rocm-arch VS tensorflow-upstream

I never could get rocm/hip to work on mint after going round and round several times over months. I finally switched distros and had it running in minutes under an arch based distro using https://github.com/rocm-arch/rocm-arch

I struggled for some time trying to make AMD's Rocm/HIP work in linux so I could use my GPU with blender. Never could get it to work across several distros (mint, ubuntu, fedora). I finally dropped it and just ran GPUless for months. I have since found myself on Manjaro and gave it another try after finding this github. Using this on manjaro I was able to install rocm/hip in NO time and am now using blender with my AMD GPU in linux.

To do this, you need to use the repository: https://github.com/rocm-arch/rocm-arch and checkout to commit 135aa026557d7c11d5f446d6c01521535e9e5747

To make it brief. Trying to install rocm-opencl-runtime and rocm-hip-runtime from rocm-arch on github.

rocm-arch README

Then why doesn't it work unless I have this installed?

Yeah, I had to install rocm using this method https://github.com/rocm-arch/rocm-arch. Afaik, it doesn't replace mesa, but provides OpenCL and HIP.

I tried to train another model using InceptionResNetV2 and the same issues happens. Also, this happens even using the model.predict() method if using the GPU. Probably this is an issue related to the AMD Radeon RX 6700 XT or some mine misconfiguration. System Inormation: ArchLinux 6.1.32-1-lts - AMD Radeon RX 6700 XT - gfx1031 Opened issues: - https://github.com/RadeonOpenCompute/ROCm/issues/2250 - https://github.com/ROCmSoftwarePlatform/tensorflow-upstream/issues/2125

AMD has had their ROCM Tensorflow port for quite a while now: https://github.com/ROCmSoftwarePlatform/tensorflow-upstream and it works pretty well on my RX 6800; unfortunately it's only compatible with Linux as the ROCm stack is built on top of the Linux kernel I believe

I mean, tensorflow has a fork with ROCm support which is maintained by AMD https://github.com/ROCmSoftwarePlatform/tensorflow-upstream although I'm not entirely sure what you're AI workloads are specifically, I'm just throwing out tensorflow because it's popular. On the enterprise side they also have radeon instinct MI, although I assume you're probably not using enterprise HW but I wanted to throw it out there anyway.

It might work, but will likely require building pytorch/tensorflow from source. I compiled both with ROCm 5.0 today, Pytorch is painless but TF required using this repo maintained by AMD instead

I saw this https://github.com/ROCmSoftwarePlatform/tensorflow-upstream and I thought it could be a way. Do you think it is not stable and ready to be used ?

The repo exists: https://github.com/ROCmSoftwarePlatform/tensorflow-upstream

https://github.com/ROCmSoftwarePlatform/tensorflow-upstream#tensorflow-rocm-port

I tried some case ROCm & Tensorflow-rocm as is on this page( tensorflow-upstream/tensorflow-rocm-release.md at develop-upstream · ROCmSoftwarePlatform/tensorflow-upstream · GitHub ), but I failed to run a simple CNN model with fashion-mnist datasets.