AMD Phenom-II X6-1075T CPU HDT75TFBGRBOX E-mail
Reviews - Featured Reviews: Processors
Written by David Ramsey   
Tuesday, 21 September 2010
Table of Contents: Page Index
Features and Specifications
Testing and Results
CINEBENCH R11.5 Benchmarks
SPECviewperf 11 Tests
PCMark Vantage Tests
Everest Ultimate Tests
Video Gaming Test
Video Transcoding Test
Phenom II X6 1075T Overclocking
AMD X6-1075T Final Thoughts
HDT75TFBGRBOX Conclusion

Everest Ultimate Tests

Lavalys EVEREST Ultimate Edition is an industry leading system diagnostics and benchmarking solution for enthusiasts PC users, based on the award-winning EVEREST Technology. During system optimizations and tweaking it provides essential system and overclock information, advanced hardware monitoring and diagnostics capabilities to check the effects of the applied settings. CPU, FPU and memory benchmarks are available to measure the actual system performance and compare it to previous states or other systems. Furthermore, complete software, operating system and security information makes EVEREST Ultimate Edition a comprehensive system diagnostics tool that offers a total of 100 pages of information about your PC.

All of the benchmarks used in this test— Queen, Photoworxx, ZLib, and AES— rely on basic x86 instructions, and consume very low system memory while also being aware of Hyper-Threading, multi-processors, and multi-core processors. Of all the tests in this review, Everest is the one that best isolates the processor's performance from the rest of the system. While this is useful in that it more directly compares processor performance, readers should remember that virtually no "real world" programs will mirror these results.


Queen and Photoworxx tests are synthetic benchmarks that operate the function many times and over-exaggerate by several magnitudeswhat the real-world performance would be like. The Queen benchmark focuses on the branch prediction capabilities and misprediction penalties of the CPU. It does this by finding possible solutions to the classic queen problem on a chessboard. At the same clock speed theoretically the processor with the shorter pipeline and smaller misprediction penalties will attain higher benchmark scores.

Here we see the $164 AMD 965 Black Edition handily beating the $195 Intel Core i5-750, while the $245 AMD 1075T and $299 AMD 1090T run pretty evenly with Intel's $280 i7-860 and $285 i7-930. The overclocked 1075T beats everything except the i7-980X, which runs away from the pack with results 35% better than the next closest competitor.

Like the Queen benchmark, the Photoworxx tests for penalties against pipeline architecture. The synthetic Photoworxx benchmark stresses the integer arithmetic and multiplication execution units of the CPU and also the memory subsystem. Due to the fact that this test performs high memory read/write traffic, it cannot effectively scale in situations where more than two processing threads are used. The EVEREST Photoworxx benchmark performs the following tasks on a very large RGB image:

  • Fill
  • Flip
  • Rotate90R (rotate 90 degrees CW)
  • Rotate90L (rotate 90 degrees CCW)
  • Random (fill the image with random colored pixels)
  • RGB2BW (color to black & white conversion)
  • Difference
  • Crop

Here, we see some interesting results: the lower-end processors tend to do as well as or better than most of their higher-end brethren. This is especially obvious in the AMD camp where the 965 Black Edition performs better than the overclocked 1075T. The worst performance is turned in by the Intel i7-860, and the best, as usual, by the 980X. The reason for these seemingly odd results is that the higher end processors tend to have longer pipelines and more advanced out-of-order execution and branch prediction capabilities. These features can result in substantial performance improvements much of the time, but the longer pipelines come with a penalty: speculative execution of code initiated by a branch predictor is all wasted if the branch goes the other way, so not only did the processor waste thousands or millions of clock cycles executing code it didn't need to, it must also re-load its pipeline with the instructions it was supposed to execute. Developers using Intel compilers should read the several white papers Intel has written about how to structure code to minimize this problem.


The Zip Library test measures combined CPU and memory subsystem performance through the public ZLib compression library. ZLib is designed as a free lossless data compression library for use on virtually any computer hardware and operating system. The ZLib data format is itself portable across platforms and has a footprint independent of input data that can be reduced at some cost in compression. The AES integer benchmark measures CPU performance using AES data encryption. It utilizes Vincent Rijmen, Antoon Bosselaers and Paulo Barreto's public domain C code in ECB mode and consumes 48 MB of memory. Both of these tests are much more applicable to the "real world" than the previous tests.

The results of the Zip compression test scale almost linearly with processor clock speed on the quad-core Intel side, but there's some threading going on as can be seen with the Core i7-980X results, where two extra cores and and extra 530MHz or so virtually double the performance of the 2.8GHz it-860 and i7-930. Extra cores help on the AMD side, too, with the stock-clocked 3.0GHz 1075T handily outperforming the 3.4GHz quad-core 965 Black Edition.

The AES encryption test is utterly dominated by the Core i7-980X, whose performance is 6.7x better than its closest competitor. The reason is Intel's Advanced Encryption Standard New Instructions (AES-NI), which dramatically accelerate AES code. AES-NI aside, the AMD processors uniformly perform better than the Intel processors without this feature.



# RE: AMD Phenom-II X6-1075T CPU HDT75TFBK6DGRmihai 2010-09-21 03:11
good job !
i wold like to see some temperatures with 1075t OC
Report Comment
# RE: RE: AMD Phenom-II X6-1075T CPU HDT75TFBK6DGRDavid Ramsey 2010-09-21 07:04
Temperatures, even under overclocked stress testing, were pretty low, never exceeding 56 degrees. Well, low in contrast to Intel processors...the max temperature of the 1075T is 62 degrees, I believe, so this overclock would require good cooling in the hot summer months.
Report Comment
# Slight correction needed here...aussiebear 2010-09-21 03:15
"...(your new Sandy Bridge Socket 1156 processor won't work in your existing Socket 1156 motherboard, sorry!)..."

=> Slight typo...The mainstream desktop version of Sandy Bridge uses LGA1155. It has a different electrical layout to the current LGA1156. They aren't compatible with each other...I checked with an Engineering Sample.
Report Comment
# 2010-09-21 03:27
"....or you want to run an NVIDIA SLI setup (which, due to some weird polittical wrangling between AMD and NVIDIA, you cannot now and probably never will be able to do),...."

I have an ASUS board in my Wish List at NewEgg that supports AMD Hex-Cores and SLI together. I had planned on using the GTX460's in it and 1090T Hex-Core once I have the cash saved.

Report Comment
# RE: 2010-09-21 04:17
I'd like to add that this is a really great review.
Report Comment
# RE: Ramsey 2010-09-21 07:06
You're right: motherboards based on NVIDIA chipsets will (obviously!) handle SLI. I had one of the classic ASUS A8N SLI Deluxe motherboards myself some years ago, but didn't know there were any similar AM3 boards available.
Report Comment
# RE: RE: 2010-09-21 07:12
Also, the PCI-E connectors are both X16 speed. Many SLI and Crossfire boards don't have full X16 speeds enabled when more than one slot is occupied. They split the available bandwidth.
Report Comment
# AhhPsy4computers 2010-09-26 14:49
Nothing to do with the fact AMD owns ATI by any chance??
Report Comment
# RE: AMD Phenom-II X6-1075T CPU HDT75TFBK6DGRRobert17 2010-09-21 03:54
Well done David. I've owned/operated/OC'd Intel, Cyrix (stop laughing), and AMD chips over the years. You nailed down all my thoughts with data sheets. I'm not known as a fanboi of anything. But I concluded years ago that AMD was making products that would be fast enough, would survive upgrades on the same MB for at least a generation or two, and all things taken together allow more budget for other component upgrades more regularly. (yes, my budget for Mr.&Mrs. Frankenclone and their kids only comes after beans, bills, and keeping Mama happy)

Is Intel good? You bethcha skippy. Could they be in any rig I build? I'd enjoy that. But my last few MB/CPUs have been AMD due to the "bang for the buck" factor. Looks like my next upgrade in that category will be also. Thanks for playing Intel. We have some nice parting gifts for you. Maybe down the road....
Report Comment
# RePSM 2010-09-21 15:53
Another very 'true to the facts' review by Benchmark. But have a few doubts. First, "Cannot support an NVIDIA SLI system "- I'm not sure this a con for a cpu. Might be wrong here but if something to be blamed for not supporting SLI, it's the 890GX/FX chipset in this case. And it's not a platform review. Secondly, any clue how the mighty i7 980x is beaten by 930 in UGS Visualization mockup? From the things it looks like TCVIS is memory bandwidth intensive, even then it doesn't make sence. finaly "if you're not doing a lot of music or video encoding" may seem to fly-by viewers as if 965 BE or i7 750 were incompetent. I've a OCed 955 BE and do a lot of transcoding for professional purpose and haven't felt the urge to upgrade to hexas yet. The only reason I say this because there are many people who think downloading some videos from youtube and converting'em to .avi is a 'lot' of encoding :D Thanks for this fine article again.
Report Comment
# Pros and ConsOlin Coles 2010-09-21 16:38
I don't always agree with the conclusions our writers give a product, but without their unique perspective this website would be quite monotone. As I warn in the conclusion of my article, take each conclusion into consideration of your own criteria for grading any particular product. What we like and dislike may not apply to you.
Report Comment
# RE: ReDavid Ramsey 2010-09-21 20:57
As another respondent has pointed out, there are still NVIDIA based AM3 solutions that will support SLI with this proc, so that's a good point (that's already been made).

"any clue how the mighty i7 980x is beaten by 930 in UGS Visualization mockup?"

Nope. I runs the tests, I reports the results, I speculate on the reasons when I can. This one's a mystery.

Yep, you can do a lot of transcoding on an overclocked 4-core proc; but more cores are still better. It's arguable whether the extra performance is worth the money; I suppose it would depend more on whether one was in a hobby or production environment...
Report Comment
# RE: RE: RePSM 2010-09-22 14:31
David, thanks for your reply. And apologies for reiterating that SLI point. And yes I suppose two extar cores ain't going to harm. And the pricing by AMD makes them more attractive. Just hope that developers make some more softwares which could scale on those. That aside these procs are just good enough to force Intel sale i7 950 @ $300. Regards.
Report Comment
# ConsultantMRFS 2010-09-21 18:56
Is "1070T" a typo above?

I thought this was a review of the

Please clarify. Thanks.

Report Comment
# RE: ConsultantDavid Ramsey 2010-09-21 19:59
Yes, thanks, "1070T" is definitely a brain fart on my end. I'll correct it.
Report Comment
# RE: AMD Phenom-II X6-1075T CPU HDT75TFBK6DGRMarkus 2010-09-22 23:35
Breathtaking that you guys fail to specify the processor's TDP anywhere in the entire article. So much blabber about it energy efficiency, but without mentioning its TDP. Bl**dy dimwits.
Report Comment
# RE: RE: AMD Phenom-II X6-1075T CPU HDT75TFBK6DGRRealNeil 2010-09-23 04:56
I Googled your question and got:

Max TDP: 125 Watts
Report Comment
# RE: RE: AMD Phenom-II X6-1075T CPU HDT75TFBK6DGRDavid Ramsey 2010-09-23 08:43
Check the "Pros" section of the last page of the article, where I mention the "Low 125 watt TDP".
Report Comment
# RE: AMD Phenom-II X6-1075T CPU HDT75TFBK6DGRPSM 2010-09-23 13:15
@ Markus: 1075T is part of a refreshment from AMD on it's Thuban core architecture. Previous 1055T and 1090T had 125W and there've been no die shrink or tweaks so these new proc also has the same TDP. Use your common sense before calling someone dimwit.
And yes, they are efficient in the regard that they don't have the luxury of 32nm and yet keep the TDP at low 125W as stated in the article. Just remember two facts that the 1st gen Phenom 2s were rated 140W and 32nm six core Intel i7 980x/970 have an envelope of 130W. And you'll see efficiency in 125W.
Report Comment
# RE: AMD Phenom-II X6-1075T CPU HDT75TFBK6DGRthomas 2010-09-22 23:39
"cons: 45nm process is kinda old today"

you talk like a child who is ashamed of coming to school in reebok shoes when all the other kids have nike and adidas, like the choice of processor comes down to its process granularity in a trendy fashion way.
Report Comment
# RE: RE: AMD Phenom-II X6-1075T CPU HDT75TFBK6DGRDavid Ramsey 2010-09-23 07:50
I wrote the article from the enthusiast perspective, and I assumed (obviously in error) that most readers would understand the advantages of the 32nm process Intel is so aggressively moving its product line towards. You know, more dies per wafer, therefore better profit margins, not to mention all the other purely technical benefits of smaller processes in general.

If you disagree with technical issues in the review, fine; if you just don't like my writing style, go start your own hardware review site and show us how to do it.
Report Comment
# my i7 930 oc is betterGarco 2010-09-23 21:07
with DDR3 triple chanel and gtx260
only with my memory i'm exceed amd
Report Comment
# correctionGarco 2010-09-23 21:50
Only with my memory i'm able exceed amd
Report Comment
Report Comment
# RE: BUILTUP CONFIGARATION OF PHENOM - II X6 CPUDavid Ramsey 2010-09-26 04:14
Ashish, if you will take this question to our forums, I'm sure you'll receive plenty of help. Also, please take off your "caps lock" key when typing.
Report Comment
# RE: AMD Phenom-II X6-1075T CPU HDT75TFBGRBOXNoe 2010-12-08 01:12
TYVM, David, for this review.
It has answered some of my questions about the new AMD hex cores. Mostly to do with performance @ same clock speeds of these processors.
However I would still like to know, how the 1035T & 1055T shape up against the 1075T/1090T/1100T.
Are these all essentially the same processor, with different clock speeds or is there some real difference when dropping from the 1075T to the 1055T?

What would be the difference of OCing a 1055T @ 4GHZ (is this possible, with a stable system?) Vs a 1075T @ 4GHZ, if all other hardware was the same?
Report Comment
# Good question, also energy and 890GXGoyta 2010-12-08 14:49
Noe made a good question, and trying to find it out was exactly what brought me here. I'm about to buy either a 1055T or a 1075T. I live in Brazil, where hardware is usually very expensive and prices don't always follow the same logic and proportions as in the U.S. Here, the 1075T almost matches the 1090T in price and therefore is usually not a good value, but occasionally one can find deals placing it closer in price to the 1055T, and in that case I'd like to know if it's worth to pay more for it, however little, as I have seen several reviews achieving stable 4 GHz and beyond for the 1055T as well.

In fact, I may not even feel the need to overclock it (the "fast enough" thing), but it's so comforting to know that if I do, I can possibly get near-980X performance for a fraction of the price...

Another good question would be power consumption. I have read that when you overclock X6's they start gushing up power like mad, reaching up to 300 watts (yes, just the processor, not the whole PC) at around 4 GHz. That's something to consider as well, when deciding if it's worth to overclock it and to what extent.

Finally, a more straightforward question: you said similar results would probably only be possible with an 890FX mainboard. I'd love to have one, but they are prohibitively expensive here. So, I have the crippled version of it, an 890GX mainboard. Do you think the GX could yield similar results?

Thanks a lot!
Report Comment
# RE: Good question, also energy and 890GXNoe 2010-12-10 01:54
Since the time of my first post here, I have been researching other sites/forums to see if the 1055T can be OC'd @ 4GHZ.

While I have found that it is possible & with a stable system, the rest of my question still remains.
Also I am now wondering about the effects OCing a 1055T this high would have on the longevity of the CPU & whether this would differ for the 1075T at all? (I realize that any answer to this would be mostly speculation & also be dependent on cooling solutions etc.)
Report Comment
# RE: RE: Good question, also energy and 890GXDavid Ramsey 2010-12-10 08:54
Noe: As long as you can keep the CPU temperatures reasonable, I think any "reduction in life" of a CPU caused by overclocking would be minimal. But this is just speculation. I've been overclocking for more than a decade and I've never lost one yet, overclocking, say, an old Motoroal 68040 from 33MHz to 40MHz is quantitatively different from taking a modern processor to 4GHz. For one thing, the TDP on a 68040 was only 20 watts!
Report Comment
# RE: Good question, also energy and 890GXDavid Ramsey 2010-12-10 08:50
Goyta: We have not tested a 1055T here at Benchmark Reviews, but I'd guess that its overclocking capability would be similar to the 1075T. Overclocking any processor increases the power consumption (which is why you need better cooling), but remember that the processor won't be running at 4GHz all the time (unless you've disabled power saving features in the BIOS). Re the overclocking performance of an 890GX mainboard, again, I haven't tested one of those, and can only guess how well it would work. The 890FX motherboards are aimed at enthusiasts and will generally have better power supply circuits, cooling,'s more than just the chipset. Obviously if you plan to overclock you should look for a higher end motherboard. That said, I imagine a good 890GX motherboard could at least come quite close to the OC capabilities of an 890FX motherboard.
Report Comment
# UpdateGoyta 2011-02-01 20:24
David, thank you very much. It has been a while since I last posted here, and in the meantime I have upgraded my PC as planned - actually, better than planned. A combination of slightly smaller prices due to launching the 1100T, a good deal and a bit more money available than I had thought I would, all have made me go for a 1090T. This is, of course, a Black Edition processor, so overclocking it is a breeze if you have proper cooling (I got an Akasa Nero 2, which while not "top" is a fairly decent CPU cooler and should give me some room if I decide to do that).

But that is not in my plans for now. I have found that even at stock speeds, it is scaringly fast! I simply don't need to overclock it, and don't think I will need it any time soon. I'm also impressed at the thermal efficiency: when idle on a not so hot day (I live in a subtropical latitude and it's summer here down South now), CPU temperature gets as low as 21°C, and I'm yet to see it go over 44°C under stress. Well, I wanted a PC to last several years, and I've got one. I'm very happy. Thanks a lot for your help!
Report Comment
# RE: RE: AMD Phenom-II X6-1075T CPU HDT75TFBGRBOXDavid Ramsey 2010-12-10 08:59
Noe, there is no "1035T". And we've never received a 1055T here for review, so I can't compare it to the 1075T/1090T/1100T...but I'm pretty sure it's just the standard Thuban 6-core design with a different multiplier, so if I had to bet, I'd say you could probably overclock it to the same degree as a 1075T. Remember that since it's not a Black Edition processor, the only way to overclock it is to raise the base clock. FWIW, AMD lists 6 Thuban processors: 1045T, 1055T, 1065T, 1075T, 1090T, and 1100T. As best I can tell the 1045T and 1065T are not available at the retail level but are OEM-only parts.
Report Comment
# RE: RE: RE: AMD Phenom-II X6-1075T CPU HDT75TFBGRBOXNoe 2010-12-10 20:38
The 1035T does exist but is probably OEM only aswell. Also there is a 1055T 125W version & a 1055T 95W version. The 95W version is interesting because, from what I have read, it has a higher temp tolerance of 71C compared to 62C for the 125W version.
If I understand it right, both these versions OCd to 4GHZ would draw the same power under load but at idle with power saving enabled, the 95W version should draw less power.
Report Comment
# RE: Phenom II x6 1075THyperion 2011-02-17 17:25
Got mine month ago. On 4+1 phase gigabyte 790FX-DS5 i couldn't overclock at all. Mosfet would get too hot and I got lower fps/results with higher frequency(3,2-3,6GHz) than the stock 3,0GHz.

So I bought the ASUS M4A89GTD PRO (8+2 phase) and I reborned with it. I reached 4,0GHz in a minute with 1,425V. Max for 3D bench is 4,2-4,3GHz and the most i got with this combination on air is 4,5GHz @ 1,596V. That was very unstable but enough for one round of super pi 1M and then BSOD.

For 24/7 I am holding it at 3,8GHz @ 1,375V. I use Scythe Mugen 2 and temperatures are very good. About 45C in games, 52-53C in occt. With 4GHz 55-57C in OCCT. Scythe Mugen 2 is very very silent cooler i recommand it.

Dont use X6 processor on 4+1 phase motherboard if you want to overclock. 4+1 phase is only OK for stock 3.0GHz nothing more.

Sry for bad english.
Report Comment
# # RE: Phenom II x6 1075TPaxos 2011-03-23 15:49
Hyperion , thanks for the post. You gave me somethink to think.
Nice job.
Report Comment
# chip still going strongDaniel Mac 2012-03-21 00:41
been a couple years since the article came out, still wanna say my oc'd 1075t on 3.9 still spanks the pants off my new 2nd gen core i5 2500 LOL
Report Comment

Comments have been disabled by the administrator.

Search Benchmark Reviews

Like Benchmark Reviews on FacebookFollow Benchmark Reviews on Twitter