CPU DirectX 12 draw calls TestUpdate AnandTech Test

Page 2 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.

TheELF

Diamond Member
Dec 22, 2012
3,993
744
126
Obviously there is something in the Intel igp that does not allow it to take advantage of DX12, so AMD does show a much bigger gain there.
Yeah there are only like 20 cores in intels i3 igp versus the like 300 something that the A10-7850 has,the more cores a card has the more calls you can send it at once.
 

ShintaiDK

Lifer
Apr 22, 2012
20,378
145
106
Yeah there are only like 20 cores in intels i3 igp versus the like 300 something that the A10-7850 has,the more cores a card has the more calls you can send it at once.

It doesnt exactly work that way.

AMDs CU is more like Intels EU if you want to compare it that way. But even that is misleading to actual performance.

7 threads per EU. And AMD is 64 per CU?

But as shown with the GTX960 vs GTX980. Its nothing to do with SP/Core count at all. But rather frontend performance.
 
Last edited:

AtenRa

Lifer
Feb 2, 2009
14,003
3,361
136
Some of us still have AM3+ mobos with a Thuban in them. Like me.

Given the advent of DX12 and improved multi-threading in terms of draw calls and drivers, and hopefully the games themselves, would a Thuban @ 3.5 out-perform a G3258 @ 3.6?

Edit: I realize that an OCed Haswell i5 is probably better than both, but that's not the question.

I will say a 3.5GHz 6-core Thuban will be way faster than 3.6GHz Dual Core Haswell.

G3420 = 3.2GHz
Q9450 = 2,66GHz
Athlon 750K = 3,4GHz up to 4GHz Turbo

Both Q9450 and Athlon 750K is faster than 3.2GHz Dual Core Haswell. DX-12 will be the death of Dual Cores for Gaming at last.

http://forums.anandtech.com/showthread.php?p=36301071


Look how much faster the Q9450 is clock to clock with the G3420

 
Last edited:

TheELF

Diamond Member
Dec 22, 2012
3,993
744
126
DX-12 will be the death of Dual Cores for Gaming at last.

These draw call benches are the equivalent to cinebench and similar benches,they only show the potential of a CPU to spew out IPC,higher cine scores (in multi) do not equal faster games and neither will this.
Games will still depend on speed for everything else except for sending commands to the vga.
If anything dual cores (and quads and hexas and everyone) will get faster due to DX12,because the vga driver thread will disappear(yust like mantle) lightening the load.
 

geoxile

Senior member
Sep 23, 2014
327
25
91
These draw call benches are the equivalent to cinebench and similar benches,they only show the potential of a CPU to spew out IPC,higher cine scores (in multi) do not equal faster games and neither will this.
Games will still depend on speed for everything else except for sending commands to the vga.
If anything dual cores (and quads and hexas and everyone) will get faster due to DX12,because the vga driver thread will disappear(yust like mantle) lightening the load.

m8 that's THIEF running Mantle. And even the old quad cores show a serious advantage, just look at minimum FPS in both Mantle charts
 

cbn

Lifer
Mar 27, 2009
12,968
221
106
Both Q9450 and Athlon 750K is faster than 3.2GHz Dual Core Haswell. DX-12 will be the death of Dual Cores for Gaming at last.

I'm glad to see the these new low level APIs improve the performance of old chips (that is an awesome thing for some many reasons). However, in my own informal testing of BF4 64 player multiplayer using Mantle API a R7 250X (on 720p high) a 4.3 Ghz Pentium G3258 soundly beat a Athlon x4 860K when using Mantle API.

Now granted the Intel chip was overclocked and maybe BF4 doesn't implement Mantle in the an ideal fashion?
 

TheELF

Diamond Member
Dec 22, 2012
3,993
744
126
Now granted the Intel chip was overclocked and maybe BF4 doesn't implement Mantle in the an ideal fashion?

BF4 is a 2 threaded game* + driver thread (which disappears when running mantle leaving the resources to be split between the two main threads) but shhh don't tell anyone.


*well it has a lot more then 2 threads but any speed comes from only two of them,remember when the beta wouldn't even start on duals,just like inquisition? Well they fixed that.
 

inf64

Diamond Member
Mar 11, 2011
3,764
4,223
136
@ TheELf

That is just not true. BF4 is running MUCH better on 4 threaded CPUs (i3 and 2M Athlons included) Vs Celerons and intel pentium crap (pardon the expression).
 

AtenRa

Lifer
Feb 2, 2009
14,003
3,361
136
@ TheELf

That is just not true. BF4 is running MUCH better on 4 threaded CPUs (i3 and 2M Athlons included) Vs Celerons and intel pentium crap (pardon the expression).


Dont tell him that, he things the dual core Celerons are superior to any AMD Quad.


A10-5800K with only the iGPU and 1866MHz memory on Win 8.1 64bit.
This is on 48 player MT map and not single player.




 

cbn

Lifer
Mar 27, 2009
12,968
221
106
If by perfectly fine you consider the stutter fest that is produced then sure .

It runs great on my Pentium G3258 and R7 250X using Mantle. ( I haven't used it much with DX11 to comment).

However, when I replace my R7 250X with a 660 GTX the game isn't smooth anymore at the same detail settings (despite 660 GTX being more powerful than R7 250X). I'm still wondering if it is a driver issue or something else? However, It seems that all the BF4 G3258 complaints seem to come from Nvidia users so I am thinking my experience might actually be normal.
 

TheELF

Diamond Member
Dec 22, 2012
3,993
744
126
A10-5800K with only the iGPU and 1866MHz memory on Win 8.1 64bit.
This is on 48 player MT map and not single player.

All four cores on the same level and none is reaching 100% ,read up on thread migration.
And better yet show us a picture with actual threads, showing that it runs with more than 2 threads being demanding.
 

PG

Diamond Member
Oct 25, 1999
3,426
44
91
BF4 is a 2 threaded game* + driver thread (which disappears when running mantle leaving the resources to be split between the two main threads) but shhh don't tell anyone.

Then explain the gap in performance between a Phenom II quad and a Phenom II hex.
There is also a good sized gap between a 2500k and 2600k.

Per sweclockers:

http://www.sweclockers.com/image/diagram/2506?k=142b45af179c625ccd8f53fea7385155



And this was only BF3, BF4 should be better in terms of being multithreaded.
Note this is multiplayer. Single player benchmarks won't show this.
 
Last edited:

mindbomb

Senior member
May 30, 2013
363
0
0
bf4 mantle scales up to 6 cores, while bf4 dx11.1 scales to 4. Maybe mantle does more, but I'm too gpu bottlenecked.
 

TheELF

Diamond Member
Dec 22, 2012
3,993
744
126
Then explain the gap in performance between a Phenom II quad and a Phenom II hex.
You explain to me why battlefield 4 only has two threads maxed!
Aten-ras picture supports this also,2 cores at max is 50% of the cpu + the graphics driver and whatever else is running and you get the ~80% usage of a quad core that he is showing.
 

AtenRa

Lifer
Feb 2, 2009
14,003
3,361
136
You explain to me why battlefield 4 only has two threads maxed!
Aten-ras picture supports this also,2 cores at max is 50% of the cpu + the graphics driver and whatever else is running and you get the ~80% usage of a quad core that he is showing.

BF4 doesnt use only 2 threads, get your facts straight.

 

inf64

Diamond Member
Mar 11, 2011
3,764
4,223
136
It's similar for me also. I have 750K@4.2Ghz with 6870 Radeon and my CPU usage is ~80-100% and my GPU usage is ~95-100%. Out of the total CPU usage BF4 takes around 3/4 so varying from 60 to 80% depending on the map and player count.
 

TheELF

Diamond Member
Dec 22, 2012
3,993
744
126
64 player map, A10-5800K with the iGPU only. Cat 14.12 win 8.1 64bit
You're halfway there, doubleclick on bf4.exe and go to the threads tab.
Already one can see ~60% usage for bf4 with 20% system idle,20% cpu power that gets wasted on "too many" cores.
 
sale-70-410-exam    | Exam-200-125-pdf    | we-sale-70-410-exam    | hot-sale-70-410-exam    | Latest-exam-700-603-Dumps    | Dumps-98-363-exams-date    | Certs-200-125-date    | Dumps-300-075-exams-date    | hot-sale-book-C8010-726-book    | Hot-Sale-200-310-Exam    | Exam-Description-200-310-dumps?    | hot-sale-book-200-125-book    | Latest-Updated-300-209-Exam    | Dumps-210-260-exams-date    | Download-200-125-Exam-PDF    | Exam-Description-300-101-dumps    | Certs-300-101-date    | Hot-Sale-300-075-Exam    | Latest-exam-200-125-Dumps    | Exam-Description-200-125-dumps    | Latest-Updated-300-075-Exam    | hot-sale-book-210-260-book    | Dumps-200-901-exams-date    | Certs-200-901-date    | Latest-exam-1Z0-062-Dumps    | Hot-Sale-1Z0-062-Exam    | Certs-CSSLP-date    | 100%-Pass-70-383-Exams    | Latest-JN0-360-real-exam-questions    | 100%-Pass-4A0-100-Real-Exam-Questions    | Dumps-300-135-exams-date    | Passed-200-105-Tech-Exams    | Latest-Updated-200-310-Exam    | Download-300-070-Exam-PDF    | Hot-Sale-JN0-360-Exam    | 100%-Pass-JN0-360-Exams    | 100%-Pass-JN0-360-Real-Exam-Questions    | Dumps-JN0-360-exams-date    | Exam-Description-1Z0-876-dumps    | Latest-exam-1Z0-876-Dumps    | Dumps-HPE0-Y53-exams-date    | 2017-Latest-HPE0-Y53-Exam    | 100%-Pass-HPE0-Y53-Real-Exam-Questions    | Pass-4A0-100-Exam    | Latest-4A0-100-Questions    | Dumps-98-365-exams-date    | 2017-Latest-98-365-Exam    | 100%-Pass-VCS-254-Exams    | 2017-Latest-VCS-273-Exam    | Dumps-200-355-exams-date    | 2017-Latest-300-320-Exam    | Pass-300-101-Exam    | 100%-Pass-300-115-Exams    |
http://www.portvapes.co.uk/    | http://www.portvapes.co.uk/    |