Slashdot Mirror
AMD Launches Piledriver-Based 12 and 16-Core Opteron 6300 Family
MojoKid writes "AMD's new Piledriver-based Opterons are launching today, completing a product refresh that the company began last spring with its Trinity APUs. The new 12 & 16-core Piledriver parts are debuting as the Opteron 6300 series. AMD predicts performance increases of about 8% in integer and floating-point operations. With this round of CPUs, AMD has split its clock speed Turbo range into 'Max' and 'Max All Cores.' The AMD Opteron 6380, for example, is a 2.5GHz CPU with a Max Turbo speed of 3.4GHz and a 2.8GHz Max All Cores Turbo speed."
6200 series have shared FPU (floating point unit). Which means that there are less FPUs that there are processing cores. To multiply two floating point numbers cores are waiting in a queue until FPU is free to use, this happens when all cores are calculating at the same time. If you are doing intensive calculations this is going to be slower than if you used 6100 series. 6100 series have dedicated FPU for each core.
I know this because we were recently buying a new cluster for calculations using YADE software.
How, here's the question: how about 6300 series, is there a dedicated FPU?
#
#\ @ ? Colonize Mars
#
I'm not even sure how you could post a story about AMD, what with it's recent decline this entire last decade, and not directly compare them to intel.
Are these even desktop or server chips? It's been so long since I bought AMD, I really couldn't tell you which line Piledriver sits in anymore, or if they've consolidated them.
The general gist I've read is that AMD is cheaper than Intel, and in the past has been "more green" due to power consumption, but with Ivy Bridge, your bang for the buck and much, much smaller lithography process has given intel the advantage in both areas.
moox. for a new generation.
AMD have been dying for 20 years now, its just fashionable for you followers to talk about it more in recent months.
They will probably die the year of the Linux Desktop.
Piledriver is the architecture, like Intel's Ivy Bridge is the architecture.
These are server chips. Best case, these are finally faster than their pre-Bulldozer parts in real, consumer desktop use. They will not beat an 8 core Sandy Bridge Xeon in FP-heavy applications, and power consumption is, at best, on the same level as the Xeons.
All they can do is work like crazy on their next line (Steamroller as it?) so they're truly competitive again.
Are these even desktop or server chips? It's been so long since I bought AMD, I really couldn't tell you which line Piledriver sits in anymore, or if they've consolidated them. The general gist I've read is that AMD is cheaper than Intel, and in the past has been "more green" due to power consumption, but with Ivy Bridge, your bang for the buck and much, much smaller lithography process has given intel the advantage in both areas.
Server chips. Opteron was always, and always has been about servers.
I am not a business owner and do not operate servers myself. For home usage, a low price CPU with adequate power will kick intel "we-cripple-all-but-i7-features" anytime in value for my $. I do not do geek pissing contests.
Tomorrow is another day...
Last year we bought some servers with 6 core cpu's
The. SQL 2012 came out with per core licensing
I did some quick math and its cheaper to buy new servers with 4 core cpu's than license SQL 2012 for 12 cores per server
AMD has lost performance/watt recently. These are intended as server chips (G34 socket, not AM3+).
These might bring back performance per watt, as AMDs have seemed to scale better in the the multi-CPU per box / multi-core per CPU segment recently.
Self proclaimed typo king, and inventor of the bear destroying coffee table (patent not pending).
AMD have been dying for 20 years now.
Except they haven't. They've been dying since Intel started their tick-tock stratgey with the Core series, and AMD hasn't been able to keep up with Intel's gains in performance.
These Opteron models are the new server line from AMD. The desktop version based on the same architecture (the Trinity alluded to in the summary) closed some of the gap against Intel. But Intel remains the market leader on single core performance, performance per core, and power utilization. AMD continues to push the number of cores upward more aggressively, but there's not many workloads where that matters enough for their slim advantage to result in a net win. And the lower efficiency means that sometimes even having more cores doesn't aggregate into enough speed to be a useful alternative. That leaves AMD to compete on pricing. And the CPU is a relatively small part of the total budget on larger servers. Load up a Dell 815 for example and you'll find the CPU pricing seems small compared to what filling its RAM capacity up costs. And then there's reliable storage, at a while higher price level altogether.
The rule of thumb I've been using for the last year, based on benchmarking of CPU heavy database work, is that I expect a 32 core AMD server to be about as fast as a 24 core Intel one, while using significantly more power. The 40% performance per watt gain claimed here--from AMD's own hand-picked best case scenario benchmark--is only enough to make the Intel performance and gap decrease in size, not go away. We'll see if these new Opterons benefit from the re-engineering work done recently more than the desktop ones did; so far it doesn't look good.
AMD had one period in the limelight. When the first good 64-bit x86 systems were Opterons launched in 2003, they had a really competitive product for servers. Intel was busy jerking off with Itanium at that time, was oblivious to power consumption (the Pentium 4 was the desktop processor available), and just generally executing terribly. It was like a textbook classic case where the near monopoly market leader was fat and dumb, and got its ass handed to it by its scrappy competitor.
It took Intel until 2006 to release its first Core microarchitecture chips and start acting right again. By 2009 they had jumped back ahead of AMD in every market again, with the Nehalem server chips. And that was it; Intel has stayed one to two generations ahead of AMD ever since.
And boom! Here comes Sony with Orbis and their AMD ARM APU strategy to save the day.
MD continues to push the number of cores upward more aggressively, but there's not many workloads where that matters enough for their slim advantage to result in a net win.
I disagree: that's exactly what Xeon and Opteron are about. What differentiates those two from the Core and Phenom processors is that the former have multiple crazy fast and very expensive low latency links to allow glueless multi socket systems. Once you've got an (16)8 (hyper)thread Xeon or 16 core opteron and have more than one socket, you're already expecting a workload to scale to 32 distinct units.
Basically these chips only make sense for pretty parallel work loads.
Load up a Dell 815 for example and you'll find the CPU pricing seems small compared to what filling its RAM capacity up costs.
I use this as my go-to online quoter.
http://www.woc.co.uk/default6.aspx?nquoter=13
I have no affiliation except that I've bought such machines from them before.
Maxing out the RAM (512G) costs £3300. Maxing out the processors costs £2300. It's not quite as much, but it's substantially over half the price.
That said, I've heard rumours that the new opterons can drive 32G DIMMS, in which case you could load it up with 1T RAM for the low, low price of £30,000. In which case, your point certainly stands.
The 40% performance per watt gain claimed here--from AMD's own hand-picked best case scenario benchmark--is only enough to make the Intel performance and gap decrease in size, not go away
True, but the Opterons are substantially cheaper. If you factor in lifetime cost including bang for buck, power and cooling, it's basically a wash and really dependent on the specific workload.
If they have closed the gap this much, then they will be a substantially cheaper option overall.
SJW n. One who posts facts.
Intel calculate their TDP based on full load which isn't necessarily maximum power use.
AMD calculate their TDP based on maximum power use.
They've been dying since Intel... bribed vendors not to use Opteron processors so that even when AMD were clearly superior, they could never get ahead of Intel. That of course meant that they never had the revenue to capitalise on their very substantial advantage. Intel, of course got away with paying only $1bn, substantially cheaper than it would have been not to engage in illegal business practicses.
FTFY.
SJW n. One who posts facts.
The official tick-tock strategy goes back to the 2006 Core branding change. But Intel had been using two design teams to research and release alternate forms of optimization for a long time before that. In the mid 90's you could make out that one team focused on new architecture style features (386, Pentium) while the other was more about performance tweaking (486, Pentium Pro). The Itanium work spawned a new team altogether. The Core architecture was birthed from releasing that two of those paths--the one that let to the terrible Pentium 4 and Itanium products--had completely botched things. They pulled out of that tailspin by using the other active architecture at the time, the one that went from Pentium 3 to Celeron to Pentium M, as the basis for the new Core.
In some ways it's kind of a shame that it happened that way, because that was the last gasp for interesting new processor features from that style of design. We used to get major architecture changes: 8 to 16 to 32 to 64 bits, extra processing styles going from 387 to MMX to SSE. Now we get tick-tock, shrink and optimize. It's pretty boring.
AMD have been dying for 20 years now.
Except they haven't. They've been dying since Intel started their tick-tock stratgey with the Core series, and AMD hasn't been able to keep up with Intel's gains in performance.
Take a look at their historical share price, its all over the place, they have had lots of ups and downs.
Intel tried to kill them early by legal means.
They always had problems with margins due them being in the bottom end of the market.
I think financially they have had a few big years of losses and required extra external funding just to survive.
Yes, they have a shared 256 bit FPU, but that can be split into two 128 bit parts. So no, multiplying two floating point numbers in two threads is performed immediately and simultaneously, the cores do not wait at all. I measured this on a previous generation Opteron 6234, the performance loss caused by running two threads on two cores of the same module vs two cores in different modules was barely measurable, 3%.
Good to see they're not tapping out yet.
AMD had one period in the limelight. When the first good 64-bit x86 systems were Opterons launched in 2003, they had a really competitive product for servers
You're right about the one period in the limelight, but it began when they first released an Athlon processor, and it ended when Intel finally got control of their TDP, and thus it's substantially longer than you suggest, though the ending is the same.
Until recently the primary arguments for AMD were lower power consumption and better performance per dollar. Now neither are true, and the only argument is that it's cheaper. But if that's the case, and you do a little math, you can see that the argument is that you can get less for less, and if you're going to do that, why not buy something with an ARM processor, and no ATI graphics drivers?
"You're right," Fisheye says. "I should have set it on 'whip' or 'chop.'"
If this is not about a button on my case, then I don't care what that old buzzword is regurgigated into.
I wasn't clear enough on what I meant by number of cores. AMD's strengths when they did well in the server market (2003 to 2009) included more sockets, more cores per socket, and higher memory bandwidth to each socket. At this point the only one of those leads they maintain is that they still cram more real cores onto a socket than Intel does. Presuming the number of sockets is the same, I was suggesting that AMD's higher core count per socket doesn't give them much of a real-world advantage. As you suggested, the multi-socket situation isn't different enough between AMD and Intel for it to be a competitive advantage for either anymore; that's fairly level now.
An Intel server with 8 cores and the current generation of HyperThreading is not necessarily any slower than these new AMD ones with 16 real cores. There are times you run into memory bandwidth issues at the top end of concurrency, and Intel has been the leader on that since Nehalem in 2009. At the low end of active cores, sometimes there is just one thing you want to run really fast, and there Intel's Turbo approach is still better than AMD's. The middle area where AMD is at least competitive--lots of cores active but not constrained by memory bandwidth--is not that wide of a range of server workloads.
Piledriver is the architecture, like Intel's Ivy Bridge is the architecture.
These are server chips. Best case, these are finally faster than their pre-Bulldozer parts in real, consumer desktop use. They will not beat an 8 core Sandy Bridge Xeon in FP-heavy applications, and power consumption is, at best, on the same level as the Xeons.
That's true. A 16-core Opteron has the same FP width as an 8-core Xeon, and a higher TDP for a given clock.
On the other hand, we buy almost all AMD because it lets us build cheap 1U or 2U 4-socket servers with 512GB of RAM each. 4-socket Intel chips (E5-4600 or E7) are much more expensive; mid-range servers work out to 50% more for Intel, and high-end servers about 80% more for equivalent speed.
From 1999 to 2003, AMD's Athlon was a moderately superior CPU to Intel's Pentium III competitor. More most of that time I felt that success was limited by AMD's lack of high quality motherboards to place the CPUs in. My memory of the period matches the early history of the Athlon at cpu-info. You can't really evaluate CPUs without the context of the motherboard and system they're placed into. And the Athlon units as integrated into the systems they ran on were still a hard sell, relative to the slightly slower but more reliable Intel options. That situation didn't really change until the nForce2 chipset was released, and now we're up to the middle of 2002 already.
I highlighted the 2003 to 2006 period instead because it was there AMD was indisputably in the lead. 64 bit support, nForce3 with onboard gigabit as the motherboard, the whole package was viable and the obvious market leader if you wanted high performance.
There are times you run into memory bandwidth issues at the top end of concurrency, and Intel has been the leader on that since Nehalem in 2009.
Certainly on the desktop. I thought on the server they both have quad channel DDR3 per socket. Of course, that gives intel a higher per-core bandwidth.
I thought that the 6200 series support slightly higher clocked memory (1866) compared to Intel (1600).
I've not cheecked more thoroughly than looking up a few figures though.
SJW n. One who posts facts.
"Athlon 64" was released in December 2003 that beat P4 in all regards, price, power consumption, performance. Intel recovered from it only in January 2006 with first "Core" CPU. How does that make AMD to be in "decline entire last decade" pretty please?
Rubbish about AMD having only one competitive time: The T-Bird Athlons offered much better bang for the buck and performance than Netburst based P4's.
Anyone who followed computer architecture knew this. Athlon XP's were generally considered better all around chips than Netburst based P4's until the P4's hit > 3.2+ Ghz. The only way Intel could even stay competitive with the T-Bird Athlons and Early Athlon XP's was stuff like the Extreme Edition.
Likewise, early dual core Netburst based products P4's weren't great chips, they were massive hot power-hogs. First generation Opterons were a much better choice for many server workloads. The general advice now is to look at your workload. If your choice is an Opteron versus a Xeon look at the system cost along with your workload. If the Opteron is cheaper then you can buy more memory (If that helps you workload). Hyper transport was significantly better than the Netburst based Xeons for multiprocessing.
For single threaded Integer+FPU performance Intel is definitely better than AMD right now.
If your running prebuilt binaries that aren't heavily threaded then Intel Xeons are your best bet, but don't forget approaching this as a systems engineering problem. If your workload loves memory then you may well be better off with an Opteron with lower single threaded performance, but a lower cost, and throw the cost delta towards more memory.
If cost is no object then your best bet is a Xeon. As much as people love to beat up AMD we have them to thank for decent x64 performance on the desktop. If they hadn't made a killer chip with the Opteron then Intel would have tried to push us all to Itanium which had great theoretical performance and great FP workload performance for apps the compiler could schedule decently for but sucked eggs running integer apps with a decent number of branches... Look at the Spec CPU Perl benchmark results for an idea how much Itanium sucked at that stuff.
"With this round of CPUs, AMD has split its clock speed Turbo range into 'Max' and 'Max All Cores.' "
Remember Episode 200 of Stargate and the "Set Weapons to Maximum!" line?
AntiFA: An abbreviation for Anti First Amendment.
With respect, why are you even commenting on this if you have not got that much out of the summary? I'll try though, these are for the sort of servers where a lot of tasks are done in parallel and it's a big deal since the best comparable Intel chips are 10 core, 2GHz and horribly expensive. That may change but Intel doesn't seem so interested in that end of the market for now and have let AMD undercut them by several multiples of the price ($9000 for 64 cores vs $80,000 for 80 cores back in January).
It could be argued that 10 Xeon cores act like 20 opteron cores, but that really depends on exactly what the tasks are.
Yes, but you are going to be getting the same amount of RAM and almost always the same type no matter which way you go. The price of a CPU really matters once you go beyond a couple of sockets. Also fuck Dell since you just get the whitebox of the week with a Dell badge on it - Supermicro and a long list of others will give you something better far cheaper and may even give you support from someone based in your own country that speaks your own language.
Well, better performance per dollar isn't necessarily false nowadays. The Athlon overlingered and Bulldozer was a failure, but the revised Piledrivers are actually doing ok, at least on the lower end. An A10-5800K is pretty much on par with an i3 3220 on heavier workloads and you get a much better IGP. For about the same as an i3 3240 you get an FX-6300, which is way better for any kind of multithreaded work.
I don't think they'll be able to hold on much longer, since Haswell at 14nm vs Steamroller at 28nm will probably be embarassing to watch, but for this generation, thanks to Intel not having gained a lot on the performance front by moving to 22nm, they managed to catch up, if only on price/performance.
I recently bought one of their non-server Trinity APU processors specifically to be used for my HTPC. The power footprint is low enough that it fits in a shoebox sized enclosure and the integrated Radeon graphics mops the floor with anything from Sandy/IvyBridge and all at a lower cost. I use it to crank out 1080p video, send audio to my AVR and the kids use it to play games with a fair amount of eye candy turned on and at a playable resolution and frame rate.
Would I buy any current AMD processors for a server farm? Probably not.
Best,
You can't really evaluate CPUs without the context of the motherboard and system they're placed into.
That is so true, and you have to look at the chipset, too. Whether AMD or Intel, if you stuck with the vendor's chipset you were usually assured of reliable operation... but intel's sucked down more power over and over again, to the point that AMD's desktop stuff was better than Intel's mobile stuff for a while, and it was cheaper, and not that much slower. All that was around the Athlon 64 period, though. Athlon was just a little slower at most tasks, a bit slower at integer, but notably faster at FP which had just become important due to 3d gaming becoming a major thing on the PC at around the same time, having originally come into flower in the Pentium era.
"You're right," Fisheye says. "I should have set it on 'whip' or 'chop.'"
Would I buy any current AMD processors for a server farm? Probably not.
The predecessors of this series, the Opteron 6200 is used in quite a few supercomputers. Actually I counted 21 Opteron bases systems in the last supercomputer top 100 list.
It supports turbo boost, virtualization (vt-x and vt-d), speedstep, etc.
Yea, the AMD IGP is better and sure as hell offers better gaming performance but and this is the big fucking but, the i3-2120 offers far better performance in the area's that count for business/enterprise users. The CPU has enough performance that even with the crappy Intel IGP, they still do what's needed quite well while offering a much lower TDP and even that's becoming important to everyone.
I've been looking into this for a while and working up a build for the new year that's based on an Intel option. Much of the reason is that I'll be using a Xeon with the Intel 4000 IGP (good enough) as the TDP is 45w for the CPU while Passmark results show performance over 8000. The next best AMD offering is a meager 6000 for a 130w TDP and pretty much the same price. I hate to say that Intel is beating AMD in multiple area's and Performance per Watt is just one of them.
Mod me up/Mod me down: I wont frown as I've no crown
As far as FP performance goes, AMD's higher-end CPU-integrated Radeons put Intel's offerings to shame, and give FP performance to the processor that the general-purpose cores couldn't hope to match (if used properly).
We'd already been hearing about CUDA from Nvidia when AMD announced their Fusion Design (1st stage was the Llano) and the first thing I thought of at that time was that AMD was going to use the GPU cores to replace the shitty FPU performance on their chips. I've posted on this numerous times and with the Bulldozer design. What I expect is that by the 4th generation, the new CPU's will look like a single core to the OS instead of the multiple cores we're used to seeing but the threading performance is going to drastically improve as they're already beginning to implement the multi-thread design efforts. Simply put, AMD is completely redefining the CPU while Intel works on simply improving what's already there. Who is going to win in the long run is going to be interesting though I suspect that if AMD can turn around their profit issues, they'll be able to improve the design of their chip to run as well as Intel on a 45nm basis and not have to go with the die shrinks that Intel is pushing.
Keep in mind that these die shrinks are beginning to reach the physical limits of the silicon itself and Intel is researching new wafer processes that are going to cost lots of money. If AMD can improve/match the Intel Performance/TDP factors while using a proven 45nm process, they will be in a much better financial position then Intel as they'll be able to continue using existing fabs that are paid for, thus offering their chips for less money.
Mod me up/Mod me down: I wont frown as I've no crown
Geez man. The 486 and Pentium Pro were not performance tweaks. The Pentium Pro for example was a wholly new out-of-order design.
Intel wasn't free of chipset issues at that time either? Remember the Rambus DRAM chipsets full of bugs like the i820? AMD's own chipsets were pretty stable, even if they had somewhat obsolete feature sets back then. VIA's chipsets had less obsolete feature sets but were chock full of bugs. NVIDIA's nForce had a great feature set and lots of bugs. I actually got one of those. With the right drivers they worked pretty well...
Yea, looks like Sandy Bridge EX is cancelled:
http://vr-zone.com/articles/ivy-bridge-ep-and-ex-coming-up-in-a-year-s-time--the-multi-socket-platform-heaven/15488.html
the i3-2120 offers far better performance in the area's that count for business/enterprise users. The CPU has enough performance that even with the crappy Intel IGP, they still do what's needed quite well while offering a much lower TDP and even that's becoming important to everyone.
Do you talk about business desktops? They are idling all the time, you have to look at the idle power, not TDP.
They're about as good as a mid-range Xeon while consuming more power?
Every time I try AMD graphics I get pissed off. Before that, it was every time I tried ATI graphics. I'm over it. So the IGP is not part of the equation for me, and therefore right now AMD is offering a poorer value proposition. My current system is a Phenom II X6 (1045T I think) on an AMD-chipset board and with a 240GT 1GB, both from Gigabyte. It looks like it's going to hold me for a while, which is nice because if I built a machine today it would probably have an intel processor and I think they are bastards.
"You're right," Fisheye says. "I should have set it on 'whip' or 'chop.'"
We're on the same boat. I don't really fancy buying Nvidia, either, mainly because I'm a rancorous sucker that once bought an FX card. The trick for buying AMD graphics is buying outdated crap. My HD5570 works like a charm, even on Linux (when I'm not trapped in that limbo that follows every Xorg ABI change, of course).
We might not have to buy Intel next time, though. AMD still has a trump card, namely earlier and better OpenCL support in widely used products like Adobe's CS. Tom's has a preview bench of the performance gains: http://www.tomshardware.com/reviews/photoshop-cs6-gimp-aftershot-pro,3208-13.html
Looking at the charts, we see some workloads benefit more from weaker IGPs than from much more powerful discrete cards. That puts AMD's best IGPs on the market in a very unique and advantageous position. This has been AMD's plan since they bought ATI, and I hope they survive long enough to see it through, at least.
AMD has lost performance/watt (on x86 at least) when they fired all the engineers who knew how to make performance/watt critical decisions. Then they hired a bunch of copy-pasters from India and China. I'll bet the CEO responsible got a hefty bonus for this "presidential" decision.
$
From 1999 to 2003, AMD's Athlon was a moderately superior CPU to Intel's Pentium III competitor. More most of that time I felt that success was limited by AMD's lack of high quality motherboards to place the CPUs in.
Avoid all things VIA and you were pretty good, I had AMDs in that period and they were excellent bang for the buck. No doubt that AMD was gaining momentum in that period, remember the first Pentium IV was released in November 2000, this is what Anandtech wrote at its release:
It's amazing at how quickly the industry can turn from being dominated almost completely by a single CPU manufacturer over to a point where the underdog is now in a position to lead the market into the 21st century. Over the past 12 - 18 months we have seen this very situation occur right in front of our own eyes. Intel, a manufacturer never associated with delays or processor shortages and AMD, a manufacturer that was associated with sub-par performance and an inability to deliver on time, essentially switched roles in the past year alone.
Live today, because you never know what tomorrow brings
Pentium Pro was a completely new design and architecture, in fact the same architecture they are using today, after the failed new architecture used in Pentium4.
What I said is that the Pentium Pro didn't include any new significant processor features in its architecture, by which I mean things like adding new instructions. The architecture changes were focused on performance instead. Those were significant, from the L2 cache improvements to the (in retrospect) vital early out of order execution work. But they sped up code rather than enabling new types of code.
In fact, if you compare feature sets, the first generation Pentium Pro was actually a step back from what was already available. The Pentium line had added MMX for accelerating some types of CPU intensive "MultiMedia" operations by then. The Pentium Pro line initially did not include MMX. That disconnect makes the split design team idea I was outlining even more obvious. From that you can go back and confirm the Pentium Pro must have been developed in parallel to the Pentium MMX, with more server oriented goals, rather than as part of a single sequence.
It is true that the Core line traces its heritage back to the P6 / Pentium Pro one. It would be a stretch to say it's the "same architecture they are using today" though. I would argue that the later redesign to optimize for low power, what lead to the Pentium M, was just as large and important. That was both critical and so disruptive that it deserves to be considered a new architecture.