The number of DLA core does not work


when I run TensorRT sample sample_mnist_api
./sample_mnist_api --data-dir /usr/src/tensorrt/data/mnist --useDLACore=1

in Jetson Power GUI
dla0 1600.0MHZ
dla1 offline

no matter useDLACore=0 or useDLACore=1


TensorRT Version:
GPU Type:
Nvidia Driver Version:
CUDA Version:
CUDNN Version:
Operating System + Version:
Python Version (if applicable):
TensorFlow Version (if applicable):
PyTorch Version (if applicable):
Baremetal or Container (if container which image + tag):

  • Jetson AGX Orin
    • Jetpack UNKNOWN [L4T 35.1.0]
    • NV Power Mode: MAXN - Type: 0
    • jetson_stats.service: active
  • Libraries:
    • CUDA: 11.8.89
    • cuDNN:
    • TensorRT:
    • OpenCV: 4.4.0 compiled CUDA: YES
    • VPI: 2.1.6
    • Vulkan: 1.3.203


We are moving this post to the Jetson AGX Orin forum to get better help.

Thank you.


We are trying to reproduce this issue internally.
Will share more information with you later.


I am trying cuda samples – cuDLAStandaloneMode

nDLACore = 1
err = cudlaCreateDevice(nDLACore, &devHandle, CUDLA_STANDALONE);

this sample works.


Just want to confirm first.

Do you indicate that the TensorRT sample cannot deploy on the DLA core=1?
But cuDLA can run on DLA core=1 successfully?


This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.