So u think that they will make a new ref C2D and then put 2 of those together again to get a quad core ?
AMD will have an advantage then. Because the K8L is a native Quad design.
Printable View
So u think that they will make a new ref C2D and then put 2 of those together again to get a quad core ?
AMD will have an advantage then. Because the K8L is a native Quad design.
Some OPN data...
ADO3600IAA5DD (A64X2 3600+, 1.9 GHz, 512 KB Cache L2 * 2) AsRock BIOS Processor support list
ADO4000IAA5DD (A64X2 4000+, 2.1 GHz, 512 KB Cache L2 * 2) AMD Compare
ADO4400IAA5DD (A64X2 4400+, 2.3 GHz, 512 KB Cache L2 * 2) AMD Compare
ADO4800IAA5DD (A64X2 4800+, 2.5 GHz, 512 KB Cache L2 * 2) AMD Compare
ADO5000IAA5DD (A64X2 5000+, 2.6 GHz, 512 KB Cache L2 * 2) AMD Compare
All them will be Rev. G1. Voltage ranges from 1.25V to 1.35V, with a TDP of 65W (ADO OPN, like Energy Efficient ones). The A64X2 3600+ is still unofficial, but its pretty probable than it is for real.
Yes! But Intel will add (or enable ;) ) SSE4 in 45nm cores, native QC part based on NGMA is expected sometime in 2008.Quote:
Originally Posted by Astennu
On the other hand AMD also added extension to SSE in K8L/K10, but at this time we don't know if it is copy of iSSE4 or something different like iSSSE3 (from Conroe).
If Intel will Introduce SSE 4 in Q4 H7 i don't think AMD will have SSE 4 in the K8L.Quote:
Originally Posted by Lightman
Possible due to cross licensing. :stick:Quote:
Originally Posted by Astennu
True. It could be so. But in the past Intel had a head start of half a year with SSE. But it would be great if the K8L has SSE 4.Quote:
Originally Posted by Lightman
K8L will not "NEED TO" run at 3.5GHz to run the max HTT3 clocks.Quote:
Originally Posted by Serge84
http://photos1.blogger.com/blogger/7...743DvWIml8.jpg
If we consider the HKEPEC table as true, than:
The differently clocked HTT is because of energy efficiency, but not because the chip is unable to achieve the max HTT clock. The bandwidth of the cHT links is tunned to be enough not to bottleneck the interCPU communication, while it wastes minimum energy.
HTT clock is not dependend of the CPU clock. For example you can run a K8 CPU at 800MHz and HTT bus at 1GHz or run a K8 CPU at 3GHz and HTT bus at 200MHz.
These are not everyday overclocks on normal (water or air) cooling and are achieved by dry ice cooling, just to get a validation. These CPUs run only few minutes on such freqfencies and are needing extreme hardware, a lot of people working around to achieve those benchmarks. There are a lot of threads on this forum about such overclocking sessions and most of these records are achieved by members of XS. You should check out these threads.Quote:
Originally Posted by Serge84
I have overclocked more than 20 various 90nm K8 CPUs, most of them between 1.8GHz-2.2GHz. According to my expireince, the average stable overclock is 25%, but with increased voltage. The higher clocked were less OC-able than the lower clocked.
I think that K8L will perform like Core2 clock, for clock. I don't think that it can outperform on the IPC front. K8L is a 3 issue core, while Core2 is 4+1 issue. Both have same SSE performance, K8L will have a little stronger FPU, while Core2 has stronger ALU.Quote:
Originally Posted by Astennu
About the clock speed I think same as HKEPEC rumors are saying that the first K8L will not break 3GHz. So far their 65nm process offers less perfromance than the 90nm and the 90nm K8 CPUs are at their freqfency edge at 3GHz. Quadcore K8L has more more than twice transistors than K8 dualcore with 2x1MB L2 and 3GHz K8L CPUS in the same power envelope will have significantly lower yields than K8 dualcores.
There will be no native quadcore Core2 CPUs, but it is irrelevant. The "true vs glued" is pointless argument used by AMD die-hard fanboys. They usually are ignoring the facts and are unable to understand how well Core2 Quad scalles in perfromance while using the 1066MHz FSB.Quote:
Originally Posted by Astennu
IMO AMD will not catch up Intel's CPU perfromance in the next year. To be sucessfull AMD have to offer competitve prices for the same perfroming Intel platforms, considering the total cost of CPU, mainboard and RAM.
Do not forget the extra cache, 12MB v 8MB so in effect 3MB per core up from 2MB for Kentsfield. This will be as well as SSE4 , higher default clock speeds (possibly 3.46-3.73) and maybe DDR3 memory.
So Intel are betting on the old world style bigger and faster it seems.
I think native cores, hyperthreading and on die memory controller are scheduled for 2008 with Bloomfield ??
Regards
Andy
info about intel seems quite irrelivant to me
if you want that, go to the intel section,i think people here want to know how well or bad the Brisbanes overclock
Sine www.amdcompare.com has been updated with revision G info, we now know the following:
- All the currently released 65nm X2 CPUs (4000+, 4400+, 4800+ and 5000+) have a 65W TDP.
- Each model seems to be available in one 1.25V and one 1.35V version. No idea how one would know which version the package contains...
Either way, core voltage doesn't really seem to have dropped from the 90nm CPUs. This will likely limit the power savings somewhat. It also doesn't bode well for overclockers...
Who want to run subzero. I brisbane is coldbugged :stick:
If what you are saying is true. AMD is dead in the water. If A K8L @ 2.9 GHz performance is on the same level as a kendsfield @ 2.9. They ave a big problem. the Kendsfield will be able to clock @ 4.0 If they tweak the core a bit.Quote:
Originally Posted by gOJDO
I think it will be dark Times for AMD then. And i hope for them they will come with a fully new and fast architecture fast. But Intel will do the same thing..... It looks like we are going back to the times of the K6 and the end of the K7 where intel cpu's where outperforming the AMD's. K7 XP core VS P4 @ 3.0+ with HT was really hard. It turned when they came with the K8.
But enough about C2D vs K8L. How are the new 65nm K8 cores clocking ? are they better ? or is it the same ?
The 65nm K8 CPUs are paper lounched today. The highest clocked 65nm CPU is 2.6GHz.
The available data for the AMD 65nm SOI3 process is very poor, we can't be sure how well it can perfrom when AMD will mature it. Because the thicknes of the gate oxide on the 65nm SOI-3 can't be scalled further than it is on the 90nm SOI-2(reached the limit allready), AMD are using more advanced stress memorization techniques to improve the mobility in the circuits.
So far on the 65nm SOI3, AMD are using 4 stressors, but the improvements achieved by stress memorization are lower when applied to smaller surfaces.
The 65nm will offer better energy efficiency, but will not offer higher clocks, at least while their 65nm process is still unmatured.
Come on metro HIT US.........we are sitting on nails here.....
launchedQuote:
Originally Posted by gOJDO
10x :)
I am glad at least a few can see that this "native" vs "glued" is just marketing bull:banana::banana::banana::banana:.Quote:
Originally Posted by gOJDO
should be as bad or even worst than 90nm parts.Quote:
Originally Posted by MaSell
sorry no oc report so far, as i said in other threads is a good friend who has the cpu, and he is also teasing me. So i believe overclock is not a big factor maybe 3.1GHz for super pi not sure thought i've been busy working i'll try to get more info tonight
:( :mad:Quote:
Originally Posted by metro.cl
People are missing the point. This CPU was newer meant to be launched with fanfare. This is just a date when large OEM’s and channel will start to receive first quantities of 65nm CPU’s that are THE SAME, as the previous 90nm X2!
It usually take couple weeks when channel has build up level of supply to be able to deliver PIB broadly.
In case of traditional launch (say C2D, or GF 8800 series), company first build that desired level of stock, and then arrange official introduction to the market..
On the other side, after fiasco with QuadFX (too little, to late, and to complex), AMD should have kept their mouth shut, so that people like our friend black sheep, wouldn’t be in position to spread story about paper launch.
It is not a story, my friend. It is a fact.Quote:
Originally Posted by Nedjo
Fact for one people is not always a fact for another ;) .Quote:
Originally Posted by gOJDO
Let say you're HP, Dell or any other big player, do you think today is paper launch for them as well??:)
For me this launch will be 'ok' if at least someone will soon do decent review! (Yes I'm thinking about you Metro.cl :p: )
http://www.amd.com/us-en/Corporate/V...114609,00.html
Can you explain what does this means?Quote:
OEMS offering systems ready to experience responsive and spectacular high-resolution 3D visual effects of Microsoft Windows Vista™ with 65nm AMD Athlon 64 X2 dual-core processors immediately, and beginning in Q1 of 2007, include Acer, Dell, Founder, Gateway, HP, Lenovo, Packard Bell, and TongFang, as well as leading system builders worldwide.
sure, some are launched now, and rest Q1 2007