Information

Did you know you could become an X-bit labs fan on Facebook or follow us on Twitter?



Discussion

Discussion on Article:
AMD FX-8350 Processor Review: Tuned-Up Bulldozer

Started by: jmlxg | Date 10/22/12 10:31:50 PM
Comments: 84 | Last Comment:  03/09/13 07:23:49 AM

Expand all threads | Collapse all threads

[1-20 | 21-21]

1. 
FYI - there are 5+ GHz. Vishera OC and reviews all over the net.

Most hardware review sites are stating that AMD has had three excellent product launches in a row with Trinity laptop, Trinity desktop and now Vishera. That is good news for eduacted consumers.

While Intel CPUs may OC as well, they typically cost hundreds more than a comparable AMD APU/CPU. You can be sure from the positive Vishera reviews that AMD won't have any trouble selling these with the FX-8350 selling for $220. on Newegg and other places. The real story is that there is absolutely NO software that AMD processors can't run just fine. In fact they run Linux apps even better than Windoze crap.

Now AMD needs to get the message out instead of the often jaded opinions by those who don't understand performance, value and cost from a consumer's POV. Few people need or are willing to buy the over-hyped, over-priced Intel highend CPUs - and for good reason. Intel's high priced CPUs are a poor value in addition to the over-heating and poor overclock-ability of Ivy Bridge - which is a pure marketing job for a losy ~5% over Sandy Bridge.
16 15 [Posted by: beenthere  | Date: 10/22/12 10:39:23 PM]
Reply
- collapse thread

 
show the post
5 13 [Posted by: AvonX  | Date: 10/23/12 09:55:02 AM]
Reply
 
beenthere demonstrates time and time again that he knows better than you do, the only thing you and jmlxg ever post is extremely unprofessional diarrhea, obviously for the sake of posting controversial diarrhea to stir up the crowd.
11 9 [Posted by: mmstick  | Date: 10/23/12 02:23:49 PM]
Reply
 
show the post
3 13 [Posted by: AvonX  | Date: 10/23/12 03:28:14 PM]
Reply
 
Apparently you take too much medication, you and jmlxg are always bouncing all over the walls in these comments sections like your lives depend on it.
9 6 [Posted by: mmstick  | Date: 10/23/12 09:41:43 PM]
Reply
 
show the post
2 10 [Posted by: 123  | Date: 10/24/12 08:15:15 PM]
Reply
 
For $199 it's the best price/performance for multi-threaded apps like video encoding, rendering, etc. It's not a gamer's CPU but it offers similar performance in multi-threaded apps to i7 2600K for $199.
8 7 [Posted by: BestJinjo  | Date: 10/25/12 01:26:04 PM]
Reply
 
Yup that's true but at what price(?) and how late(?)
Power consumption if you really use this in any above mentioned tasks, and run it fully multithreaded you will soon say yourself that you'd pay much les electricity bill running i7-2600K vs FX-8350. And these aren't even contemporary parts as Sandy Bridge CPUs are launched SEVEN QUARTERS ahead of Vishera. So if you'd already buy i7 youd pay off yourself just on electricity bill if you run old 1100T (most efficient CPU until this one) or even small cluster ow power savvy x2 Athlons.

YUp. This is a good part. But i'm wondering where all of those highly acclaimed ""power optimizations"" of new Bulldozers vs. old K10.5 disappear. And those were 45nm parts for god sake this 32nm should wipe a floor with them considering ""power optimizations"" and more advanced node itself. So this is the reason for another 140W disappointment.
1 0 [Posted by: OmegaHuman  | Date: 11/13/12 07:49:35 AM]
Reply
 
While Intel CPUs may OC as well, they typically cost hundreds more than a comparable AMD APU/CPU.


LOL, you must be joking. Intel doesn't cost 100 dollar than comparable AMD cpu.

i5 3570 is very competitive, if not overall better than FX-8350. FX-8350 might have an advantage in heavily multi-threaded workloads, but it loses significantly in the other types of workloads

i7 3770 beats FX-8350 even in the majority of highly mutli-threaded benchmarks. In single/lightly threaded workloads, it completely destroy FX-8350

Yea i7 3770 might cost $100 more, but FX-8350 can't compete with it (except in very few cases)


5 2 [Posted by: maroon1  | Date: 10/23/12 03:47:09 PM]
Reply
 
Since you brought The Price matter, I think FX-8350+any Mainstream 9X main cost (only) $30-$50 less than i5 3570K+any mainstream Z77 Mainboard. But to gain an equal performance u'll need to OC Vishera about 500-800Mhz (4.5Ghz) more than IB (3.8Ghz). Now please Sum how much u'll pay for each power consumption monthly and annual. Which one make you poorer??

And about "The real story is that there is absolutely NO software that AMD processors can't run just fine" matter. If you don't need it now, why make it? I think when the time has come, Intel will ready for it. And as usual, AMD will take more advance technology which no application can match up (again) yet.

But I very thanks to you. 'coz someone like you (who buy AMD's high end) makes AMD still stay in competition.
4 2 [Posted by: jpunk  | Date: 10/23/12 07:54:03 PM]
Reply
2. 
Dear site Admins at Xbit, how complicated would it be for every user to have an ignore list for the comments section? I really don't want to read jmlxg's hate posts anymore. They don't add anything of value to, um, anything.
13 11 [Posted by: Nightgawk  | Date: 10/22/12 11:14:22 PM]
Reply
3. 
This fan boyism is so immature (referring to jmlxg). What people dont realize is that if AMD goes down, so does the drive for innovation, faster and better priced products.

Its a good sign that AMD is offering 8 core alternatives to the i5 and pricing them accordingly. But they still need to do better to show dominance in the mid range area. Esp gaming.
11 10 [Posted by: mecow  | Date: 10/23/12 12:18:40 AM]
Reply
- collapse thread

 
show the post
5 10 [Posted by: veli05  | Date: 10/23/12 06:37:57 AM]
Reply
 
show the post
2 7 [Posted by: jpunk  | Date: 10/23/12 08:08:33 PM]
Reply
 
There is nothing wrong with buying an Intel CPU. I have one. It doesn't mean we cannot see some advantages that FX-8350 brings for certain users at its $199 price level. No, it's not a more well-rounded CPU than an overclocked i5 3570K is for us gamers, but for heavy multi-taskers, it's a better choice for many tasks.

Also, if you noticed the comments from the AMD-haters here, they can't even admit that HD7000 series is offering more price/performance, more overall single-GPU performance and more value via game bundles.

Most of us don't expect AMD to beat Intel in CPU race but we at least expect objectivity in this sub-forum and certain posters are blatantly trolling and crapping in every AMD thread.
6 8 [Posted by: BestJinjo  | Date: 10/25/12 01:35:17 PM]
Reply
 
"What people dont realize is that if AMD goes down, so does the drive for innovation, faster and better priced products."

That's obvious to anyone who has half a brain. The AMD-haters that have polluted Xbitlabs' subforum are trolls, delusional fanboys or IQ < 95. The same type of people would discuss politics without understand how economics, foreign policy or budgets work. You can't reason with people like that. AMD could release a CPU 2x faster than i7 3770K and GPU 2x faster than GTX780 and they both could cost half of their competitors and these fanboy trolls will still find a way to hate on AMD. That's how they are. That's why you cannot reason with them.

All of them should be permanently banned as they cannot objectively discuss both positives and negatives of different products, and neither contribute on the technical side when it comes to NV, AMD and Intel products.

The science of fanboyism
http://techreport.com/blo.../the-science-of-fanboyism
7 7 [Posted by: BestJinjo  | Date: 10/25/12 01:28:08 PM]
Reply
4. 
AMD deliverd on its promise that that piledriver was going to be 15 to 20% better then bulldozer and it set out to do just that. I wasn't expecting piledriver to be an intel killer like most people, but it did what AMD set it out to do and that's to fix a lot of the problems that pleged bulldozer and the performance increase in many benchmarks shown that it did just that. Overall i'm happy to see progress being made, it's a step in the right direction for AMD this time around unlike Bulldozer where it actually went backwards in performance in many benchmarks against the old deneb AMD cpu's.
13 11 [Posted by: SteelCity1981  | Date: 10/23/12 01:28:00 AM]
Reply
- collapse thread

 
show the post
2 11 [Posted by: AvonX  | Date: 10/23/12 08:06:45 AM]
Reply
 
who's talking about overclocking? the stock version did diliver promies in gained performance over the bulldozer model it replaced.
4 6 [Posted by: SteelCity1981  | Date: 10/23/12 12:03:55 PM]
Reply
5. 
>Cachemem test from the Aida64 2.60 suite shows a significant increase in the L2 cache memory bandwidth.

Nope, it's the other way around. From the images you posted, L2 bandwidth is incredibly low.
Something is wrong.
5 7 [Posted by: Marburg U  | Date: 10/23/12 03:11:05 AM]
Reply
- collapse thread

 
I love how i get pommeled by negative votes for just evidencing that two images blatantly contradict the text.
3 3 [Posted by: Marburg U  | Date: 10/23/12 09:21:37 AM]
Reply
6. 
show the post
8 11 [Posted by: kvarta  | Date: 10/23/12 03:33:58 AM]
Reply
7. 
Well, it's a year later, and we all expected these kind of improvements. But for me personally, the FX series is sort of irrelevant, as I only use my computer where this architecture falls short. (gaming, plus other simple stuff where any extensive multithreading isn't that useful). Upgrading to something like an FX-4300 would also be pointless as it is slower than my current Nehalem i7. I'll continue to buy AMD GPUs and maybe get a Trinity CPU for my next HTPC. (going to be a mini-ITX affair, so I want decent 3D performance as well). But for my main rig... I'll see what Haswell has to offer first.
4 5 [Posted by: Joe Public  | Date: 10/23/12 05:12:56 AM]
Reply
- collapse thread

 
show the post
4 13 [Posted by: TAViX  | Date: 10/23/12 08:00:24 AM]
Reply
 
FX-8350 is about as fast as a Core i7-875K for games:
http://techreport.com/rev...8350-processor-reviewed/6

You are saying Q9650 is as fast as an i7 for games?

The average performance for the price falls between i5-3570K and i7-2600K
http://techreport.com/rev...350-processor-reviewed/14

Not everyone just plays games. If you do, of course Intel is faster. For everything else, FX-8350 offers decent value for a lot of consumers at $199 price level.
5 7 [Posted by: BestJinjo  | Date: 10/25/12 01:39:19 PM]
Reply
8. 
show the post
8 11 [Posted by: medo  | Date: 10/23/12 06:58:30 AM]
Reply
- collapse thread

 
AMD is back in point of view. sadly the FX-6300 is not listed in this benchmark, however looking at other sites benchmark it looks pretty sweet to me, as budget king, which performs between the i3 and i5 most of the time, which is great and can ever surpass the i5 in multi-threaded loads


Here is a review for FX-6300
http://www.techspot.com/r.../586-amd-fx-8350-fx-6300/

I agree that FX-6300 is good CPU for money.

However, i5 3470 beats FX-6300 in every multi-threaded benchmark.

You need at least FX-8xxx series to surpass i5 in in multi-threaded loads.

In gaming benchmarks i3 3220 beats FX-6300

4 3 [Posted by: maroon1  | Date: 10/23/12 03:15:20 PM]
Reply
 
"You need at least FX-8xxx series to surpass i5 in in multi-threaded loads."

Why in the world are you comparing $185 i5-3470 against a $132 FX-6300?

Based on price:
FX-8320 $169 vs. $185 i5-3470
FX-8350 $199 vs. $225 i5-3570K

Average performance of FX-8350 is between i5-3570K and i7-2600K:
http://techreport.com/rev...350-processor-reviewed/14

FX-8320 for $169 will also land between i5-3470 and i5-3570K in performance.

The main downsides are gaming performance, and power consumption. Stock overall performance out of the box favors FX-8300 CPUs for non-gamers based on these prices.
6 8 [Posted by: BestJinjo  | Date: 10/25/12 01:43:17 PM]
Reply
 
Gaming performance or power consumption isn't a downside. I haven't found a single game that was hurt by my FX-8120, but I did found video recording was improved a great deal, as well the overall responsiveness of the gameplay is better with an AMD machine, even if it has lower high framerates. Framerates != Responsiveness. Power consumption isn't really a problem, it consumes less than previous AMD processors with each generation, and if you really worried about power consumption you would underclock/volt it to save power. My FX-8120 runs two HD 7950s in crossfire just fine, thank you very much.
6 1 [Posted by: mmstick  | Date: 10/28/12 01:27:50 PM]
Reply
9. 
I started reading and after a few sentences I thought, wow this is better written and more professional than the typical xbitlabs article already. So I scrolled back up and sure enough, the author was not Anton Shilov. Well done, Ilya Gavrichenkov.
6 3 [Posted by: mikato  | Date: 10/23/12 09:58:30 AM]
Reply
- collapse thread

 
Anton writes the daily news short articles, Ilya writes mostly long articles, primarily on cpu's. There are around 10 writers at Xbit, Oleg and Ilya are probably the best . Anton's english is not perfect, but generally any errors get fixed fast.
3 2 [Posted by: cashkennedy  | Date: 10/23/12 06:56:38 PM]
Reply
10. 
There where comparison of max overclock sandy vs buldozer 4.6ghz vs. 4.6ghz, it would be nice to see now ivy vs piledriver on their max 4.4ghz vs 5ghz.
3 5 [Posted by: kingpin  | Date: 10/23/12 10:10:47 AM]
Reply
11. 
according to LR, AMD FX processors are as good as intel at gaming

and certainly they are better at multitasking, which isn't mesured by benchmarks

EDIT: BTW AMD scored a great victory, you don't have to beat you competition to be competitive, you just have to trade blows with them when talking about value, AMD completely destroys intel, while it loses at power, and matches intel at performance, so yes, For me , vishera destroys IVB, even if it doesn't do so at performance benchmarks (it only matches IVB) it gives me a much better value, it's also better at multitasking which is important to me
4 5 [Posted by: madooo12  | Date: 10/23/12 01:00:26 PM]
Reply
- collapse thread

 
According to techreport review, intel quad core performed better at multi-tasking
http://techreport.com/rev...8350-processor-reviewed/9
5 3 [Posted by: maroon1  | Date: 10/23/12 03:28:24 PM]
Reply
 
show the post
1 9 [Posted by: 123  | Date: 10/24/12 08:07:36 PM]
Reply
 
Says who? The CPU professor 123? Rofl
5 2 [Posted by: mmstick  | Date: 11/01/12 06:38:00 AM]
Reply
12. 
I think it would be helpful to actually show the cost of the extra power use, in a year for instance.

Like occasional gamers, or the 10% of computers that actually work hard more than a few minutes in week, my cpu will indeed be maxed out more more than a few minutes now and then. In my case doing chess position analysis, multi-core. I do that about 1-5 hours in a week.

So, just how much would it cost in power use for the 8350 vs a more power efficient intel chip?

A KwH (Kilowatt Hour of electricity) costs about 16 cents here.

So the math is quite easy. Rounding everything to very rough numbers: 90 watts more power/1000 (Kilowatts) * 5 hr/week * 52 weeks * 16 cents/KwH = very roughly $4/year.

It would cost me about $4/year in extra electric power bill cost vs a more efficient system.

But since I have an AM3+ system already, this is a drop-in upgrade.

For me, this will be a very easy cost choice.

7 4 [Posted by: halbhh  | Date: 10/23/12 01:13:07 PM]
Reply
- collapse thread

 
show the post
3 10 [Posted by: AvonX  | Date: 10/23/12 01:35:41 PM]
Reply
 
I am correct for my own costs, here where I live. It is easy to do this math.

On our electric bills, the cost per KwH is listed clearly.

Easy and clear, here.

BUT, I explained my OWN cost. Not yours!

I am always curious. What are you running, how many hours a week is your rig at idle, and how many hours at 100% load, and what is your cost per KwH, and total yearly cost difference for you, when 100% load uses 90 more watts?

I'm always curious.

6 5 [Posted by: halbhh  | Date: 10/23/12 01:48:13 PM]
Reply
 
show the post
3 10 [Posted by: AvonX  | Date: 10/23/12 02:10:48 PM]
Reply
 
How about you stop finding excuses for Intel? You completely ignored his comment, and it is true, as many others have discovered on the recent FX-8350 thread over at Overclockers, it would take 12 years before our power bills would equate the difference between an AMD and Intel processor, and in 2012, those of us who are professionals and enthusiasts in the field of IT already run plenty of highly multithreaded software. Considering AMD wins out in highly multithreaded software that we all use, it is a no brainer not to get AMD at the low price it is, businesses may even employ these in their own servers as they stomp over Xeon's.
7 5 [Posted by: mmstick  | Date: 10/23/12 02:34:33 PM]
Reply
 
show the post
2 12 [Posted by: AvonX  | Date: 10/23/12 02:39:19 PM]
Reply
 
Worst comeback ever, we can mark that up as yet another loss for AvonX, he couldn't even write a coherent reply to save his ass LOL. No one cares about your shopping list.
5 6 [Posted by: mmstick  | Date: 10/23/12 02:46:19 PM]
Reply
 
show the post
3 12 [Posted by: AvonX  | Date: 10/23/12 02:49:45 PM]
Reply
 
I don't need to do anything but sit here and look at your rating, all your thumbs downs, and laugh.
5 6 [Posted by: mmstick  | Date: 10/23/12 09:44:04 PM]
Reply
 
show the post
4 8 [Posted by: mmstick  | Date: 10/23/12 02:37:15 PM]
Reply
 
I live in Philippines 90 watts here is almost 10 dollars per month per Processor. That why we consider the most Well performed Processor and Cost Efficient in Ownership
4 1 [Posted by: xentar  | Date: 10/23/12 10:16:21 PM]
Reply
 
24/7? What are you running on your system? If you are very short on $, you aren't running your PC turned on 24/7 because electricity costs matter that much to you. Use common sense.
6 7 [Posted by: BestJinjo  | Date: 10/25/12 01:46:45 PM]
Reply
 
Several people at overclockers discovered a similar estimate, they found that the power difference between Intel and AMD would not equate saving money,that it would take 12 years before the power bill caused by the CPU would equal the price of the Intel equivalent, not counting the cost of power for the Intel CPU during that time.
6 8 [Posted by: mmstick  | Date: 10/23/12 02:39:38 PM]
Reply
13. 
Xbit, do something about these trolls...

This place is literally, an anarchic warzone.
9 6 [Posted by: mmstick  | Date: 10/23/12 02:18:41 PM]
Reply
14. 
"First, the performance of individual FX-8350 cores is significantly lower than that of the cores in contemporary Intel processors."


First, yes, the difference is obvious, you might use the word significant, but they are still in the same ballpark and what you write implies the opposite.

"Second, when more than four cores of the FX-8350 processor are utilized, the performance gain from adding new cores to the equation is lower because of the “paired” design."


Second, here we have a major vision problem. Your own diagram clearly shows AMD keeps scaling almost linearly over 4 threads, while Intel's scaling efficiency drops dramatically and as a result the performance at 8 threads is pretty similar. This should tell you the advantage of the CMT approach over the HT, but I understand it's hard to see it through blue glasses.

I don't bother myself to read the rest of your review, you emphasised more then enough times there's is no improvement on this page, I assume you found ways to back your hypotesis.
2 3 [Posted by: Martian  | Date: 10/23/12 02:28:06 PM]
Reply
15. 
Look at the market segment these are aimed at. Not the high end gamers who don't need anything better than a 939 chip or a socket 775 as no game needs the computing power but graphic power.
As the article says these are aimed at mid range work stations.
Equipped with a high end graphic card for work!
The toy boys are such a small but shrill market segment.
When there are programs which can use the power of high end computers.
No O/S's other than Linux can use these. Windows seems to be abandoning the desktops x86 field. Last years O/S for M/S was down by 30%. So if they were down this much it means Intel and Amd were down the same %. Even if Intel picked up sales from the fruity machines they were a much larger number of sales down by volume than AMD both Chip manufactures have had to rethink their market segments. AMD have left the top end single threaded performance segment which seems to be the segment which most benchmarks are testing for., the multicored designs are becoming far more important. If AMD are pitching this against the i5's which are really an 8 core if one uses their reckoning.
4 4 [Posted by: tedstoy  | Date: 10/24/12 03:27:19 AM]
Reply
16. 
to my little knowledge of CPU DESIGN it looks like AMD is on the selling of APU architecture and BIG features just as what it did on fx8150 but it boiled down to little improvement in CPU performance. those arc and features just hype up the user communities enough to w8 for the release but at the final release time it looks like a BIG let down by failing to compete. that is a lot of cores and high 4 GHz frequency going against half the cores at much lower speed.
2 4 [Posted by: idonotknow  | Date: 10/24/12 10:29:51 AM]
Reply
- collapse thread

 
show the post
2 10 [Posted by: 123  | Date: 10/24/12 08:05:29 PM]
Reply
 
Spread spreading misinformation like the other posters here:

Performance Rating in Desktop Applications (not server applications):

FX-8350 = 100%
i5 3570K = 102%

CineBench R11.5
WinRar 4.11 & 4.20
dBpoweramp R14.2
iTunes 10.5
MainConcept H.264/AVC Pro
Paint.Net
POV-Ray
PCMark7
TrueCrypt 7.1a
X26 HD Benchmark 4.0 & 5.0
http://www.computerbase.d...st-amd-fx-8350-vishera/5/
7 8 [Posted by: BestJinjo  | Date: 10/25/12 01:50:48 PM]
Reply
 
There is one beef I have with all these performance averages. They always factor in both the single and multi-threaded results from a multi-threaded programs like Cinebench and PovRay. These programs are optimized for multi-threaded and will be used as such. Thus they should be factored in as such. Including the single thread results in equal measures is ridiculous!

This cancels out some benchmarks where multi-core processors are on a home ground in favor of more single thread oriented CPUs. The same should be said about H.264 and X264 encoding benchmarks where the 1st and 2nd pass are weighted equally despite the 2nd pass having much more impact due to the fact that it takes much longer time than the 1st pass. F.ex if you have 10.000 frames of video it will take FX-8350 around 170s to complete Pass 1 but 660s for pass 2 for a total of 830s according to Xbitlabs results. i5-3570 will take around 180s for pass 1 and 830s for pass 2 for a total of 1010s.

If we weigh both parts equally the FX-8350 is 5,5% faster in pass 1 and 20,5% in pass 2 or 13% for both. If we however correct in terms of real world application the difference for both passes taken for the same video will turn out to be around 18%. This is statistically significant difference and in many cases it's much greater.

For example if we take results from Hardware Info: http://uk.hardware.info/r...eg-to-x264-video-encoding

Equal weight: 5,8% in favor of FX-8350
Real weight: 13,4% in favor of FX-8350

Add to this SysMark and PCMark which are arbitrarily weighted and these weights not being made known to us but seem to favor Intel disproportionately. As a result we have an average that is a wet dream of any Intel marketing person but does a disservice to consumers as it relaxes the pressure on Intel and strips AMD of it's advantages.

I am not knocking on Intel, they do great processors. But reviewers need to make an effort in being more evenhanded. I get the feeling they are still angry about their over-hyped expectations being Bulldozed over by a power hungry beast that didn't perform to expectation but still was a solid 10% improvement on average over X6 1100T despite losing in few titles and benchmarks to it's older brother.

It was a radical change and did not meet the unrealistic expectations we set for AMD. Many people fail to grasp just how much of an engineering brilliance the Intel Core architecture is. Especially the Sandy Bridge which made great strides in terms of power consumption. Compare the Bulldozer to the 1st generation of 32nm Core i7 965 and they trade blows at a similar power consumption level. The Sandy Bridge completely changed that and is probably the best revamp of any processor architecture ever made. Expecting AMD to copy that with it's limited resources is a delusional ignorance of the highest degree.

The fact that they remain within a spitting distance of Intel (about 15% below i7-3770) is incredible. I know few here remember what happened to the other competitors of Intel, but consider the last Cyrix processor "Samuel" with maybe 2/3 of the performance of the Duron and Celeron budget CPUs of AMD and Intel. That is a truly big difference. In reality 15% is almost not recognizable for a user.

Currently with the release of FX-8350 AMD is closing in on Intel in terms of Performance. I was personally hoping for better luck in reducing power consumption but all in all it's a nice step forward. I will be getting one in my own platform and playing with it soon and I am looking forward to it. I am also hoping for AMD to score big with Steamroller next year as it will address the two places where this architecture suffers the most at the moment, i.e. power efficiency and single thread execution. Depending on how well Intel deliver on Haswell it could be an interesting fight.
6 2 [Posted by: wICE_man  | Date: 10/30/12 08:43:43 AM]
Reply
17. 
What a surprise to find the lowly 2nd level desktop support trolls spewing their usual I know all and you know nothing AMD is crap diatribe.
Please get a life.
We all want to talk about the hardware. Not your opinion of the brand of hardware. We dont want to read your constant pathetic tit for tat remarks. You dont score any points here. Why open your mouth and confirm your stupidity and lack of any meaningful life away from your computer to the world. Keep it shut and keep us guessing.
My appologies to everyone else.

This was a well written and informative article. Thanks X-Bit!
6 3 [Posted by: oldengineer  | Date: 10/25/12 07:44:30 PM]
Reply
18. 
There is one beef I have with all these performance averages. They always factor in both the single and multi-threaded results from a multi-threaded programs like Cinebench and PovRay. These programs are optimized for multi-threaded and will be used as such. Thus they should be factored in as such. Including the single thread results in equal measures is ridiculous!

This cancels out some benchmarks where multi-core processors are on a home ground in favor of more single thread oriented CPUs. The same should be said about H.264 and X264 encoding benchmarks where the 1st and 2nd pass are weighted equally despite the 2nd pass having much more impact due to the fact that it takes much longer time than the 1st pass. F.ex if you have 10.000 frames of video it will take FX-8350 around 170s to complete Pass 1 but 660s for pass 2 for a total of 830s according to Xbitlabs results. i5-3570 will take around 180s for pass 1 and 830s for pass 2 for a total of 1010s.

If we weigh both parts equally the FX-8350 is 5,5% faster in pass 1 and 20,5% in pass 2 or 13% for both. If we however correct in terms of real world application the difference for both passes taken for the same video will turn out to be around 18%. This is statistically significant difference and in many cases it's much greater.

For example if we take results from Hardware Info: http://uk.hardware.info/r...eg-to-x264-video-encoding

Equal weight: 5,8% in favor of FX-8350
Real weight: 13,4% in favor of FX-8350

Add to this SysMark and PCMark which are arbitrarily weighted and these weights not being made known to us but seem to favor Intel disproportionately. As a result we have an average that is a wet dream of any Intel marketing person but does a disservice to consumers as it relaxes the pressure on Intel and strips AMD of it's advantages.

I am not knocking on Intel, they do great processors. But reviewers need to make an effort in being more evenhanded. I get the feeling they are still angry about their over-hyped expectations being Bulldozed over by a power hungry beast that didn't perform to expectation but still was a solid 10% improvement on average over X6 1100T despite losing in few titles and benchmarks to it's older brother.

It was a radical change and did not meet the unrealistic expectations we set for AMD. Many people fail to grasp just how much of an engineering brilliance the Intel Core architecture is. Especially the Sandy Bridge which made great strides in terms of power consumption. Compare the Bulldozer to the 1st generation of 32nm Core i7 965 and they trade blows at a similar power consumption level. The Sandy Bridge completely changed that and is probably the best revamp of any processor architecture ever made. Expecting AMD to copy that with it's limited resources is a delusional ignorance of the highest degree.

The fact that they remain within a spitting distance of Intel (about 15% below i7-3770) is incredible. I know few here remember what happened to the other competitors of Intel, but consider the last Cyrix processor "Samuel" with maybe 2/3 of the performance of the Duron and Celeron budget CPUs of AMD and Intel. That is a truly big difference. In reality 15% is almost not recognizable for a user.

Currently with the release of FX-8350 AMD is closing in on Intel in terms of Performance. I was personally hoping for better luck in reducing power consumption but all in all it's a nice step forward. I will be getting one in my own platform and playing with it soon and I am looking forward to it. I am also hoping for AMD to score big with Steamroller next year as it will address the two places where this architecture suffers the most at the moment, i.e. power efficiency and single thread execution. Depending on how well Intel deliver on Haswell it could be an interesting fight.
4 0 [Posted by: wICE_man  | Date: 10/30/12 10:12:30 AM]
Reply
19. 
hello i am condenser about a thing, i am building a computer and everything should work fine but i have an AMD Bulldozer
FX-4300 Zambezi CPU and i don't know if this CPU will work with my computer components, if you know could you pleas reply here? my computer specs will be this:

ASUS M5A97
AMD® Bulldozer FX-4300 Zambezi (3.80GHz) OR the FX-8350.
AMD® Radeon HD 7750
500GB 7200RPM Seagate Barracuda
RAM 8GB DDR3 1600MHz
Microsoft Windows 8 (64-Bit Edition)

still don't know if i should take windows 8 or windows 7, if you would know witch is best (for gaming the latest games) you could pleas say it
0 0 [Posted by: therobin9810  | Date: 03/09/13 07:23:13 AM]
Reply
20. 
hello i am condenser about a thing, i am building a computer and everything should work fine but i have an AMD Bulldozer
FX-4300 Zambezi CPU and i don't know if this CPU will work with my computer components, if you know could you pleas reply here? my computer specs will be this:

ASUS M5A97
AMD® Bulldozer FX-4300 Zambezi (3.80GHz) OR the FX-8350.
AMD® Radeon HD 7750
500GB 7200RPM Seagate Barracuda
RAM 8GB DDR3 1600MHz
Microsoft Windows 8 (64-Bit Edition)

still don't know if i should take windows 8 or windows 7, if you would know witch is best (for gaming the latest games) you could pleas say it
0 0 [Posted by: therobin9810  | Date: 03/09/13 07:23:43 AM]
Reply

[1-20 | 21-21]

Back to the Article

Add your Comment


Our Sponsors

Crucial.com Western Digital G.Skill