WPrime 2.00 Benchmark Thread

[Uriel]

Would rather people keep the image format if possible + CPUz shots. I'll edit the original post.

 

[Topitoff]

Topitoff - just a query - your benchmark results show 3900 mhz. CPUz shows 3600. Which is it? Is there a turbo mode or something running?

Still - impressive results from the i3. Getting the same 4 thread result as my Deneb @3.3GHz, a quad core (albeit unlocked from dual ).

Edit: Topitoff's shot also indicates 4GHz in the notepad file

I have the cpu set at 200 x 20 in the BIOS, but have left the speedstep etc. enabled so it will reduce multi. The benchmark shows 3991.4MHz which is just under 4GHz

I was also quite impressed how this compares to the AMD quads.

 

[JeffyB]

I can run this tomorrow when I'm home. I'll do 2 runs, one with and one without ht.

 

[Coolasmoo]

This is actually 191 x 20 with Turbo / Speedstep, hence the CPU-Z shot


Just a quick one for now, 8 threads

 

[Jokester]

Just had a closer look at my results:-

4threads (HT):- 7.925s
4threads (no HT):- 7.659s

Substantially quicker with HT turned off.

 

[Elfmeister.]

 

[Meaker]

Only got 1 stick of ram atm at 800mhz.

555 BE @ 3.95ghz unlocked to 4 cores.

 

[mmj_uk]

Just had a closer look at my results:-

4threads (HT):- 7.925s
4threads (no HT):- 7.659s

Substantially quicker with HT turned off.

That's strange, it shouldn't be any different if it prioritizes physical cores over logical ones.

 

[Jokester]

That's strange, it shouldn't be any different if it prioritizes physical cores over logical ones.

That's what I thought as well, so I was surprised to see that.

 

[Uriel]

Just thinking about making this thread more about info, with a hint less epeen (if that's possible round these parts).

I give you the first results graph - a bit of info on scaling vs clockspeed, cores and architecture:

I decided not to use deneb x4s running 3 cores in the deneb x3 results for example. Any thoughts?

Edit: Already we have an anomaly @ Elfmeister something's up with your result. Try disabling CnQ.

 

[Elfmeister.]

I think the results are correct even though it states 878Mhz as if it did what would 3.8Ghz get?

I'm pretty sure that by looking and comparing with your chart the time is about correct.

 

[Uriel]

It may have taken a little time for the CPU to get up to speed. All the other Deneb results seem to line up in an almost linear fashion with clockspeed. You end up getting about the same time at mine at 3.2GHz. There could be something else causing the issue but my money's on CnQ, unless you were running something else at the same time.

Edit: my hypothesis seems to fit with your times with less threads being closer to the other Denebs. It would make sense for the shortest test to be the most severely affected.

 

[Elfmeister.]

I need to learn how to read a chart, been looking at it backwards!

I see your point now.

 

[ghop]

I'll chuck my i5 750 at 3.8ghz into the mix

 

[Elfmeister.]

Now without CnQ, cost me 1.2 seconds on 4 threads but evened out on 1.

 

[JeffyB]

I7 d0 4.34ghz ht on, will do ht off later.

 

[Trunks9486]

Here is mine!
Q6600 at 3400MHz

 

[Greebo]

Until I get round to doing a 1,2,3 core run, can I sumit mine from hwbot please?

8.189 secs.

http://www.hwbot.org/community/submission/870274_greebo_wprime_32m_core_2_q9650_3ghz_8sec_189ms

 

[Danny_75]

860 21x209

 

[Rroff]

Is it me or does this benchmark seem quite sensitive - possibly even more sensitive to memory bandwidth/latency than just pure CPU? I haven't had time to test yet just as a casual observation.