Unstoppable: DDR400 vs. Rambus

Page 4 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.

SteelCityFan

Senior member
Jun 27, 2001
782
0
0


<< Dexvx, you've posted the most relevent fact in this discussion. Applications only use a fraction of the memory bandwidth provided by both DDR and RDRAM. Low latency memory is what matters most for 3D graphics rendering on today's systems and it is one area where RDRAM falls short. Unless they can improve that part of the technology RDRAM is going to disappear, slowly but surely. It's a shame, because the design is really better suited to work with P4's processors than DDR memory, but the latency issue will undoubtedly diminish its performance in the next generation of apps. >>




I still don't understand why someone of your admitted superior intelligence cannot see that with every speed improvement (PC1066/PC1200) of RDRAM, the latency goes down...Down below that of DDR.
 

SteelCityFan

Senior member
Jun 27, 2001
782
0
0


<<
Article Title..
Full Speed Ahead: DDR400 vs. RDRAM (PC1200) - DDR400 vs RDRAM. Can DDR compete against RDRAM?

Conclusion
Conclusion: DDR400 Outperforms RDRAM (PC800) - Much Depends On The Chipset

Ah yes.... I can see the logic behind that..

"Lets test DDR400 vs RDRAM (PC1200) and show everyone that RDRAM (PC1200) will be one fast RAM (which everyone knows anyway) and conclude with comparing the lastest DDR400 with 2 yearsish old RDRAM (PC800). Nevermind that it was supposed to be DDR400 vs RDRAM PC1200. We have to make DDR400 look better!"

>>




Not to mention he also used a hand picked DDR400 module capable of CL 2.5 which will be released after the intial CL3 modules.

Tom's hardware is a joke.
 

Acanthus

Lifer
Aug 28, 2001
19,915
2
76
ostif.org
rambus claims to have multi Ghz RDRAM chips designed, and plans to have prototypes soon (saw in on CNN marketwatch, CEO was talking about it) imagine pc3000 rambus next year..... on an AMD Opertron. feel the power.
 

BDSM

Senior member
Jun 6, 2001
584
0
0
SteelCityFan.. Why does Tom claim there will be cas 3 DDR400 first?.. Kingmax has their own DDR400 module which is cas 2.5..
And there has been pics on the net showing a kingmax cas 2 rated DDR400 module also.
 

oldfart

Lifer
Dec 2, 1999
10,207
0
0
Whoopie....I run Samsung PC2700 @ PC3200 (DDR400) cas 2.5 TODAY on an EPOX i845D setup. My benches look better than any of the DDR setups Tom did. I get ~3050 in SiSoft mem benches.
 

Athlon4all

Diamond Member
Jun 18, 2001
5,416
0
76


<< The nForce is NOT a dual-channel (i.e. 128-bit pathway) chipset. The nForce is an INTERLEAVED (64-bit) chipset. Interleaving does not improve latency. There is alot of misinformation going on by chipset makers. >>

This is something that I am to the point where I am more than confused about nForce. According to nVidia it is 2 64-bit Memory Controllers interleaved, and I guess I fail to see what the difference is between 2 interleaved memory controllers and 2 interleaved memory channels that there are on other Dual Channel Chipsets like E7500 or i850.
 

Bozo Galora

Diamond Member
Oct 28, 1999
7,271
0
0

Dear Mr. Fart:

If you point to those benches you are so friggin' proud of one more time on these forums..............
 

fkloster

Diamond Member
Dec 16, 1999
4,171
0
0


<< Ah, I guess 6th period just ended, huh! >>





<< See you tomorrow, my overzealous, under-educated adversary! >>




<< (sorry about the flame, but I just couldn't help myself. You are too easy ) >>

-Zakule

Ok gloves are comin' off....I don't know how my original response to your false statement has prompted you to attack me but its time for a little education of your own.....6th period has just started for you :

I am a 35 year old lumber trader from portland, oregon. I graduated from University of Portland in Psychology in 88. I have a wife, 2 kids, and am very succesful at what I do. I have been building and testing computers and memory subsystems for the last ten years and was one of the first people around here to jump on the serial memory bandwagon. I believe serial memory is the future. Think of memory subsystems like this....:

To order food from McDonalds you got two choices...

1) Parrallel memory: You walk in the front door, and then you can choose multiple different places to order from...but you have to park the car...

2) Serial memory: You drive through the drive through and order...your car goes through a single drive up, but the line is optimized.....

Which is better....well, that depends and a few things...one in particular that comes to mind is hardware prefetch and the cpu's abiltiy to have a 'wide enough' freeway to access the memory






<< You are mistaken. PC1066 RDRAM suffers from the same latency issues and as far PC1200 RDRAM goes, chipset support for it may not ever come to pass. Intel is on the verge of completely phasing out RDRAM because of lack of interest by consumers. It's more likely than not that Rambus will not get the chance to correct the latency issue. I wouldn't hold your breath for faster RDRAM since Intel may not even support PC1066 with the 850E. >>

-Zakule

All I want is some BACKUP to your crap Zakule...you can pretend I'm in gradeschool all you want but people here will give you no credit till you can back up what you post....lets break this down for you to make it simple....

1) We would like to know...what makes you 'think' PC-1066 has latency issues @ all...and what makes you 'think' 32bit PC-1200 has the identical latency that PC-1066.

2) Show me one single document stating that Intel "is on the verge of completely phasing out rdram" this is complete crap...prove me wrong...

3) What latency issue does rdram have that Rambus needs to correct...you do realize that coupled with Intel's hardware prefetch , any latency issue that might have existed with i820 & i840 is all but lost i i850...benchmarks show this...real world apps show this...PLEASE ELABORATE....

4) If Intel drops PC-1066 for i850e, what are they going to put in all those rimm slots that Asus is puting in there new P4T-533's...lol

Zakule.... ANSWER THE QUESTIONS...you must back up what you throw out....if not ....STFU!!



<< Any 3D app with a directx8 engine is going to perform better with DDR than PC800 Rambus, period. >>

-Zakule

IS 3DMARK AN APPLICATION ZAKULE?

IS 3DMARK BASED ON A DIRECTX8 ENGINE ZAKULE?

lol of course this is just one of many (if not almost all) 3D apps that perform better with current serial memory implementations...Zalule wishes badly he would have never made this obsurd blurb...

Zakule, if you would like to list a few DX8 apps that run faster on DDR systems...please list so I can disprove...
 

oldfart

Lifer
Dec 2, 1999
10,207
0
0
No prob Mr. Bozo. Its not that I'm "proud" or braggin'. Its just to show that it is possible to run DDR350 - 400 on an i845 setup and get some good memory BW. I've seen plenty of reviews such as the one Tom did, that do not show that capability. The EPOX 845D board coupled with high quality DDR ram such as Samsung PC2700 is a nice combo. Just helping out my fellow Anandtech'rs by sharing what I think is a great setup that you can put together today.
 

Athlon4all

Diamond Member
Jun 18, 2001
5,416
0
76


<< No prob Mr. Bozo. Its not that I'm "proud" or braggin'. Its just to show that it is possible to run DDR350 - 400 on an i845 setup and get some good memory BW. I've seen plenty of reviews such as the one Tom did, that do not show that capability. The EPOX 845D board coupled with high quality DDR ram such as Samsung PC2700 is a nice combo. Just helping out my fellow Anandtech'rs by sharing what I think is a great setup that you can put together today. >>

I understand that. It does seem that the EPoX 845-D board isn't getting the publicity that it should be, but anyway.

Now Fkloster/Zakule, you both are I feel not keeping at the topic on hand, you are flaming, and I am asking that you 2 can remain civilized and cut the personal attacks and comments, and stick at the topic at hand. Please! Thanks. I am only interested in discussing this, not attacking personally people, this is just computer parts! Not a matter of right or wrong!

Now, that being said, I do however have to agree with fkloster's 4 questions Zakule. Some of the things you have said (especially the PC1066+533fsb and latency) go totally against what not just THG, and Anandtech have said, but what Ace's Hardware, and Game PC have found regarding PC1066's latency and performance, and I have looked up the article that ExtremeTech did on PC1066, and they too found the same conclusion about PC1066 that THG, Ace's Hardware and Game PC made about PC1066 on the 533fsb platform. So, I still think that PC1066 is the best solution for the P4 once it hits the streets with 850e. So, that's all I have to say for now.
 

Degenerate

Platinum Member
Dec 17, 2000
2,271
0
0


<< Yes thats is *very* true. However, that was November 2001, willamettes were barely pushing 2Ghz. Now that Northwoods are pushing over 3Ghz with an improved core, the performance gap of PC1066 and DDR SDram has intensified because of the CPU that is ABLE to demand the bandwidth offered by RDram. Before that time, the RDram bandwidth was more or less useless to the Pentium IV. With the advent of higher clock speeds, there comes the need for MORE memory bandwidth, especially on CPU intensive and memory intensive applications. With PC1066 RDram, the P4 enjoys a significant lead across the board against non-RDRam p4s, and that lead will only GROW as p4s become faster. >>

Well said.

BTW, Has DDR come to an end - interms of speed and scalability?. I know RDRAM is not.

 

dexvx

Diamond Member
Feb 2, 2000
3,899
0
0
Oh blah blah... my RDram setup at 150Mhz FSB get near the 4000 mark on Sisoft. Does that matter? Sisoft is a synthetic benchmark that has no definitive correlation with real world results, it is based off optimal results. Sisoft also says my P4's FPU is stronger than an Athlon XP1800 or a McKinley 1Ghz, is that true? Heck no.

I just noticed the title and the conclusion to Tom's article... and dang... thats really funny. If I wrote an English paper like that, I'd fail the class. Looking at the prices of memory + motherboards, it looks like if you buy 512MB of ram (high quality RDram and high quality PC2700 DDR SDram) with a motherboard (Asus P4T-E and Asus P4b-266C for comparison's sake) they end up at roughly the same cost. This is pertenant to the United States, it may be different in Europe, but then again Europe has really high protective tariffs anyways.

Fkloster:

I'm a EE student at U of Washington Seattle, most of the time, serial is *inferior* to parallel for practical purposes. I have no idea why Rambus on serial is more superior than SDram on parallel, but im not a tech wiz. I'd have to say a lot of design is revolved around parallel, not serial (easy example is to take 2 60W light bulbs and put them on serial with a fixed voltage and then the same 2 bulbs and put them in parallel).
 

Athlon4all

Diamond Member
Jun 18, 2001
5,416
0
76


<< Oh blah blah... my RDram setup at 150Mhz FSB get near the 4000 mark on Sisoft. Does that matter? Sisoft is a synthetic benchmark that has no definitive correlation with real world results, it is based off optimal results. Sisoft also says my P4's FPU is stronger than an Athlon XP1800 or a McKinley 1Ghz, is that true? Heck no. >>

Agreed, same can be said about 3DMark 2001. Just look at R8500 vs. GF3/GF4!!

However, the real world results as I have stated more times than I can count, are there for PC1066 vs. DDR400 and DDR333.

<< Well said. >>

Agreed

<< BTW, Has DDR come to an end - interms of speed and scalability?. I know RDRAM is not. >>

Agreed. DDR400 will prolly never hit the market.

<< I just noticed the title and the conclusion to Tom's article... and dang... thats really funny. If I wrote an English paper like that, I'd fail the class. Looking at the prices of memory + motherboards, it looks like if you buy 512MB of ram (high quality RDram and high quality PC2700 DDR SDram) with a motherboard (Asus P4T-E and Asus P4b-266C for comparison's sake) they end up at roughly the same cost. This is pertenant to the United States, it may be different in Europe, but then again Europe has really high protective tariffs anyways. >>

Dang. That's what I keep on trying to tell everyone, now I know someone will opint out that there is no PC1066, but high quality RDRAM (which I consider Samsung) with the right board easily hits PC1066 speeds as long as you've got either a 533fsb CPU or one that can be overclocked to it.

<< I'm a EE student at U of Washington Seattle, most of the time, serial is *inferior* to parallel for practical purposes. I have no idea why Rambus on serial is more superior than SDram on parallel, but im not a tech wiz. I'd have to say a lot of design is revolved around parallel, not serial (easy example is to take 2 60W light bulbs and put them on serial with a fixed voltage and then the same 2 bulbs and put them in parallel). >>

I'm no expert either alright, but I disagree. Maybe Fkloster can confirm this, but to me, its like the P4 and it's long pipeline compared to the P3 and its shorter pipeline.

The P4 on a Long Pipeline at first seems to perform terribly alright, but once the benefits of the longer pipeline vs. the P3 are put to its advantage, you end up with a faster product. Just take a look at the final 2GHz .18 micron Williamette, and compare its performance to the last .18 Coppermine P3 (which I believe was 1.1GHz on the final stepping). The Williamettte kicks butt!!!! I think pararell vs Serial is very similar to that. Now, there is one other key factor however added to the equation besides Serial getting more MHz, the other factor is because of its lower pin count (16 bit width), it is fairly easy and fairly cost effective to implement a Dual Channel RDRAM Memory COntroller, where with DDR, I don't care what the real prices are on nForce chips and mobo's, nVidia and the mobo makers have got to be just swallowing up profit losses to sell nForce 420-D and 415-D boards where they are. So, anyway. That's all I have to say. Does this make any sense?

edit:

<< I guess the only way to get individuals like yourself to consider any testimony is to provide links to other sites confirming what I'm saying. There is nothing about any of the review sites that makes their reviews more credible than any independent benchmarks you can peform yourself. They offer break downs of how they went about performing the benchmark, which are time consuming to prepare, and there's no way I could take the time to do that. >>

Alright then, you've made your position clear ok, how about you tell if not Fkloster, then me what your benchmarks have said and how they have been run? I am curious to see where your conclusions have come from
 

Zakule

Member
May 1, 2002
35
0
0
Fkloster, I this point I'm going to throw in the towel since there's seems little reason to continue debating with somebody as hot-headed as yourself. You may now return to quoting statistical analysises and know that all is right with the world again because big, mean, Zakule has ceased his incessant posting of his fabricated data. I guess the only way to get individuals like yourself to consider any testimony is to provide links to other sites confirming what I'm saying. There is nothing about any of the review sites that makes their reviews more credible than any independent benchmarks you can peform yourself. They offer break downs of how they went about performing the benchmark, which are time consuming to prepare, and there's no way I could take the time to do that. If I had my own website called "Zakule's Hardware Guide" then you would be more inclined to consider what I'm saying to you, but I don't.

You would do well for yourself not to put as much faith as you do in raw statistics handed to you by review sites since they can easily be fabricated and a often times are irrelevent even when the data is accurate, but this is a decision you'll have to make on your own. For now, I'm going to take a break from this forum so that you don't burst a blood vessel or something after reading more of my posts.

 

MadRat

Lifer
Oct 14, 1999
11,965
279
126
Sure looks like Zakule is retiring from the thread because he made dumb claims. Not once has he backed up anything he's claimed, rather its all this general this and that nonsense. I have a feeling that Zakule is one of those paranoid critters that avoids taking a stand at all costs.
 

Athlon4all

Diamond Member
Jun 18, 2001
5,416
0
76


<< Sure looks like Zakule is retiring from the thread because he made dumb claims. Not once has he backed up anything he's claimed, rather its all this general this and that nonsense. I have a feeling that Zakule is one of those paranoid critters that avoids taking a stand at all costs.
>>

Please cut those remarks out madrat. Those are unecessary
 

aka1nas

Diamond Member
Aug 30, 2001
4,335
1
0
"<FONT size=4>Currently, games are coded to cache their textures on the video card and let the video card render frames. The amount of data that actually moves across the AGP bus while the video card is spitting out frames is usually less than 200 MB/s. You see the video card already has everything it needs except coordinates on where it is to paint the textures.

If anybody ever wrote a game that used AGP for 3D rendering nobody would buy it because it would look terrible. Imagine having to wait for the processor to send the texture to memory and then to the graphics bus before it gets rendered. Why would anybody do that when the GPU+DDR on the video card can make the same calculations and render the frame in about one tenth the time it would take for the system processor to accomplish the same task with main memory? You wouldn't, and currently no game designers do.</FONT>"

Actually, isn't part of the point of the AGP interface that it also has a DMA channel, allowing of all thing, Direct Memory Access? The cpu should not affect the speed of System memory to video card memory AGP transfers at all. I think the big advantage speedwise with cards like the geforce 3 is through the drivers, which tend to offload more tasks to the CPU as Nvidia further optimizes them.

and actually, that new 3dLabs architecture, the P10, or more accurately, its successors, will ask developers to do just that, by using system memory as something akin to virtual memory.
 

SteelCityFan

Senior member
Jun 27, 2001
782
0
0
I have to go with fkloster and madrat on this one. He posts false statements contrary to well known facts, and basically tells us to "trust me, I am right, and countless review / news sites are wrong".

Put up or shut up.
 

FishTankX

Platinum Member
Oct 6, 2001
2,738
0
0
Zakule:RDRAM PC800 is a match for DDR333 and will handily beat DDR266 in Cas2.5 configurations. In Cas2.0 configurations PC800 can't keep up with DDR333 and it'll be a tossup between DDR266 and PC800 in many latency sensitive benchmarks.

Note to Zakule:I'd suggest you shouldn't speculate on RDRAM's death. The pentium4 was designed to work with RDRAM and it does, beautifully.

 

FishTankX

Platinum Member
Oct 6, 2001
2,738
0
0


<<

<< Oh blah blah... my RDram setup at 150Mhz FSB get near the 4000 mark on Sisoft. Does that matter? Sisoft is a synthetic benchmark that has no definitive correlation with real world results, it is based off optimal results. Sisoft also says my P4's FPU is stronger than an Athlon XP1800 or a McKinley 1Ghz, is that true? Heck no. >>

Agreed, same can be said about 3DMark 2001. Just look at R8500 vs. GF3/GF4!!

However, the real world results as I have stated more times than I can count, are there for PC1066 vs. DDR400 and DDR333.

<< Well said. >>

Agreed

<< BTW, Has DDR come to an end - interms of speed and scalability?. I know RDRAM is not. >>

Agreed. DDR400 will prolly never hit the market.

<< I just noticed the title and the conclusion to Tom's article... and dang... thats really funny. If I wrote an English paper like that, I'd fail the class. Looking at the prices of memory + motherboards, it looks like if you buy 512MB of ram (high quality RDram and high quality PC2700 DDR SDram) with a motherboard (Asus P4T-E and Asus P4b-266C for comparison's sake) they end up at roughly the same cost. This is pertenant to the United States, it may be different in Europe, but then again Europe has really high protective tariffs anyways. >>

Dang. That's what I keep on trying to tell everyone, now I know someone will opint out that there is no PC1066, but high quality RDRAM (which I consider Samsung) with the right board easily hits PC1066 speeds as long as you've got either a 533fsb CPU or one that can be overclocked to it.

<< I'm a EE student at U of Washington Seattle, most of the time, serial is *inferior* to parallel for practical purposes. I have no idea why Rambus on serial is more superior than SDram on parallel, but im not a tech wiz. I'd have to say a lot of design is revolved around parallel, not serial (easy example is to take 2 60W light bulbs and put them on serial with a fixed voltage and then the same 2 bulbs and put them in parallel). >>

I'm no expert either alright, but I disagree. Maybe Fkloster can confirm this, but to me, its like the P4 and it's long pipeline compared to the P3 and its shorter pipeline.

The P4 on a Long Pipeline at first seems to perform terribly alright, but once the benefits of the longer pipeline vs. the P3 are put to its advantage, you end up with a faster product. Just take a look at the final 2GHz .18 micron Williamette, and compare its performance to the last .18 Coppermine P3 (which I believe was 1.1GHz on the final stepping). The Williamettte kicks butt!!!! I think pararell vs Serial is very similar to that. Now, there is one other key factor however added to the equation besides Serial getting more MHz, the other factor is because of its lower pin count (16 bit width), it is fairly easy and fairly cost effective to implement a Dual Channel RDRAM Memory COntroller, where with DDR, I don't care what the real prices are on nForce chips and mobo's, nVidia and the mobo makers have got to be just swallowing up profit losses to sell nForce 420-D and 415-D boards where they are. So, anyway. That's all I have to say. Does this make any sense?

edit:

<< I guess the only way to get individuals like yourself to consider any testimony is to provide links to other sites confirming what I'm saying. There is nothing about any of the review sites that makes their reviews more credible than any independent benchmarks you can peform yourself. They offer break downs of how they went about performing the benchmark, which are time consuming to prepare, and there's no way I could take the time to do that. >>

Alright then, you've made your position clear ok, how about you tell if not Fkloster, then me what your benchmarks have said and how they have been run? I am curious to see where your conclusions have come from
>>



Athlon4All, the reason why serial architectures do better is because you're only dealing with one chip at a time. Essentially with RDRAM only one chip is transfering information down the pathway at any one time. Thus, since it has no other "Brothers" to slow it down (other chips, like in DDR where information is drawn in paralell) data access can occur at obscene speeds. PC800 runs at 1600MB/s
Couple it with a narrow fast bus, (Which means less traces running around the motherboard, and less problems with EMI causing a clockspeed barrier) and you ultimatley have a more scalable architecture. The problems with latency are related with waking up the chip and waiting for data transmission to start. The reason why RDRAM exhibits less latency as frequency increases is because, like I said, it doesn't have any brothers to slow it down and thus doesn't have to wait on all the other chips to start data transmission like DDR does. Thus, with RDRAM the latency problem is with the individual. With DDR, it's with the collective. Where DDR has to do a bank refresh and column access strobe stuff with all of the chips, RDRAM just engages one chip and starts the data flying off it's merry way.

It's a bit like this.

DDR is like controlling a squad of weaker soldiers that can work together

RDRAM is like controlling a single very powerful and fast soldier

With DDR, the thing limiting the soldiers performance is how well you can coordinate them to work together

With RDRAM the limit is with the soldier itself.

Another advantage of RDRAM is it's relativley lower datapath. 16 bits on RDRAM versus 64 on DDR means it has more headroom. As quickly as you solve the EMI problems, you can march up the datapath. Thus, at the same width RDRAM will utterly smash DDR into oblivion. And since as I said with RDRAM's serial architecture the limit is with the chip itself, it's easier to ramp up the speeds since you have no weakest link in the chain, since the chain is one link.

I know i'm sounding really uncoherrant, just trying to provide a sliver of useful information.

Hope that helped, Athlon4All. Too bad the Athlon can't benefit from tremondous memory bandwidth RDRAM provides. Perhaps one day when RDRAM's latency is lower than DDR II's, the hammer could work with RDRAM. What a day that will be...
 

mchammer187

Diamond Member
Nov 26, 2000
9,114
0
76
rambus technology ownz and i think it will scale much better than ddr(still waiting on DDR 2 tests)

running an 850 chipset and luvin it

i still think the sooner RAMBUS INC dies the better for all of us
 

Degenerate

Platinum Member
Dec 17, 2000
2,271
0
0


<< the hammer could work with RDRAM >>

Yep, And the day we might see this may be quite far off. I would like to see both companies adopt differernt types of ram. It allows users to choose and innovation through competition.
 

MadRat

Lifer
Oct 14, 1999
11,965
279
126
If I remember right the RDRAM's bandwidth is a huge advantage in and of itself. Intel's future server chipsets were geared to include an L3 cache that acted as a high speed buffer for the memory. Since the L3 cache was eliminated we don't see all the advantages of having the extreme bandwidth, at least not until PC1200. RDRAM has this label of having poor latency, when in actuality the latency varies with the depth of the data. Some data can be pulled from PC800 memory faster than DDR400, but on average the DDR400 is quicker. The average access time of RDRAM drops with each speed increase, while the same is not necessarily true of DDR. Plus, when talking increased speed of the chip, the increases in DDR performance are tiny compared to the increases in RDRAM performance.

I am sure Intel will bring the L3 cache back into the design. When that happens people will want the bandwidth of RDRAM at every speed grade, over DDR. And before anyone says that they'll bring dual channel DDR to the P4 and eliminate RDRAM, remember that the same can be done with RDRAM. RAMBUS's 2% royalty on gross manufacturer's price isn't enough to warrant discountinuing such a potent product.
 

Athlon4all

Diamond Member
Jun 18, 2001
5,416
0
76
FishTankX, thanks so much for the input.



<< Athlon4All, the reason why serial architectures do better is because you're only dealing with one chip at a time. Essentially with RDRAM only one chip is transfering information down the pathway at any one time. Thus, since it has no other "Brothers" to slow it down (other chips, like in DDR where information is drawn in paralell) data access can occur at obscene speeds. PC800 runs at 1600MB/s
Couple it with a narrow fast bus, (Which means less traces running around the motherboard, and less problems with EMI causing a clockspeed barrier) and you ultimatley have a more scalable architecture. The problems with latency are related with waking up the chip and waiting for data transmission to start. The reason why RDRAM exhibits less latency as frequency increases is because, like I said, it doesn't have any brothers to slow it down and thus doesn't have to wait on all the other chips to start data transmission like DDR does. Thus, with RDRAM the latency problem is with the individual. With DDR, it's with the collective. Where DDR has to do a bank refresh and column access strobe stuff with all of the chips, RDRAM just engages one chip and starts the data flying off it's merry way.
>>

Lots of great stuff! Thanks!!!! I always thought Serial meant one-bit at a time, pararell multiple (doesn't makes too much sense hence RDRAM has a 16-bit bus).



<< Another advantage of RDRAM is it's relativley lower datapath. 16 bits on RDRAM versus 64 on DDR means it has more headroom. As quickly as you solve the EMI problems, you can march up the datapath. Thus, at the same width RDRAM will utterly smash DDR into oblivion. And since as I said with RDRAM's serial architecture the limit is with the chip itself, it's easier to ramp up the speeds since you have no weakest link in the chain, since the chain is one link. >>

Yeah, exactley. I still hate Intel for canceling Tulloch which was going to be introing 32-bit RIMM's:disgust:. Hopefully SiS and Rambus will launch a 32-bit Dual Channel RDRAM chipset. Now that would ROCK!!!!


<< Hope that helped, Athlon4All. Too bad the Athlon can't benefit from tremondous memory bandwidth RDRAM provides. Perhaps one day when RDRAM's latency is lower than DDR II's, the hammer could work with RDRAM. What a day that will be... >>

Yah!! That does seem far off, but its prolly less far off then I think it is. For now though, DDR is great for the Athlon and RDRAM is king of the P4.

Thanks again FishTankX
 
sale-70-410-exam    | Exam-200-125-pdf    | we-sale-70-410-exam    | hot-sale-70-410-exam    | Latest-exam-700-603-Dumps    | Dumps-98-363-exams-date    | Certs-200-125-date    | Dumps-300-075-exams-date    | hot-sale-book-C8010-726-book    | Hot-Sale-200-310-Exam    | Exam-Description-200-310-dumps?    | hot-sale-book-200-125-book    | Latest-Updated-300-209-Exam    | Dumps-210-260-exams-date    | Download-200-125-Exam-PDF    | Exam-Description-300-101-dumps    | Certs-300-101-date    | Hot-Sale-300-075-Exam    | Latest-exam-200-125-Dumps    | Exam-Description-200-125-dumps    | Latest-Updated-300-075-Exam    | hot-sale-book-210-260-book    | Dumps-200-901-exams-date    | Certs-200-901-date    | Latest-exam-1Z0-062-Dumps    | Hot-Sale-1Z0-062-Exam    | Certs-CSSLP-date    | 100%-Pass-70-383-Exams    | Latest-JN0-360-real-exam-questions    | 100%-Pass-4A0-100-Real-Exam-Questions    | Dumps-300-135-exams-date    | Passed-200-105-Tech-Exams    | Latest-Updated-200-310-Exam    | Download-300-070-Exam-PDF    | Hot-Sale-JN0-360-Exam    | 100%-Pass-JN0-360-Exams    | 100%-Pass-JN0-360-Real-Exam-Questions    | Dumps-JN0-360-exams-date    | Exam-Description-1Z0-876-dumps    | Latest-exam-1Z0-876-Dumps    | Dumps-HPE0-Y53-exams-date    | 2017-Latest-HPE0-Y53-Exam    | 100%-Pass-HPE0-Y53-Real-Exam-Questions    | Pass-4A0-100-Exam    | Latest-4A0-100-Questions    | Dumps-98-365-exams-date    | 2017-Latest-98-365-Exam    | 100%-Pass-VCS-254-Exams    | 2017-Latest-VCS-273-Exam    | Dumps-200-355-exams-date    | 2017-Latest-300-320-Exam    | Pass-300-101-Exam    | 100%-Pass-300-115-Exams    |
http://www.portvapes.co.uk/    | http://www.portvapes.co.uk/    |