UPDATED! AMD Announces FX-9590 and FX-9370: Return of the GHz Race
by Jarred Walton on June 13, 2013 5:50 PM EST
AMD Announces FX-9590 and FX-9370: Return of the GHz Race
Today at E3 AMD announced their latest CPUs, the FX-9590 and FX-9370. Similar to what we’re seeing with Richland vs. Trinity, AMD is incrementing the series number to 9000 while sticking with the existing Piledriver Vishera architecture. These chips are the result of tuning and binning on GlobalFoundries’ 32nm SOI process, though the latest jump from the existing FX-8350 is nonetheless quite impressive.
The FX-8350 had a base clock of 4.0GHz with a maximum Turbo Core clock of 4.2GHz; the FX-9590 in contrast has a maximum Turbo clock of 5GHz and the FX-9370 tops out at 4.7GHz. We’ve asked AMD for details on the base clocks for the new parts, but so far have not yet received a response; we're also missing details on TDP, cache size, etc. but those will likely be the same as the FX-8350/8320 (at least for everything but TDP).
6/13/2013 Update: We have now received the most important pieces of information from AMD regarding the new parts. The base clock on the FX-9590 will be 4.7GHz and the base clock of the FX-9370 will be 4.4GHz, so in both cases it will be 300MHz below the maximum Turbo Core speed. The more critical factor is also the more alarming aspect: the rumors of a 220W TDP have proven true. That explains why these parts will target system integrators first, and the FX-9000 series also earns the distinction of having a higher TDP, but it also raises some serious concerns. With proper cooling, there's little doubt that you can run a Vishera core at 5.0GHz for extended periods of time, but 220W is a massive amount of power to draw for just a CPU.
To put things in perspective, the highest TDP part ever released by AMD prior to the FX-9000 series is the 140W TDP Phenom II X4 965 BE. For Intel, the vast majority of their chips have been under 130W, but a few chips (e.g. Core 2 Extreme QX9775, Core i7-3970X, and most of the Xeon 7100 series PPGA604 parts back at the end of the NetBurst era) managed to go above and beyond and hit 150W TDPs. So we're basically looking at a 76% increase in TDP relative to the FX-8350 to get a 19% increase in maximum clock speed. It's difficult to imagine the target market for such a chip, but perhaps a few of the system integrators expressed interest in a manufacturer-overclocked CPU.
For those who remember the halcyon days of the NetBurst vs. Sledgehammer Wars, the irony of AMD pimping the “first commercially available 5GHz CPU” can be a bit hard to take. Yes, all other things being equal (cache sizes, latency, pipeline depth, power use, etc., etc…), having a higher core clock will result in better performance. The stark reality is that all other things are almost never “equal”, however, which means pushing clocks to 5GHz will improve performance over the existing FX-8000 parts but clock speed alone isn’t enough. AMD continues to work on their next generation architecture, Steamroller, which will debut later this year in the Kaveri APUs as a 28nm part, but in the interim we have to make do with the existing parts.
As we covered extensively last week, Intel has just launched their latest Haswell processors, and on the desktop we’re seeing relatively small performance gains. That’s somewhat interesting as this is a “Tock” in Intel’s Tick-Tock cadence, which means a new architecture and that usually means improved performance. However, similar to the last Tock (Sandy Bridge), Haswell is more of a mobile-focused architecture, which means performance gains on the CPU are minor but power and battery life gains can be significant, especially in lighter workloads. Also similar to the “Tock” when we moved from Clarkdale to Sandy Bridge, the jump in graphics performance with the HD 5000 series parts (and even more so with the Iris and Iris Pro parts) can be quite large relative to Ivy Bridge.
So Intel has been relatively tame on the CPU performance increases this time around and for they’ve focused on reducing typical power use and improving graphics. Meanwhile AMD’s answer on their high-end desktop platforms is…more clock speed. We’ll have full reviews of the new parts in the future, as the new CPUs are not yet available, but given the ability of Vishera to overclock quite easily to the 4.8-5.2GHz range on air-cooling (and 8GHz+ with exotic overclocking methods!) the higher Turbo Core speeds were inevitable.
We could also talk model numbers and question the need to increment from the 8000 series to the 9000 series when nothing has really changed this time around—the more sensible time to make that jump should have been when Vishera first launched, at least from the technology side of things. It would also be nice to see more of a unification of model numbers in AMD’s product stack, as we currently have FX-4000, FX-6000, FX-8000, and now FX-9000 parts all built on the Zambezi/Bulldozer and Vishera/Piledriver architectures. FX-4000 (two modules/four cores), FX-6000 (three modules/six cores), and FX-8000 (four modules/eight cores) made sense, but FX-9000 breaks that pattern. At present there are no updates being announced for the FX-4000 and FX-6000 families, but those will likely come. Will they be FX-5000 and FX-7000 parts now, or will they remain 4000/6000? If AMD were to use an Intel-style naming convention, Bulldozer was 1st Generation, Piledriver is 2nd Generation, and ahead we still have Steamroller (3rd Generation) and Excavator (4th Generation), but they’ve chosen a different route.
Whatever the name of the part, more than ever it’s important to know what you’re actually getting in terms of hardware before making a purchase—that holds true for AMD CPUs, APUs, and GPUs, but it also applies to Intel’s CPUs and NVIDIA’s GPUs, never mind the variety of ARM SoCs out there. The FX-9000 series is now AMD’s highest performance four module/eight core processor for their AM3+ platform, but it’s an incremental improvement from the FX-8000 series in the same way that the Radeon HD 8000 series is an incremental improvement on the HD 7000 GCN offerings. At least on the AMD CPU side of things we can generally go by the “higher numbers are better” idea, but that won’t always be the case.
AMD did not reveal pricing details on the new parts, and the press release says these new CPUs will “be available initially in PCs through system integrators”. They may replace the existing FX-8350 and FX-8320 eventually, but they will initially launch at a higher price depending on how AMD and their partners feel they stack up against the competition.
Source: AMD Press Release
Facebook
Twitter
RSS
115 Comments
View All Comments
JarredWalton - Tuesday, June 11, 2013 - link
If they bump the TDP past 150W, then Bulldozer and its derivatives truly will be AMD's NetBurst. What amazes me is that Intel actually had the guts to can Tejas. Anand actually had a chance to run some early benchmarks on Tejas at one point, so it was basically complete and Intel realized that the part just wasn't going to be any good. I think the only way AMD fixes the Bulldozer architecture is if they seriously reorganize the pipeline at some point and stop going so deep, but I don't see that happening.Soleron - Tuesday, June 11, 2013 - link
Jarred, this is a halo part. Low production numbers, low yields, high TDP, SUPER high cost. Like expect $500 easy.I'm not sure why you think this is a Bulldozer replacement.
Hector2 - Tuesday, June 11, 2013 - link
I think it was an easy decision for Intel to make on Tejas in the end. The power numbers came in real high at the high frequency and they realized they could achieve better real performance at lower power and lower frequencies with a dual core. This became a "right hand turn" for them and setup the direction for all future architecturestipoo - Tuesday, June 11, 2013 - link
Really? I looked over all the Tejas stuff but it never appeared to get to the benchmark stage, unless he withheld them? In which case, even now that it doesn't matter at all, I would still absolutely love to see the benchmarks, surely Intel can't care now.JarredWalton - Tuesday, June 11, 2013 - link
I know Anand had a chance at some point to play with early silicon. I don't know if he still has any numbers, or maybe they just let him use it at a lab but no benches? I'll have to ask him....Hector2 - Wednesday, June 12, 2013 - link
What I was referring to you won't find outside of Intel because Tejas never got that far out of the gate. It was clear during the design phase in Austin it would take too much power to get to the single core MHz target they wanted. Dual core beat it.JDG1980 - Tuesday, June 11, 2013 - link
Why don't you think that AMD is going to reduce the pipeline length? I was under the impression that there were already some steps being made in that direction with Steamroller. The original Zambezi Bulldozer release was such a fiasco that it got AMD's management team canned, and the new management openly admits it was a failure. Stuff like this 5 GHz chip is clearly just a stopgap solution; in the medium term (next couple of years) they either need to fix their architecture so single-thread IPC is at least at Sandy Bridge standards, or they need to just ditch the construction equipment line of cores altogether and return to a K10 derivative (just as Intel ditched NetBurst for the P6-derived line of CPUs that continues to this day).silverblue - Wednesday, June 12, 2013 - link
I doubt that AMD can get SB level single thread performance with Steamroller. These cores are much smaller than Intel's; the real performance boost should be in multithreaded scenarios, though it shouldn't be difficult for Steamroller to, well, steamroll previous FX processors in even light workloads. Nehalem single threaded performance would be nice.bji - Wednesday, June 12, 2013 - link
If AMD can stay afloat for a few more years (and they've managed to do so under worse conditions than now so I don't see why they won't), they'll close the performance gap with Intel.Haswell has demonstrated that x86 is asymptotically approaching "the fastest per-core that it will ever be". The writing was already on the wall with Ivy Bridge, and now Haswell has put the definitive stamp on the issue.
It's simply not cost effective for Intel to pump the ever increasing R & D dollars, not to mention transistor count, necessary to advance x86 IPC significantly. The x86 market is not growing relative to other chip markets anymore thanks to mobile devices, and "more than good enough for 99% of uses" was already achieved by x86 some time ago. The just aren't that many dollars chasing higher x86 performance anymore and Intel can't continue to spend what is necessary to advance x86 speeds on a reduced performance dollar budget.
Given that, AMD now has time to play catch up. Intel is no longer going to be making each of its successive chip architectures significantly faster than the previous, so AMD is no longer chasing a moving performance target. Because AMD has not hit the same walls that Intel has hit in terms of IPC improvements yet, it has room to advance its performance more quickly than Intel does - until it hits the same walls in a couple of years.
At that point, AMD and Intel will have fairly similarly performing parts from an IPC perspective. Intel will still have superior process technology which will allow it to have a better high end story, although not nearly as much better as it has now. Intel will also have better thermals and power use due to superior process technology as well as generally better designs.
Even though AMD will eventually reach near parity with Intel on performance, it will not benefit from it the way Intel has. Because by that point, the x86 market will be even further cannibalized by mobile devices and AMD will be fighting for an ever larger piece of an ever smaller revenue stream. Intel already milked x86 for the best of what it was worth, from a profit perspective, over the past few years, and by the time AMD is in a position to significantly challenge Intel, the milking will be over. AMD will continue to do just well enough to stay afloat but will never make boatloads of money off of x86 like Intel has.
testbug00 - Wednesday, June 12, 2013 - link
Considering that overclocked piledriver uses 268 watts (from the source i heard) and everything i have seen point to a max 220W power usage it is amazing.and they could get it down to 150 (maybe) if the parts are similar to the Richland xxx5/xxx7 parts... i don't know :(
And my understanding is that Steamroller is a deep change in the bulldozer uarch.... :)
Also, Considering that netburst's power consumption is more from leakage (and i believe most of Bulldozer's is not) the issue is a lot more of the silicon it is made on....
on another note i met someone who apparently has run their 8350 at 1.7 volts since they got it (right when it came out) 0.0.... This scares me because AMD has been really conservative with voltages on Llano and Trinity.... If they are not conservative i think 150W might be possible for the part that turbos to 4.7 :)