Stack Overflow
Stack Overflow

Questions tagged [amd-rocm]

The ROCm Platform brings a rich foundation to advanced computing by integrating the CPU and GPU with the goal of solving real-world problems. This software enables the high-performance operation of AMD GPUs for computationally-oriented tasks in the Linux operating system.

42 questions
1
vote
0 answers

I am installing rocM to use tensorflow in the ec2 g4ad environment, but an error ''ROCk module is NOT loaded, possibly no GPU devices'' occurs

I was setting up to run tensorflow in g4ad environment (amd gpu). i followed this https://github.com/Grench6/RX580-rocM-tensorflow-ubuntu20.4-guide usname -a => Linux ip-172-31-37-18 5.4.0-1060-aws #63~18.04.1-Ubuntu SMP Mon Nov 15 14:31:31 UTC 2021…
yyyy
  • 57
  • 6
1
vote
1 answer

Issue with 3D convolutions with PyTorch using ROCM/MIOpen - Forward Convolution cannot be executed due to incorrect params

I am trying to use PyTorch's nn.Conv3d for convolutional autoencoders in a system with AMD GPUs. We have the latest ROCM (4.5) and MIOpen (2.14). The same training script works with NVIDIA GPUs. I managed to get the same training with nn.Conv2D,…
Eray Inanc
  • 21
  • 2
1
vote
1 answer

ROCm Installation with Fedora 32

I have tried to install ROCm ( https://rocmdocs.amd.com/en/latest/ ) on Fedora 32 using the process that was described here https://rigtorp.se/notes/rocm/ The rocminfo function correctly identifies my Radeon RX 5700. Codes from hip-samples compile…
Des Albert
  • 281
  • 2
  • 5
  • 17
1
vote
1 answer

Limit MPI to run on single GPU even if we have single Node multi GPU setup

I am new to distributed computing and I am trying to run a program which uses MPI and ROCm(AMD framework to run on GPU). The command I am using to run the program is mpirun -np 4 ./a.out But it is defaultly running on the available 2 GPUs in my…
Sai Pavan Kalyan Munaga
  • 112
  • 2
  • 9
1
vote
2 answers

No OpenCL / HSA support for rx 470 / vega 8 on Ubuntu 18.04 using ROCM

I installed ROCm, ROCm-Tensorflow and PlaidML on a fresh installation of Ubuntu 18.04 using the instructions given…
Carl Schaf
  • 11
  • 2
1
vote
1 answer

C++: confusing variadic template causing "candidate function not viable" error

I was trying to port a CUDA project into ROCm platform which make use of C++ templates extensively. During this process, I am getting following compilation error /root/warp-ctc/include/detail/gpu_ctc.h:381:5: error: no matching function for call to…
harish2704
  • 591
  • 6
  • 16
1
vote
0 answers

Tensorflow on AMD GPU

I have AMD RX 470 and want to run Deep Neural Net using my GPU. I have checked ROCm and could not understand how to get this running. I also could not find any simple instructions to install. I am new to Ubuntu, if anyone can provide simple…
Tushar Gautam
  • 95
  • 9
0
votes
0 answers

How to get PyTorch neural network working on Ryzen 5600G with RoCm 5.5?

Asked here. No reply. Perhaps people on the PyTorch forum aren't familiar with RoCm with the processor's GPU. The output of running on CPU is: Files already downloaded and verified Files already downloaded and verified GPU available? True Number of…
Nav
  • 19,885
  • 27
  • 92
  • 135
0
votes
0 answers

What is the correct way of using mixed_precision with tensorflow-rocm?

From what I can read, mixed precision has been supported for a long time by rocm and in the TensorFlow-rocm upstream package. However, when I try to use it, tf still reports compatibility issues: Mixed precision compatibility check (mixed_float16):…
user1603472
  • 1,408
  • 15
  • 24
0
votes
0 answers

pyopencl and rocm (7900 XTX)

I've spent a few days trying to get pyopencl to work with my 7900 XTX GPUs. I have drivers installed, rocm 5.5, and I can see the devices when I run clinfo but cl.get_platforms() still fails with PLATFORM_NOT_FOUND_KHR. Would appreciate it if…
William Gazeley
  • 141
  • 8
0
votes
1 answer

Setting up Pytorch in Venv for both CUDA and ROCm

I want to install PyTorch on multiple different machines with different hardwares, using both CUDA and ROCm hardware, but I'm not sure how to setup a venv that works for both, so to have as simple an environment solution as possible for all. I've…
Udinanon
  • 54
  • 4
0
votes
1 answer

Segfault when using pytorch with rocm in linux

I have an amd rx 6600 and I am trying to use pytorch with rocm. I am running archlinux and using the package provided by the distro. When I try to access the gpu memory the program crashes. It seems that memory is being allocated but I cannot read…
Moshiur Rahman
  • 103
  • 7
0
votes
0 answers

Can OneAPI or ROCm run natively on Windows with AMD GPU?

I am trying to identify any potential options to accelerate linear algebra calculations by using the GPU. To be more precise I need to accelerate an explicit dynamics solver. Since in each increment it solves a linear system I thought maybe I could…
Greydas
  • 1
  • 2
0
votes
1 answer

How do I trace power consumption for Radeon GPUs?

I developed an OpenCL application and now I'm trying to assess the energy consumption of the same application running on two different GPUs: one NVIDIA Titan V and one Radeon RX6900 XT. The idea is to measure the instant power of the GPU at regular…
Iago Storch
  • 58
  • 5
0
votes
0 answers

AMD ROCm with Pytorch on Navi10 (RX 5700 XT) and HSA_OVERRIDE_GFX_VERSION=10.3.0 fails

I saw this post recommending to use HSA_OVERRIDE_GFX_VERSION=10.3.0 to run Pytorch with ROCm on a 5700XT card, but I could'nt get it to work. My steps: sudo pacman -S python-pytorch-opt-rocm git clone https://github.com/pytorch/examples.git cd…
Eric Armbruster
  • 9
  • 2
1
2
3