Overclock.net - Overclocking.net
     
 
Home Gallery Reviews Blogs Register Today's Posts Mark Forums Read Members List


Go Back   Overclock.net - Overclocking.net > Graphics Cards > Graphics Cards - General

Reply
 
LinkBack Thread Tools
Old 11-11-07   #1 (permalink)
4.4GHz
 
Ihatethedukes's Avatar
 
intel nvidia

Join Date: Oct 2006
Posts: 3,548

Rep: 271 Ihatethedukes is a proven memberIhatethedukes is a proven memberIhatethedukes is a proven member
Unique Rep: 202
Hardware Reviews: 1
Trader Rating: 7
Default Bottlenecks Re-examined: Lightmark an OpenGL Benchmark

Purpose:
Bottlenecks are the point at which one factor of a system slows down the rest. A similar concept is the 'rate limiting' step in chemical reaction chains. In computers, specifically gaming, they appear frequently. Despite their common occurrence, the general populace seem to have little or no knowledge of how exactly they work and effect system performance. As such, bottlenecks are important to study and characterize more clearly so that a firm grasp might be obtained by all and will be reflected in their choice of hardware.

Experiment:
The experiment was run on the new Lightmark graphics bench mark with an eVGA 8800GTX at 650/1800 clocks, a Q6600 processor at 3.0Ghz and DDR2 ram at 1000MHz and 5-5-5-12 timings. This was all on a DFI Infinity 975X/G motherboard.

The procedure was to set all quality fields in the drivers to the highest setting (meaning highest quality) and then take two sets of data points. One set of data points would be collected in a progressive series of benchmark runs of standard 4:3 resolutions from 640x480 through 1600x1200 at 0xAA/0xANISO. The second set would be collected in the same resolutions, except at 16xQ CSAA/16x ANISO, also set in the drivers.

Results:
Res ******FPS 0x/0x****FPS 16x/16x
640x480*****257.3********208.3
800x600*****248.3********190
1024x768*****239.7*******172
1280x1024****235.3*******123.5
1600x1200****219.5*******91.3

Analysis:
The % pixel increase over the baseline (640x480) curve, you can clearly see that it increases exponentially. Since graphical output (FPS) of a given card working as fast as it can is inversely related to the graphical load, you can see that the graphical output will be decreasing exponentially. The CPU load is not as dependent on the raw pixel load, as the GPU was made specifically to do that job. However, it still will receive a SMALL amount of extra load as it must direct process and direct more information to the GPU for graphical processing. From this we can conclude that the CPUs exponential curve will be significantly shallower than the GPUs. This situation is ripe for what are considered bottlenecks. At the lower resolution the graphical load will be light allowing the GPU to output extremly high FPS. The CPU's load will lighten, but very little, allowing it to only output a few more FPS. Since the machine can only output as many FPS as the SLOWEST COMPONENT of the system you'll have what is called a bottleneck, since the CPU will not be able to output as many FPS as the GPU. The observed FPS output of the system will therefore be only as much as the CPU can output.



In the first graph, there is an extremely high amount of agreement between the exponential trendlines of the data sets and the actual data set, this is shown by the 0x/0x data set being nearly perfect with an R value of ~1. The single curve shown is consistent with a CPU bottleneck as there is no obvious intersection of outputs where a steeper graphical output would overtake the CPU curve as the resolution increased. There is to be noted that at the 1600x1200 resolution 0/0 value is less in agreement with the exponential curve than the rest of the data points in the set, but only slightly. With that result truncated from the data set the R value increases further to ~0.99 for the exponential trendline, indicating better accuracy. This could be caused by the GPU just beginning to intersect and become the limiting component. Another test at a higher resolution would show with more certainty but there was no monitor of that resolution to test on.

The 16x/16x has a very high R value indicating accuracy, however, its R value is significantly lower. Upon closer visual inspection, there is clearly the expected intersection between the CPU output curve and the GPU output curve at 1024x768 resolution. At 1280x1024 and 1600x1200 there is an obviously steeper rate of FPS decline than at 1024x756 or lower resolution. To test to see if this is not an anomaly I made two separate curves of the single 16x/16x data set. One of 640x480 through 1024x756 and another of 1024x756 through 1600x1200.



The shallow, low resolution curve is clearly very close to the same curve as the fully CPU bound 0x/0x curve indicating that it is indeed a CPU bound section of the 16x/16x data set. It should be noted that the curve IS placed approximately 50FPS lower than its CPU bound homolog 0x/0x indicating that either AA or ANISO DOES have a negative impact upon CPU output.



The second, steeper curve created from the 16x/16x data set needs to be shown that it is actually GPU bound, and not a mysterious depression of CPU output. This will be done by comparing the observed data points to the theoretical values predicted. Because there are only two points of this curve that are unequivocally decreasing more steeply, analysis will be done on them, the 1280x1024 and 1600x1200 resolutions.

Theoretically, 1600x1200 resolution is approximately a 46% heavier pixel load upon the GPU than 1280x1024. From that, we can figure that the system output, if GPU bound would be relatively close to this value. Taking the 1280 res point and dividing it by the 1600 data point (as it's inversely proportional to load) we should see a ~46% difference. We see about ~39% decrease in performance, clearly supporting the claim that it is a largely GPU bound result!

Conclusions:

It has become clear that both the CPU and GPU curves are exponentially decreasing under exponentially increasing graphical load. It has also been clarified that the GPU curve is steeper, beginning at a much higher FPS but sloping down quickly and finishing at a much lower FPS than the CPU. It is upon this common mechanism that virtually all bottlenecking occurs. To those who fear bottlenecking so much, there is such a thing as a GPU bottleneck as well. The only way to avoid this, is to ride that inflection just between being CPU bound and GPU bound. This can be adjusted by increasing graphical load by adding detail. But with this particular application and hardware, it's at 1024x756 res 16xAA/16x ANISO or, as best as we can tell, at 1600x1200 res 0xAA/0xANISO. Here is a hastily thrown together graph of how the GPU/CPU curves intersect.



It is also well to keep in mind that your LCD monitor, should it go over the venerable 1280x1024 resolution only has a 60FPS refresh rate. Meaning, your monitor is REALLY bottlenecking all performance above 60FPS REGARDLESS of graphical load or CPU/GPU balancing.
Attached Thumbnails
bottlenecks-re-examined-lightmark-opengl-benchmark-bench1.jpg  bottlenecks-re-examined-lightmark-opengl-benchmark-bench2.jpg  bottlenecks-re-examined-lightmark-opengl-benchmark-bench3.jpg  bottlenecks-re-examined-lightmark-opengl-benchmark-bench4.jpg  
__________________

[23:30] skertso: peons just don't get it done
98% of the internet population has a Myspace. If you're part of the 2% that isn't an emo bastard, copy and paste this into your sig.

System: My System
CPU
Core 2 Duo E8400
Motherboard
DFI Lanparty X48
Memory
4x2gig G Skill DDR1000
Graphics Card
HD4870XT 790/1100
Hard Drive
2x300GB Seagates
Power Supply
Tagan ITZ 800W
Case
DD Torture Rack
CPU cooling
TDX
GPU cooling
stock
OS
64 bit Vista
Monitor
Samsung 245BW+Samsung 204B
Ihatethedukes is offline Overclocked Account   Reply With Quote
Old 11-11-07   #2 (permalink)
Overclocker
 
1337guy's Avatar
 
intel nvidia

Join Date: Aug 2007
Location: *Cape Town* FTW!
Posts: 588

Rep: 42 1337guy is acknowledged by some
Unique Rep: 37
Trader Rating: 0
Default

good read!
__________________
ß₤ứə Çřёώ We Are Gr33n Machine
I WANT TO FOLD FOR OCN BUT MY CELERY JUST AINT CUTTING IT!

System: 2 suxx0r 2 fold 4 teh cure :'(
CPU
prescott celery D @ 3.20ghz
Memory
1GB-DDR400
Graphics Card
6600GT stock @ 500/900
Hard Drive
80gig hitachi deskstar-123MB/s burst-51MB/s avg read
Sound Card
onboard
Power Supply
500W AOpen
CPU cooling
Stock
GPU cooling
Stock
OS
XP Pro SP3 32bit
Monitor
17' crt 1280x1024
1337guy is online now 1337guy's Gallery   Reply With Quote
Old 11-11-07   #3 (permalink)
New to Overclock.net
 
shinyboy's Avatar
 
intel nvidia

Join Date: Sep 2007
Posts: 591

Rep: 20 shinyboy is acknowledged by some
Unique Rep: 19
Trader Rating: 0
Default

Nicely done. Excellent addition to your other bottlenecking article.

you must really like that song
__________________
System: My System
CPU
Q6600 G0 3.42
Motherboard
GA-P35-DS3R
Memory
4GB(1gbX4) Crucial Ballistix 918mhz 4-4-4-12 2.2v
Graphics Card
8800gts 512 (800/1944/1100)
Hard Drive
Western Digital Caviar AAKS 320GB
Power Supply
Corsair HX620
Case
Antec Nine Hundred
CPU cooling
Thermalright Ultra 120 Extreme with 80cfm fan
OS
Vista64 Home Premium
Monitor
24" Acer X241W
shinyboy is offline   Reply With Quote
Old 11-11-07   #4 (permalink)
4.4GHz
 
Ihatethedukes's Avatar
 
intel nvidia

Join Date: Oct 2006
Posts: 3,548

Rep: 271 Ihatethedukes is a proven memberIhatethedukes is a proven memberIhatethedukes is a proven member
Unique Rep: 202
Hardware Reviews: 1
Trader Rating: 7
Default

Mute works wonders.
__________________

[23:30] skertso: peons just don't get it done
98% of the internet population has a Myspace. If you're part of the 2% that isn't an emo bastard, copy and paste this into your sig.

System: My System
CPU
Core 2 Duo E8400
Motherboard
DFI Lanparty X48
Memory
4x2gig G Skill DDR1000
Graphics Card
HD4870XT 790/1100
Hard Drive
2x300GB Seagates
Power Supply
Tagan ITZ 800W
Case
DD Torture Rack
CPU cooling
TDX
GPU cooling
stock
OS
64 bit Vista
Monitor
Samsung 245BW+Samsung 204B
Ihatethedukes is offline Overclocked Account   Reply With Quote
Old 11-11-07   #5 (permalink)
AMD Overclocker
 
Z_Vengeance's Avatar
 
amd nvidia

Join Date: Mar 2007
Location: University of Michigan
Posts: 573

Rep: 56 Z_Vengeance is acknowledged by some
Unique Rep: 48
Folding Team Rank: 193
Trader Rating: 2
Default

Wow, just wow. Well done, incredibly professional Rep +
__________________
Just started folding for 37726...Finally and excuse to leave the PC on.

System: t3hservbox
CPU
X2 3600+ Brisbane 2.94 Ghz
Motherboard
Gigabyte GA-M59SLI-S5
Memory
2x2Gb G.Skill DDR2 1000
Graphics Card
XFX 8800GT 512mb
Hard Drive
790Gb on 3Hds
Sound Card
Creative Sound Blaster Live!
Power Supply
PC Power and Cooling Silencer 750
Case
Apevia X-Navigator
CPU cooling
ZALMAN CNPS 9500 AM2
GPU cooling
Stock
OS
Windows Vista Business 64bit
Z_Vengeance is offline I fold for Overclock.net   Reply With Quote
Old 11-11-07   #6 (permalink)
RAM Fan
 
rottenotto's Avatar
 
intel ati

Join Date: Apr 2006
Location: Raleigh, NC area
Posts: 2,307

Rep: 170 rottenotto is acknowledged by manyrottenotto is acknowledged by many
Unique Rep: 141
Trader Rating: 0
Default

This is yourwork?

System: My System
CPU
Intel E6600 (LL629A)
Motherboard
DFI BLOOD IRON P35-T2RL
Memory
GSkill ( 2x1G) DDR2-800 HZ's
Graphics Card
Diamond HD3870
Sound Card
Turtle Beach Riviera
Case
XG VIPER ( hey, it was free.)
CPU cooling
Tuniq w/SS121
OS
Windows XP Home (OEM)
Monitor
Sceptre 22" + Sceptre 20"
rottenotto is offline   Reply With Quote
Old 11-11-07   #7 (permalink)
4.4GHz
 
Ihatethedukes's Avatar
 
intel nvidia

Join Date: Oct 2006
Posts: 3,548

Rep: 271 Ihatethedukes is a proven memberIhatethedukes is a proven memberIhatethedukes is a proven member
Unique Rep: 202
Hardware Reviews: 1
Trader Rating: 7
Default

Yes, it's MY work. I am a Ph. D. student after all. Doing things like this is my profession.
__________________

[23:30] skertso: peons just don't get it done
98% of the internet population has a Myspace. If you're part of the 2% that isn't an emo bastard, copy and paste this into your sig.

System: My System
CPU
Core 2 Duo E8400
Motherboard
DFI Lanparty X48
Memory
4x2gig G Skill DDR1000
Graphics Card
HD4870XT 790/1100
Hard Drive
2x300GB Seagates
Power Supply
Tagan ITZ 800W
Case
DD Torture Rack
CPU cooling
TDX
GPU cooling
stock
OS
64 bit Vista
Monitor
Samsung 245BW+Samsung 204B
Ihatethedukes is offline Overclocked Account   Reply With Quote
Old 11-11-07   #8 (permalink)
sk8 d1tches!
 
s1rrah's Avatar
 
intel nvidia

Join Date: Oct 2006
Location: houston, tx
Posts: 2,935

Rep: 475 s1rrah is a proven members1rrah is a proven members1rrah is a proven members1rrah is a proven members1rrah is a proven member
Unique Rep: 291
Trader Rating: 9
Default

To quote quagmire: "Heh, heh ... Awww Riiight!"

...

__________________
...
ReV1eWs:
ND-1 VGA Cooler | Mod'd Scythe Infinity | Iceberq 6 VGA Cooler | Spirit RS RAM cooler | Zalman 9500 on NOS | MagicTune
...
Aumotocnic: "An unfortunate member of the overclock.net insomnia club"
...
OSAMT: "Member of OCN Songwriter and Musician Thread"
...

System: The Maker(tm)
CPU
Q6700 @ 3.8ghz
Motherboard
Asus Maximus Formula
Memory
2gig Corsair 1066mhz @ 1143mhz
Graphics Card
EVGA 8800GT SC
Hard Drive
2 x 500gig WD SATAII
Sound Card
Auzentech Prelude 7.1
Power Supply
TT PurePower 500 Watt
Case
TT Armor w/ 250mm fan
CPU cooling
T.R.U.E. (lapped)
GPU cooling
TT ND-1
OS
XP Home
Monitor
Samsung 226BW
s1rrah is online now Overclocked Account   Reply With Quote
Old 11-11-07   #9 (permalink)
RAM Fan
 
rottenotto's Avatar
 
intel ati

Join Date: Apr 2006
Location: Raleigh, NC area
Posts: 2,307

Rep: 170 rottenotto is acknowledged by manyrottenotto is acknowledged by many
Unique Rep: 141
Trader Rating: 0
Default

Quote:
Originally Posted by Ihatethedukes View Post
Doing things like this is my profession.
LOL- well, it shows........ Nice work, but as you point out, the real bottleneck is probably the monitor. Doesn't exactly make the point moot, but in real terms, this isn't really a problem for 99% of the gaming world, is it?

System: My System
CPU
Intel E6600 (LL629A)
Motherboard
DFI BLOOD IRON P35-T2RL
Memory
GSkill ( 2x1G) DDR2-800 HZ's
Graphics Card
Diamond HD3870
Sound Card
Turtle Beach Riviera
Case
XG VIPER ( hey, it was free.)
CPU cooling
Tuniq w/SS121
OS
Windows XP Home (OEM)
Monitor
Sceptre 22" + Sceptre 20"
rottenotto is offline   Reply With Quote
Old 11-11-07   #10 (permalink)
4.4GHz
 
Ihatethedukes's Avatar
 
intel nvidia

Join Date: Oct 2006
Posts: 3,548

Rep: 271 Ihatethedukes is a proven memberIhatethedukes is a proven memberIhatethedukes is a proven member
Unique Rep: 202
Hardware Reviews: 1
Trader Rating: 7
Default

I've been pointing out the monitor for some time. However that's really just a side point. This was mainly to show people exactly where the bottlenecking point REALLY is in a high end rig sans monitor. Much lower than they thought. This was to quash the stupid rumor that a 3.0GHz AMD would 'really bottleneck a GTS"... which is a load of rubbish. An overclocked GTX can only outpace a lowly 3.0Ghz Intel through 1024x756 resolution at high eye candy like anyone with a high end rig would play. ...Even less with a higher clocked CPU. With a 3.5Ghz Intel, the GTX could only keep up through ~800x600 res!
__________________

[23:30] skertso: peons just don't get it done
98% of the internet population has a Myspace. If you're part of the 2% that isn't an emo bastard, copy and paste this into your sig.

System: My System
CPU
Core 2 Duo E8400
Motherboard
DFI Lanparty X48
Memory
4x2gig G Skill DDR1000
Graphics Card
HD4870XT 790/1100
Hard Drive
2x300GB Seagates
Power Supply
Tagan ITZ 800W
Case
DD Torture Rack
CPU cooling
TDX
GPU cooling
stock
OS
64 bit Vista
Monitor
Samsung 245BW+Samsung 204B
Ihatethedukes is offline Overclocked Account   Reply With Quote
Reply



Currently Active Users Viewing This Thread: 1 (0 members and 1 guests)
 
Thread Tools



All times are GMT -4. The time now is 04:05 PM.


Overclock.net is a Carbon Neutral Site Creative Commons License Internet Security By ControlScan

Terms of Service / Forum Rules | Privacy Policy | Advertising | Become an Official Vendor
Copyright © 2008 Shogun Interactive Development. Most rights reserved.
Page generated in 0.28003 seconds with 10 queries