Half a croissant, on a plate, with a sign in front of it saying '50c'
h a l f b a k e r y
There's no money in it.

idea: add, search, annotate, link, view, overview, recent, by name, random

meta: news, help, about, links, report a problem

account: browse anonymously, or get an account and write.

user:
pass:
register,


     

Please log in.
Before you can vote, you need to register. Please log in or create an account.

-80C SSD Results Are In

A grand total of 16 days at -80C, what performance boost do we see?
  (+5)
(+5)
  [vote for,
against]

So, against my better judgement, or perhaps in my dedication to the importance of experimental evidence, I've tested the effect of -80C treatment of a fairly standard Samsung SSD.

To do this, I ran the Passmark Performance Test 10.0 test suite on the CPU (CPUMark) and the disk (DiskMark) before and after 16 days at -80C. The absolute beast* of a test rig is as follows:

Dell Optiplex 7010

Intel i7 3770

16gb DDR3 Ram (4 x 4gb sticks, 2 green 2 blue)

ATI FirePro 8700 graphics card

bs0-co Performance dust package

the SATA 3.0 cable the Dell came with

slightly sticky keyboard

2 (count 'em) 23" Dell 1080p monitors

a 3tb 3.5" storage HDD**

bs0-custom 120mm zip-tie fan mod

Windows 10 build 19041.746

PC was off*** between pre/post tests to ensure software spec. was frozen****.

1 ThermoScientific Forma957 -80C lab freezer.

and the test subject: a Samsung 860 EVO SATA SSD.

Protocol:

Take 1 SSD. Run Benchmarks

Put SSD into ziploc bag.

Place bag/SSD in Forma957 for 16 days @-80C

Lie to colleague about why a computer component is in the freezer.

Remove bag/SSD, allow to warm up for ~1hr

Refit to test-rig & re-run benchmarks

I ran the post treatment benchmarks 3 x since the first run was strangely low. Runs 2 & 3 seemed similar. CPU & drive data all viewable on <link>.

Conclusion: While there is no objective difference in the drive performance, I feel this is just one section of a broader narrative. Subjectively, I now find my file storage experience to be significantly less harsh. Boot times are quantitatively (21 seconds in pre & post) the same, but qualitatively a world apart... the post treatment 21 seconds felt smoother, more relaxed while pre-treatment was a harsher, workmanlike experience. Some might say that this is down to pre-treatment being early afternoon halfway through a full week Vs. dicking about on the internet on a Friday evening, but I know what I felt. I'm really looking forward to my file-storage experience going forward and may even consider a -80C treated SATA cable to fully unlock the benefits.

16 day SATA drive -80C treatment is available for $98.75 +S&H directly from bs0-co. Value combo drive/cable treatments from only $108.49 and the budget special "throw the whole mail package in the cold room for 20mins/1 coffee whichever is quicker" is $54.95. PCI-E 4.0 NvME drives are currently not supported, preliminary testing suggests a costlier LN2 solution will be required.

*in the context of 2012-vintage office equipment

**subtly pocketed while upgrading a server

*** no choice, was boot drive.

**** they write themselves.

bs0u0155, Feb 05 2021

Results https://drive.googl...7i/view?usp=sharing
[bs0u0155, Feb 05 2021]

[link]






       GOOOO SCIENCE!!!!
Voice, Feb 05 2021
  
      
[annotate]
  


 

back: main index

business  computer  culture  fashion  food  halfbakery  home  other  product  public  science  sport  vehicle