I have installed:
- CUDA Version: 11.5.1
- cuQuantum SDK Version: 0.1.0.30
- cuTensor Version: 1.4.0.6
on a machine with Fedora 35 and a Quadro P520 card.
I built the cuQuantum examples (see the samples directory on Github).
All of the statevec examples fail:
> ./gate_application
Error: internal error in line 81
> ./permutation_matrix
permutation_matrix example FAILED: wrong result
> ./diagonal_matrix
diagonal_matrix example FAILED: wrong result
> ./exponential_pauli
exponential_pauli example FAILED: wrong result
> ./expectation
Error: internal error in line 79
> ./expectation_pauli
Error: internal error in line 72
> ./sampler
sampler example FAILED: wrong result
> ./measure_zbasis
measure_zbasis example FAILED: wrong result
> ./batch_measure
batch_measure example FAILED: wrong result
> ./accessor_get
accessor_get example FAILED: wrong result
> ./accessor_set
accessor_set example FAILED: wrong result
The tensornet_example appears to run OK (the output is shown below)
What can I do to diagnose/fix this problem?
Output from the tensornet example:
> ./tensornet_example
cuTensorNet-vers:1
===== device info ======
GPU-name:Quadro P520
GPU-clock:1493000
GPU-memoryClock:3004000
GPU-nSM:3
GPU-major:6
GPU-minor:1
========================
Include headers and define data types
Define network, modes, and extents
Total memory: 0.28 GiB
Allocate memory for data and workspace, and initialize data.
Initialize the cuTensorNet library and create a network descriptor.
Find an optimized contraction path with cuTensorNet optimizer.
Create a contraction plan for cuTENSOR and optionally auto-tune it.
Contract the network, each slice uses the same contraction plan.
numSlices: 1
29.89 ms / slice
484.97 GFLOPS/s
Free resource and exit.
Output from nvidia-smi:
> nvidia-smi
Wed Dec 29 06:52:09 2021
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 495.46 Driver Version: 495.46 CUDA Version: 11.5 |
|-------------------------------+----------------------+----------------------+
| GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|===============================+======================+======================|
| 0 Quadro P520 Off | 00000000:2D:00.0 Off | N/A |
| N/A 33C P8 N/A / N/A | 4MiB / 2002MiB | 0% Default |
| | | N/A |
+-------------------------------+----------------------+----------------------+
+-----------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=============================================================================|
| 0 N/A N/A 1201 G /usr/libexec/Xorg 4MiB |
+-----------------------------------------------------------------------------+