Tag Archives: benchmark

Samsung SM951 NVMe on Asus x99 Deluxe – Baseclock <> CPU strap magic

Samsung SM951 M.2 2280 MZVPV512
Samsung SM951 M.2 2280 MZVPV512


“I did buy a new little toy, the Samsung SM951 NVMe 512 GB M.2 SSD Drive.”


I tested the Samsung SM951 NVMe M.2 on Windows 7 and Windows 10 by using the M.2 slot on the motherboard and by using the M.2 addon card which comes shipped together with the Asus x99 Deluxe.


  • Asus x99 Deluxe BIOS 1901 @ ~ 125.5 MHz Baseclock (while 125 MHz CPU strap)*
  • i7-5930K @ ~ 4.4 GHz, 125 MHz Strap, 1.31 Vcore, 1.24 Vcache, 1.24 Vsysagent
  • NV GTX 770
  • 16 GB Corsair DDR4 @ ~ 3 Ghz, 1.35 Vmem
  • 2x  SSD OCZ Vertex 2 (Sata2) (Raid0)
  • 2x  Seagate HDD  3 TB/HDD (Raid1)
  • PSU Corsair AX1200i (why the heck an AX1200i?)
  • Corsair Obsidian 450 D


*The ‘Baseclock’ and the ‘CPU strap’ will become more important over time in this SSD benchmark drama-post. I couldn’t think of the Baseclocks offset to the CPU strap affecting the benchmarks. At first i thought its overclocking on this motherboard in general, which affects the benchmarks.
Theres is an old problem known to Windows 8 respecting system timers and clocks leading to incorrect benchmarks. Seems that Windows 10 and 7 are affected too.




Asus x99 Deluxe M.2 slot populated with unrelated m.2 device. Image source: http://rog.asus.com
Asus x99 Deluxe M.2 slot populated with unrelated m.2 device. Image source: http://rog.asus.com
Asus Hyperkit M.2 Addon Card. Image source: http://rog.asus.com
Asus Hyperkit M.2 Addon Card. Image source: http://rog.asus.com


IMAG1047“No matter which OS or which PCIe slot i use, the SSD seems to be throttled or bottlenecked.”




“As soon as the Baseclock is higher than my CPU strap. The benchmarks do no longer represent the correct values!”

“Baseclock frequency below CPU strap frequency may result in the same behaviour”

“You can say that any offset between the CPU strap and Baseclock may result in “bogus” or shifted benchmarks”



The trip to find the cause for the benchmark results:



“A bad driver can also act as a bottleneck.”


First ATTO run on Windows 7 – smells like bottleneck.

The SM951 M.2 2280 MZVPV512 NVMe SSD is using the Asus x99 Deluxe onboard M.2  slot.

Some people may not be able to see the device on OS side (Win 7 !). And those people may make their way through the internet and find a “Hotfix” by Microsoft (Windows6.1-KB2990941-v3-x64). I did  install the Hotfix. It may work for you but you may not get 100% out of your device.

Because of the “bad” results i got, i did install Windows 10. I did hope that i can get the drivers off the SSD when installing a fully UEFI compatible OS. But …


SM951 M.2 2280 MZVPV512 NVMe SSD, Baseclock @ 125.5 MHz, CPU strap 125 MHz, not system drive, connected using onboard M.2 slot




“There is a throttle …”



There is a throttle

Keep in mind that the SM951 NVMe model indeed is able to throttle itself to prevent overheating. What if this throttle mechanic is not working properly? Keep that in mind. It is possible …

… but it’s not  threating us here. 🙂





First ATTO run on Windows 10 – smells like bottleneck.

…even with Windows 10 i still do seem to be using the NVMe drivers provided by Windows (or worse the previously installed Hotfix).

The SM951 M.2 2280 MZVPV512 NVMe SSD is using the Asus x99 Deluxe onboard M.2  slot. Comparing with other tests on the internet you expect read speeds > 2.2 GB/s.


SM951 M.2 2280 MZVPV512 NVMe SSD, Baseclock @ 125.5 MHz, CPU strap 125 MHz, not system drive, connected using onboard M.2 slot


Second ATTO run on Windows 10 – smells like bottleneck.

The SM951 M.2 2280 MZVPV512 NVMe SSD is using the Asus x99 Deluxe onboard M.2  slot. This time i did set x4 mode manually and did disable a couple unneccessary stuff in the BIOS to make sure nothing weird is going on there. With no reward. Same results.


SM951 M.2 2280 MZVPV512 NVMe SSD, Baseclock @ 125.5 MHz, CPU strap 125 MHz, not system drive, connected using onboard M.2 slot






Third ATTO run on Windows 10 – smells like bottleneck.

This time i did use the Hyperkit Card shipped with the Asus x99 Deluxe. Same results.


SM951 M.2 2280 MZVPV512 NVMe SSD, Baseclock @ 125.5 MHz, CPU strap 125 MHz, not system drive, connected using M.2 addon card for PCIe


ASUS M.2 addon card “Hyper” for PCIe 3.0




The drivers Windows 10

Just for the records. Unfortunately i did not make screenshots of the Windows 7 drivers. The MS drivers were mentioned already in the past when it led to problems with NVMe like this. But they do pretty well now. They improved it

Storage Controller

Windows 10 Device Manager-> Storage Controller->Standard or Basic NVM Express-Controller->Properties->Driver->Driver details



Storage Device







“It’s not the drivers fault”


But it turned out, that it is not the driver who is causing these “bad” results.



“The drama …”



The relief – no bottleneck

It was the fact that the System was overclocked. As soon as i lowered the Baseclock back to 100 MHz. The results became better. The Baseclock was previously set to 125.5 Mhz. I then had read results > 2.2 GB/s and write results > 1.7 GB/s with SM951 SSD used as non-system drive. Unfortunately i did not make a screenshot of it. (What i did not think of here is, that the CPU strap also was set back to 100 MHz – the same frequency the Baseclock is running at)

Last ATTO run on Windows 10 @ 100 MHz Baseclock (system drive!)

However i then did configure the Samsung SM951 NVMe SSD as system drive. The performance results would be a bit better when it is not used as system drive.


SM951 M.2 2280 MZVPV512 NVMe SSD, Baseclock @ 100 MHz, system drive !, connected using onboard M.2 slot


(I noticed the following before i finally discovered that the baseclock<>CPU strap offset is causing the shifted benchmarks, but i then ignored it because of the Anti Virust software which came out as a potential cause when configured to be super sensitive)

What’s left to say?

If you multiply the old results with (Baseclock of 125.5  MHz) with 1.255 you get results matching pretty well with the results of Baseclock of 100 MHz.

For example the 8 MB result of the first run:

1398442 Write     x     1.255 = 1755044,71
1717986 Read     x     1.255 = 2156072,43


  • Was the higher Baseclock really throttling or bottlenecking  the SSD?


  • Or is it just the benchmark not being aware of a higher Baseclock  and mucking up the results? Possible that the realtime clock is affected by Baseclock?


  • Will i ever be able to overclock and enjoy the Samsung SM951 NVMe performance at the same time?


Apart from ATTO i sure did run other benchmarks on the overclocked system and they sure came up with not the same results because they dont “measure” all the same way but they all left you thinking of either a bottleneck or throttle. I unfortunately made no screenshots of the runs before but i will present some with stock clock speeds and Samsung SM951 as system drive.


Samsung SM951 NVMe M.2 SSD as system drive Windows 10 @ 100 MHz Baseclock
samsung_sm951_nvme_2280_512_gb_windows_10_system_disk_baseclock_100_mhz_no_overclock_qd32_th1 samsung_sm951_nvme_2280_512_gb_windows_10_system_disk_baseclock_100_mhz_no_overclock_qd32_th6
CrystalDiskMark: Queue depth 32 Threads 1 CrystalDiskMark: Queue depth 32 Threads 6
samsung_sm951_nvme_2280_512_gb_windows_10_system_disk_baseclock_100_mhz_no_overclock_qd64_th12 samsung_sm951_nvme_2280_512_gb_windows_10_system_disk_baseclock_100_mhz_no_overclock_qd128_th12
CrystalDiskMark: Queue depth 64 Threads 12 CrystalDiskMark: Queue depth 128 Threads 12

As system drive and some disturbing stuff going on the whole time in the background the results are OK.  But to answer the questions of “How did the Baseclock affect the benchmarks?”  or “Will i ever be able to overclock and enjoy the Samsung SM951 NVMe performance at the same time?” we would’ve to pick another route.


As soon as the Baseclock is higher than my CPU strap. The benchmarks do no longer represent the correct values!

No matter if the ‘useplatformclock’ is enabled or not. The benchmark results do look like the SSD was throttled or bottlenecked as soon as the ‘Baseclock’ is higher than the ‘CPU strap’. I thought i revealed my Anti Virus software to be the root of al evil but it was not.

The realtimeclock RTC

Just for the records:
The value for useplatformclock was initially set to Yes on Win 10
The default value on Win 7 may be unset or No

This fact was one thing that concerned me that i was right following the Baseclock- / hwclock- / timer-way


‘bcdedit’ output while not a single parameter was handed over

I did play with this setting with overclocked and non overclocked system. But it took some days to finally notice that it has something to do with the ‘Baseclock’ and ‘CPU strap’. I did step away from this setting, when i thought it had something to do with the Anti Virus software. However this setting does not help to solve the problem on systems with not equal Baseclocks and CPU straps.


“Finally i could narrow down the cause but i couldn’t solve it yet.”





What i thought and wrote, when it seemed to be the Anti Virus software compromising the benchmark results. I trapped myself when i quick-overclocked the system again (by leaving Baseclock and CPU strap the same) to test different situations:

OK folks.. scratch all that

i tend to play now with “useplatformclock” (bcdedit) and overclock the system again. But guess what. Neither overclocking nor playing with useplatformclock variable did make any difference to the benchmarks.

But i think i revealed who was in charge for the performance trouble in the beginning …


… it was …

… my freaking Anti Virus software!


I did compare the useplatformclock setting of a Windows 7 system to my Windows 10 system to make sure that this could be a true reason for the mucked up results and it turned out to really be a root for the mess. You now need to know that i went from Windows 7 to Windows 10, just because of this performance mess, by upgrading Windows 7 to Windows 10. There was a chance that some important settings wern’t migrated or merged correctly. Upgrading does leave room for a lot of mistakes at this level. Later on i made a complete fresh install of Windows 10 and this time i installed it directly on the SM951 NVMe SSD, but as i already mentioned, the results didnt change anymore no matter what i touched.

  • Because the Baseclock and CPU strap are equal during this period i never had any shifted benchmark results again

I was freaking out because i really need to know the cause for the performance drama at the beginning to wipe out any missconfigurations and make sure every component is running fine and smooth and then when i was almost giving up i took the Anti Virus software into account.

It’s not that i never was thinking about it but i did underestimate it and i also wasn’t aware anymore of the configuration of my Anti Virus software.

  • Apart from the Baseclock and CPU strap there was only one more thing that could form a bridge  between all these odd things.

As tired as i might be the Anti Virus software was the only thing that could “transport” or “connect” the performance mess from one OS to another – if you are changing the OS by upgrading it. The complete fresh install i mentioned earlier wasn’t affected by the Anti Virus software, because i didn’t install it, but the old Windows 7 and the upgraded Windows 10 installations both had the same Anti Virus installation running.

  • But they also had a Baseclock CPU strap offset

So i went ahead and installed the Anti Virus software. With said software running in the background i still did get normal results. Again that did hit me hard. I thought i got it. But in the same moment, i realized that i didn’t change it’s configuration.

With the configuration window infront of me the settings, i usually made, came into my mind and i set them according previous installations of this Anti Virus software. And guess what. I finally could reproduce the ‘BAD RESULTS’. With its settings set back to defaults, everything is fine. No performance issues.


CrystalDiskMark: Samsung SM951 NVMe M.2, Queue depth 32 Threads 4, Baseclock 125 MHz, system drive !, onboard M.2 (Baseclock and CPU strap are equal here!)



I know what some people will say. 🙂 All i can respond is, that i am aware of Anti * ware digging into things and some other things. My problem in this case relies more in the experience i had with this Anti Virus software. I’m using it for years now and never had any issues like denied or failed or interrupted installations due to scanning attempts or  or any kind of interruption that would ask for my attention or a closer look. It always had been the perfect Anti Virus software for me. “Install it and forget it”. Now it got its revenge for all the years not paying attention, not treating it like a tamagotchi and not taking care of it.

I promise i will treat you better now, dear Anti Virus.

But i can say now that i was right not believing my Anti Virus software to be the one compromising the results.

SiSoftware Sandra Lite i7-5930K benchmark

Overclock with no bluescreen is no serious overclock

Now, 2 weeks after purchasing this new RIG i went a step forward and decided to consult SiSoftware Sandra Lite to get some more details and i7-5930K benchmark. After playing with it in the first 1-2 hours i got the 5th bluescreen during the overclocking evolution period, which may hopefully end today. I received my 5th bluescreen during SiSoftware Sandra tests/Benchmarks. You may have a look at the Hardware / Computer section for upcoming posts and updates.


Quick Overview of the System (or have a quick look at previous posts):

  • Asus X99 Deluxe (white/black) Motherboard
  • Intel i7-5930K  at 3.5 GHz (will use MX-4 paste)
  • Corsair Vengeance LPX DDR4, 16 GB, 2800MHz  4-Modules-Memory-Kit
  • Corsair RM1000 Power Supply
  • Kraken X60 Watercooling
  • 4x Corsair 140mm Fans (purple/violet)
  • Corsair Obsidian 450D Case


History settings

History settings (i will skip experiments that weren’t tested in longterm view, for example playing with Vcore for the CPU or when i switched back to basic settings when trying to figure things out/ bluescreens) from oldest -> to newest Setting(s):


CPU i7-5930K (including Turbo)in GHz: Corsair LPX DDR4 RAM in MHz: Asus x99 Deluxe Baseclock in MHz:
3,7 @ base values, unknown voltage (release BIOS 0505) 2166 @ base values, unknown voltage (release BIOS 0505) 100 @ base (BIOS 0505)
4,1 @ 1,23 V (release BIOS to BIOS 0801) 2800 @ 1.35 V (release BIOS + BIOS 0701, XMP Profiles values didn’t work) 100 (BIOS 0505 – 0701)
4,2 @ 1,25 V (BIOS 0701 + BIOS 0801) 2800 @ 1.2 V (BIOS 0701 + 0801, XMP values started to work with 0801, 0701 was still unstable) 127,5 (BIOS 0801)
4,25 @ 1,25 V (BIOS 0801) – current 3000 @ 1.35 V (BIOS 0801) – current 125 (BIOS 0801) – current
4,375 @ 1,265 V (BIOS 0801) 3000 @ 1.35 V (BIOS 0801) 125 (BIOS 0801)
4,425 + 4,5 @ 1,276 V (BIOS 0904) 3088 @ 1.35 V 128,7 (BIOS 0904)

These current settings values (antepenultimate row) are valid until 26. September 2014 – for further information please read this post (most recent at this moment) or  this one. The penultimate row in the table are values tested after publishing this post. Final or most recent settings you can find in the most recent link above. Some values were tested on different BIOS versions, some were stable some were not. The table doesn’t show all these combinations. In all cases you can say, that the newer setting also did run at BIOS version 1 behind. For example 4.5 GHz was also tested on 0801.


The i7-5930K benchmark

Update 28. September 2014: Unfortunately i didn't write down the PW for SiSoftware Ranker. The links now point to the new account.

With a baseclock slightly decreased from 127.5 to 125 MHz and RAM voltage, now again, at 1.35 V – but this time with 3000 MHz clockspeed – i hope to get closer to a smooth running System. Check it out directly: SiSoftware Sandra Ranking Page of tatoismus.net >>

This one has a better overview: Another Ranking Page of SiSoftware

After these little changes were made, all tests did pass with no further problems. The screenshots show the rank from 15. Sept. to 16. Sept 2014. Ranked #123. (Just 8 hours later im ranked #326 🙂 they’re all cheating)


i7-5930K benchmark SiSoftware Ranker
i7-5930K benchmark SiSoftware Ranker


i7-5930K benchmark SiSoftware Ranker
i7-5930K benchmark SiSoftware Ranker


Cooling the i7-5930K

Additionally i installed a 120mm fan in the rear of the case just to get the warm air a little bit faster out. When i was facing 90 °C and more in the past at full load with the 127.5 baseclock setup, i now still reach 90 °C and more but it takes a tiny bit longer to get there 😉

Just to make sure: temperature was never the issue, i was always monitoring temps when i did any sort/kind of benchmarks. During benchmarks the CPU cores sure get to their limits but never on a timeperiod long enough cause any heatdamage or impact results or cause bluescreens. Well, i talk about SiSoftware Sandra. — Armed with prime95, things become different.


Sorry Sandra

Few words about Sandra SiSoftware. I hate it. Or lets say it was frustrating me in the beginning. Its okay for a wide range of tests, but i will never use it again i think, untill my computer produces another bluescreen.


Uploading the i7-5930K benchmark with a certain user name to SiSoftware Ranker
Uploading the i7-5930K benchmark with a certain user name to SiSoftware Ranker


I can haz user account?

You have to run it as admin. I mean you have to login as admin. “Run as Admin” isn’t enough. And then you can/are able connect to “Local Computer”. Don’t ask how you can upload results to their Ranking-Website using a specific username. I managed it but it hurts explaining it. In the end it is simple but i expect things do work different. You don’t register or create an account in a way you would expect. You simple put a name and email address and password in the fields and fires return key until a picked account name is being accepted. Not talking about the bad named and bad placed module “Top Results”. Who expects that you enter your account information in here? And why locate it in Benchmarks? And you should really not use their FAQ or you will find yourself smashing your head on the desk.




Recognize my RAM correctly pls

By the way: SiSoftware Sandra doesn’t know that my RAM is running at 3000 MHz. It always says for whatever reason “2133 MHz”. You have to look at DRAM Frequency and multiply it by 2 “DDR = Double Data Rate”. Seems that Sandra is only reading some vendor model strings and thats it.



Another challenge for Corsairs DDR4, i7-5930K and Kraken x60 – new BIOS 0801 for Asus x99 Deluxe

Almost a week now since i purchased all the good new parts for my new computer. A few days now playing with overclocking (OC) parameters. Yesterday my computer froze two times and i had to start figuring things out again. You may know from my previous post, that i had to run the DDR4 RAM Corsair Vengeance LPX 2800 MHz at 1.35 V because i was experiencing issues and that the CPU i7-5930K was clocked at 4.1 GHz which was fine so far. The root cause for the system hangs is unknown yet. Could’ve been either CPU or RAM. The baseclock hadn’t been touched since today in the morning.


Sorry guys, i’m not going to show you lots of graphs of games and benchmarks.
But i can offer a link to SiSoftware Sandra results.
Little update 26. September: 4.5 GHz achieved. Video clip soon. Scroll down for more information.


Well, the first things i tend to do was adjusting DRAM voltage and set CPU back to its basic settings. That worked so far with little throwbacks – if i remember correctly – but even than that i decided to check Asus webpage for new BIOSes for the Asus x99 Deluxe and there it is.



Seen, downloaded, installed.

And suddenly the XMP profiles did work pretty well with my DDR4 RAM. But there was a downside. The baseclock got raised to 127.5 MHz and the CPU received a slight voltage bonus and runs at 1.250 V now. (In the following picture the CPU runs at 4.2 GHz which was not the fact today in the morning).


CPU-Z: i7-5930K at 4.2 GHz and 1.25 V and 127.5 baseclock
CPU-Z: i7-5930K at 4.2 GHz and 1.25 V and 127.5 baseclock


That’s what was happening last night till today morning. I also made the first steps towards temperature enhancements. But failed. I set the CPU voltage to 1.110 V and hoped it would be enough to run the CPU smoothly and be able too cool it down. Negative Houston. Not stable enough for prime95. The overclock-process continues. When i came home from work today in the night (now) i proceeded the work on this. I configured the XMP profile and made no changes to the CPU voltage but i added 1 step to the ratio, means 4.2 GHz for the CPU.

Remember i donated a watercooling system to my computer. The Kraken X60. The Corsair fans i installed in place of the Kraken fans are not made to handle so much heat – it seems. The temperature hits the 92 ° C  mark. Not good at all.


i7-5930K at 4.2 GHz and 90 ° C
i7-5930K at 4.2 GHz and 90 ° C


There is at this moment no way i can enhance the cooling yet if i want to stick to my purple fans. Two fans are covering the radiator and if i would go quadro-fan i had to buy a new case or install the radiator in the fron which in turn would mean good-bye 3.5″ inch harddrives.

I started prime95 right before i started to write this post and it did accompany the hole time. The result now is, that the CPU and RAM seem to work stable but the temperature is really an issue here. I have to point out that the problem with the temperature occurs with the increase of the baseclock. I had no problems yesterday when the baseclock was at 100 MHz.

Now i could:

  • buy another case and install 4 fans on that radiator and leave it installed in the top
  • install 4 fans on that radiator an move it to the front of the case and lose 3.5 inch harddrives
  • remove the purple fans and try the Kraken fans or any other fans which cool better and have to chose between decibels and efficiency and leave it in the top of the case without losing harddrives
  • compare the cooling system to other cooling systems and buy a new one or directly start with a custom water cooling system
  • or  put the baseclock back to 100 and see if i can get it stable without XMP
  • or reset to basic factory default settings … what? who did say that?



SiSoftware Sandra Benchmarks with Intel i7-5930K


Three weeks later and with an Intel i7-5930K at 4.375 GHz i still am juggling with temperatures. Even when running the Kraken X60 at full speeds, the temperature hits 91 °C during the prime95 stress test. I didn’t change anything yet but my first attempt, my first step will  be to install the Kraken fans in place of the Corsairs. Will update this post today once again.


cpu-z i7 5930k at 4.375 GHz
CPU-Z: i7-5930k at 4.375 GHz


Ok today (26. September 2014) i installed the Kraken fans

which come with the Kraken x60. The results are much better. The fans tho, are noisy as fuck but i can get things straight now. I also managed to weak the i7-5930K at 4.5 GHz with a vcore of 1.390 V. The temperature almost instantly raised to 95°C when running heat-tests with prime95. With the fans at fulls-peed this is really the limit. Just when graphics card would kick in, or something else that generates more heat in the sytem, i’m pretty much fucked. So when you were looking for a review of Kraken X60 and i7-5930K i can tell you that you might achieve those 4.5 GHz with that Kraken X60 water-cooling-set but you will not be happy with it. I will try some other fans in the near future. I spent a lot of time at work to compare fans, their pressure and throughput etc.


4.5 GHz achieved

temperatures > 90 °C (with prime95 heat-test  and Kraken fans at 100%). Regarding prime95 and current settings (after publishing this post) please read this post, important!


I made a short clip of the system when running at 4.5 GHz to capture the noise too. It was a very important step and lucky me, the right one to get my temperature problems solved and detect what the problem relies on.

Well, since i reached the limit of my current built i will go back to 4.375 GHz where temperatures and water-cooling run smoother. When running a heat-test the temperature does not hit the 90 °C mark and fans are not going crazy.



CPU-Z: i7-5930k at 4.375 GHz [1.290 V]

As soon as the Vcore, preselected by the mainboard, does not lead to a stable system, you are in that performance spectrum of the CPU, where you 1. start to lose Performance/Watt 2. and have to add some extra Volts on the preselected value to make it stable.

It turned out that when i want to run my system at these 4.375 GHz, i add 0.01 – 0.02 extra Volts to it (preselect value 1.27 sometimes 1.28) and will end up with a Vcore of 1.29 . Obviously i did not get the first price in the silicon valley lottery but it could be worse and with only 0.01 extra Volts i’m very close to the stable region of that die. However, the preselected Vcore value at 4.5 GHz was 1.310 Volts. I had to add 0.07 Volts to make it run stable. Hot, but stable. That does also mean that for 1 extra ratio / multiplier i have to add almost three times as much Volts to the preselect value as i have to when running at 4.375 GHz.




I definetly will get some other fans but for now they do their job pretty well. To be continued.