Contribute
Register

OS X 10.8.3 and NVIDIA 6xx OpenCL Benchmarks

Joined
Dec 3, 2011
Messages
16
Motherboard
X79-UP4
CPU
i7 3930k
Graphics
GTX 690
Mac
Classic Mac
Mobile Phone
  1. iOS
Article: OS X 10.8.3 and NVIDIA 6xx OpenCL Benchmarks

I am running a GTX670 but everything that I have read says that 5xx series is the way to go over the 6xx. The AMD 7970 seems to almost double it's score. Not sure what the move is here, I'm probably going to wait until the mac pros are released as those cards are going to be optimized for FCPX (and hopefully the adobe suites).

I guess the question to mac man is. If you do photo/video editing can you give us a definitive answer on what card to get within the $350-$550 range; just to put the issue to bed.

I'm not the macman but I had an EVGA GTX 580 Classified Hydro Copper before my current GTX 690 which is exactly two GTX 680s on one PCB. Compute performance supposedly dropped from Fermi to Kepler in order to focus on gaming performance and low power consumption. I haven't noticed much of a difference personally but I really only use the compute performance heavily for Folding. If you are looking for a sweet spot in regards to price I wonder if the Radeon HD 5870 would be a best-value option. Before the GTX 580 Classified Hydro Copper I had a Gigabyte HD 5870 which was the card Apple sold to go with their Mac Pros (but I had a regular Gigabyte model and not the Apple model since it's a fraction the price). They are around $100-150 used on eBay and I think they are the best compute vs price cards on the market. I sold it to a guy who has a dozen HD 5870s he uses for his bitcoin farm. I'm willing to bet 3 HD 5870s would be cheaper than a 580 or 680 and would probably be higher in the compute category and they work right out of the box in OS X.
 
Joined
Nov 28, 2011
Messages
23
Mac
Classic Mac
Mobile Phone
Article: OS X 10.8.3 and NVIDIA 6xx OpenCL Benchmarks

todays test with 7950:
luxmark.png


and gtx680
gtx680_luxmark.png


both on stock 10.8.3 kexts
 
Joined
Jan 14, 2010
Messages
369
Motherboard
Aorus X570 Elite
CPU
Ryzen 7 3700X
Graphics
Vega 64
Mac
  1. iMac
Classic Mac
  1. Apple
  2. eMac
  3. iMac
  4. LC
  5. Power Mac
Mobile Phone
  1. iOS
Article: OS X 10.8.3 and NVIDIA 6xx OpenCL Benchmarks

todays test with 7950:
1757

and gtx680
794

both on stock 10.8.3 kexts

I am confident thatApple/nVidia will remedy the issue of poor OpenCl performance; My old 5770HD eats my GTX 660 Ti SC for breakfast in regards to OpenCl performance. Not only does all of the current Mac models use nVidia exclusively, but the release of the QK5000 and GTX 680 Mac editions would lead me to believe that a fix is around the corner.
 
Joined
Jun 24, 2012
Messages
7
Motherboard
ASUS MAXIMUS HERO Vll Z97
CPU
i7-4790K OC @ 4,5GHz
Graphics
R9 290
Mac
  1. MacBook Air
  2. Mac Pro
Classic Mac
  1. Portable
Mobile Phone
  1. Android
  2. iOS
asus sabertooth z77 + ati 7970 vapor x score 1970
 

Attachments

  • Capture d’écran 2013-04-21 à 16.41.46.jpg
    Capture d’écran 2013-04-21 à 16.41.46.jpg
    199.9 KB · Views: 162
Joined
Apr 19, 2013
Messages
6
Motherboard
Z77-DS3H
CPU
Xeon 1230v2 4 cores
Graphics
Gigabyte 660Ti
Mac
  1. MacBook Pro
Classic Mac
Mobile Phone
  1. Other
those explanation of poor performance in 10.8.3 doesn't explain how it was possible to reach high performance on 10.8.2! ok, luxmark was wrong about graphics card, but somehow showed good performance! Don't you find this is strange?
My Gigabyte 660ti shows 670 in 10.8.3
 

Obvious Answer Man

Super Moderator
Joined
Jan 12, 2010
Messages
1,408
Article: OS X 10.8.3 and NVIDIA 6xx OpenCL Benchmarks

those explanation of poor performance in 10.8.3 doesn't explain how it was possible to reach high performance on 10.8.2! ok, luxmark was wrong about graphics card, but somehow showed good performance! Don't you find this is strange?
My Gigabyte 660ti shows 670 in 10.8.3
What high performance in 10.8.2?

If you read the article correctly, the only score that changed between 10.8.2 and 10.8.3 was LuxMark due to broken OpenCL drivers in 10.8.2
 
Joined
Apr 19, 2013
Messages
6
Motherboard
Z77-DS3H
CPU
Xeon 1230v2 4 cores
Graphics
Gigabyte 660Ti
Mac
  1. MacBook Pro
Classic Mac
Mobile Phone
  1. Other
Article: OS X 10.8.3 and NVIDIA 6xx OpenCL Benchmarks

What high performance in 10.8.2?

If you read the article correctly, the only score that changed between 10.8.2 and 10.8.3 was LuxMark due to broken OpenCL drivers in 10.8.2

So, with broken video drivers LuxMark showed better performance? Isn't it funny?
It DID show higher performance!

No matter that in 10.8.3 it now correctly detects calculations units count - in 10.8.2 LuxMark was able to do faster calculations (please tell me how it was possible by your theory)!

What I want to say, is that in 10.8.3 something wrong with drivers/luxmark even they shows correct units count now.
 

MacMan

Administrator
Staff member
Joined
Feb 2, 2010
Messages
8,637
Motherboard
ASUS TUF Z390-PRO GAMING - 2606 - UEFI
CPU
i9-9900K
Graphics
Vega 64
Mac
  1. MacBook Pro
  2. Mac Pro
Classic Mac
  1. Power Mac
  2. PowerBook
Mobile Phone
  1. iOS
Article: OS X 10.8.3 and NVIDIA 6xx OpenCL Benchmarks

So, with broken video drivers LuxMark showed better performance? Isn't it funny?
It DID show higher performance!

No matter that in 10.8.3 it now correctly detects calculations units count - in 10.8.2 LuxMark was able to do faster calculations (please tell me how it was possible by your theory)!

What I want to say, is that in 10.8.3 something wrong with drivers/luxmark even they shows correct units count now.
If you followed the links in the article you would have read that Kepler cards are WORSE at OpenCL than Fermi cards due to the architecture change. So if you want the best OpenCL performance then get a Fermi card or an AMD 7xxx card.
 
Joined
Apr 19, 2013
Messages
6
Motherboard
Z77-DS3H
CPU
Xeon 1230v2 4 cores
Graphics
Gigabyte 660Ti
Mac
  1. MacBook Pro
Classic Mac
Mobile Phone
  1. Other
Article: OS X 10.8.3 and NVIDIA 6xx OpenCL Benchmarks

If you followed the links in the article you would have read that Kepler cards are WORSE at OpenCL than Fermi cards due to the architecture change. So if you want the best OpenCL performance then get a Fermi card or an AMD 7xxx card.
I agree with this fact (fermi - kepler), but not agree with arguments exposed in the article about drivers in 10.8.2 and 3.
How can bad drivers in 8.2 increase performance in bench?
 
Top