Radeon pro w7900 does not work

[SturtKoh]

Issue Type

Feature Request

Have you reproduced the bug with TF nightly?

Yes

Source

binary

Tensorflow Version

tf 2.11.1.550

Custom Code

No

OS Platform and Distribution

Linux Ubuntu 22.04.2 LTS

Mobile device

No response

Python version

3.10.6

Bazel version

No response

GCC/Compiler version

No response

CUDA/cuDNN version

ROCM 5.4.6.50406-148-22.04

GPU model and memory

No response

Current Behaviour?

I have Radeon PRO w7900 (gfx1100)
It dosen't work with below messages...
I tensorflow/core/common_runtime/gpu/gpu_device.cc:1990] Ignoring visible gpu device (device: 0, name: , pci bus id: 0000:23:00.0) with AMDGPU version : gfx1100. The supported AMDGPU versions are gfx1030, gfx900, gfx906, gfx908, gfx90a.

when can i be able to use this device.
and how about replace gfx1100 from gfx1030 or add gfx1100 to source?

Standalone code to reproduce the issue

no standalone code

Relevant log output

I tensorflow/core/common_runtime/gpu/gpu_device.cc:1990] Ignoring visible gpu device (device: 0, name: , pci bus id: 0000:23:00.0) with AMDGPU version : gfx1100. The supported AMDGPU versions are gfx1030, gfx900, gfx906, gfx908, gfx90a.

[bondhugula]

I experience the same issue. I'm using the maintained wheel package tensorflow_rocm-2.11.1.550-cp310-cp310-manylinux2014_x86_64.whl from https://pypi.org/project/tensorflow-rocm/#files on a system with the AMD Radeon RX 7900 XTX.

python
Python 3.10.6 (main, Mar 10 2023, 10:55:28) [GCC 11.3.0] on linux
Type "help", "copyright", "credits" or "license" for more information.
>>> import tensorflow as tf
2023-06-04 09:14:08.461404: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations:  AVX2 FMA
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
t>>> tf.add(1,2).numpy()
2023-06-04 09:14:25.206047: I tensorflow/compiler/xla/stream_executor/rocm/rocm_gpu_executor.cc:843] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2023-06-04 09:14:25.516725: I tensorflow/compiler/xla/stream_executor/rocm/rocm_gpu_executor.cc:843] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2023-06-04 09:14:25.516780: I tensorflow/compiler/xla/stream_executor/rocm/rocm_gpu_executor.cc:843] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2023-06-04 09:14:25.516800: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1990] Ignoring visible gpu device (device: 0, name: Radeon RX 7900 XTX, pci bus id: 0000:83:00.0) with AMDGPU version : gfx1100. The supported AMDGPU versions are gfx1030, gfx900, gfx906, gfx908, gfx90a.
2023-06-04 09:14:25.517051: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations:  AVX2 FMA
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
2023-06-04 09:14:25.530288: I tensorflow/core/common_runtime/gpu_fusion_pass.cc:507] ROCm Fusion is enabled.
2023-06-04 09:14:25.530966: I tensorflow/core/common_runtime/gpu_fusion_pass.cc:507] ROCm Fusion is enabled.

I noticed a PR on gfx1100 support from a few weeks ago that is still open: #2101

[NiklasRichter2222]

I have the same problem. Is there anything to fix it yet?

[briansp2020]

Are there still people who are waiting for 7900XTX support? Though the performance is still a bit poor, TensorFlow-upstream now runs when built on the latest ROCm release. I was looking into the status of ROCm support for 7900XTX and found a few issues opened by different people and wanted to link all to the issue I opened in MIOpen repo. Though there has not been any confirmation from the developer, I think the performance issues are due to insufficient optimization of MIOpen.
ROCm/MIOpen#2342

[vampireLibrarianMonk]

Hello I am still receiving the following error with the latest docker and tensorflow-rocm 2.13.0.570.

2023-12-17 19:48:20.262228: I tensorflow/core/common_runtime/gpu/gpu_device.cc:2015] Ignoring visible gpu device (device: 0, name: , pci bus id: 0000:2d:00.0) with AMDGPU version : gfx1100. The supported AMDGPU versions are gfx1030, gfx900, gfx906, gfx908, gfx90a, gfx940, gfx941, gfx942.