Advanced search

Message boards : Graphics cards (GPUs) : GTX 1080 Ti goes official

Author Message
Profile Retvari Zoltan
Avatar
Send message
Joined: 20 Jan 09
Posts: 2353
Credit: 16,339,242,850
RAC: 5,288,795
Level
Trp
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 46579 - Posted: 3 Mar 2017 | 16:49:19 UTC

https://www.nvidia.com/en-us/geforce/products/10series/geforce-gtx-1080-ti/
http://www.geforce.com/whats-new/articles/nvidia-geforce-gtx-1080-ti

GPU Engine Specs:
3584 NVIDIA CUDA® Cores
1582 MHz Boost Clock
Memory Specs:
11 Gbps Memory Speed
11 GB GDDR5X Standard Memory Config
352-bit Memory Interface Width
484 GB/sec Memory Bandwidth
Technology Support:
Simultaneous Multi-Projection
VR Ready
NVIDIA Ansel
NVidia SLI® HB Bridge Supported
NVIDIA G-SYNC™-Ready
NVIDIA GameStream™-Ready
NVIDIA GPU Boost™ 3.0
Microsoft DirectX 12 API with feature level 12_1
Vulkan API
OpenGL 4.5
PCIe 3.0 Bus Support
OS Certification Windows 7..10, Linux, FreeBSDx86
Display Support:
Maximum Digital Resolution 7680x4320@60Hz
Standard Display Connectors DP 1.43, HDMI 2.0b
Multi Monitor
HDCP 2.2
Graphics Card Dimensions:
Height 4.376"
Length 10.5"
Width 2-Slot
Thermal and Power Specs:
Maximum GPU Temperature 91°C
Graphics Card Power 250 W
Recommended System Power 600 W
Supplementary Power Connectors One 6-pin, One 8-pin

PappaLitto
Send message
Joined: 21 Mar 16
Posts: 511
Credit: 4,672,242,755
RAC: 0
Level
Arg
Scientific publications
watwatwatwatwatwatwatwat
Message 46580 - Posted: 3 Mar 2017 | 17:53:57 UTC

I never thought I'd say or type 352-bit bus before lol.

Profile Retvari Zoltan
Avatar
Send message
Joined: 20 Jan 09
Posts: 2353
Credit: 16,339,242,850
RAC: 5,288,795
Level
Trp
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 46581 - Posted: 3 Mar 2017 | 18:10:32 UTC - in response to Message 46580.

I never thought I'd say or type 352-bit bus before lol.

How about the 11 GB RAM?

3de64piB5uZAS6SUNt1GFDU9d...
Avatar
Send message
Joined: 20 Apr 15
Posts: 285
Credit: 1,102,216,607
RAC: 0
Level
Met
Scientific publications
watwatwatwatwatwat
Message 46582 - Posted: 3 Mar 2017 | 20:49:35 UTC
Last modified: 3 Mar 2017 | 20:51:04 UTC

Didn't we speak of GPUGRID enforcing a 1 Job per GPU policy soon? So many people were asking for that ... and I can already see the 1080ti load bouncing like a rubber ball. I am not aware of any CPU which can feed this monster entirely, not even a 7700K ...maybe unless overclocked to the sky and LN2 cooled. Well... but the 1080ti certainly is Dynamite for F@H.
____________
I would love to see HCF1 protein folding and interaction simulations to help my little boy... someday.

Trotador
Send message
Joined: 25 Mar 12
Posts: 103
Credit: 13,920,977,393
RAC: 1,390,776
Level
Trp
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 46652 - Posted: 14 Mar 2017 | 19:45:49 UTC

There is already one 1080Ti crunching GPUGRId

http://www.gpugrid.net/hosts_user.php?userid=81692

Betting Slip
Send message
Joined: 5 Jan 09
Posts: 670
Credit: 2,498,095,550
RAC: 0
Level
Phe
Scientific publications
watwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwatwat
Message 46653 - Posted: 14 Mar 2017 | 20:03:55 UTC - in response to Message 46652.

There is already one 1080Ti crunching GPUGRId

http://www.gpugrid.net/hosts_user.php?userid=81692


Those are 1080's

Evo01
Send message
Joined: 10 Oct 11
Posts: 13
Credit: 192,770,371
RAC: 0
Level
Ile
Scientific publications
watwatwatwatwatwat
Message 46654 - Posted: 14 Mar 2017 | 20:05:05 UTC - in response to Message 46652.

There is already one 1080Ti crunching GPUGRId

http://www.gpugrid.net/hosts_user.php?userid=81692


That would be me. Everything is going good so far. Modest overclock of 1999 MHz and 1377 MHz vram. Just put my 1080 back in. I'll see if running @ x8 will affect performance.

Evo01
Send message
Joined: 10 Oct 11
Posts: 13
Credit: 192,770,371
RAC: 0
Level
Ile
Scientific publications
watwatwatwatwatwat
Message 46655 - Posted: 14 Mar 2017 | 20:05:35 UTC - in response to Message 46653.
Last modified: 14 Mar 2017 | 20:10:55 UTC

There is already one 1080Ti crunching GPUGRId

http://www.gpugrid.net/hosts_user.php?userid=81692


Those are 1080's


One is a 1080 Ti.

http://imgur.com/a/Oqsck

Caelus
Send message
Joined: 8 Nov 16
Posts: 9
Credit: 19,338,667
RAC: 0
Level
Pro
Scientific publications
wat
Message 46765 - Posted: 24 Mar 2017 | 8:46:41 UTC - in response to Message 46582.

Didn't we speak of GPUGRID enforcing a 1 Job per GPU policy soon? So many people were asking for that ...


Wait.. What? Why?

3de64piB5uZAS6SUNt1GFDU9d...
Avatar
Send message
Joined: 20 Apr 15
Posts: 285
Credit: 1,102,216,607
RAC: 0
Level
Met
Scientific publications
watwatwatwatwatwat
Message 46766 - Posted: 24 Mar 2017 | 10:22:55 UTC - in response to Message 46765.
Last modified: 24 Mar 2017 | 10:23:28 UTC

Didn't we speak of GPUGRID enforcing a 1 Job per GPU policy soon? So many people were asking for that ...


Wait.. What? Why?


see this discussion:
http://www.gpugrid.net/forum_thread.php?id=4501

I do not second that for reasons of high-end GPU utilization and load fluctuation, but apparently quite a few crunchers have a different opinion.
____________
I would love to see HCF1 protein folding and interaction simulations to help my little boy... someday.

Caelus
Send message
Joined: 8 Nov 16
Posts: 9
Credit: 19,338,667
RAC: 0
Level
Pro
Scientific publications
wat
Message 46773 - Posted: 24 Mar 2017 | 22:59:09 UTC - in response to Message 46766.

Didn't we speak of GPUGRID enforcing a 1 Job per GPU policy soon? So many people were asking for that ...


Wait.. What? Why?


see this discussion:
http://www.gpugrid.net/forum_thread.php?id=4501

I do not second that for reasons of high-end GPU utilization and load fluctuation, but apparently quite a few crunchers have a different opinion.


My 970 gtx OC is not being used fully with 1 long WU.

So I use 2 long WU's which most of the time take 92-97% GPU usage together. and almost all of the WU's are being finished in 10-13 hours.
with SWAN being used as well.

There were only a couple of single long WU's that would utilize about 75% of my card.

So unless they can somehow make the GPU be utilized to fullest with 1 WU there's no reason to cap 1WU/GPU.

They should just make a filter for host. let the server be smart choosing for whom to send 1 or 2 jobs.

Caelus
Send message
Joined: 8 Nov 16
Posts: 9
Credit: 19,338,667
RAC: 0
Level
Pro
Scientific publications
wat
Message 46775 - Posted: 25 Mar 2017 | 12:01:35 UTC - in response to Message 46773.

Interestingly enough. just got a WU that uses 95% of my gpu...
Kudos for that!

Post to thread

Message boards : Graphics cards (GPUs) : GTX 1080 Ti goes official

//