Stack Exchange Network

Stack Exchange network consists of 175 Q&A communities including Stack Overflow, the largest, most trusted online community for developers to learn, share their knowledge, and build their careers.

Visit Stack Exchange

Questions tagged [graphics-processing-unit]

The tag has no usage guidance.

12
votes
1answer
2k views

What are actual Tesla M60 models used by AWS?

Wikipedia says that the Tesla M60 has 2x8 GB RAM (whatever it means) and TDP 225–300 W. I use an EC2 instance (g3s.xlarge) which is supposed to have a Tesla M60. But nvidia-smi command says it has ...
0
votes
1answer
34 views

Poor man's virtual GPU, using a multiuser OS + GPU, instead of specialist vGPU card?

I've read about this system in a white paper somewhere, but can't remember where, or any details, and haven't found it since. The comment was in regard to GPU virtualisation with Type 1 (bare metal) ...
3
votes
0answers
39 views

Hypervisor support for vGPU + VM suspend?

Short version - how well do current hypervisors support vGPU with VM suspend/resume capability? Longer version: I've used VMware Workstation for many years in my home lab, with the GPU (used for ...
1
vote
1answer
46 views

Google Cloud - Monitor running on Microsoft Display Driver instead of NVIDIA K80 GPU

My Google Cloud Instance is running on Microsoft Display Driver,instead of the GPU.I tried to install Hyper-V,but Google Cloud Processors don't support it.Please help,i need to run Unity,but can't ...
0
votes
1answer
155 views

PCI Express 2.0 x16 vs 3.0 x8

Will a PCI Express 2.0 x16 graphics card fit in a PCI Express 3.0 x8 slot, and if so, will it affect the performance? Theoretically I take it the two configurations should be equal with respect to ...
4
votes
0answers
85 views

Erase GPU memory

We have Nvidia GPU cards that can be used by different users in an OpenStack environment. A first user creates a VM with access to a GPU card, then deletes the VM when done. Another user then creates ...
0
votes
0answers
17 views

NVIDIA Drivers on server

I'm settin an Ubuntu server up for some deep learning stuff, and I know that i need to install CUDA and cuDNN, both from nvidia. But I can't find an answer to something. Do i need to install NVIDIA ...
4
votes
0answers
806 views

Hyper-V PCIe Passthrough of GPU working (but not 100%)

I have managed to be able to passthrough a PCIe GPU (AMD RX580) into a Windows 10 Guest on a Windows Server 2016 Standard host. The problem is that whenever the GPU will be used this error throws up:...
0
votes
1answer
151 views

Adding more GPU resources to AWS EC2 Ubuntu Server

I am running a g2.2xlarge AWS EC2 instance on Ubuntu Server 16.04 LTS (HVM), SSD Volume Type. The specs on this system are as follows (source): The g2.2xlarge version comes with 15 GiB memory, 60 ...
1
vote
0answers
180 views

ESXI PCIe GPU Passthrough does not allow for CUDA

I am trying to do cuda development in an ESXI environment, so I installed a Quadro 5800 in my ESXI machine (Dell T7500). I did passthrough to the Windows 7 VM that I will be doing development in, but ...
3
votes
1answer
1k views

Windows 10, two monitors with two different sessions

I want to do some thing but I can't find anything about it. I remember that on Linux you can do a multisit workstation with one PC and several screens and perifericals (mouse, keyboard, etc), ...
0
votes
1answer
170 views

Building a Machine Learning Server

We need to train large networks using TensorFlow that take several days to complete on a GPU. Amazon offers GPU instances like p2.16xlarge with e.g. 16 GPUs (NVIDIA K80). Now I was wondering if ...
2
votes
1answer
313 views

Supermicro X10 motherboard with discrete GPU and onboard IPMI GPU and access via KVM

Is it possible to have both GPUs running and connected to displays at the same time (with mirrored displays for example) but then also connect via the IPMI iKVM to the built in GPU? I will need ...
-1
votes
1answer
921 views

GeForce GTX 1060 card in Dell R710 or R730xd for machine learning?

We are investigating speeding up some machine learning code written using Theano and Keras, in particular by getting a GPU card. Does anyone have direct experience with this or a very similar ...
1
vote
1answer
157 views

Nvidia Pascal architecture: DMA Size / maximum amount of host system RAM?

We are planning to build a pair of multi-GPU Linux servers for machine learning and data science tasks. Per our requirements, we need to put a lot of RAM in these machines; we're planning on 24x 64GiB ...
0
votes
1answer
49 views

Where to find high/critical temperatures for GPU?

I am looking for a database that has high and critical temperatures listed for CPU's and GPU's, or a tool that will be able to extract this information. Google is filled with 'my gpu runs at 63C, is ...
1
vote
1answer
2k views

PowerEdge T410 with GeForce GTX 970 - Independent power source needed?

I am attempting to install a GeForce GTX 970 graphics card in our Dell PowerEdge T410 server for the purpose of rendering 3D graphics. After inserting the graphics card into the PCI-E slot it became ...
1
vote
1answer
438 views

Use GPU to speed up server processing

I have a server that handles strings of data pushed from another server. Sometimes we receive thousands a second. This might be overly simplistic but would putting a Graphics card in the server assist ...
-1
votes
1answer
1k views

libGL error: failed to load driver: swrast error on AmazonEC2 with Ubuntu14

I have a t2.large instance on Amazon EC2 with 8Go of ram and 30Go of disk space. The OS used is Ubuntu 14.04 Trusty and the desktop manager is xfce4. I'm using xrdp to remotely access the desktop, ...
1
vote
1answer
2k views

What hypervisors support vGPU? [closed]

Does anyone know if any open source hypervisor supports vGPUs? It looks like XenServer and vSphere are the only two hypervisors that support virtual graphics cards (true vGPU, not passthrough or ...
-3
votes
2answers
701 views

Video memory required for desktop virtualization [closed]

I am planning to set up 3 virtual desktops using vmware. I have this server with video memory of 32mb and 32 GB RAM. What is the recommended video memory for this set up and is it possible to upgrade ...
3
votes
3answers
3k views

GPU support on OpenStack/CloudStack

I'm wondering if anyone here has had success with any of the cloud orchestration layers using a GPU (preferably vGPU)? I've been able to get XenServer 6.2 to successfully see our nvidia GRID K1 card ...
0
votes
0answers
985 views

XenServer 6.5 upgrade: NVIDIA GRID K1 gives “PAT Configuration unsupported”

We have two Supermicro SYS2027GR-TR2 servers that were running XenServer 6.2 SP1. Each system has one NVIDIA GRID K1 video card installed. We just upgraded the servers to XenServer 6.5 by doing a ...
1
vote
0answers
400 views

Amazon EC2 VNC Nvidia GPU usage?

I have a GPU instance on Amazon Web Services I am using Ubuntu 14.04 LTS The console show that the drivers are loaded perfectly, see below output $nvidia-smi -q | head ==============NVSMI LOG=======...
1
vote
0answers
789 views

Conflict between Nvidia Grid K2 & integrated graphics on Supermicro VDI?

My office has a Supermicro SYS-1027GR-TR2-2NVK2 VDI server with dual Nvidia GRID K2 cards running Windows Server 2012 R2 & RemoteFX. We are an architectural firm and use 3D graphics software. ...
2
votes
1answer
290 views

How important is the CPU when building a CUDA system?

I'm just a clueless sysadmin and we need to put together a couple of machines specifically for users to use CUDA. We're looking at the Dell PowerEdge T620 and jamming four CUDA cards into the sucker. ...
1
vote
1answer
765 views

How to be able to use IPMI yet have graphics acceleration with a discrete graphics card?

In my lab, we have a compute server (two of them, but identical in config) running Fedora 19, built on the Supermicro H8QGI-F and 4 x AMD Opteron 6272s. It has an nVidia GT 610 discrete graphic card, ...
2
votes
1answer
4k views

Installing a dual display graphics card in a Windows 2008 server

Trying to hook up a Dell Poweredge T620 to 2 27" monitors via a PNY Nvidia NVS 310. Server running Windows 2008 R2 Standard SP1. Nothing fancy, but need a very large desktop area (2 x 2560 x 1440). ...
3
votes
0answers
682 views

Сan I use IOMMU for VT-d to give each virtual machine one at a time GPU?

If I use VMWare with 4 virtual-machines and 4 GPUs (nVidia Quadro/Tesla), then can I give (move) some devices to different virtual-machines for each by a single card? If I have one of these CPU, then ...
0
votes
2answers
2k views

NVIDIA Tesla K20C in Dell PowerEdge R720xd — power cables

I am trying to put an NVIDIA Tesla K20C into a Dell PowerEdge R720xd. I'm having a bit of trouble understanding the power requirements of the card. First, here is a picture of two pages of the ...
1
vote
1answer
128 views

Should I turn off hybrid server with GPU on IDLE?

There is a server with 2 CPUs (Intel Xeon E5-2670, Sandy Bridge) and 1 AMD GPU (Tahiti XT Radeon HD 7970). There are also SSD (system and executable files) and HDD (heavy data) that connected to this ...
-1
votes
1answer
212 views

Nagios monitoring nvidia on Windows OS

Can somebody give me advice, about monitoring on Nagios. How i can monitor GPU temperature on NVidia graphic card, under Windows 2008 R2 OS?
1
vote
1answer
784 views

How AWS does GPU virtualization? [closed]

What kind of technology is Amazon using for GPU virtualization ? Can multiple VMs on an AWS GPU instance concurrently share GPU and have acceleration for their CUDA/ openCL programs ? I know following ...
0
votes
1answer
556 views

CUDA: Is it possible to dynamically restrict the number of cores / threads / clock freq. while a process is running on a GPU?

I'm running multiple NVidia GTX 680 under Ubuntu 10.04 in a pretty hot environment (troubles with rack cooling) and sometimes it's getting over 95C. When I detect the overheating, can I somehow tell ...
0
votes
1answer
613 views

Dedicated GPU in Dell PowerEdge C1100

We recently purchased a Dell PowerEdge C1100 off lease with the initention of using it for graphics processing. We installed an AMD HD 7000 series GPU in it that runs off of board power and it sends ...
0
votes
1answer
2k views

GPU (Specifically NVidia) Cloud Computing Centres [closed]

In the CPU computing world, you have giant cloud providers like Microsoft Azure, Amazon EC2 and Rackspace. You have also smaller companies that provide dedicated hosting services. Amazon EC2 has ...
1
vote
0answers
1k views

Linux CLI program to verify/control nVidia hardware RAID?

I have a server with a Supermicro motherboard that has an nVidia RAID controller on board. When I boot up, I can hit F10 and see/modify the RAID settings. However, I don't want to reboot this server ...
1
vote
2answers
874 views

Can I safely use a 1U server with an actively cooled Nvidia GTX 680 video card?

I'm about to configure some new GPU capable nodes for our needs and I was wondering if someone has any experience with using simple video cards like Nvidia GTX 680 (actively cooled with a fan) in a 1U ...
1
vote
2answers
269 views

How does two gpus work?

I am current having a highend GPU installed in my server - and I am considering to install a cheap GPU to support the monitor. Reason is that the server is using the highend GPU for OpenCL and i ...
0
votes
1answer
3k views

What does CUDA compute capability indicate? How to identify device CUDA C version computability?

I am attempting to identify if my Nvidia GPU device is compatible with the latest version of CUDA. Searching the online documentation within CUDA Zone along with the Wikipedia page I am able to ...
0
votes
2answers
962 views

start dummy X server for user logged remotely

I have a server (CentOS6) which has an ATI GPU. For users to have access to this GPU for computation with OpenCL, they need to have an X session open unfortunately (a restriction on the ATI driver). ...
7
votes
2answers
5k views

How to run GPGPU Memory Testing

We use a lot of GPGPU computing (mostly with CUDA, but some OpenCL). Often when users are running code, the code errors out with a memory error on only one of our hosts. I suspect one of the cards ...
-1
votes
2answers
776 views

Restoring raid 5 array after bios flash [closed]

I have just flashed my BIOS and now my machine does not detect my raid5 array! It has three 2TB drives in it so that is a LOT of data that will be lost! I have NOT deleted the array and it does not ...
5
votes
4answers
12k views

RemoteFX On NVIDIA Lower Cost Video Cards

I am looking into a Windows Server 2008 SP1 with RemoteFX enabled, however I do not want to buy one of the NVIDIA Quadro $1000+ video cards to do it (as only a small number of users will be using ...
1
vote
2answers
905 views

Using CUDA_VISIBLE_DEVICES with sge

Using sge with resource complex called 'gpu.q' that allows resource management of gpu devices (these are all nvidia devices). However on the systems there are multiple gpu devices (in exclusive mode) ...
1
vote
1answer
646 views

Cloud Linux with OpenGL acceleration?

We are thinking about launching some Linux server-side services which would greatly benefit of having real accelerated OpenGL available. Currently we are running normal server instances with Mesa ...
5
votes
1answer
225 views

HP z800 running Vista loses NVIDIA display settings after Windows Update

Not sure if this is a SuperUser question or not... I'm approaching from the administrator's perspective. One of my users is on an HP z800 workstation running a financial trading application. This ...
1
vote
1answer
2k views

Geforce 470 Card in Dell R710 or R5400 - Will it Blend?

Is it possible to install a NVIDIA Geforce card in a Dell R710 or R5400 Dual Xeon system? The server itself is certified only for Quadro systems. I don't desire the added rendering or memory from the ...
3
votes
1answer
2k views

Is having a [high-end] video card important on a server?

My application is quite interactive application with lots of colors and drag-and-drop functionality, but no fancy 3D-stuff or animations or video, so I only used plain GDI (no GDI Plus, No DirectX). ...
0
votes
1answer
225 views

Raid5 Write cache - Nvidia motherboard

I can't figure out where to enable write-cache for nvida's raid. When using an intel motherboard with ICH10, there is a setting in the raid-software that enables write cache. I can't find that setting ...