Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[BUG] Compressions not working on Titan Xp (CC 6.1) #98

Open
DrivenByNostalgia opened this issue Mar 1, 2024 · 4 comments
Open

[BUG] Compressions not working on Titan Xp (CC 6.1) #98

DrivenByNostalgia opened this issue Mar 1, 2024 · 4 comments

Comments

@DrivenByNostalgia
Copy link

Hi everyone,

should nvCOMP be working for Pascal generation cards? Despite the docs mentioning that the minimum hardware requirement for nvCOMP was compute capabilities 6.0 ("Pascal (sm60) or higher GPU architecture is required. Volta (sm70)+ GPU architecture is recommended for best results."), the compression fails on all our systems with Titan Xp cards, which have compute capability 6.1. On newer cards, all compression modes work as desired. We use nvCOMP in version nvcomp_3.0.5_windows_12.x.

We observe three different behaviors:

  1. BitcompManager::get_compressed_output_size crashes the application with: "Unhandled exception at 0x00007FFD07BB286E (ucrtbase.dll) in *.exe: Fatal program exit requested.".
  2. ZstdManager::compress throws the exception: "CUDA error: 98 (cudaErrorInvalidDeviceFunction: invalid device function)
    from: cudaOccupancyMaxActiveBlocksPerMultiprocessor( &num_blocks_per_sm, lz_compression_kernel, block_size, 0 )".
  3. get_compressed_output_size with all other managers (ANS, Cascaded, Deflate, Gdeflate, LZ4, Snappy) returns 0 on any compression input.

In summary, none of the compressions work on any of our Titan Xp cards. We do not have any other Pascal cards for testing, so I cannot say whether the documented minimum requirement of compute capability is wrong and Pascal cards are not supported altogether or whether this is an issue specific to the Titan Xp. For the moment, we can circumvent the issue by simply deactivating compression on systems with CC < 7.0, but it would be sad to lose this feature for an entire GPU generation.

Best regards,
Daniel

@DrivenByNostalgia DrivenByNostalgia added ? - Needs Triage bug Something isn't working labels Mar 1, 2024
@eschmidt-nvidia
Copy link
Collaborator

Hi Daniel,

Unfortunately, this is a bug in our documentation.

We depend on cuda::std::atomic, which only supports CC >= 7.0 on Windows (CC >= 6.0 on Unix).

As a result, our Windows builds do not support CC < 7.0.

-Eric

@DrivenByNostalgia
Copy link
Author

Ok, thank you for clarifying that.

Copy link

github-actions bot commented Apr 4, 2024

This issue has been labeled inactive-30d due to no recent activity in the past 30 days. Please close this issue if no further response or action is needed. Otherwise, please respond with a comment indicating any updates or changes to the original issue and/or confirm this issue still needs to be addressed. This issue will be labeled inactive-90d if there is no activity in the next 60 days.

Copy link

github-actions bot commented Jul 3, 2024

This issue has been labeled inactive-90d due to no recent activity in the past 90 days. Please close this issue if no further response or action is needed. Otherwise, please respond with a comment indicating any updates or changes to the original issue and/or confirm this issue still needs to be addressed.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

No branches or pull requests

2 participants