There is actually an important gain in Mem Bandwidth when going from 2 to 3 Dimms, if you don t see it, you have old hardware, Sandra will show it for sure.
Francois
There is actually an important gain in Mem Bandwidth when going from 2 to 3 Dimms, if you don t see it, you have old hardware, Sandra will show it for sure.
Francois
DrWho, The last of the time lords, setting up the Clock.
i am sure of that, and you will see it for sure in memory benchmarking, the big question would be if this is big added value in normal applications....Originally Posted by Drwho?
http://xtreview.com/addcomment-id-66...s-SMT-OFF.html
Another conclusion of trichannel is a failure. Its originally made by pconline.cn.
And another epic failure in translation. And not only this, xtreview also publish it as their own.
You can see the original screens by techpowerup that tho gave credit to pconline. But also failed translation.
http://www.techpowerup.com/73680/Cor..._Let-down.html
How many people does it need to do basic chinese translation
But just sad to see actually. Its all some copy/paste babelfish journalism.
really nice news postShintai...... everybody already concluded in those news posts that the tests were garbage .....0 added value
yes Movieman we already saw your happy post regarding the new toys.... however the strange part was that OBR with the same NDA and hardware tempered it real fast... so wonder who is happy with synthetic and who is happy with real life
Last edited by duploxxx; 10-30-2008 at 02:35 AM.
Lets cut to the chase here: Why the hell are you in these threads since your obviously not looking for info but to disrupt the thread and piss on everyone involved?i am sure of that, and you will see it for sure in memory benchmarking, the big question would be if this is big added value in normal applications....
really nice news post
yes Movieman we already saw your happy post regarding the new toys.... however the strange part was that OBR with the same NDA and hardware tempered it real fast... so wonder who is happy with synthetic and who is happy with real life
Your sarcasm towards me and the others here isn't appreciated and to put it bluntly give it a frigging break, we're all sick of it.
Is that plain enough for you?
OBR ran what he thought was relevant and I did the same.
I teased him a little and also made a point about violating the NDA with posted benchmarks but it was civil between he and I.
I also didn't have anywhere near the time to test that he has had so kindly add that into your sarcastic equation.
If I show what you consider to be too much enthusiam then that I'm probably guity of.
I'll let you in on a little secret: I'm having plain old fashioned fun.
Yea, fun and I can tell you that at pushing 57 years of age thats not something you say often. Fun like little kid fun. The wonder of exploration, that kind of fun and if I'm too much for you or you can't handle that then guess what? I don't give a damn.
For months I've watched you piss on Intel threads and I'm sick of it.
Stay the hell out of the Intel threads since you don't have anything positive to add.
Crunch with us, the XS WCG team
The XS WCG team needs your support.
A good project with good goals.
Come join us,get that warm fuzzy feeling that you've done something good for mankind.
Wow, I got serious deja vu reading this. It's like AMD threads and -------!
OOOOOPS
SuperMicro X8SAX
Xeon 5620
12GB - Crucial ECC DDR3 1333
Intel 520 180GB Cherryville
Areca 1231ML ~ 2~ 250GB Seagate ES.2 ~ Raid 0 ~ 4~ Hitachi 5K3000 2TB ~ Raid 6 ~
The point that movieman was making that it is ok to look for anomalies, but you got to do it with style.
it is ok to show up with issues, and ask for solution, what he did not like is the "sarcasm" part.
Let's try to elevate the debate.
DrWho, The last of the time lords, setting up the Clock.
Thank you. Unfortunately my heritage is Irish and it does pop up at times.
What bothers me the most at this forum and at I imagine others is that many people have lost the ability to just plain simply enjoy the hardware no matter who made it.
To all;
Both AMD and Intel have had their day in the sun to shine with their products.
AMD's X2's and Opterons were great products in their day.
Today it's Intels day in the sun and people should just accept that for what it is.
It seems to me that some people just can't get that simple thought into their minds but when you look at this from a rational point of view and realise that most of these people here are fairly intelligent you wonder if it's not that they don't get it but that they don't want to get it.
They've married their "being" to one company and refuse to see that another company may just have trumped the "one they love"
That to me is a closed mind and by doing so they miss so much.
Enjoy what is and not what was or might have been.
That's living in an unrealistic world and to be blunt, deluding yourself.
Crunch with us, the XS WCG team
The XS WCG team needs your support.
A good project with good goals.
Come join us,get that warm fuzzy feeling that you've done something good for mankind.
Are you absolutely sure? From various sources I've heard (and seen) that the difference in performance between dual and triple channel is close to nothing. Actually, I am not quite sure yet, because the extra channel should be adding much more bandwidth than the 500MB's I've seen (DDR3 @ 933MHz, exact same system settings). It's either Lavalys Everest that screws up, although I'm not likely to believe that, or something in the bios/motherboard design of the Intel reference motherboard is making the triple channel run at dual channel, which also would surprise me.
What are the possible underlying causes that make people report a lack of performance gain going from dual channel to triple channel? Software/hardware?
Where courage, motivation and ignorance meet, a persistent idiot awakens.
i am sure
I always said that Core 2 Quad does not need much mem Bandwidth, so, on real application, if memory is not important, you will see very little from Mem Bandwidth.
In the mean time, on application like SETI, Rosetta, folding@home, you got to feed 8 threads, the bandwidth will come handy. If you do H264 with profile level 4, you ll go and see 16 frames in both directions, this will get handy too.
Just remember, to keep 8 threads happy, you ll need the bandwidth, it is just a matter of time before the software use it 100%.
I heard people telling me that nobody will use MMX, it was so hard to use ... Today, you can t boot most of the OS without it.
and yes, I am very sure that 3 Dimms goes faster than 2 Dimms. (on mem test) If it does not, the proto is broken
Last edited by Drwho?; 10-31-2008 at 07:36 PM.
DrWho, The last of the time lords, setting up the Clock.
Thanks for the reply.
If I understand correctly, we should all notice the difference between dual and triple channel, but it's very likely that if we use non-multicore applications that the difference will be very small. The bandwidth that is added because of the extra channel is to provide enough bandwidth to fully cover the 8 threads, but is 'overkill' when using in single/dual threaded applications.
Now, that only leaves the everest bandwidth problems. As far as I know, the Lavalys Everest program is quite accurate when it comes to calculating the memory bandwidth and latency, but in tests I've seen the difference still is only 500MB/s:
Maybe this is the problem:
Lavalys Everest 4.60 new features & improvements:
- Asus EPU and Gigabyte DES support
- Enhanced hardware monitoring capabilities
- Optimized benchmarks for Intel Atom and VIA Nano
- Preliminary support for Intel Core i7 and X58
- Support for the latest chipset and graphics technologies
Only two tests actually show the difference between dual and triple channel, which probably is the correct performance scaling.
Where courage, motivation and ignorance meet, a persistent idiot awakens.
What it boils down to is that most of today's client applications do not produce a demand that exceeds even modest memory bandwidths, aided with a strong cache structure. Increase in BW either by clocking up the bus or increasing memory clocks gives minor improvements, in most cases -- some exceptions are WinRAR's internal benchmark which all it does is read/writes random data to memory while executing it's compression engine... it shows significant sensitivty to BW. I have also seen noteable sensitivity with Mainconcepts H264 encoder.
So, in what Dr. Who? is saying, at 12 GB/s + memory bandwidth is not really going to impact what you observe in real life -- not because the BW is not real, but because the applications used for desktop never deman throughput that exceeds the capabilities.
You will see the BW play an important role in 2S servers, where those applications are more throughput oriented as opposed to client side which are really just task based.
One hundred years from now It won't matter
What kind of car I drove What kind of house I lived in
How much money I had in the bank Nor what my cloths looked like.... But The world may be a little better Because, I was important In the life of a child.
-- from "Within My Power" by Forest Witcraft
Anybody notice the big jump in latency going to tri-channel? Around 15% worse latency
Thanks for the reply.
If I understand correctly, we should all notice the difference between dual and triple channel, but it's very likely that if we use non-multicore applications that the difference will be very small. The bandwidth that is added because of the extra channel is to provide enough bandwidth to fully cover the 8 threads, but is 'overkill' when using in single/dual threaded applications.
Now, that only leaves the everest bandwidth problems. As far as I know, the Lavalys Everest program is quite accurate when it comes to calculating the memory bandwidth and latency, but in tests I've seen the difference still is only 500MB/s:
Only two tests actually show the difference between dual and triple channel, which probably is the correct performance scaling.
And if you look, his timings have changed
The clocks and settings of the memory aint the same either.
Plus we dont know the BIOS version.
Crunching for Comrades and the Common good of the People.
Yeah, huge.... trichannel has a whole 25 ns of latency... how terrible.
One hundred years from now It won't matter
What kind of car I drove What kind of house I lived in
How much money I had in the bank Nor what my cloths looked like.... But The world may be a little better Because, I was important In the life of a child.
-- from "Within My Power" by Forest Witcraft
Actually, the problem is not the hardware here, it is the software, I have my friend Ronen working with the everest guys, I am not sure of the status, but I know from sure that the processor affinities does not allow the max bandwith to be always measured properly.
I will check and update you guys later, Monday.
In the mean time, this 2 numbers shows that Core i7 is the 1st having a real integrated memory controler ..(kidding! don t shoot!)
If you use Sandra, you will see that Banwidth is better with 3.
Francois
DrWho, The last of the time lords, setting up the Clock.
Seriously? I don't really find that a propper way to compare hardware, although these are more real-life measurements than raw numbers.
Good, let's hope the preliminary support gets turned into full support sooner than later.
Where courage, motivation and ignorance meet, a persistent idiot awakens.
Why is the CPU 22MHz faster for the dual-channel benchmark and 11MHz faster on the memory than the triple-channel benchmark?Thanks for the reply.
If I understand correctly, we should all notice the difference between dual and triple channel, but it's very likely that if we use non-multicore applications that the difference will be very small. The bandwidth that is added because of the extra channel is to provide enough bandwidth to fully cover the 8 threads, but is 'overkill' when using in single/dual threaded applications.
Now, that only leaves the everest bandwidth problems. As far as I know, the Lavalys Everest program is quite accurate when it comes to calculating the memory bandwidth and latency, but in tests I've seen the difference still is only 500MB/s:
http://xtreview.com/addcomment-id-66...s-SMT-OFF.html
and also, shouldn't the dual-channel benchmark pwn the single much more than this?
Last edited by AuDioFreaK39; 11-01-2008 at 01:09 PM.
EVGA X58 SLI Classified E759 Limited Edition
Intel Core i7 Extreme 980X Gulftown six-core
Thermalright TRUE Copper w/ 2x Noctua NF-P12s (push-pull)
2x EVGA GeForce GTX 590 Classified [Quad-SLI]
6GB Mushkin XP Series DDR3 1600MHz 7-8-7-20
SilverStone Strider ST1500 1500W
OCZ RevoDrive 3 240GB 1.0GB/s PCI-Express SSD
Creative X-Fi Fatal1ty Professional / Logitech G51 5.1 Surround
SilverStone Raven RV02
Windows 7 Ultimate x64 RTM
I'd trust Lavalys/Sandra more than Superpi, to be honest, especially when you want to put a number on the performance scaling of brand new technology. Superpi is good if you want to compare technology you understand, not really that good if you don't know the technology by heart.
Bios release is a possibility, but I can't understand why Intel would send out motherboards that don't feature the benefits of triple channel right away. This is one of the KEY features of the X58/Nehalem platform, it wouldn't make any sense.
In addition, even if the bios isn't ready, why would Intel keep this information internal? They know people will focus on this features, why on earth would they choose for the path that leads to bad publicity when different reviewing websites claim triple channel just doesn't work.
Different settings, different results. All I know is that the results of the triple channel that we see now is way too low to be correct. And if they are correct ...
Just got the QPI performance scaling confirmed by another source, so I wonder what tests you ran ;-).They are so wrong...at least in the tests we ran.
This makes me certain that I'll need a setup myself to test everything out. Why oh why did I pass for the Madshrimps Nehalem coverage ...
Actually, I was comparing with NF2, because that's when I first experienced the benefit of dual channel, just like the Core I7 is the first platform that uses triple channel.Well, NF2 was back in 2002, 6 years ago. Memory bandwidth demand has increased quite alot from those days, and thus the comparison from NF2 is quite much worthless IMO. Besides, I only saw sub 15 % improvements, though, the RAM was cheap kingston and FSB was sub 166 all the time.
I was running 260+ FSB, maybe not such a fair comparison.
To be honest, I should re-read some reviews to draw a decent conclusion, but I think you get my point when I show you the table with 0% improvement going from dual to triple channel. In the past we always DID notice the bandwidth increasements, 'we' as in the (extreme) overclockers. The fact that we are NOT noticing them at the moment is a sign.
In real-life applications, I don't even worry about dual channel. You're not going to notice anything when opening Internet Explorer or Word, but you will notice when you run resource hungry programs such as video encoding or data compression programs. But isn't the Core I7 / X58 platform designed for the normal end-user? I don't see why you bring up the 2S server example, because it has nothing to do with dual/triple channel working or not.
My question is why we don't see any improvement in benchmarks, which very often extrapolate the differences in performance. When we see differences in benchmark utilities, we can be sure (or not) if technology is working, even at 12GB/s.
No idea why they are not clocked exactly the same, not my benchmarks anyway. The small difference in frequency is NOT the reason why the differences in performance are this small, though ;-).
And yeah, the xtreview benchmarks are screwed, I think.
Where courage, motivation and ignorance meet, a persistent idiot awakens.
You got a very valid point, only the people with access to the official press kit can access to the lastest BIOS, this one has a very important patch for the memory controler. If you use a prototype of Smackover, without this bios (version has to be superior of 2000), you are not optimumI'd trust Lavalys/Sandra more than Superpi, to be honest, especially when you want to put a number on the performance scaling of brand new technology. Superpi is good if you want to compare technology you understand, not really that good if you don't know the technology by heart.
Bios release is a possibility, but I can't understand why Intel would send out motherboards that don't feature the benefits of triple channel right away. This is one of the KEY features of the X58/Nehalem platform, it wouldn't make any sense.
In addition, even if the bios isn't ready, why would Intel keep this information internal? They know people will focus on this features, why on earth would they choose for the path that leads to bad publicity when different reviewing websites claim triple channel just doesn't work.
Different settings, different results. All I know is that the results of the triple channel that we see now is way too low to be correct. And if they are correct ...
Just got the QPI performance scaling confirmed by another source, so I wonder what tests you ran ;-).
This makes me certain that I'll need a setup myself to test everything out. Why oh why did I pass for the Madshrimps Nehalem coverage ...
Actually, I was comparing with NF2, because that's when I first experienced the benefit of dual channel, just like the Core I7 is the first platform that uses triple channel.
I was running 260+ FSB, maybe not such a fair comparison.
To be honest, I should re-read some reviews to draw a decent conclusion, but I think you get my point when I show you the table with 0% improvement going from dual to triple channel. In the past we always DID notice the bandwidth increasements, 'we' as in the (extreme) overclockers. The fact that we are NOT noticing them at the moment is a sign.
In real-life applications, I don't even worry about dual channel. You're not going to notice anything when opening Internet Explorer or Word, but you will notice when you run resource hungry programs such as video encoding or data compression programs. But isn't the Core I7 / X58 platform designed for the normal end-user? I don't see why you bring up the 2S server example, because it has nothing to do with dual/triple channel working or not.
My question is why we don't see any improvement in benchmarks, which very often extrapolate the differences in performance. When we see differences in benchmark utilities, we can be sure (or not) if technology is working, even at 12GB/s.
No idea why they are not clocked exactly the same, not my benchmarks anyway. The small difference in frequency is NOT the reason why the differences in performance are this small, though ;-).
And yeah, the xtreview benchmarks are screwed, I think.
For other motherboard maker, make sure you get the latest BIOS released this week.
Last edited by Drwho?; 11-01-2008 at 01:52 PM.
DrWho, The last of the time lords, setting up the Clock.
Posting Permissions
Reply With Quote
Bookmarks