AMD™ Ryzen© Blender® Benchmark Scores™©® Thread

Screenshot (8).png
So, I'm not sure why I see beefier systems running the 6950X and WAY the hell overclocked seem to be slower than my machine:

ASUS X99-E WS
Intel Core i7-5960X with a miled overclock (screenshot included)
64GB of G.Skill Ram
I did spend a little bit of time tuning the system with this 64GB memory kit.

I see 40+ seconds on higher end machines and as much as over a minute.. Same renderings.

I rendered in 36.57 seconds.. so idk what's different..

Note, I didn't close any back ground apps and system has been up and running for three days with my Plex Media server running and trans coding in the background
 
Last edited:
Picked up an ES Xeon from ebay to play around with: Intel Xeon E5 2630 V4 ES QK3G 2.2GHz 10Core 25MB 85W LGA2011-3
150 samples = 42.86 seconds
It runs perfect on an ASrock X99 I got open box at Micro Center. That store is killing my bank account.
 
I did 50.77 with standard 5930k 16GB DDR4 2133 Mhz
What do you think about this result? is it good or should be better?
 
O wow look the F stepping can go higher! I remember someone in this AMD thread or another one saying AMD couldn't have a new stepping this quickly. I guess the F stepping is hitting 4ghz boost!
 
Brackle said:
O wow look the F stepping can go higher! I remember someone in this AMD thread or another one saying AMD couldn't have a new stepping this quickly. I guess the F stepping is hitting 4ghz boost!
Click to expand...


That isn't what I stated, I stated the latest they can get another spin is they would have had to start in June.......even that would have been cutting it close.
 
razor1 said:
That isn't what I stated, I stated the latest they can get another spin is they would have had to start in June.......even that would have been cutting it close.
Click to expand...

hmmm i don't even think it was you who I was talking about? Can't even remember tbh, I just remember someone saying they couldn't have a new stepping from that french review.

Well it looks like they do have a newer stepping from that french review which was at 3.15GHZ F3, which now looks like 3.7/4.0GHZ F4
 
oh yeah that wasn't me, I remember talking about respins lol, but I know I didn't say that, sorry.
 
46.75 from the rig below, good enough to do me a couple more years! Will be doing a GPU upgrade this year, Vega/Volta im lookin at you!

Edit: Tried it again, tweaked my memory
 
Last edited:
1:47.47 on non-OC 4-core i5-4690K versus 36 seconds on 8-core Ryzen. Give me something with a reasonable price and I'll happily switch!
 
46.40 with my Xeon E5 1650 @ 4.8 GHz and some piddly Kingston HyperX DDR3 1600 RAM.
 
1:07.33 on a 2600k @ 4.6ghz. Not too shabby. I'm gonna bring her up to full benchmarking speed and BRB to edit this post.

Edit : 1:04.77 @ 5ghz

Vw4XBlL.png
 
Last edited:
I did 3 runs:

2010 Mac Pro w/ 6 core 3.33GHz Xeon 16GB RAM - 00:54:95

2017 Kaby Lake w/4 core 4.8GHz 32GB RAM @ 3600 - 00:54:51

2017 Kaby Lake w/4 core 5.0GHz 32GB RAM @ 3866 - 00:52:11

My old faithful Mac is hanging in there (at least for this test).

I didn't change any settings in Blender (150 sample ver).
 
Last edited:
Rig in sig (all stock), same version of Blender but downloaded as a zip instead of installed via MSI:

CPU Render 01:06.89
GPU Render 00:14.56 128x128 tiles
GPU Render 00:10.53 256x256 tiles

2010 Mac Pro 2 x 2.93 GHz Hexa-core Xeon w/32 GB RAM 00:30.84
2013 Mac Pro 1 x 2.7 GHz 12-core Xeon w/64 GB RAM 00:29.03

Neither Mac has been restarted in a while and both have corporate images that are far from ideal.
 
Last edited:
brentsg said:
I did 3 runs:

2010 Mac Pro w/ 6 core 3.33GHz Xeon 16GB RAM - 00:54:95

2017 Kaby Lake w/4 core 4.8GHz 32GB RAM @ 3600 - 00:54:51

2017 Kaby Lake w/4 core 5.0GHz 32GB RAM @ 3866 - 00:52:11

My old faithful Mac is hanging in there (at least for this test).

I didn't change any settings in Blender (150 sample ver).
Click to expand...


Seems abit off, my i7-4770k at 49x49x49x46 does the blender in 38.96 what Kaby Lake cpu are you testing on?

Best regads Otto
 
My laptop i7-4800MQ @ 3.3ghz all core boost finished at 01:21:29

Desktop i7-4770K @ 4.3ghz finished at 01:01:11
 
xeon E5 2699 v4 with no clocking changes
dual channel ram instead of quad, if that matters, lots of background programs
00:12.65

in line with expectations I suppose
ryzen logo 2699 v4.PNG


interesting/fun thread!
 
Last edited:
Man I want to throw this on one of our SQL box's here at work but no open GL. But would be neat to see what a 36 core 72 thread system can do to this benchmark. ;)
 
StealthNinja007 said:
xeon E5 2699 v4 with no clocking changes
dual channel ram instead of quad, if that matters, lots of background programs
00:12.65

interesting/fun thread!
Click to expand...

interesting with the scaling here, my 4x E7 8880 v2 did only slightly better with 4 times more cores, scaling seems to hit a wall here :)

Best regards Otto
 
since there was plenty of intel benchmarks i decided for shits and giggles to try this on my phenom II x4 940 @ 3Ghz(was suppose to be at 3.9Ghz no clue why it was reset to stock settings since it was last restarted) just to see how far processors have come along in the last 8 years.. render took 3:08.58

the sad part is that it's only about 20 seconds slower than the FX 8350 time some one else posted..
 
Last edited:
Shintai said:
EDRAM cost peanuts compared to any other solution. Its like 3$ for a 128MB cache in production cost. But cost is still cost and if people wont pay extra for it. Mobile SKUs are getting EDRAM right and left to save on DRAM speed and power. 7 of 13 i7, 5 of 9 i5 and 2 of 5 i3 SKL mobile SKUs got EDRAM. Or 14 out of 27 ix based SKUs got EDRAM.

HBM is a pipe dream. Not to mention its on a fast track for a power crisis of its own.

DDR4 with 50-60GB/sec? You mean 3200-3600Mhz that's only OC? By the time the APUs come out you see 2667Mhz or so as chips that isn't OCed. And we all know OEMs will go even cheaper than that.

Its a shame AMD abandoned its GDDR sideport memory. But again, a faster APU competes with its own discrete GPUs. And an APU got no value as such being faster. Its a much better business trying to sell people a RX460 or so.
Click to expand...

It depends, HBM is confirmed in 2018 but mostly mobile SoC where it makes sense. On DT i can see a quad core with Vega and single stack HBM1 as viable it will also push bandwidth to 150GB/s odd,. Still no 460 but close enough
 
OrangeKhrush said:
It depends, HBM is confirmed in 2018 but mostly mobile SoC where it makes sense. On DT i can see a quad core with Vega and single stack HBM1 as viable it will also push bandwidth to 150GB/s odd,. Still no 460 but close enough
Click to expand...

i could definitely see HBM being used at some point, especially if they end up developing a new ryzen/vega based APU for another xbox 1 refresh down the line to replace the current ones.. would it be cost effective on a consumer level? probably not but if you want to market something no one else will have on the market it might be worth the investment.
 
You must log in or register to reply here.
Back
Top