AMD ULPS Is Killing Multi GPU Performance & Smoothness

[Doco]

Thanks tommy, I'l have a look at that, might give it a go and yeh Ive read through the boost bios page just not sure if it'l be worth it. My main card is in the top slot (1200/1425, lazy on the memory clock but solid on the core), as for the new card it could be just a bad clocker, does happen, but I'd like to see it more POWER! will help stabilise it lol

 

[LtMatt]

Been running higher power limits since I found out how to apply it due to the boost bios being a pile of ****, if you don't want to flash your bios, you can hack the power limit and it will keep your clocks from spiking, which can give quite a hit to fps, details here:

http://forums.overclockers.co.uk/showthread.php?p=24212468#post24212468

It's very simple, I was just thorough with the instructions.

It's maybe just a lazy card though as the voltage is 1.25 in the first place.

Bios flashing is where it's at, there is an Ice-Q tbios thread here somewhere, maybe somebody can put up the link.

Btw, put your better gpu in the top slot for better performance in non CrossFire titles-if you play any.

Tommy if you use one of the custom bios created by Kaboom then +20% seems sufficient. However if you stick with the boost bios then 30% is needed i find.

 

[tommybhoy]

Your probably right matt, I just like the big numbers and being different.

 

[LtMatt]

I reckon if your cards are at stock clocks then the impact of ULPS performance hit is smaller. However if you overclock the performance hit of ULPS is massive. Tommy or anyone else would be good to see some stock comparisons.

7950's @1100/1500 ULPS off with frame pacing

Spoiler

7950's @1100/1500 ULPS on with frame pacing

Spoiler

Not entirely sure what clock or gpu usage i was getting from the second gpu with ULPS on as gpu 2 monitoring is unavailable with it enabled. I also overclock my DDR3 via BLK so im not sure if that has an effect on my performance with ULPS on as it does cause some problems with sleep mode ive noticed.

 

[imginy]

I reckon if your cards are at stock clocks then the impact of ULPS performance hit is smaller. However if you overclock the performance hit of ULPS is massive. Tommy or anyone else would be good to see some stock comparisons.

7950's @1100/1500 ULPS off with frame pacing

Spoiler

7950's @1100/1500 ULPS on with frame pacing

Spoiler

Not entirely sure what clock or gpu usage i was getting from the second gpu with ULPS on as gpu 2 monitoring is unavailable with it enabled. I also overclock my DDR3 via BLK so im not sure if that has an effect on my performance with ULPS on as it does cause some problems with sleep mode ive noticed.

Massive difference there

 

[alex_123_fra]

I haven't formally benched these but my Alienware M18x with dual 6990s in x-fire is certainly silky smooth with ULPS disabled. No stuttering at all. Confirmed consistent usage of both cards on MSI afterburner.

Love this. Can't believe I have put up with 1.5 years of less smooth gaming before I made this change.

 

[tommybhoy]

I reckon if your cards are at stock clocks then the impact of ULPS performance hit is smaller. However if you overclock the performance hit of ULPS is massive. Tommy or anyone else would be good to see some stock comparisons.

Here you go bud-

[email protected] 7950 Stock Boost clocks-CrossFire@925/1250/+20%(modded non boost bios).

Spoiler

SD(Max everything this time, my previous BM's had motion blur disabled):

+~4% average/+~3% max/+~19% minimum difference!

The minimum this time is massive, definitely disable ulps in the most demanding titles anyway for maximum performance with CrossFire.

Any 78 series CrossFire users able to check the ulps performance hit to see if it's across the board with the 7 series?

***NOTE-I have an anomaly with AB, gpu1 is showing as gpu2 on the OSD and vice versa(IDK why, but just in case there is any queries about weird gpu usage)***

 

[tommybhoy]

[email protected] 7950 CrossFire@1200/1500/+20%(modded non boost bios)-Ulps Enabled.

Spoiler

+~29% average/+~15% max/+~30% minimum difference!


Which leads me to the OC'ing gains, with stock 7950-Boost clocks-CrossFire@925/1250/+20% Ulps Enabled, v's 7950 CrossFire@1200/1500 OC Ulps Disabled, the 7950's Oc scaling in SD is:

+25% average/+~21% max/+~30% minimum.

Superb OC'ing scaling and performance for ~£400 all in.

Matt, any chance you can do a comparison with my 1200/1500 Ulps Disabled for comparison to see how our rigs are comparing?

 

[LtMatt]

Can do Tommy. I couldn't complete the benchmark with ULPS on as it crashed, likely because the other gpu was stuck at stock voltage of the bios im using which is 1.175v. However with ULPS i did manage to bench safely as i could change the voltage of both cards.

CPU @4.7
2133mhz DDR3

My minimum is a bit higher and my average slightly lower. I wonder if my minimum is higher as im using some rather tight timings on my DDR3? I guess my average is lower though because im pci-e 2 8x8 vs your pci-e 3.

Spoiler

 

[tommybhoy]

Cheers matt, good to know it's similar performance, maybe extra processes holding me back a touch or the memory timings like you say.

Never oc'd ram before, wouldn't know where to start tbh as I never thought ram clocking brought much to the table anyway, but in this case it might.

I vote you contact an anand guru and tell him to get on the case to Amd about the ulps performance hit, you could go down in history as the guy who pointed it out, but if Amd send you 2 9970's as thanks, ones for me.

 

[LtMatt]

Cheers matt, good to know it's similar performance, maybe extra processes holding me back a touch or the memory timings like you say.

Never oc'd ram before, wouldn't know where to start tbh as I never thought ram clocking brought much to the table anyway, but in this case it might.

I vote you contact an anand guru and tell him to get on the case to Amd about the ulps performance hit, you could go down in history as the guy who pointed it out, but if Amd send you 2 9970's as thanks, ones for me.

It might not be the ram that was just a guess. Is your ram at the same speed? I tweaked the secondary timings a little after looking at one of 8packs posts, not sure how much if any difference it made though.

I don't have a twitter account so i asked Abundant Cores (Humbug) to pass it onto AMD Roy & Thracks and he did.

It would be nice to see ULPS on/off available as a feature in CCC. I'm convinced it will bring extra fps and lower frame times as well. Hopefully a review site will pick up on it and do some official testing with it on and off.

Another thing id like to see added to CCC would be the option to change flip queue size. The default setting of 3 can produce some rather unsavory input lag in twitch shooters. Nvidia users have the option to tweak it so we should as well. Of course it can be done easily in RP, but still having the option to do it in CCC would be nice.

 

[tommybhoy]

Yes my ram runs that out the box, dk if it clocks further or not, I imagine it will though as the price/marketing blurb makes it look as if it will.

Definate disable option needed now for the masses too, would be easier but not a biggie for me as AB is simple enough and asks to reboot when you press apply it would probably be the sa.e amount of key presses going through CCC.

Never used the flip queue size yet, but I'm not the sharpest mut on the block by far anyway with twitch shooters anyway, I need a tank or I'm cannon fodder in bf3.

Tell humbug to request 3 9970's then.