Quote

I've started comparing Handbrake and I can say that the multi-threaded Cinebench results of the 1950x don't necessarily translate into better multi-threaded performance in this application.

Of course they don't, Handbrake uses AVX

@PCGuy_5960

 

Handbrake with H.264, the overclocked 1950x is somewhat close to the the overclocked 7900x.  In H.265, which is even better with AVX, the 7900x just shreds the 1950x despite a 6 core deficit.  Cores weren't being completely utilized by 1950x in either H.264 or H.265.

 

Handbrake (H.264 Medium - Medium Quality) 1 min remaining

 

1950x

 

 

 

7900x

 

 

Handbrake (H.264 Ultrafast - Low Quality) 1 min remaining

 

1950x

 

 

7900x

 

 

Handbrake (H.265 Veryfast - Higher Quality) seconds remaining

 

1950x

 

 

7900x

 

What memory speed did you use with 1950X?

Obviously, when 7900X has 1GHz higher clocks, the singlecore is significantly higher XD.

Don't forget to show it to TahoeDust to boost his obsession with X299 and hate against everything AMD.

Nice testing btw

Nice, I’m hoping to get my hands on an e5 16xx 10 or 12 core variant, one of the beastly unlocked OEM ones.  I’d love to see how it stacks up vs your 5960x, 1950x and 7900x

@Damascus Nice! I didn't know that unlocked 10/12 core Xeons existed!

They are super rare, the E5 1681 v3 is what I’m aiming for.  10 cores, 20 threads, a baseclock of 2.9ghz and it’s unlocked to OC.  I’m hoping to get my hands on one when all of the v3 machines are replaced by the oncoming x299, TR4 and equivalent Naples/Xeon chips hit the market.

@dave_k

 

I'm using G.Skill Trident Z 4 x 8 3200 c14 kits on both setups.  Exact same kits.

 

As I'm sure you are aware, Ryzen does not exactly overclock memory as well as Skylake-X.  I could get 3600 and 3733 MHz to load on the TR 1950x, but they weren't stable at all so I ran with the DOCP of 3200 c14, which is definitely not slow by Ryzen standards.

 

I only run my CPUs / Memory overclocked so stock performance means very little to me.  If my Skylake-X chip can run the exact same kit at 4000 MHz, then that's what I'm testing with.  If the Ryzen TR chip could do the same, I would be running it.  

 

Hope that makes sense.

 

@Damascus

 

Sounds like you have a lot of fun ahead bud!  Let me know if I can help.

I did a small test of file compression.  2 GB folder with software installation files in it.  

 

Using Windows built-in file compression (it's only single threaded):

 

Of course, lower is better.

 

1950x:  4:33

7900x:  3.34

 

Winrar (nicely multi-threaded) with same folder:

 

1950x:  1:13

7900x:  0:33

 

 

 

1950x

 

 

7900x

 

Thanks, I’m curious to see how a poor mans i9 performs (1681 10c/20t, 1685 12c/24t or 1691 14c/28t) in comparison to the 7900x, 7920x or 7940x.

Looks like Blender is where the 1950x really shines!

 

Blender v2.79 running the BMW Benchmark from here.

 

1950x - 2:20

7900x - 2:46

 

1950x

 

 

7900x

 

Nice, that’s close to a 10% win

HWBOTx265 4k Overkill Mode

 

Full utilization of all cores on both CPUs for this one, but AVX2 holds the 1950x back when compared to the smaller 7900x.

 

1950x: 19.95 FPS

7900x;  23.15 FPS

 

1950x

 

 

7900x

 

Firestrike and Time Spy Extreme CPU tests.

 

1950x Firestrike CPU test: 24,922

7900x Firestrick CPU test: 26,705

 

1950x Time Spy Extreme (AVX2):  8,025

7900x Time Spy Extreme (AVX2):  9,038

 

1950x Time Spy Extreme (AVX-512):  7,992  **When AVX-512 is selected the 3DMark software defaults to AVX2 since Zen doesn't support AVX-512.

7900x Time Spy Extreme (AVX-512):  11,726  **Ran at 4.8 GHz as apposed to previously mentioned 4.9 GHz do to much heavier load from AVX-512.

 

1950x FS

 

 

7900x FS

 

 

1950x TSE AVX2

 

 

 

7900x TSE AVX2

 

 

1950x TSE AVX-512

 

 

7900x TSE AVX-512

 

 

That's a nice collection of data

It would be interesting to test gaming in Wolfenstein 2: The new colossus. I'd try downloading the demo and check the FPS, because that game utilizes all of the available threads. I think they should perform equally.