torch.linalg.eigvals with XPU #566
Description
Describe the issue
Sample code
import torch
import intel_extension_for_pytorch as ipex
matrix = torch.randn(3, 3).to("xpu")
print(matrix.device)
print(torch.linalg.eigvals(matrix).device)
will produce the following error
RuntimeError: Expected all tensors to be on the same device, but found at least two devices, xpu:0 and cpu! (when checking argument for argument real in method wrapper_XPU_out_complex_out)
When inputs are on a CUDA device, this function synchronizes that device with the CPU.
I believe the synchronisation is not implemented for this function in XPU.
Environment
PyTorch version: 2.1.0a0+cxx11.abi
PyTorch CXX11 ABI: Yes
IPEX version: 2.1.10+xpu
IPEX commit: a12f9f650
Build type: Release
OS: Rocky Linux release 8.9 (Green Obsidian) (x86_64)
GCC version: (GCC) 8.5.0 20210514 (Red Hat 8.5.0-20)
Clang version: N/A
IGC version: 2024.0.0 (2024.0.0.20231017)
CMake version: version 3.17.0
Libc version: glibc-2.28
Python version: 3.10.4 (main, Mar 31 2022, 08:41:55) [GCC 7.5.0] (64-bit runtime)
Python platform: Linux-4.18.0-477.43.1.el8_8.x86_64-x86_64-with-glibc2.28
Is XPU available: True
DPCPP runtime version: 2024.0
MKL version: 2024.0
GPU models and configuration:
[0] _DeviceProperties(name='Intel(R) Data Center GPU Max 1550', platform_name='Intel(R) Level-Zero', dev_type='gpu, support_fp64=1, total_memory=131072MB, max_compute_units=1024, gpu_eu_count=1024)
Intel OpenCL ICD version: 23.22.26516.34-682.el8_8
Level Zero version: 1.3.26516.34-682.el8_8
Versions of relevant libraries:
[pip3] intel-extension-for-pytorch==2.1.10+xpu
[pip3] numpy==1.26.4
[pip3] torch==2.1.0a0+cxx11.abi
[pip3] torch-fidelity==0.3.0
[pip3] torchaudio==2.1.0a0+cxx11.abi
[pip3] torchmetrics==1.3.2
[pip3] torchvision==0.16.0a0+cxx11.abi