• Competitor rules

    Please remember that any mention of competitors, hinting at competitors or offering to provide details of competitors will result in an account suspension. The full rules can be found under the 'Terms and Rules' link in the bottom right corner of your screen. Just don't mention competitors in any way, shape or form and you'll be OK.

Better OpenCL support in NVIDIA's CUDA SDK

humbug said:
Anands bench there is very synthetic, its like using WIE or IBT to measure performance.
Toms Hardwear use real world applications, if you look through that its very much Titan in one and the 7970 in the other, depending on which application.
http://www.tomshardware.com/reviews/geforce-gtx-titan-opencl-cuda-workstation,3474-23.html

As for Tomb Raider

That's the £300 7970 Ghz faster than the £900 GTX Titan.

To match the GTX 680 all that is needed is a 7870.
Click to expand...

While our very own TR performance thread showed otherwise.

I'll happily bench my Titan (in single or dual card mode) at whatever settings you would care to provide (lets say 1080p upwards so we actually make the cards work). I can do any resolution up to 1600p.

As for the Toms test. NV have always had suspect OpenGL performance from their consumer cards in pro apps, anyone who can spend thousands on software will do the same with hardware, and Quadro/FireGL cards will both beat out consumer stuff.
 
Last edited:
layte said:
While our very own TR performance thread showed otherwise.

I'll happily bench my Titan (in single or dual card mode) at whatever settings you would care to provide (lets say 1080p upwards so we actually make the cards work). I can do any resolution up to 1600p.
Click to expand...

Does it? I did spent some time looking for a thread (I think is was LtMatt's Benchmark thread) where I posted a Tomb Raider result with my 7870 Tahiti LE @ 1200 Mhz that was only 10% behind someones GTX 780 @ about the same clocks.

Shame I couldn't find it.
 
Last edited:
Last edited:
That's an old benchmark result, things have changed a lot since then for both sides. A lot of benches tend to disable TressFX as well for some reason which always baffles me as its not like Physx where one side is locked out. All that does though is allow the Nvida cards (excluding the titan and to a lesser degree the 780) to score more fps.
 
Rusty0611 said:
I thought we were past posting cherry picked benchmarks to illustrate our (purposefully) fallacious points?
Click to expand...

:D

I wouldn't mind but that bench is so wrong. I will bench Tomb Raider when I get home at 10 and at 1080P and I bet I get more fps than what that is showing at 1050P
 
LtMatt said:
Yes i remember what he's talking about. Can't remember what thread it was in though sorry. It was very close to a 780 though few fps behind from memory.
Click to expand...

I think I will save your Thread, it would be nice to keep that updated.
 
humbug said:
Does it? I did spent some time looking for a thread (I think is was LtMatt's Benchmark thread) where I posted a Tomb Raider result with my 7870 Tahiti LE @ 1200 Mhz that was only 10% behind someones GTX 780 @ about the same clocks.

Shame I couldn't find it.
Click to expand...

I thought I'd do a quick test. I copied the res and settings from here:
tr.PNG
My results with identical settings:
tr%20titan.PNG
My Specs (SLI was disabled for the test):
spec.png

As you can see, a mildly overclocked Titan can beat a heavily overclocked 7970 at a title which AMD has every advantage in. So you can understand why I say Nvidia's OpenCL game performance is not quite the apocalypse you think it is.

Sorry for all the OT.
 
Last edited:
layte said:
I thought I'd do a quick test. I copied the res and settings from here:
tr.PNG
My results with identical settings:
tr%20titan.PNG
My Specs (SLI was disabled for the test):
spec.png

As you can see, a mildly overclocked Titan can beat a heavily overclocked 7970 at a title which AMD has every advantage in. So you can understand why I say Nvidia's OpenCL game performance is not quite the apocalypse you think it is.

Sorry for all the OT.
Click to expand...

Thanks for posting but why on earth are you comparing a £900 gpu vs a £300 gpu? (actually it was £270 after i sold the games)

I think all this does is emphasise what a kick ass card a clocked 7970 ghz is.
 
LtMatt said:
Thanks for posting but why on earth are you comparing a £900 gpu vs a £300 gpu? (actually it was £270 after i sold the games)

I think all this does is emphasise what a kick ass card a clocked 7970 ghz is.
Click to expand...

Because our fair and balanced (Fox news style) chum Humbug was under the mistaken impression that the card had 'junk' performance in OpenCL games processing. It didn't even come to a 'stuttering halt' either. :) TR has to be pretty much the current worst case scenario for NV cards as well.

Now back to our scheduled petty arguing and name calling. :D
 
layte said:
TR has to be pretty much the current worst case scenario for NV cards as well.

Now back to our scheduled petty arguing and name calling. :D
Click to expand...

No that's probably Hitman Resolution, closely followed Sleeping Dogs, Tomb Raider comes after that.

Regardless i don't think a 13% advantage on a card costing 200% less is anything to get excited about, with all due respect.
 
LtMatt said:
No that's probably Hitman Resolution, closely followed Sleeping Dogs, Tomb Raider comes after that.
Click to expand...
I'm game if you are :p

LtMatt said:
Regardless i don't think a 13% advantage on a card costing 200% less is anything to get excited about, with all due respect.
Click to expand...
I never said it was a like for like comparison. It was just a quick test for the benefit of Humbug to show that he was mistaken in his claims. If a title using compute developed with help from AMD can still run well (in some cases better) on the competitions hardware, then said hardware can hardly be considered to have bad performance.

Lets move on.
 
What has this forum come to really? More AMD charts in an nvidia thread.

Even my 670 scores higher in nearly all the games charts that review sites put out for the 670 but i don't post how biased sites are for not adding those 10fps to the charts.

Nobody would deny the 7970 is a good card, but so are the 680, 7950, Titan, 780 and 670, Don't even get me started on a mid range 7870, i am sure the Bang For The buck is probably the best there has been this generation but its still a fair bit slower in most games than the aforementioned cards which is why people pay more, to play games they want to play at the resolution and settings they want they buy what they want.

layte posted his titan at those settings after it was stated that a 7970 was faster than a titan. He proved that is not the case.
 
You must log in or register to reply here.
Back
Top Bottom