NvMapReserveOp failed when running Cuda-segmentation

Hello.

I’m trying to use your CUDA-optimized PCL algorithms. (GitHub - NVIDIA-AI-IOT/cuda-pcl: A project demonstrating how to use the libs of CUDA-PCL.)

With the Cuda-segmentation demo, I get an CUDA error on the cudaExtractCluster part, while the cudaSegmentation part runs fine.
Other demos such as cuda-filter runs fine.

NvMapReserveOp 0x80000003 failed [22]
NvMapReserveOp 0x80000001 failed [22]
NvMapReserveOp 0x80000000 failed [22]

Do you know why this happens?
And can you help me use the Cuda-segmentation?

Thank you!

Here is the .pcd file:

Please let me know if the link has expired, then I’ll upload it again.

Jetson AGX Xavier Developer Kit
PCL 1.8
CUDA 10.2

Thanks for reporting this.

We are trying to reproduce this issue internally.
Will get back to you later.

Any progress on this?

Hi,

Thanks for your patience.

The reason of the failure is that the scan range is too large to fit in the cache.
We have tested the default sample.pcd on JetPack 4.6 and it can work well without error.

$ ./demo ./sample.pcd 

GPU has cuda devices: 1
----device id: 0 info----
  GPU : Xavier 
  Capbility: 7.2
  Global memory: 31920MB
  Const memory: 64KB
  SM in a block: 48KB
  warp size: 32
  threads in a block: 1024
  block dim: (1024,1024,64)
  grid dim: (2147483647,65535,65535)

-------------------------
CUDA segment by Time: 20.6349 ms.
CUDA modelCoefficients: -0.00269913 0.0424975 0.999093 2.10639
CUDA find points: 7519
-------------------------
PCL(CPU) segment by Time: 69.4973 ms.
Model coefficients: -0.0026991 0.0424981 0.999093 2.10639
Model inliers: 7519

Thanks.

Any tips on how I can make it work for my case then?

Hi,

Your test_P.pcd file is an HTML file rather than pcd file.
Could you generate a data file with generate PCD format and try it again?

sample.pcd

# .PCD v0.7 - Point Cloud Data file format
VERSION 0.7
FIELDS x y z
SIZE 4 4 4
TYPE F F F
COUNT 1 1 1
WIDTH 119978
HEIGHT 1
VIEWPOINT 0 0 0 1 0 0 0
POINTS 119978
DATA ascii
62.7612 8.7600002 2.3940001
60.686398 8.6639996 2.3243999
58.545597 8.7323999 2.2523999
58.503597 8.9136 2.2523999
57.5868 8.9591999 2.2212
...

test_P.pcd

<!DOCTYPE html>
<html lang="en" data-color-mode="auto" data-light-theme="light" data-dark-theme="dark">
  <head>
    <meta charset="utf-8">
  <link rel="dns-prefetch" href="https://github.githubassets.com">
  <link rel="dns-prefetch" href="https://avatars.githubusercontent.com">
  <link rel="dns-prefetch" href="https://github-cloud.s3.amazonaws.com">
  <link rel="dns-prefetch" href="https://user-images.githubusercontent.com/">
  <link rel="preconnect" href="https://github.githubassets.com" crossorigin>
  <link rel="preconnect" href="https://avatars.githubusercontent.com">



  <link crossorigin="anonymous" media="all" integrity="sha512-1G4rYJktwRTQKn7fVfJUxH8RRZFUJlGo77xMZfBfIhZPx4BHVrzPE1VgnafttXI8G3y/PywH3uXyhNkSLp3+oA==" rel="stylesheet" href="https://github.githubassets.com/assets/light-d46e2b60992dc114d02a7edf55f254c4.css" /><link crossorigin="anonymous" media="all" integrity="sha512-hI5b2oqTE9njfjYrfuzXqA4bSGSNrE5OMc9IiFhZy+RDGg9Qn4Si1A97o0MlinlwFt3xAifvoLX0s7jHmHSvVw==" rel="stylesheet" href="https://github.githubassets.com/assets/dark-848e5bda8a9313d9e37e362b7eecd7a8.css" /><link data-color-theme="dark_dimmed" crossorigin="anonymous" media="all" integrity="sha512-klQdb3t14AYaRMkB0v9buaf5Ftfbec/sbxdkvyQpG6oBvzZxxH6N5QwA4llOyZsoyjqiZaTra2ci5TgInnLqQg==" rel="stylesheet" data-href="https://github.githubassets.com/assets/dark_dimmed-92541d6f7b75e0061a44c901d2ff5bb9.css" /><link data-color-theme="dark_high_contrast" crossorigin="anonymous" media="all" integrity="sha512-CBsfpBvg1D/Hvn8FFY4JwUVgoKjgynOSFKwgThDHrHASVid/Isgz0ueab5xSuSVx8vEvNL9UfYcpWIJRJYTCjg==" rel="stylesheet" data-href="https://github.githubassets.com/assets/dark_high_contrast-081b1fa41be0d43fc7be7f05158e09c1.css" /><link data-color-theme="dark_colorblind" crossorigin="anonymous" media="all" integrity="sha512-09ipkynAtzCqasl2D2//N51bUOVnOzBFdadcXdMWyphI81s1FWmJ9AD1NRq3e0PMfiJEiVSm9mjTYd7gv2xtWA==" rel="stylesheet" data-href="https://github.githubassets.com/assets/dark_colorblind-d3d8a99329c0b730aa6ac9760f6fff37.css" /><link data-color-theme="light_colorblind" crossorigin="anonymous" media="all" integrity="sha512-OJwnC/pGdOV3QMoWud8vp0nxtQhtzAcpNWB7mSSh/e7fPslExSb07EOdNTAJsBAS4bN7Yrdxm2F7htANgTIMsA==" rel="stylesheet" data-href="https://github.githubassets.com/assets/light_colorblind-389c270bfa4674e57740ca16b9df2fa7.css" /><link data-color-theme="light_high_contrast" crossorigin="anonymous" media="all" integrity="sha512-5swg0RJGlhj0UH3SLkJ6e/BYm/DmpyGTaUSCUBhf1HtC4lBV+zM9mxOQ8febH318pxcUzUpp09qi0z7EKfWuDQ==" rel="stylesheet" data-href="https://github.githubassets.com/assets/light_high_contrast-e6cc20d112469618f4507dd22e427a7b.css" />
  <link crossorigin="anonymous" media="all" integrity="sha512-T3N453hWCYsL8yKfu3yye2yyO/D51Lq2iT5svAdl7UKvV2rBPcV7iOgr3fihzB9vYV7YFIK3PxpyTTkfxAshog==" rel="stylesheet" href="https://github.githubassets.com/assets/frameworks-4f7378e77856098b0bf3229fbb7cb27b.css" />
  <link crossorigin="anonymous" media="all" integrity="sha512-yWhDdGSAlV6IshHsZl8tDb/WDirYex8FzdWXPDjYMuhx2dXdYgomJyseMLeOWCZg2Ym2Ui/bKxzkz5EvUXaeOg==" rel="stylesheet" href="https://github.githubassets.com/assets/behaviors-c96843746480955e88b211ec665f2d0d.css" />
  <link crossorigin="anonymous" media="all" integrity="sha512-MCJFYfbQoT4EXC6aWx5Wghs8FC/jslHEeN2iWXphliccmede2dQlhIBTAUCBq9Yu5poltu4askungzvyCsycGg==" rel="stylesheet" href="https://github.githubassets.com/assets/tab-size-fix-30224561f6d0a13e045c2e9a5b1e5682.css" />
  
  
  
  <link crossorigin="anonymous" media="all" integrity="sha512-s6gQ9zPmpX9HnhI35eVCp8zhuTUUEsP2bEbw5wm8DqB0eGsiHVfGDC+mIBp9RvV3pQLa2Gmu5GRqKVzIjb5lDg==" rel="stylesheet" href="https://github.githubassets.com/assets/github-b3a810f733e6a57f479e1237e5e542a7.css" />
...

Thanks.

Hello again.

Could you try this link?

When I download from the link, the start of the file looks like this:

.PCD v0.7 - Point Cloud Data file format

VERSION 0.7
FIELDS x y z intensity
SIZE 4 4 4 4
TYPE F F F F
COUNT 1 1 1 1
WIDTH 11561
HEIGHT 1
VIEWPOINT 0 0 0 1 0 0 0
POINTS 11561
DATA ascii
0.10262119 3.9719279 -1.8527585 6
-2.0323465 28.214588 -0.49376351 7
0.65582639 25.100803 -0.73075426 5
-0.13816692 6.0729017 -1.7004814 11
0.21307819 8.065402 -1.6136531 6
-0.9215402 41.029652 0 5

Thank you.

Hi,

Thanks.

The file looks good.
We will test this internally and share more information.

Hi,

Thanks for the pcd file.

We test it on Xavier with JetPack 4.6.
Confirmed that the cuda-segmentation sample can work correctly.

$ ./demo test14frame350.pcd

GPU has cuda devices: 1
----device id: 0 info----
  GPU : Xavier
  Capbility: 7.2
  Global memory: 31920MB
  Const memory: 64KB
  SM in a block: 48KB
  warp size: 32
  threads in a block: 1024
  block dim: (1024,1024,64)
  grid dim: (2147483647,65535,65535)

-------------------------
CUDA segment by Time: 11.1412 ms.
CUDA modelCoefficients: -0.00629804 -0.0541567 0.998513 2.0456
CUDA find points: 1392
-------------------------
PCL(CPU) segment by Time: 14.0393 ms.
Model coefficients: -0.00629818 -0.0541568 0.998513 2.0456
Model inliers: 1392

Thanks.

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