A computer components & hardware forum. HardwareBanter

If this is your first visit, be sure to check out the FAQ by clicking the link above. You may have to register before you can post: click the register link above to proceed. To start viewing messages, select the forum that you want to visit from the selection below.

Go Back   Home » HardwareBanter forum » Video Cards » Nvidia Videocards
Site Map Home Register Authors List Search Today's Posts Mark Forums Read Web Partners

Faster CUDA performance ??



 
 
Thread Tools Display Modes
  #1  
Old May 31st 10, 08:27 PM posted to alt.comp.periphs.videocards.nvidia
Smarty
external usenet poster
 
Posts: 94
Default Faster CUDA performance ??

I am using an nVidia GeForce 8800 GT video card purchased about 2 years
ago and have several programs which speed up rendering and filtering by
using the CUDA GPU.

I am wondering if a new video card would significantly improve my CUDA
performance? Since many of the rendering and filtering jobs I do take a
long time (several hours per job) on this Intel Extreme QX9650 quadcore
machine, I am trying to find a way to significantly shorten the renders
and filtering.

I have 1 PCIe X16 slot on this Dell XPS420 mainboard, so this may limit
my choices as to which, if any, nVidia card could be used as an update.

I very much appreciate any suggestions / comments.


  #2  
Old May 31st 10, 10:56 PM posted to alt.comp.periphs.videocards.nvidia
poky patrol
external usenet poster
 
Posts: 2
Default Faster CUDA performance ??

On Mon, 31 May 2010 19:27:27 +0000 (UTC), "Smarty"
wrote:

I am using an nVidia GeForce 8800 GT video card purchased about 2 years
ago and have several programs which speed up rendering and filtering by
using the CUDA GPU.

I am wondering if a new video card would significantly improve my CUDA
performance? Since many of the rendering and filtering jobs I do take a
long time (several hours per job) on this Intel Extreme QX9650 quadcore
machine, I am trying to find a way to significantly shorten the renders
and filtering.

I have 1 PCIe X16 slot on this Dell XPS420 mainboard, so this may limit
my choices as to which, if any, nVidia card could be used as an update.

I very much appreciate any suggestions / comments.


Yes, a new top of the line card will give you better performance for
sure but you are looking at spending over $500.00 to get it. If your
mb has SLI I would just put in a second 8800GT instead and that will
give you better performance for less cost. But that depends on if you
have a motherboard with dual PCI-E slots or not and if it supports
Nvidia SLI and not ATI Crossfire.
  #3  
Old May 31st 10, 11:06 PM posted to alt.comp.periphs.videocards.nvidia
Smarty
external usenet poster
 
Posts: 94
Default Faster CUDA performance ??

poky patrol wrote:

On Mon, 31 May 2010 19:27:27 +0000 (UTC), "Smarty"
wrote:

I am using an nVidia GeForce 8800 GT video card purchased about 2
years ago and have several programs which speed up rendering and
filtering by using the CUDA GPU.

I am wondering if a new video card would significantly improve my
CUDA performance? Since many of the rendering and filtering jobs I
do take a long time (several hours per job) on this Intel Extreme
QX9650 quadcore machine, I am trying to find a way to significantly
shorten the renders and filtering.

I have 1 PCIe X16 slot on this Dell XPS420 mainboard, so this may
limit my choices as to which, if any, nVidia card could be used as
an update.

I very much appreciate any suggestions / comments.


Yes, a new top of the line card will give you better performance for
sure but you are looking at spending over $500.00 to get it. If your
mb has SLI I would just put in a second 8800GT instead and that will
give you better performance for less cost. But that depends on if you
have a motherboard with dual PCI-E slots or not and if it supports
Nvidia SLI and not ATI Crossfire.


Thanks for your reply!

My Dell motherboard does not support SLI, and only has a single 16X
PCI-E slot. I guess this means I am left with only an expensive single
card replacement? Is the $400 upgrade the "ONLY" way to get a GPU
improvement for CUDA, and if so, what type of speed improvement am I
likely to see compared to my older 8800GT?

Thanks once again.

--

  #4  
Old June 1st 10, 07:01 AM posted to alt.comp.periphs.videocards.nvidia
Jim[_31_]
external usenet poster
 
Posts: 115
Default Faster CUDA performance ??

"Smarty" wrote in message
...
My Dell motherboard does not support SLI, and only has a single 16X
PCI-E slot. I guess this means I am left with only an expensive single
card replacement? Is the $400 upgrade the "ONLY" way to get a GPU
improvement for CUDA, and if so, what type of speed improvement am I
likely to see compared to my older 8800GT?

I can't find any benchmarks for the 8800 but the GTX 480 is at least 2x as
fast the 285 which is likely 2x as fast the 8800/9800.
http://tinyurl.com/27t3krx
A 470 is shouldn't be that much slower (448 shaders at 1215MHZ vs 480 at
1401MHZ) for CUDA. The 465 only 352 shaders at 1215MHZ but would still be
big improverment the 8800.
These cards can get load if that bothers you. Also check if big enough PSU.
Nvidia recommends 600W for the 480 and 550 for the 470/465 but those are
inflated for cheap power supplies. On the 2nd to last page of that review
their PC with 480 was under 500watts.


  #5  
Old June 1st 10, 07:55 AM posted to alt.comp.periphs.videocards.nvidia
Paul
external usenet poster
 
Posts: 13,364
Default Faster CUDA performance ??

Smarty wrote:
poky patrol wrote:

On Mon, 31 May 2010 19:27:27 +0000 (UTC), "Smarty"
wrote:

I am using an nVidia GeForce 8800 GT video card purchased about 2
years ago and have several programs which speed up rendering and
filtering by using the CUDA GPU.

I am wondering if a new video card would significantly improve my
CUDA performance? Since many of the rendering and filtering jobs I
do take a long time (several hours per job) on this Intel Extreme
QX9650 quadcore machine, I am trying to find a way to significantly
shorten the renders and filtering.

I have 1 PCIe X16 slot on this Dell XPS420 mainboard, so this may
limit my choices as to which, if any, nVidia card could be used as
an update.

I very much appreciate any suggestions / comments.

Yes, a new top of the line card will give you better performance for
sure but you are looking at spending over $500.00 to get it. If your
mb has SLI I would just put in a second 8800GT instead and that will
give you better performance for less cost. But that depends on if you
have a motherboard with dual PCI-E slots or not and if it supports
Nvidia SLI and not ATI Crossfire.


Thanks for your reply!

My Dell motherboard does not support SLI, and only has a single 16X
PCI-E slot. I guess this means I am left with only an expensive single
card replacement? Is the $400 upgrade the "ONLY" way to get a GPU
improvement for CUDA, and if so, what type of speed improvement am I
likely to see compared to my older 8800GT?

Thanks once again.


I'd want to see some benchmarks first, before spending one thin dime on
new hardware.

Not very many algorithms are "perfect scaling", able to use as many
computing elements as you can give them.

The best place to get this kind of information, is from the company
that sold you the software. And that is one of my pet peeves, that
such information is virtually non-existent. How are end-users supposed
to know how to get the best from their software ? The companies
writing the software, sure aren't helping...

It would be pretty sad, if you bought a GTX480, ran the algorithm,
and it didn't run any faster than it did on your 8800GT.

Paul
  #6  
Old June 1st 10, 07:53 PM posted to alt.comp.periphs.videocards.nvidia
Smarty
external usenet poster
 
Posts: 94
Default Faster CUDA performance ??

Paul wrote:

Smarty wrote:
poky patrol wrote:

On Mon, 31 May 2010 19:27:27 +0000 (UTC), "Smarty"
wrote:

I am using an nVidia GeForce 8800 GT video card purchased about
2 years ago and have several programs which speed up rendering
and filtering by using the CUDA GPU.

I am wondering if a new video card would significantly improve
my CUDA performance? Since many of the rendering and filtering
jobs I do take a long time (several hours per job) on this
Intel Extreme QX9650 quadcore machine, I am trying to find a
way to significantly shorten the renders and filtering.

I have 1 PCIe X16 slot on this Dell XPS420 mainboard, so this
may limit my choices as to which, if any, nVidia card could be
used as an update.

I very much appreciate any suggestions / comments.

Yes, a new top of the line card will give you better performance
for sure but you are looking at spending over $500.00 to get it.
If your mb has SLI I would just put in a second 8800GT instead
and that will give you better performance for less cost. But that
depends on if you have a motherboard with dual PCI-E slots or
not and if it supports Nvidia SLI and not ATI Crossfire.


Thanks for your reply!

My Dell motherboard does not support SLI, and only has a single 16X
PCI-E slot. I guess this means I am left with only an expensive
single card replacement? Is the $400 upgrade the "ONLY" way to get
a GPU improvement for CUDA, and if so, what type of speed
improvement am I likely to see compared to my older 8800GT?

Thanks once again.


I'd want to see some benchmarks first, before spending one thin dime
on new hardware.

Not very many algorithms are "perfect scaling", able to use as many
computing elements as you can give them.

The best place to get this kind of information, is from the company
that sold you the software. And that is one of my pet peeves, that
such information is virtually non-existent. How are end-users supposed
to know how to get the best from their software ? The companies
writing the software, sure aren't helping...

It would be pretty sad, if you bought a GTX480, ran the algorithm,
and it didn't run any faster than it did on your 8800GT.

Paul


Thanks Paul and Jim for your insightful comments. I share Paul's
concern about making a steep investment with no assurance of a
productivity pay-off. My ONLY motive for replacing this video card with
an expensive alternative is to get a big boost in rendering speed, and
I would be extremely unhappy if that did not pan out.

I also have the issue which Jim raises to deal with. My power supply is
the smaller "standard" supply Dell offered in this XPS420. They had an
optional 750 watt supply (I think it was 750) but the smaller supply I
purchased which is either 400 or 500 watts does not have a lot of spare
capacity left. I have 3 hard drives, 2 optical drives, a couple PCI and
PCI-E cards, along with the QX9650, RAM, etc. I suspect I have a
hundred watts to spare at most, but had not considered the extra power
supply load and inevitable heating at all.

I'm going to do a bit more research and see what if any info I can get
from Pegasys, the authors of TMPGExpress, the program I most often used
to transcode, render, and filter.

Thanks once again.

Smarty
  #7  
Old June 2nd 10, 01:18 PM posted to alt.comp.periphs.videocards.nvidia
Phat_Jethro
external usenet poster
 
Posts: 7
Default Faster CUDA performance ??

On 6/1/2010 2:53 PM, Smarty wrote:
snip

Thanks Paul and Jim for your insightful comments. I share Paul's
concern about making a steep investment with no assurance of a
productivity pay-off. My ONLY motive for replacing this video card with
an expensive alternative is to get a big boost in rendering speed, and
I would be extremely unhappy if that did not pan out.

I also have the issue which Jim raises to deal with. My power supply is
the smaller "standard" supply Dell offered in this XPS420. They had an
optional 750 watt supply (I think it was 750) but the smaller supply I
purchased which is either 400 or 500 watts does not have a lot of spare
capacity left. I have 3 hard drives, 2 optical drives, a couple PCI and
PCI-E cards, along with the QX9650, RAM, etc. I suspect I have a
hundred watts to spare at most, but had not considered the extra power
supply load and inevitable heating at all.

I'm going to do a bit more research and see what if any info I can get
from Pegasys, the authors of TMPGExpress, the program I most often used
to transcode, render, and filter.

Thanks once again.

Smarty


The age of the PSU makes a difference as well as they lose some capacity
over time.
I started with a new 550W 3 years ago. It was fine in my system with
E6600, 2Gb RAM, 2 HDD's and 2 optical with 8800GTS.
3 years later with upgrades to a E8500, 4Gb RAM. 4 HDD's. Now the PSU
starts the Insta-shutoff "feature" when running 3D games.
700W PSU fixed that issue.

J
--
Jethro[AGHL] aka Phat_Jethro
Reply Email: jethro86 (at) gmail (dot) com
  #8  
Old June 2nd 10, 05:25 PM posted to alt.comp.periphs.videocards.nvidia
Smarty
external usenet poster
 
Posts: 94
Default Faster CUDA performance ??

Phat_Jethro wrote:

On 6/1/2010 2:53 PM, Smarty wrote:
snip

Thanks Paul and Jim for your insightful comments. I share Paul's
concern about making a steep investment with no assurance of a
productivity pay-off. My ONLY motive for replacing this video card
with an expensive alternative is to get a big boost in rendering
speed, and I would be extremely unhappy if that did not pan out.

I also have the issue which Jim raises to deal with. My power
supply is the smaller "standard" supply Dell offered in this
XPS420. They had an optional 750 watt supply (I think it was 750)
but the smaller supply I purchased which is either 400 or 500 watts
does not have a lot of spare capacity left. I have 3 hard drives, 2
optical drives, a couple PCI and PCI-E cards, along with the
QX9650, RAM, etc. I suspect I have a hundred watts to spare at
most, but had not considered the extra power supply load and
inevitable heating at all.

I'm going to do a bit more research and see what if any info I can
get from Pegasys, the authors of TMPGExpress, the program I most
often used to transcode, render, and filter.

Thanks once again.

Smarty


The age of the PSU makes a difference as well as they lose some
capacity over time. I started with a new 550W 3 years ago. It was
fine in my system with E6600, 2Gb RAM, 2 HDD's and 2 optical with
8800GTS. 3 years later with upgrades to a E8500, 4Gb RAM. 4 HDD's.
Now the PSU starts the Insta-shutoff "feature" when running 3D games.
700W PSU fixed that issue.

J


Not entirely surprising. Electrolytic caps used for filtering lose some
of their capacitance. Heat sinks and diode bridges and other components
get loaded with dust and dirt, raising their temperatures, and then
causing some thermal safeguards to kick in sooner.

Thanks for the warning!

--

  #9  
Old June 2nd 10, 08:56 PM posted to alt.comp.periphs.videocards.nvidia
Paul
external usenet poster
 
Posts: 13,364
Default Faster CUDA performance ??

Smarty wrote:
Phat_Jethro wrote:

On 6/1/2010 2:53 PM, Smarty wrote:
snip
Thanks Paul and Jim for your insightful comments. I share Paul's
concern about making a steep investment with no assurance of a
productivity pay-off. My ONLY motive for replacing this video card
with an expensive alternative is to get a big boost in rendering
speed, and I would be extremely unhappy if that did not pan out.

I also have the issue which Jim raises to deal with. My power
supply is the smaller "standard" supply Dell offered in this
XPS420. They had an optional 750 watt supply (I think it was 750)
but the smaller supply I purchased which is either 400 or 500 watts
does not have a lot of spare capacity left. I have 3 hard drives, 2
optical drives, a couple PCI and PCI-E cards, along with the
QX9650, RAM, etc. I suspect I have a hundred watts to spare at
most, but had not considered the extra power supply load and
inevitable heating at all.

I'm going to do a bit more research and see what if any info I can
get from Pegasys, the authors of TMPGExpress, the program I most
often used to transcode, render, and filter.

Thanks once again.

Smarty

The age of the PSU makes a difference as well as they lose some
capacity over time. I started with a new 550W 3 years ago. It was
fine in my system with E6600, 2Gb RAM, 2 HDD's and 2 optical with
8800GTS. 3 years later with upgrades to a E8500, 4Gb RAM. 4 HDD's.
Now the PSU starts the Insta-shutoff "feature" when running 3D games.
700W PSU fixed that issue.

J


Not entirely surprising. Electrolytic caps used for filtering lose some
of their capacitance. Heat sinks and diode bridges and other components
get loaded with dust and dirt, raising their temperatures, and then
causing some thermal safeguards to kick in sooner.

Thanks for the warning!


"Utilize NVIDIA CUDA For Filtering and Decoding"

http://tmpgenc.pegasys-inc.com/en/pr..._new.html#cuda

It would appear the main advantage comes from some "sharpen" operations
done in CUDA. Otherwise, it is hard to say what exactly CUDA buys.

And the word Encoding is not associated with CUDA.

They do have a SPURS plugin, which would use a Cell based accelerator
card, for encoding.

*******

On another encoder software page for a different product, they claimed to
be doing encoding with CUDA, but the only performance metric was something like

"Up to 50% better performance"

with no references to hardware used at all (i.e. indicating which processor
and which video card are being compared).

I guess you're supposed to fill your computer with various odds
and ends, to get acceleration :-)

Paul
  #10  
Old June 3rd 10, 09:36 AM posted to alt.comp.periphs.videocards.nvidia
Jim[_31_]
external usenet poster
 
Posts: 115
Default Faster CUDA performance ??

"Smarty" wrote in message
...
Thanks Paul and Jim for your insightful comments. I share Paul's
concern about making a steep investment with no assurance of a
productivity pay-off. My ONLY motive for replacing this video card with
an expensive alternative is to get a big boost in rendering speed, and
I would be extremely unhappy if that did not pan out.

http://www.tomshardware.com/reviews/...pu,2299-8.html
Its all I could find. AFAIK Cuda is only used for the filters (going from
the press release) so unless you use a lot my guess is you're not going to
see big gains (not $300 worth at least).


 




Thread Tools
Display Modes

Posting Rules
You may not post new threads
You may not post replies
You may not post attachments
You may not edit your posts

vB code is On
Smilies are On
[IMG] code is On
HTML code is Off
Forum Jump

Similar Threads
Thread Thread Starter Forum Replies Last Post
CUDA on Debian Merciadri Luca Nvidia Videocards 2 August 29th 09 07:02 PM
CUDA ? johns Nvidia Videocards 8 December 3rd 08 06:48 PM
Anyone here using CUDA yet? heycarnut Nvidia Videocards 0 January 23rd 07 02:56 AM
Faster RAM or Lower CAS, which gives more performance? Harry Muscle Overclocking AMD Processors 6 August 20th 03 03:29 PM
Faster RAM or Lower CAS, which gives more performance? Harry Muscle Asus Motherboards 6 August 20th 03 03:29 PM


All times are GMT +1. The time now is 06:06 AM.


Powered by vBulletin® Version 3.6.4
Copyright ©2000 - 2024, Jelsoft Enterprises Ltd.
Copyright ©2004-2024 HardwareBanter.
The comments are property of their posters.