AMD FX-8370E CPU Review: Vishera Down to 95W, Price Cuts for FX
by Ian Cutress on September 2, 2014 8:00 AM ESTAMD FX-8370E Conclusion
Since the bygone days of the GHz wars, energy efficiency is now a key part in any x86 CPU manufacturer handbook. When designing a CPU, parts can be engineered to either be all-out guns blazing on performance, or it can strike a balance between performance and power. When AMD first announced the FX-9590, it was presumed that the Vishera architecture was the former, given the large power increase to get to 5 GHz with turbo. That same principle comes across in these new energy efficient processors, especially when the FX-8370E is 700 MHz less than the FX-8370 it tries to emulate for a 30W decrease.
Trying to have an energy efficient part of an architecture that loves high frequency at the expense of power is an odd scenario, one borne from the initial production of motherboards that supported these processors. When there were only 95W and 125W CPUs to worry about, motherboards were made to only cope with this setting, until 220W CPUs hit the ecosystem. These 95W parts allow AMD to offer an upgrade path to an 8-thread machine without replacing the motherboard. The fact that AMD is going this far might suggest they have some strong data that a user would more likely replace a CPU than a motherboard. Admittedly replacing a CPU usually requires a BIOS update or less, whereas upgrading a motherboard is a bigger ordeal.
In terms of absolute performance, the FX-8370E sits somewhere between the FX-6350, FX-8150 and FX-8350. The multi-core performance puts it ahead of the FX-6350 CPU, but the single core performance can juggle around with all three, sometimes between the FX-8150 and FX-8350 due to the generational gap but often on par with the FX-8150. The same goes with gaming, where it competed with the FX-8150 near the bottom of our charts. The new FX-8370, the non-E part, should come out a clear winner over the FX-8350, so it stands to reason that the FX-8370E sits below them both due to the base frequency difference.
For competition against Intel, the nearest sets of numbers we have are the i3-4330, i3-4360 and the i5-4690, positioned well below and above the price point respectively. Intel wins hands down on the single threaded performance, even against the FX-9590, although having access to 8 threads on the FX-8000/9000 series is becoming more important for tasks like compression, multi-threaded web browsing and media creation.
AMD’s ideal scenario is a gamer using a combination of an FX-8370E ($200) with, for example, an MSI 970 Gaming motherboard ($90) and an R9 285 GPU ($250). Altogether this would cost around $540 for the start of an 8-thread system. This will do fine in gaming at 1080p, and the parallel to draw is that this performs the same as an FX-8150, but at lower power. It is a shame that the FX-8150 came out in October 2011, and nearly three years later we are saving only 30 watts of TDP (24%) and $45 on release price difference (18%) for the same performance on what should be the flagship line for a major x86 manufacturer.
At the end of the day, AMD needs to upgrade the architecture (and the chipset). At some point the architectures of the FX and APU line either need to diverge their separate ways, or there needs to be a hard earned reconciliation attempt to find a node and a manufacturing process suitable for both low power graphics cores and high frequency processor cores. We know about AMD's plans for 2016, dealing with ARM and x86, and the announcements on K12 so far point to AMD targeting servers, embedded markets and ultra low power client devices. Here's hoping desktop side gets a good boost.
Facebook
Twitter
RSS
107 Comments
View All Comments
fluxtatic - Wednesday, September 3, 2014 - link
Yeah, that 40 years it held true was a total goof. That Moore, what an idiot! /sSamus - Wednesday, September 3, 2014 - link
I wish I could look more than 40 years into the future...But on a serious note, Moore's law still stands true, and will for the foreseeable future. You are right, we can't shrink things forever (we're already approaching the sub-atomic level) but there are creative ways around this; 3D transistors, quantum computing (currently vaporware IMHO) etc.
ironargonaut - Wednesday, September 3, 2014 - link
You are the fool Moore made no such assumption. Nor did he make any such statement. Others took what he said and condensed it into "Moore's law".Gigaplex - Tuesday, September 2, 2014 - link
"Seriously, how hard is to make a decent CPU"Let's see you do a better job if you think it's easy.
imin83 - Wednesday, September 3, 2014 - link
"Seriously, how hard is to make a decent CPU"-the correct reply to that statement would be, "Watch out, we got a badass over here"
IUU - Friday, September 5, 2014 - link
Well, even though I readily agree that Moore's Law will eventually come to an end, regarding the present technologies, I don't think this will happen until some years(may be 5? 10?).I bought my i7 920 at the end of 2008. So ~ 6 years later or about 3 Moore's cycles I bought a laptop
with an intel cpu that consumes officially 1/3 of the energy of the old beast. Taking into consideration the on-chip gpu, this is probably considerably less for the cpu part. Yet it performs, as a cpu,
about 10% faster on single threaded and moderately threaded applications(3-4 threaded apps). So, for any practical purpose, it's 10% faster for less than one third of the energy requirements.
If you do the multiplications and the divisions you will probably find that moore's law still holds true, not only from a manufacturing perspective but from a more substantial one;Flops per Watt.
The only problem is that performance per dollar went backwards for various reasons that are artificial and not based on the physical feasibility of things. Thus while you were purchasing a 130 watt cpu back in 2008 for ~300 dollars, now you cash out on average 500. But this is nothing.
Think about it. Many people happily waste hundreds of dollars per year for the¨"latest mobile tech", ie they spend for chips that are from an order of magnitude to possibly 2 orders of magnitude less capable, and it seems normal to almost everyone. Now go support the mobile involution in order to pay for an ordinary cpu not 1000 but 10000 dollars and then be nostalgic for the good old days when you could buy a haswell extreme for 1000 bucks.
Samus - Wednesday, September 3, 2014 - link
On one hand, AMD's stagnation is pissing me off because Intel hasn't had any competitive pressure to produce anything faster since Nehalem (Haswell is only about 20% faster in IPC, yet 5 years newer)On the other hand, Intel would still be assfucking us with Netburst if it wasn't for AMD's Athlon.
Intel strongarmed AMD out of the game. The lost revenue destroyed their R&D budget and they haven't rebounded since.
ddriver - Wednesday, September 3, 2014 - link
My biggest issue with intel is the decision to cram IGP inside high end products, which makes about ZERO sense. Integrated graphics are OK for low and lower midrange products, but in a high end product it is just waste of die space. Intel wastes 2/5 of the die on graphics which ends up never being used, and for what? To get better "video card" market share, even at the price of selling stuff that ends up never being used? Throw in 50% more cores and cache please, or just make the chip smaller and cheaper...Samus - Wednesday, September 3, 2014 - link
While I agree with you from an engineering perspective, you are free to purchase XEON or -E class CPU's if you don't like 2/5 of your die wasted.It does seem the Bloomfield Nehalem (Socket 1366) CPU's made the most efficient use of die for performance, being 45nm and all, and as soon as Intel integrated the graphics onchip it all the sudden lost its triple-channel memory controller (because there was no room left for it) so the die area can be better used, but in practice, the integrated graphics helps Intel's bottom line more than a triple channel controller or more cache, both of which 90% of consumers will benefit little from, while also increasing power consumption.
silverblue - Wednesday, September 3, 2014 - link
QuickSync could be useful...?