AMD Athlon 64 FX-60: A Dual-Core farewell to Socket-939
by Anand Lal Shimpi on January 9, 2006 11:59 PM EST- Posted in
- CPUs
AMD's Socket-939 has been the platform of choice almost immediately after its introduction, so it is fitting that the last Socket-939 processor to be released would be the Athlon 64 FX-60.
After today's launch of the FX-60, there will be no faster Socket-939 CPUs produced. Instead, everything else will be Socket-AM2 (the new name for Socket-M2). Next quarter, AMD will launch their Socket-AM2 platform along with AM2 versions of the Athlon 64, Athlon 64 X2 and the FX-62. Given that the AM2 platform adds DDR2 support, it is entirely feasible that the Athlon 64 FX-62 won't receive a clock speed bump over the FX-60 and just use the higher bandwidth memory as justification for the higher model number.
Although we've generally shied away from recommending AMD's FX line of processors, we can't help but be a little excited about the FX-60. When AMD introduced their X2 line of dual-core processors, the FX series remained single core, but maintained a fairly high clock speed. AMD even went as far as to release the FX-57, clocked a full 400MHz higher than the fastest X2. With the FX-60, that trend is over; from this day forward, all members of the FX series of processors are now dual core. They are still sold under the Athlon 64 FX brand, despite being dual core chips.
Our excitement over the Athlon 64 FX-60 isn't really about its performance, although at 2.6GHz it is quite stellar; rather, it is more of an excitement out of principle. We've favored and recommended dual core processors to power users as soon as they were available, even though dual core processors were generally far slower at single-threaded applications than their equivalently priced single core alternatives. With the FX-60, at least at the high end, the same is no longer true.
The fastest single core AMD processor is still the Athlon 64 FX-57 running at 2.8GHz, which AMD will continue to sell alongside the FX-60. But with the clock speed gap between the 2.6GHz dual core FX-60 and the 2.8GHz single core FX-57 a meager 7.6%, you can effectively go to one CPU and get the best single-threaded and multithreaded performance. Remember that the best applications that scale with clock speed generally give you a 50% return on every 100% increase in clock speed, so in most of the single-threaded cases, the FX-57's performance advantage will be in the 0 - 4% range. But on the flip side, the fact that the FX-60 is a dual core processor will buy it a lot in multithreaded applications.
As with all FX series processors, the FX-60 debuts at $1031 in quantities of 1000, so you can expect street pricing to be at or around that number. The FX-57 will drop to $827 mark as it will co-exist with the FX-60.
The FX-60 is really just a multiplier unlocked 2.6GHz Athlon 64 X2. It is still a 90nm processor and there are no architectural changes that we've been made aware of or have been able to find on our own. We stress the point that it is still a 90nm chip because of the fact that its closest competitor, the Pentium Extreme Edition 955, just debuted on Intel's 65nm process. Because Intel is on a smaller manufacturing process, they can cram more transistors into a smaller space. So although the Pentium EE 955 is a 376-million transistor chip, they only take up 162 mm2 of space. The Athlon 64 FX-60 by comparison is a 233-million transistor chip, but its die is a larger 199 mm2. The move to 65nm for AMD should cut the die size roughly in half assuming no architectural changes, but until then, Intel will at least have the manufacturing advantage.
You shouldn't, however, assume that the smaller, cooler running manufacturing process will result in a power advantage for Intel. The problem is that those 376 million transistors are used to build a beast of a chip with a 31-stage pipeline, so power consumption is still actually higher on the Extreme Edition than on AMD's fastest dual core:
After today's launch of the FX-60, there will be no faster Socket-939 CPUs produced. Instead, everything else will be Socket-AM2 (the new name for Socket-M2). Next quarter, AMD will launch their Socket-AM2 platform along with AM2 versions of the Athlon 64, Athlon 64 X2 and the FX-62. Given that the AM2 platform adds DDR2 support, it is entirely feasible that the Athlon 64 FX-62 won't receive a clock speed bump over the FX-60 and just use the higher bandwidth memory as justification for the higher model number.
Although we've generally shied away from recommending AMD's FX line of processors, we can't help but be a little excited about the FX-60. When AMD introduced their X2 line of dual-core processors, the FX series remained single core, but maintained a fairly high clock speed. AMD even went as far as to release the FX-57, clocked a full 400MHz higher than the fastest X2. With the FX-60, that trend is over; from this day forward, all members of the FX series of processors are now dual core. They are still sold under the Athlon 64 FX brand, despite being dual core chips.
Our excitement over the Athlon 64 FX-60 isn't really about its performance, although at 2.6GHz it is quite stellar; rather, it is more of an excitement out of principle. We've favored and recommended dual core processors to power users as soon as they were available, even though dual core processors were generally far slower at single-threaded applications than their equivalently priced single core alternatives. With the FX-60, at least at the high end, the same is no longer true.
The fastest single core AMD processor is still the Athlon 64 FX-57 running at 2.8GHz, which AMD will continue to sell alongside the FX-60. But with the clock speed gap between the 2.6GHz dual core FX-60 and the 2.8GHz single core FX-57 a meager 7.6%, you can effectively go to one CPU and get the best single-threaded and multithreaded performance. Remember that the best applications that scale with clock speed generally give you a 50% return on every 100% increase in clock speed, so in most of the single-threaded cases, the FX-57's performance advantage will be in the 0 - 4% range. But on the flip side, the fact that the FX-60 is a dual core processor will buy it a lot in multithreaded applications.
As with all FX series processors, the FX-60 debuts at $1031 in quantities of 1000, so you can expect street pricing to be at or around that number. The FX-57 will drop to $827 mark as it will co-exist with the FX-60.
The FX-60 is really just a multiplier unlocked 2.6GHz Athlon 64 X2. It is still a 90nm processor and there are no architectural changes that we've been made aware of or have been able to find on our own. We stress the point that it is still a 90nm chip because of the fact that its closest competitor, the Pentium Extreme Edition 955, just debuted on Intel's 65nm process. Because Intel is on a smaller manufacturing process, they can cram more transistors into a smaller space. So although the Pentium EE 955 is a 376-million transistor chip, they only take up 162 mm2 of space. The Athlon 64 FX-60 by comparison is a 233-million transistor chip, but its die is a larger 199 mm2. The move to 65nm for AMD should cut the die size roughly in half assuming no architectural changes, but until then, Intel will at least have the manufacturing advantage.
You shouldn't, however, assume that the smaller, cooler running manufacturing process will result in a power advantage for Intel. The problem is that those 376 million transistors are used to build a beast of a chip with a 31-stage pipeline, so power consumption is still actually higher on the Extreme Edition than on AMD's fastest dual core:
94 Comments
View All Comments
shortylickens - Tuesday, January 10, 2006 - link
Is it just me or does AMD seem to be moving architectures along a little too quickly?Socket A had an incredibly long lifespan. It moved from Athlon B's to C's (thunderbird) to XP to MP and even a Duron thrown in for good measure.
With the tow of the latest passing on (754,940) it seems like AMD just cant get it right. Now they are are already peaking with socket 939. From now on, we'll only have pity chips thrown to us just so we dont feel bad about going into it.
Well I feel bad. :(
Nyati13 - Tuesday, January 10, 2006 - link
Socket A was around for a long time, but there were 4 different FSB specs, several different chipsets, and 2 different RAM types all lumped under Socket A. You couldn't tell for certain that a Socket A CPU would work with any random Socket A motherboard because of all the spec changes. You can say that any Socket 939 CPU will work in any Socket 939 motherboard.DigitalDivine - Tuesday, January 10, 2006 - link
That's the disadvantage of having an integrated memory controller. Memory types change, and in the past there have been numerous memory types, in order to take advantage of the changes, amd has to change their socket.jakerugged - Tuesday, January 10, 2006 - link
In the review under the gaming tests you say - "We should also mention that we had to re-run our AMD numbers in this test since the last review as we were seeing sub-par AMD performance. A clean install and re-run of the numbers yielded the results you see today; the Intel numbers didn't change." Why did the Intel numbers NOT change and why did the AMD numbers change? Was it only in the Gaming tests or once you had good AMD numbers in the gaming tests did you then run the SYSMARK, etc tests in order to get max performance? If you did thats not good testing methodolgy. Can we see these sub-par numbers, how bad are they?Its ok to say that this CPU is fast but only if you add in that you may have to repeatedly re-load and re set-up your system until it is "just so" before it gives the kind of performance that you would expect.
Betwon - Tuesday, January 10, 2006 - link
About the of FX-60, they(both the websites) find:"our processor worked just fine at 2.8GHz clock speed. Unfortunately, Athlon 64 FX-60 didn’t get along with the 15x clock multiplier."--from xbitlabs
"With a retail AMD heatsink/fan, the best we could do is 2.8GHz at 1.40V. With more exotic cooling you could probably manage better, but stepping up the voltage all the way up to 1.50V wouldn't yield a 3GHz overclock on air."--from anand
They agree.
jakerugged - Wednesday, January 11, 2006 - link
Whoa there.....This has gone on a little bit longer than even I thought.My original comment was about the general stability of the FX60, because Anandtech.com just put in a little one liner about how they had to re-load the entire FX60 test rig (Im assuming this means re-install the O/S, all drivers, patches and benchmark tools.) because it was not performing correctly. They still have not said why or what these low figures were?
To be honest, Im not really into O/Cing but I am into stability and I dont want to have to re-load my system just so I can play a few games after using Word or sending a couple of e-mails.
Betwon - Tuesday, January 10, 2006 - link
About the of FX-60, they(both the websites) find:"our processor worked just fine at 2.8GHz clock speed. Unfortunately, Athlon 64 FX-60 didn’t get along with the 15x clock multiplier."--from xbitlabs
"With a retail AMD heatsink/fan, the best we could do is 2.8GHz at 1.40V. With more exotic cooling you could probably manage better, but stepping up the voltage all the way up to 1.50V wouldn't yield a 3GHz overclock on air."--from anand
They agree.
PrinceGaz - Tuesday, January 10, 2006 - link
Why don't you quote a bit more of what xbit labs said, Betwon?"We managed to get our CPU to work stably with the clock frequency multiplier set to 14x without increasing the Vcore, which equaled 1.3V throughout the entire test. In other words, our processor worked just fine at 2.8GHz clock speed. Unfortunately, Athlon 64 FX-60 didn’t get along with the 15x clock multiplier.
Having increased the Vcore by 10% above the nominal, we still couldn’t get our hero to run stably at 3GHz frequency. Although the CPU would boot the Windows XP just fine and could even go through some test applications, it would still crash to the Blue Screen of Death (BSOD) when both cores were fully loaded. So, we had to give up or desperate intention to conquer the 3GHz height.
We managed to get our processor to work absolutely impeccably at 2.9GHz with the Vcore set to 1.44V. This frequency was achieved as 14 x 207MHz."
So they managed 2.9GHz totally stable, not just 2.8GHz. And on the final page
"However, we shouldn’t say that Presler got completely and hopelessly defeated by the new Athlon 64 FX-60. Due to the new finer production technology, the new dual-core processors from Intel can boast excellent overclocking potential. As for the frequency potential of the AMD processors, it has been almost completely exhausted by now. As a result, when we compare the results demonstrated by the overclocked AMD Athlon 64 FX-60 and Intel Pentium Extreme Edition 955, the former is not always the winner. So, if you do not mind your system being a little bit noisy and generating quite a bit of heat, then Pentium Extreme Edition 955 might be a way to go."
Note the wording-- "the former [o/c FX-60] is not always the winner". The meaning being that the FX-60 at 2.9GHz beats the EE955 at 4.26GHz more often than not, but there are situations where the o/c EE955 wins. So when both are overclocked to their max, they are either equal or the FX-60 has a slight advantage overall. Of course the FX-60 has a significant advantage when it comes to heat, power consumption, and noise.
Betwon - Tuesday, January 10, 2006 - link
I had say that:"OC:
955 is 4.26GHz, FX-60 is 2.9GHz -->Now, the ratio is 1.46 (4.26/2.9). -->P4 starts to be better than X2. "
Note:
"As for the frequency potential of the AMD processors, it has been almost completely exhausted by now."
"Due to the new finer production technology, the new dual-core processors from Intel can boast excellent overclocking potential."
flyck - Tuesday, January 10, 2006 - link
but they also benchmark them both... and p4 is overclocked in those benchmarks still slower then X2. And they also say the power consumption of that overclocked p4 is insane.