From gpu-z, it says it is a slightly cutdown rtx 2080 super. And it looks like it may be passively cool too.
A Proud member of the O.F.A. (Old Farts Association). Be well, do good work, and keep in touch.® (Garrison Keillor) I want some more patience. RIGHT NOW!
It’s totally different than a “cut down 2080”. It has features and special compute capabilities that are beneficial for AI. Better integer performance and good low precision performance. Plus SRIOV. that’s why it’s $1000 still.
I have no clue what "restore" means but it is a Chinese supplier and will take until the end of the month to get to me IF I ordered one, which I have not as of right now.
Is the highest stable GPU memory clock usually the fastest processing at e@h?
Tom M
A Proud member of the O.F.A. (Old Farts Association). Be well, do good work, and keep in touch.® (Garrison Keillor) I want some more patience. RIGHT NOW!
Is the highest stable GPU memory clock usually the fastest processing at e@h?
Tom M
best performance at E@h depends on more than just one metric.
GPU cores and clock speed are probably the largest influence, and GPU memory bandwidth, then GPU memory clock, and to a lesser extent even the CPU clock/performance.
you need to balance the cores with memory bandwidth though. Too many cores can get bottlenecked if your memory bandwidth is lacking. The 40-series for example seems to get limited by this.
My just wondering question......what is the longest you ever got a Nvidia card to run here?
For some reason my 660Ti is still running here since Sept. 2012 mainly in the same box but the last 2 months I have plugged it into a couple of my even older boxes.
My just wondering question......what is the longest you ever got a Nvidia card to run here?
For some reason my 660Ti is still running here since Sept. 2012 mainly in the same box but the last 2 months I have plugged it into a couple of my even older boxes.
I guess it is beyond the warranty now
LOL yes it's past ALL warranties now!!
AND that same card ran for years before that in someone elses systems as well.
I’ve got a GTX 550Ti that still works. Also a GTX 295 that still works. But there’s no use running them since they take forever to process WUs for the amount of power they burn.
Is the highest stable GPU memory clock usually the fastest processing at e@h?
Tom M
best performance at E@h depends on more than just one metric.
GPU cores and clock speed are probably the largest influence, and GPU memory bandwidth, then GPU memory clock, and to a lesser extent even the CPU clock/performance.
you need to balance the cores with memory bandwidth though. Too many cores can get bottlenecked if your memory bandwidth is lacking. The 40-series for example seems to get limited by this.
Sorry. Context IS everything, Tom!
I am wondering if you open up the power limits and discover that you can reliably memory OC a rtx 3080 ti at say +3000 it should process faster than than the same card at +1500?
And how long do you need to run an extreme memory OC before you tentatively label it "reliable"? I have run +2000 on my smaller rtx 3080 ti for 48 hours without an apparent failure.
Tom M
A Proud member of the O.F.A. (Old Farts Association). Be well, do good work, and keep in touch.® (Garrison Keillor) I want some more patience. RIGHT NOW!
going from +1500 to +3000 is also more complicated than just power limits, you can't just raise the power and expect that to work. I would argue that probably no card will be stable with that configuration anyway. it might be a little faster if you could even do it. but you'll get more performance just using the extra power limit to increase core clocks. all of this just starts making the card very inefficient though.
I think the 30-series cards have some form of memory error detection/recovery so that it doesnt just flat out crash. even with a high memory clock, actual performance can degrade because of all the memory errors. you would need to watch if the tasks are actually running faster and validating.
From gpu-z, it says it is a
)
From gpu-z, it says it is a slightly cutdown rtx 2080 super. And it looks like it may be passively cool too.
A Proud member of the O.F.A. (Old Farts Association). Be well, do good work, and keep in touch.® (Garrison Keillor) I want some more patience. RIGHT NOW!
It’s totally different than a
)
It’s totally different than a “cut down 2080”. It has features and special compute capabilities that are beneficial for AI. Better integer performance and good low precision performance. Plus SRIOV. that’s why it’s $1000 still.
_________________________________________________________________________
Tom M wrote: Thank you. That
)
Okay tom here's an upgrade you can do multiples of:
https://www.aliexpress.us/item/3256804554181908.html?spm=a2g0o.productlist.main.105.64255332Qk87cn&algo_pvid=1c5ac6c7-9da9-48bf-a81e-9dc9039c1865&algo_exp_id=1c5ac6c7-9da9-48bf-a81e-9dc9039c1865-52&pdp_ext_f=%7B%22sku_id%22%3A%2212000030302190391%22%7D&pdp_npi=2%40dis%21USD%21416.2%21395.39%21%21%21%21%21%40211bd8be16756443477466183d073e%2112000030302190391%21sea&curPageLogUid=OOf2ps8sPJ0b
I have no clue what "restore" means but it is a Chinese supplier and will take until the end of the month to get to me IF I ordered one, which I have not as of right now.
Is the highest stable GPU
)
Is the highest stable GPU memory clock usually the fastest processing at e@h?
Tom M
A Proud member of the O.F.A. (Old Farts Association). Be well, do good work, and keep in touch.® (Garrison Keillor) I want some more patience. RIGHT NOW!
Tom M wrote:Is the highest
)
best performance at E@h depends on more than just one metric.
GPU cores and clock speed are probably the largest influence, and GPU memory bandwidth, then GPU memory clock, and to a lesser extent even the CPU clock/performance.
you need to balance the cores with memory bandwidth though. Too many cores can get bottlenecked if your memory bandwidth is lacking. The 40-series for example seems to get limited by this.
_________________________________________________________________________
My just wondering
)
My just wondering question......what is the longest you ever got a Nvidia card to run here?
For some reason my 660Ti is still running here since Sept. 2012 mainly in the same box but the last 2 months I have plugged it into a couple of my even older boxes.
I guess it is beyond the warranty now
MAGIC Quantum Mechanic
)
LOL yes it's past ALL warranties now!!
AND that same card ran for years before that in someone elses systems as well.
I’ve got a GTX 550Ti that
)
I’ve got a GTX 550Ti that still works. Also a GTX 295 that still works. But there’s no use running them since they take forever to process WUs for the amount of power they burn.
_________________________________________________________________________
Ian&Steve C. wrote: Tom M
)
Sorry. Context IS everything, Tom!
I am wondering if you open up the power limits and discover that you can reliably memory OC a rtx 3080 ti at say +3000 it should process faster than than the same card at +1500?
And how long do you need to run an extreme memory OC before you tentatively label it "reliable"? I have run +2000 on my smaller rtx 3080 ti for 48 hours without an apparent failure.
Tom M
A Proud member of the O.F.A. (Old Farts Association). Be well, do good work, and keep in touch.® (Garrison Keillor) I want some more patience. RIGHT NOW!
going from +1500 to +3000 is
)
going from +1500 to +3000 is also more complicated than just power limits, you can't just raise the power and expect that to work. I would argue that probably no card will be stable with that configuration anyway. it might be a little faster if you could even do it. but you'll get more performance just using the extra power limit to increase core clocks. all of this just starts making the card very inefficient though.
I think the 30-series cards have some form of memory error detection/recovery so that it doesnt just flat out crash. even with a high memory clock, actual performance can degrade because of all the memory errors. you would need to watch if the tasks are actually running faster and validating.
_________________________________________________________________________