Monday, October 22nd 2012

AMD Announces 2012 FX "Vishera" Line of Performance Desktop Processors

AMD announced the 2012 FX "Vishera" line of eight-core, six-core, and quad-core desktop processors. Based on the new "Piledriver" CPU micro-architecture, the new processors feature increased performance and an updated instruction set, over the previous generation. To begin with, the processors are based around the "Vishera" silicon, built on the 32 nm HKMG process at Global Foundries. With a transistor count of 1.2 billion and a die area of 315 mm², Vishera packs four Piledriver modules, with two cores each, 2 MB L2 cache per module (8 MB total), and 8 MB of L3 cache. Eight-, six-, and four-core models are carved out by toggling the number of modules between four, three, and two.

The Vishera silicon also features an updated CPU instruction set, which includes SSE/2/3/S3/4.1/4.2/4A, AVX, AES-NI, FMA/FMA2/FMA3, XOP, and F16C. An x86 processor by design, Vishera features the AMD64 x86-64 instruction set. Its updated integrated memory controller supports up to 64 GB of dual-channel DDR3 memory, with a standard speed of DDR3-1866 MHz, and more possible with overclocking. The memory interface is single, monolithic 128-bit, unlike the dual 64-bit IMC approach of the "Stars" micro-architecture. Built in the same socket AM3+ package as the previous generation FX, the new chips are compatible with existing AM3+ motherboards with a BIOS update. The 2012 FX processor lineup includes a total of four models, the FX-8350 flagship eight-core, FX-8320 performance eight-core, FX-6300 mainstream six-core, and FX-4300 value quad-core. All models feature unlocked base-clock multipliers, making each of them fit for overclocking. Their specifications and target SEP pricing are tabled below. Market prices could be about 5~10% above the SEP prices.
Add your own comment

40 Comments on AMD Announces 2012 FX "Vishera" Line of Performance Desktop Processors

#1
[H]@RD5TUFF
kid41212003 said:

Also, people should realize that we've came to a point where cpu's performance is no longer matter for gaming due to better programming for multicore cpu.

What is really matter now is gpu. Spend less on cpu and get a better gpu will give you more FPS!
Not true, the issue is the majority of games are console ports and with console tech over 5 years old, the games just aren't made to push PC's very hard if at all.:shadedshu

The trend will continue till the new consoles come out.
Posted on Reply
#2
kid41212003
[H]@RD5TUFF said:
Not true, the issue is the majority of games are console ports and with console tech over 5 years old, the games just aren't made to push PC's very hard if at all.:shadedshu

The trend will continue till the new consoles come out.
That's so two years ago. The OLD Unreal Engine has been optimized greatly for multicore cpu in the past 2 years if you haven't realized (Dishonored for ex.).

Even if your statement is true (absolutely unlikely), Vishera can handle all non-multicore games just fine as its current clockspeed (even a Phenom II can do so).

Funny fact: All Capcom (a huge console game publisher) games in the past three years support multi-threads.
Posted on Reply
#3
[H]@RD5TUFF
kid41212003 said:
That's so two years ago. The OLD Unreal Engine has been optimized greatly for multicore cpu in the past 2 years if you haven't realized (Dishonored for ex.).

Even if your statement is true (absolutely unlikely), Vishera can handle all non-multicore games just fine as its current clockspeed (even a Phenom II can do so).

Funny fact: All Capcom (a huge console game publisher) games in the past three years support multi-threads.
Funny thing I never said squat about cores or the AMD chips not being able to handle gaming. My point was and still is that because the vast majority of games are straight console ports, they don't require much oomph from PC's. Way to get defensive about nothing.:wtf:
Posted on Reply
#4
kid41212003
That's also not entirely true. It's not because of console that devs don't make games that "push our pc hard enough".

It's because the market for PC games is not big enough for publishers to make the investment (think about the people who have i7 and GTXs).

Prettier a game, more expensive it is to make. I'm pretty sure all the devs out there want as much money as possible to make the prettiest evar but they just don't get funded that way.

And, I just love to argue.
Posted on Reply
#5
cdawall
where the hell are my stars
largon said:
Power consumption is still nothing short of horrible and goes beyond horrible when OC'ed.
Piledriver is a fail in my book.
26 watts in difference?



While not exactly as low as the lower voltage/lower wattage/smaller die intel chips it is still a vast improvement over the previous generation.
Posted on Reply
#6
NC37
Just what I wanted to see. Surpassed my expectations in Handbrake tho. Much larger bump over the BD and PIIs than I thought it would have.

Think I might just pick one of these up. Maybe be my last AMD CPU if things don't improve. Now to just wait for a good deal. Sorry Newegg but $220 is too much. Gimmie that $200 price point or give me a special bundle game deal and then I'll bite.
Posted on Reply
#7
ramcoza
cdawall said:
26 watts in difference?

http://tpucdn.com/reviews/AMD/FX-8350_Piledriver_Review/images/power_full_load.gif

While not exactly as low as the lower voltage/lower wattage/smaller die intel chips it is still a vast improvement over the previous generation.
He clearly said "when overclocked"..
According to TPU, it consumes 254W when O'ced. Now compare it to the stock 134W. It's almost twice the power consumption. At least to me, it's unacceptable.
Posted on Reply
#8
bencrutz
ramcoza said:
He clearly said "when overclocked"..
According to TPU, it consumes 254W when O'ced. Now compare it to the stock 134W. It's almost twice the power consumption. At least to me, it's unacceptable.
read again
he clearly said:
largon said:
Power consumption is still nothing short of horrible
and there's this:
and goes beyond horrible when OC'ed.
Piledriver is a fail in my book.
Posted on Reply
#9
Aquinus
Resident Wat-man
ramcoza said:
According to TPU, it consumes 254W when O'ced. Now compare it to the stock 134W. It's almost twice the power consumption. At least to me, it's unacceptable.
...and you think my 3820 only eats 130 watts OC'ed as well as stock? I don't think so. Overclocking makes my power usage skyrocket on SB-E. :) Maybe even as high as 225 watts? Could be higher.
Posted on Reply
#10
ramcoza
Aquinus said:
...and you think my 3820 only eats 130 watts OC'ed as well as stock? I don't think so. Overclocking makes my power usage skyrocket on SB-E. :) Maybe even as high as 225 watts? Could be higher.
Cool down, my friend. Why are you comparing piledriver to LGA2011. Let's compare it with something within it's performance range.


i7 3770K overclocks from 3.5GHz to 4.6GHz, which is 31% overclock. It consumes only 39.3% more power, when load. (http://www.anandtech.com/show/5771/the-intel-ivy-bridge-core-i7-3770k-review/4)


FX-8350 overclocks from 4GHz to 4.8GHz, which is only 20% overclock. It consumes hefty 59% more power, when load. (http://www.anandtech.com/show/6396/the-vishera-review-amd-fx8350-fx8320-fx6300-and-fx4300-tested/8)


According to that 8350 review, i7 3770K at 4.6GHz would have been used only 167W, which will be lower than that of FX-8350's stock power consumption



I didn't try to bash you. But I always respect the reality rather than speculations. If you really need to compare a lower tier of product to higher tier. Try to compare it with the best or at least second best. Then compare the performance gained percentage with power consumption percentage. For example try to compare FX8350 @4.8GHz against i7 3930K @ stock, because i7 3970K(@stock clock) will prevail Fully O'ced FX. Now compare the power consumption of stock i7 3930K and FX's (@4.8GHz) power consumption. Otherwise compare it with i7 3770K or i5 3570K (Both FX and Ivy fully overclocked). Still ivybridge overclocks better than FX-8350 (Ivy bridge's 31% OC vs 8350's 20% OC) on air cooler :shadedshu
Posted on Reply
#12
3870x2
kid41212003 said:
That's also not entirely true. It's not because of console that devs don't make games that "push our pc hard enough".

It's because the market for PC games is not big enough for publishers to make the investment (think about the people who have i7 and GTXs).

Prettier a game, more expensive it is to make. I'm pretty sure all the devs out there want as much money as possible to make the prettiest evar but they just don't get funded that way.

And, I just love to argue.
I have to go with [H] on this one, though you provide a perfectly valid point.

We as the PC community want to move forward, are limited in graphics technology from earlier consoles.

There are a few gleaming examples though, like dishonored, that shine through, but they are few and far between.
Posted on Reply
#13
SIGSEGV
ramcoza said:
Cool down, my friend. Why are you comparing piledriver to LGA2011. Let's compare it with something within it's performance range.

i7 3770K overclocks from 3.5GHz to 4.6GHz, which is 31% overclock. It consumes only 39.3% more power, when load. (http://www.anandtech.com/show/5771/the-intel-ivy-bridge-core-i7-3770k-review/4)

FX-8350 overclocks from 4GHz to 4.8GHz, which is only 20% overclock. It consumes hefty 59% more power, when load. (http://www.anandtech.com/show/6396/the-vishera-review-amd-fx8350-fx8320-fx6300-and-fx4300-tested/8)

According to that 8350 review, i7 3770K at 4.6GHz would have been used only 167W, which will be lower than that of FX-8350's stock power consumption

I didn't try to bash you. But I always respect the reality rather than speculations. If you really need to compare a lower tier of product to higher tier. Try to compare it with the best or at least second best. Then compare the performance gained percentage with power consumption percentage. For example try to compare FX8350 @4.8GHz against i7 3930K @ stock, because i7 3970K(@stock clock) will prevail Fully O'ced FX. Now compare the power consumption of stock i7 3930K and FX's (@4.8GHz) power consumption. Otherwise compare it with i7 3770K or i5 3570K (Both FX and Ivy fully overclocked). Still ivybridge overclocks better than FX-8350 (Ivy bridge's 31% OC vs 8350's 20% OC) on air cooler :shadedshu
/facepalm

i think you missed the point...
perhaps you should at least read on wikipedia first..
Posted on Reply
#14
Vinska
Aww gee wiz, I would get a Piledriver CPU right now. And do benchmark of "Son versus Father: a duel where Piledriver tries to prove he's better than his pops!"
Too bad here in Lithuania computer parts usually "lag behind" by at least a week. (The bulldozer "lagged" by more than a month, for example). That's a long time to deal with this mouth watering. As 'dose Piledrivers do look tasty...
Posted on Reply
#15
eidairaman1
Powerload is the biggest improvement I noticed. Performance is better actually. lets compare a 8320 to 8150 now.
Posted on Reply
Add your own comment