...hmmmm...Rambus and AMD...then, Nvidia &...oh wow...guys, just imagine this: Rambus gets all friendly with AMD, and then Nvidia merges with 3DFX (VooDoo) to countermeasure it...lol.
- Status
...hmmmm...Rambus and AMD...then, Nvidia &...oh wow...guys, just imagine this: Rambus gets all friendly with AMD, and then Nvidia merges with 3DFX (VooDoo) to countermeasure it...lol.
XDR2 for HD7900 is just a hoax. No one produces this type of memory - go check web pages. The whole quality of this rumor article is questionable.
nottheking
Distinguished
- Jan 5, 2006
- 1,456
- 0
- 19,310
[citation][nom]dragonsqrrl[/nom]Basically AMD is designing GCN with compute performance and efficiency in mind.[/citation]
This is one thing I'm crossing my fingers for: true FP-64 support. With the claim given for the 6000 series a year back, I remember crossing my fingers and being disappointed; sure, it was more efficient than the 20% rate for the 5900 cards that had some DP support added, but it was still 25%. Furthermore, it wasn't because it took a whole cluster to do it; it's just among each cluster's set of SPs, (which were NOT symmetric) it only ever had enough parts to handle one DP-FP op at once, even for the ludicrously common ones such as the multiply-accumulate instructions.
I'm hoping that this time around, this is fixed, and we can see a true 50% efficiency rate, which is akin to how VMX in CPUs works; the single-precision elements in their SIMD units can essentially pair up to act as single dual-precision elements.
If this can be done with GCN, the prospects are definitely ones to salivate over: 2.048 TFlops of dual-precision computing power from a single GPU?
[citation][nom]xtra0rdinaryxd[/nom]rambus created ddr, ddr2, ddr3 and ddr4...it is their technology and patents...[/citation]
Actually, Rambus only invented (or has a claim to inventing) the original DDR. DDR2, DDR3, and the preliminary work being done on DDR4 (as it's not finalized...) were all done by JEDEC, of which Rambus is NOT a member of.
[citation][nom]DSpider[/nom]It's not 8000 MHz... For example the HD 5670/6670 which uses GDDR5 at 4000 MHz, it's actually 5 x 800 MHz.Or just like 1333 MHz DDR3 modules are actually clocked at 666 MHz (DDR3: Double Data Rate 3).I think the way they put it is actually pretty stupid (marketing?). It's like saying a dual core processor clocked at 3.2 GHz is 6.4 GHz just because it's dual core.[/citation]
Actually, you're a bit off there; GDDR5's effective data rates are quadruple that of its command pin clock speed, not x5: For a GDDR5-4000 module, that means the command pins run at 1 GHz, and the data pins transfer at 2 GHz double-pumped to an effective 4 GHz.
For XDR2, yes, it's effectively x16 the rate of the "nominal" clock speed, which I'm assuming is, likewise, the clock rate of the command pins; so XDR2-8000 technically runs at 500 MHz, but the data transfer rate is effetively 8000 MHz.
You're definitely off on the dual-core comparison, though, because the increased bandwidth is done through the SAME number of data pins; the transfer rate per-pin has, indeed, gone up. This is why the term "Megatransfers per second" (MT/s) was invented, to eliminate confusion. From the sounds of it, XDR2 simply takes the idea of DDR3/GDDR5 and goes even farther: the command pins operate at speed n, with the data pins operating at speed n8, double-pumped to make it effective as n16.
So for XDR2-8000, as mentioned above, has a nominal clock rate of 500 MHz, but still has a transfer rate of 8000 MT/s, hence the "effective" 8000 MHz.
[citation][nom]crc8[/nom]XDR2 for HD7900 is just a hoax. No one produces this type of memory - go check web pages. The whole quality of this rumor article is questionable.[/citation]
No one produces it, because Rambus is a "fabless" company. They DID invented it, and their original announcement of the standards & designs date back to 2005. No one really cared, as no one really cared about the original XDR, either... That is, until the PS3 started using it.
So XDR2 seems to be indeed very real, so I would believe if AMD is deciding they're going to use it. Rambus' particularly proprietary memory technologies (RDR and XDR, two they have an uncontested claim of ownership over) happen to be infamous for being expensive to produce... As a result, it's unsurprising to see it not used for the 800-series, instead seeing GDDR5 in that role.
This is one thing I'm crossing my fingers for: true FP-64 support. With the claim given for the 6000 series a year back, I remember crossing my fingers and being disappointed; sure, it was more efficient than the 20% rate for the 5900 cards that had some DP support added, but it was still 25%. Furthermore, it wasn't because it took a whole cluster to do it; it's just among each cluster's set of SPs, (which were NOT symmetric) it only ever had enough parts to handle one DP-FP op at once, even for the ludicrously common ones such as the multiply-accumulate instructions.
I'm hoping that this time around, this is fixed, and we can see a true 50% efficiency rate, which is akin to how VMX in CPUs works; the single-precision elements in their SIMD units can essentially pair up to act as single dual-precision elements.
If this can be done with GCN, the prospects are definitely ones to salivate over: 2.048 TFlops of dual-precision computing power from a single GPU?
[citation][nom]xtra0rdinaryxd[/nom]rambus created ddr, ddr2, ddr3 and ddr4...it is their technology and patents...[/citation]
Actually, Rambus only invented (or has a claim to inventing) the original DDR. DDR2, DDR3, and the preliminary work being done on DDR4 (as it's not finalized...) were all done by JEDEC, of which Rambus is NOT a member of.
[citation][nom]DSpider[/nom]It's not 8000 MHz... For example the HD 5670/6670 which uses GDDR5 at 4000 MHz, it's actually 5 x 800 MHz.Or just like 1333 MHz DDR3 modules are actually clocked at 666 MHz (DDR3: Double Data Rate 3).I think the way they put it is actually pretty stupid (marketing?). It's like saying a dual core processor clocked at 3.2 GHz is 6.4 GHz just because it's dual core.[/citation]
Actually, you're a bit off there; GDDR5's effective data rates are quadruple that of its command pin clock speed, not x5: For a GDDR5-4000 module, that means the command pins run at 1 GHz, and the data pins transfer at 2 GHz double-pumped to an effective 4 GHz.
For XDR2, yes, it's effectively x16 the rate of the "nominal" clock speed, which I'm assuming is, likewise, the clock rate of the command pins; so XDR2-8000 technically runs at 500 MHz, but the data transfer rate is effetively 8000 MHz.
You're definitely off on the dual-core comparison, though, because the increased bandwidth is done through the SAME number of data pins; the transfer rate per-pin has, indeed, gone up. This is why the term "Megatransfers per second" (MT/s) was invented, to eliminate confusion. From the sounds of it, XDR2 simply takes the idea of DDR3/GDDR5 and goes even farther: the command pins operate at speed n, with the data pins operating at speed n8, double-pumped to make it effective as n16.
So for XDR2-8000, as mentioned above, has a nominal clock rate of 500 MHz, but still has a transfer rate of 8000 MT/s, hence the "effective" 8000 MHz.
[citation][nom]crc8[/nom]XDR2 for HD7900 is just a hoax. No one produces this type of memory - go check web pages. The whole quality of this rumor article is questionable.[/citation]
No one produces it, because Rambus is a "fabless" company. They DID invented it, and their original announcement of the standards & designs date back to 2005. No one really cared, as no one really cared about the original XDR, either... That is, until the PS3 started using it.
So XDR2 seems to be indeed very real, so I would believe if AMD is deciding they're going to use it. Rambus' particularly proprietary memory technologies (RDR and XDR, two they have an uncontested claim of ownership over) happen to be infamous for being expensive to produce... As a result, it's unsurprising to see it not used for the 800-series, instead seeing GDDR5 in that role.
Sure Rambus is fabulous and fables, but none of the XDR producers announced a XDR2 so far (close to the release of theHD7900) - for a good reason because it’s not going to be faster than GDDR5. What really counts is band width per given memory device; GDDDR5@5.5Gbitx32=22GByte/s XDR2@10Gbitx16=20Gbit/s. We will eventually see what HD7900 uses, my take it’s not going to be XDR2.
someoneelse
Distinguished
- Feb 20, 2009
- 126
- 0
- 18,680
valu3hunt3r
Distinguished
- Nov 6, 2009
- 37
- 0
- 18,530
According to Charlie from Semi-Accurate.
Guys,
Let me be blunt here, THERE IS NO XDR2 IN SI/HD7000/GCN. Trust me on this, the spec list floating is complete bull, and you can tell by who is re-posting it and who is not. Some people know, and they are being VERY quiet on the subject.
This is not meant to knock XDR2 and/or Rambus, it is just a statement about what is in and what is not in the next GPU.
-Charlie
http://semiaccurate.com/forums/showpost.php?p=132861&postcount=1160
Guys,
Let me be blunt here, THERE IS NO XDR2 IN SI/HD7000/GCN. Trust me on this, the spec list floating is complete bull, and you can tell by who is re-posting it and who is not. Some people know, and they are being VERY quiet on the subject.
This is not meant to knock XDR2 and/or Rambus, it is just a statement about what is in and what is not in the next GPU.
-Charlie
http://semiaccurate.com/forums/showpost.php?p=132861&postcount=1160
wannabepro
Distinguished
- Oct 5, 2011
- 296
- 0
- 18,810
Im still hanging on my 9600gt...but i cant hold out forever..ill be plunging massively into the new technological markets...woohoooo!!!
CyberAngel
Distinguished
- Dec 11, 2008
- 113
- 0
- 18,680
[citation][nom]marraco[/nom]I hope that, when released, Tomshardware tests it with PCI-E 2 and PCI-E 3. Because I have no plan to upgrade my mother.[/citation]
30% less power (eg, only 70%) at the SAME bandwidth
It's doubled thus 140% or 40% MORE power is being used...
30% less power (eg, only 70%) at the SAME bandwidth
It's doubled thus 140% or 40% MORE power is being used...
Very interesting using XDR2 is a very good choice. It makes the PCB simpler to design and it also consume less power. The main concern here is no major memory manufacturer have started even sampling XDR2. There are some rumour floating around that GF will be making them. Anyways one thing to note is XDR2 memory controller have progammable pins. With one controller it supports DDR3, GDDR5 and XDR2 http://www.rambus.com/assets/documents/products/xdr2_memory_architecture.pdf. So if indeed yields or pricing for XDR2 is a problem amd can still go back with GDDR5 without a redesign.
masterofevil22
Distinguished
- May 13, 2010
- 229
- 0
- 18,690
AMD is bringing the heavy pimp hand with this release!! I may wanna trade in my 6970 if it means getting double the ROPs and another 100Gigs/second of memory bandwidth... all while using less electricity in what will likely be a cooler and quieter card...
Pretty tempting..
I wonder if the new 7950's will be able to UNLOCK into 7970's????
Pretty tempting..
I wonder if the new 7950's will be able to UNLOCK into 7970's????
verbalizer
Distinguished
- May 28, 2010
- 2,930
- 0
- 20,960
this article is now false...
AMD HD Radeon will only be using GDDR5.
period.
http://www.tomshardware.com/forum/331651-33-7xxx-series-rumors-technical-data
AMD HD Radeon will only be using GDDR5.
period.
http://www.tomshardware.com/forum/331651-33-7xxx-series-rumors-technical-data
teslafreakshow
Distinguished
- Dec 9, 2011
- 17
- 0
- 18,510
Actually rambus is superior. Instead of using multiple parallel lines of data is uses less differential pairs which can be clocked and way higher speeds and use pins than normal RAM. Its basically just like the move form parallel hard drives to SATA. It can also uses the same controllers and similar interface. The ps3 uses XDR Ram as well.
- Status
TRENDING THREADS
-
[SOLVED] Is it safe to use a recapped PSU for a long time ?- Started by zwtch_17
- Replies: 7
-
-
-
-
Discussion What's your favourite video game you've been playing?- Started by amdfangirl
- Replies: 3K
Facebook
Twitter
Instagram