Stack Overflow
Stack Overflow

Questions tagged [tesla]

Nvidia Tesla is a brand of GPUs targeting the high performance computing market.

Nvidia Tesla has very high computational power (measured in floating point operations per second or FLOPS) compared to microprocessors. Teslas power some of the world's fastest supercomputers, including Titan at Oak Ridge National Laboratory and Tianhe-1A.

Tesla products primarily used

  • In simulations and in large scale calculations (especially floating-point calculations).
  • For high-end image generation for applications in professional and scientific fields.
  • For password brute-forcing.

.

89 questions
0
votes
0 answers

Is it training too slow or at normal speed? GPU + python + tensorflow-gpu

I am training a "faster_rcnn_inception_resnet_v2_atrous_coco" for custom object detection using tensorflow's api. I set up a machine at azure with following configuration: Intel cxeon CPU E5-2690 v3 @ 2.60GHz RAM 56GB windows10 64bit GPU tesla k80…
user9632288
0
votes
1 answer

GCP GPU nvidia P100 instance

recently google approved my quota for 4 nvidia tesla p100 on a project i'm working(so I have the quota). The issue is that i don't know how is called the nvidia p100 in gcp, and i can't find it anywhere. i'm making the instance like this. gcloud…
kcmando1
  • 1
0
votes
1 answer

Google Cloud tesla K80, only one device showing up?

I've setup an instance on Google Cloud with the following specs: 4 vCPUs, 15 GB memory, 1 Tesla K80 GPU Tesla K80 consists of 2 GPU units and each should show up as a separate device in the nvidia's logs. However, when I run nvidia-smi in the shell…
Kunal24
  • 201
  • 1
  • 7
0
votes
1 answer

Multiprocessing for Python parallelization error - "function' object is not iterable"

We have NVIDIA Tesla K80 GPU accelerator computing in our data center with the following characteristics: Intel(R) Xeon(R) CPU E5-2670 v3 @2.30GHz, 48 CPU processors, 128GB RAM, 12 CPU coresrunning under Linux 64-bit. I am running the following code…
Desta Haileselassie Hagos
  • 23,140
  • 7
  • 48
  • 53
0
votes
1 answer

How to obtain the module/object code of a Theano numpy program

In my University we have a Cluster having Tesla GPUs. However the resource is shared by several departments and the supercomputing department requires users to provide uniquely the module/code object of the program one needs to run in the cluster.…
Nacho
  • 792
  • 1
  • 5
  • 23
0
votes
0 answers

freeing GPU memory without sudo priviliges

I use theano for some deep learning experiments. I have killed a 3 weeks running process by ctrl+c, to start a new process. As I see, although I have killed the process, the gpu memory is not released. According to nvidia-smi, the memory is free,…
yusuf
  • 3,591
  • 8
  • 45
  • 86
0
votes
1 answer

Caffe on Windows common.cpp:166] Check failed: error == cudaSuccess

When I use two different GPUs for Caffe win7, it does not work. OS system: win7 SP1 GPUs: Quadro K620, Tesla K40 Caffe: Caffe for windows The problem is that every time I update to the latest Driver 369.26 for K620, then Tesla K40 will not work. And…
Mona Jalal
  • 34,860
  • 64
  • 239
  • 408
0
votes
0 answers

CUDA: safeCall() Runtime API error invalid device symbol

I'm trying to run the cudaSift in CudaSift project with a Nvidia Tesla M2090 on a remote machine with CUDA 7.5. The machine has 4 of these GPUs, but I'm quite sure from the debuggining that the initialization is done correctly, anyway this is the…
justHelloWorld
  • 6,478
  • 8
  • 58
  • 138
0
votes
1 answer

Cuda does not modify input if grid dimension is too large

Consider the following code: #include #include #include #include using namespace std; __global__ void reduce_or(char* A) { if(threadIdx.x == 0) { A[blockIdx.x] = 1; } } #define…
user1512263
  • 217
  • 1
  • 7
0
votes
1 answer

Concurrent execution of two processes sharing a Tesla K20

I have been experiencing a strange behaviour when I launch 2 instances of a kernel in order to run at the same time while sharing the GPU resources. I have developed a CUDA kernel which aims to run in a single SM (Multiprocessor) where the threads…
Bub Espinja
  • 4,029
  • 2
  • 29
  • 46
0
votes
1 answer

Overlap kernel execution on multiple streams

We have a fairly a single kernel (see below) that we fire off with a grid, block of 1,1 kernel<<<1,1>>> And then it dynamically fires off lots of smaller kernels. In general, the data flows from kernel to kernel, with the input starting with the…
Dr.YSG
  • 7,171
  • 22
  • 81
  • 139
0
votes
1 answer

Is there a relation between single and double precision in NVIDIA Tesla?

In the model Tesla K20 the peak single-precision floating point performance is about 3.52 TFlops but the double-precision is 1.17 TFlops,so the ratio is 3. The Tesla K20X has 3.95 and 1.31, and Tesla K40 has 4.29 and 1.43 TFlops, the ratio seems to…
emmamm05
  • 13
  • 3
0
votes
1 answer

OpenCL: too slow async commands submiting

My OpenCL program (don't be scared, this is auto-generated code for 3D CFD) shows strange behavior -- a lot of time are spent in opencl_enq_job_* procedures (opencl_code.c), where are only async OpenCL…
Pavel
  • 363
  • 1
  • 2
  • 14
0
votes
1 answer

Concurrent Kernel Launch Example - CUDA

I'm attempting to implement concurrent kernel launches for a very complex CUDA kernel, so I thought I'd start out with a simple example. It just launches a kernel which does a sum reduction. Simple enough. Here it is: #include #include…
xiii1408
  • 361
  • 2
  • 11
0
votes
1 answer

Event Sampling in Tesla GPU

I am trying to work with the CUPTI library in CUDA to read some performance counters like instructions executed, memory access etc. When executing the sample provided with CUPTI installation (/usr/local/cuda-5.0/extras/CUPTI/sample/event_sampling)…
Vaibhav Sundriyal
  • 567
  • 5
  • 11
  • 18
1 2 3 4
5
6