between cores (L2 is mirrored in shared L3). This is why my AMD dualies suffer lags (crossbar isn't quite what you may think) and my Intel C2D (with its shared L2) does not.

The windows scheduler does not seem to prefer leaving a running thread on the same core (known as soft affinity) for extended periods of time. If you are running a single threaded app, you will most likely see the cpu time split to some degree between all of your cores (60-40 for example). When I run single threaded apps in Ubuntu, the load will remain on the same core for a long period of time (several seconds usually) before something causes the scheduler to switch it and I experience lag. If you want to know the reason for this, look up NUMA (Non Unified Memory Architecture).

When the XP scheduler (not NUMA aware) switches the cpu your thread is running on, all of the data in the first cpu's cache needs to go into the second cpu. This requires it to be written to memory and then read into the cache of the second cpu. If your 2 cpus have a shared cache (Phenom, C2D, or between cores 0&1 or 2&3 of your C2Q) that delay will be greatly reduced.

This is just my best educated guess as to why this happens. Whenever I am playing a game (probably the only time you will notice) and I experience these lags, there is usually a dip accompanied by a rise in Task Manager or System Monitor (depending on my OS at the time). The good news is that some games are compensating for this. STALKER for example forces its main thread on CPU 0 and will peak its utilization while running less demanding threads on your other cpu(s).

If you want to avoid these evil task switches, you can use task manager or taskset to set your (single-threaded only) app's affinity to one core.

[Logos]

I've heard this on countless forums, and here, " AMD runs games and Windows smoother."

Is this just an excuse for AMD lacking in benchmarking, fps, etc... ???

What's behind these claims?

behind those claims is a legend: let me explain. This legend is based on a true story: it all started with the "rambus" disaster, in year 2000. Starting in 2000 Intel went through 2 or 3 dark years. In year 2000, in order to get the maximum performance out of the first Pentium 4, you had to use the so called "rambus" memory modules that started selling for 1200 euros at the time (I was in Germany so that was 2400 DM), and were at the same time almost impossible to find. At the same time AMD cpus were getting faster and faster, and cheap as well. Finally Intel replaced their bloody i820 chipset (needed for Rambus) with i840, running SDRAM memory: and the combination of P4 + SDRAM was terrible. AMD cpus were selling more and more. Intel, in 2002, finally converted their i840 chipset into a i845 that could use DDR RAM (there was also an i850 for rambus, much cheaper than in the beginning, but still too expensive). Anyway the result is that for all these reasons, most gamers bought AMD cpus (and via chipsets, mostly on MSI mobos) during more than three years, where those AMD things were really faster (except for videos). That's where the story ends.

Then when Intel came around with their first dual-core, in 2004 I think, AMD couldn't follow in either speed or efficiency. Not to mention that according to something I read recently, AMD hasn't been able to modify their cpu's architecture since 2003, while Intel produced one generation of dual-core after the other, and then the quad cores. But the legend remained

Now if you talk about recent comments giving superiority to AMD versus Intel, sorry I'm lost. I haven't read a single review for quite a long time that didn't give Intel as a clear winner in all areas: gaming, video editing etc...see Q6600 success in this forum for instance

[metalazzo]

Too much craps in this post...
MSI mb for gamers with AMD chip
Except for rambus being crappy, what remains of the post is bull

[jas420221]

I am a system builder for extra coin, so frequently I have AMD and Intel systems with similar internals (vid card, ram, drives, etc) side by side. The only thing I can tell you is I do not see ANY appreciable, or measureable difference...and those that do, probably feel the HP difference when installing new tires on thier car.... what Im getting at is, its just not there...and if it is, its not b/c of the CPU!

[Logos]

Too much craps in this post...
MSI mb for gamers with AMD chip
Except for rambus being crappy, what remains of the post is bull

ignored an despised maybe give up the booze

[SkullCracka]

I am a system builder for extra coin, so frequently I have AMD and Intel systems with similar internals (vid card, ram, drives, etc) side by side. The only thing I can tell you is I do not see ANY appreciable, or measureable difference...and those that do, probably feel the HP difference when installing new tires on thier car.... what Im getting at is, its just not there...and if it is, its not b/c of the CPU!

your right its not the cpu its the total package cpu,ram,mobo, and video wich give that uber smooth, sily HD quality.

[metalazzo]

In end 2002, NF2 was THE chipset for AMD chips (thoroughbed or whatever, barton...) and NOT via or whatever
And in 2003 (not 3 years later), "gamers" switched to P4C which was goot at overclocking with good performances...
And if I remember correctly, the first true dual core chip was an AMD one (even before the false P4 dual core)
Well, you should stop booze

[jas420221]

your right its not the cpu its the total package cpu,ram,mobo, and video wich give that uber smooth, sily HD quality.

I think in my post I covered the ram, and video card. The only differences from some of my systems were ONLY the CPU and mobo. If it was the mobo, many other people would believe this is true. I do not believe many people think this is true. Like my reference above, I think its a "butt-dyno" situation. Both are silky smooth for me with the same systems sans CPU and mobo.