This refers to one application's using multiple graphics-processing units, either in traditional (graphical) or general-purpose (GPGPU) applications.
Questions tagged [multi-gpu]
387 questions
-1
votes
1 answer
Find the idle GPU in a multi-GPU machine
I have the following code running under cuda (Windows 10, VS 2015).
//Code for running on one or 2 gpu's
const unsigned __int64 MemOutputSize = (1i64 << 25)*64; //2GB
int deviceCount;
cudaGetDeviceCount(&deviceCount);
unsigned long long*…
Johan
- 74,508
- 24
- 191
- 319
-1
votes
1 answer
CUDA + OpenMP Multi-GPU Batch processing
I am trying to do the following:
I assume that I have a system with heterogeneous processing units (PUs), including CPUs, GPUs, and Intel Xeon Phis. The GPU devices can also have different characteristics. Hence, splitting the workload across these…
sm13294
- 563
- 7
- 23
-1
votes
1 answer
nvidia-smi reports identical memory usage for both GPUs
Thank you for your time.
Is it unexpected or even pathologic for nvidia-smi to report the same memory usage for both gpus? Specifically, I have a 2 gpu system, and the numerator for "Memory-Usage" listed for both gpus is the same regardless of the…
user3391229
- 798
- 9
- 17
-1
votes
2 answers
Multiple Tesla K80 GPU's and parfor loops
I received a computer with 4xGPU's Tesla K80 and I am trying the parfor loops from Matlab PCT to speed up FFT's calculation and it is yet slower.
Here is what I am trying:
% Pupil is based on a 512x512 array
parfor zz = 1:4
gd =…
Nicolas
- 1
- 1
-1
votes
1 answer
Atomic Exchange Sorting Algorithm in MultiGPU
How can atomic exchange sorting algorithm can be implemented in MultiGPU? Is there references available??
-1
votes
1 answer
CUDA multi - gpu add function
I followed the following example:
multi-GPU basic usage
The Code is doing summation:
The man who is answered checked as accepted, sends add function like this:
for(int i=0;i<10000;++i) {
for(int dev=0; dev<2; dev++) {
…
ehah
- 675
- 1
- 7
- 11
-1
votes
1 answer
VS2010 Nsight 3.0, Multiple GPUs card but can only see one device.
Symptoms:
I'm trying to first of all make sure there are actually two nvidia cards in this box, so
in VS2010 -> NSight -> Windows -> SystemInfo -> Display Devices
I can see that there seems to be two devices.
NVIDIA GeForce GTX 560 Ti
Name …
Stochastika
- 305
- 1
- 2
- 14
-2
votes
1 answer
How to simplify CUDA_VISIBLE_DEVICES=0,1,6,7
Every time when I start training, I need to manully type a command like CUDA_VISIBLE_DEVICES=0,1,6,7, depending on how many GPUs I am going to use and which ones are currently free.
This answer offered an ugly yet practical walk-around. I.e. write…
zheyuanWang
- 1,158
- 2
- 16
- 30
-2
votes
1 answer
PyTorch model output different dimension when using DataParallel
I implemented my PyTorch model with DataParallel for multi-GPU training. However, it seems that the model doesn't consistently output the right dimension. In the training loop, it seems that the model gave the correct output dimension for the first…
Kaihua Hou
- 310
- 1
- 2
- 11
-2
votes
1 answer
Issue with using Multi GPU NVIDIA
I'm learning how to use multi GPU for my CUDA application. I tried out a simple program which successfully ran on a system having two Tesla C2070. But when I tried to run the same program on a different system having a Tesla K40c and a Tesla C2070,…
Vijay
- 7
- 1
-2
votes
1 answer
OpenCL for APU+GPU
I am thinking of assembling this system:
AMD CPU(A8-3870 APU which has Radeon HD 6550D inside: 400 stream processors:xxx GFLOPS) nearly 110$
AMD Graphics card: HD 7750 (512 stream processors:819 GFLOPS peak performance) nearly 170$
an appropriate…
huseyin tugrul buyukisik
- 11,469
- 4
- 45
- 97
-3
votes
1 answer
CUDA fails when trying to use both onboard iGPU and Nvidia discrete card. How can i use both discrete nvidia and integrated (onboard) intel gpu?
I had recently some trouble making my pc (ivybridge) use the onboard gpu (intel igpu HD4000) for normal screen display usage, while i run my CUDA programs for computations on the discrete Nvidia GT 640 i have on my machine. The problem was that…
Aperture Laboratories
- 254
- 1
- 2
- 12