Missing NVDEC on multiple GPU system

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU): NVIDIA A16
• DeepStream Version: 6.1.1
• JetPack Version (valid for Jetson only) N/A
• TensorRT Version N/A
• NVIDIA GPU Driver Version (valid for GPU only) : 515.65.01
• Issue Type( questions, new requirements, bugs) bug??
• How to reproduce the issue ? (This is for bugs. Including which sample app is using, the configuration files content, the command line used and other details for reproducing)

We have a machine with 8x NVIDIA A16 GPU. Each NVIDIA A16 GPU present itself as 4 GPU to the operating system. So, the output command for the ‘nvidia-smi’ command present 32 GPUs on the machine.

The test command works if we select a GPU id between 0 and 15.

gst-launch-1.0 -m rtspsrc location=rtsp://wowzaec2demo.streamlock.net/vod/mp4:BigBuckBunny_115k.mp4 ! rtph264depay ! nvv4l2decoder ! debugspy ! fakesink

If we select a GPU greater than 15 we get the error bellow:

/opt/nvidia/deepstream/deepstream-6.1# gst-launch-1.0 -m rtspsrc location=rtsp://wowzaec2demo.streamlock.net/vod/mp4:BigBuckBunny_115k.mp4 ! rtph264depay ! nvv4l2decoder ! debugspy ! fakesink

(gst-plugin-scanner:27): GStreamer-WARNING **: 19:48:32.636: Failed to load plugin ‘/usr/lib/x86_64-linux-gnu/gstreamer-1.0/deepstream/libnvdsgst_udp.so’: librivermax.so.0: cannot open shared object file: No such file or directory

(gst-plugin-scanner:27): GStreamer-WARNING **: 19:48:32.649: Failed to load plugin ‘/usr/lib/x86_64-linux-gnu/gstreamer-1.0/libgstchromaprint.so’: libavcodec.so.58: cannot open shared object file: No such file or directory

Setting pipeline to PAUSED …

ERROR: Pipeline doesn’t want to pause.

Got message #10 from element “fakesink0” (state-changed): GstMessageStateChanged, old-state=(GstState)GST_STATE_NULL, new-state=(GstState)GST_STATE_READY, pending-state=(GstState)GST_STATE_VOID_PENDING;

Got message #11 from element “debugspy0” (state-changed): GstMessageStateChanged, old-state=(GstState)GST_STATE_NULL, new-state=(GstState)GST_STATE_READY, pending-state=(GstState)GST_STATE_VOID_PENDING;

Got message #12 from element “nvv4l2decoder0” (error): GstMessageError, gerror=(GError)NULL, debug=(string)“v4l2_calls.c(651):\ gst_v4l2_open\ ():\ /GstPipeline:pipeline0/nvv4l2decoder:nvv4l2decoder0:\012system\ error:\ No\ such\ file\ or\ directory”;

ERROR: from element /GstPipeline:pipeline0/nvv4l2decoder:nvv4l2decoder0: Could not open device ‘/dev/nvidia0’ for reading and writing.

Additional debug info:

v4l2_calls.c(651): gst_v4l2_open (): /GstPipeline:pipeline0/nvv4l2decoder:nvv4l2decoder0:

system error: No such file or directory

Setting pipeline to NULL …

Freeing pipeline …

• Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description)

So, we have this unusual behavior, only the GPUs from 0 to 15 have the NVENC. The GPUs from 16 to 31 present the error above.

Regards,