Is anyone here already using a Ryzen 1800X processor ?

[schack]

He used 16 threads, not 8.

In any case the extra .8 GHz makes a difference.

[cma6]

"2 tips:
- don't use the bmi version of Stockfish 8 but use the popcnt version. The latter one is faster.
- enable SMT "

When the WC speaks (on CC or photography), I listen!

Are your tips in references only to a Ryzen system?

And what about the problem of lack of Windows patchs for Ryzen systems?

[shrapnel]

From what I've seen in my online engine-engine matches, enabling SMT in BIOS does seem to be the way to go.
What is NOT so certain is how many Threads to allot the Engine.
I can tell you straight of the bat though, that using all 16 Threads for the Engine is NOT a good idea....

[schack]

Windows 10 is fully supported, as is (I think) 8.1. It's Windows 7 that is not supported, but there are ways around that if you google a bit.

[schack]

I'm not sure this is correct. From what I have seen with Ryzen, the SMT is more efficiently implemented than with current Intel chips, meaning that hyperthreading is more than worth the overhead costs. This means that the full 16 threads will be strongest.

That said, there are some reasons you might want to reserve threads for other purposes, avoid excessive heat if you're overclocking, etc.

[quote="shrapnel"]From what I've seen in my online engine-engine matches, enabling SMT in BIOS does seem to be the way to go.
What is NOT so certain is how many Threads to allot the Engine.
I can tell you straight of the bat though, that using all 16 Threads for the Engine is NOT a good idea....[/quote]

[cma6]

JP:
Can AsmFish popcnt user many threads, e.g. 64 physical cores?

[shrapnel]

I'm not sure this is correct. From what I have seen with Ryzen, the SMT is more efficiently implemented than with current Intel chips, meaning that hyperthreading is more than worth the overhead costs. This means that the full 16 threads will be strongest.

Well, I'm not too sure either. We are all unofficial Testers for this new Platform.
In any case, "more efficiently implemented" does not necessarily mean 100 % efficiency. Also, I feel some Threads should be left for background services, some of which may be essential and may indirectly affect the strength of the Engine....lots of factors at work.
So, more Testing is the only way to find out.

[cma6]

I should have clarified: "use 64 out of 72 physical cores".

[jpqy]

JP:
Can AsmFish popcnt user many threads, e.g. 64 physical cores?

Sure..with any cores you have!

Now it has as max. setting 256threads

option name Threads type spin default 1 min 1 max 256

But you can put it easy to 512threads for example..and assemble it.

JP.

[jstanback]

I agree that using all 16 threads on Ryzen is probably not best. To take a stab at how many threads is best for my program Wasp, I ran the arasan19.epd test suite (200 positions) for 1 second per position and calculated the average depth reached. My system is a Ryzen 1700 running at 3.7 Ghz on all cores with SMT turned ON. I used 64 Mbytes hash. Here is some data. Knps is the combined nodes/second, Depth is the average depth reached (not necessarily fully completed), and EBF is effective branching factor for the last 4 completed plies.

Code: Select all

  Threads  Knps   Depth   EBF
    1          1447    14.2   1.72
    2          2886    14.9   1.72  
    4          5660    15.9   1.68
    6          8294    16.5   1.71
    8        10806    16.7   1.68
   10       12045    16.7   1.69
   12       13141    16.7   1.71
   14       14149    16.7   1.69
   16       15135    16.7   1.67

So for my program anyway, I don't get any depth increaset from using more than 8 threads. But I did a similar test a couple weeks ago at 5s per position and got very slightly higher avg depth for 10 threads as compared to 8. Also, sometimes more cores can give a different (hopefully better) move for a given search depth. So maybe 9 or 10 threads is best for me. Maybe if I improve my lazy SMP search I can make better use of the additional nodes/second for threads beyond 8.

FYI, as a comparison I get 1534 Knps for 1 thread on an i5-4690K at 3.9 Ghz. So for my program the Ryzen and Intel systems have nearly identical speed if clock rates are equal.

John