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

Reads basecalled: Metal command buffer execution failed #35

Closed
vdejager opened this issue Oct 17, 2022 · 3 comments
Closed

Reads basecalled: Metal command buffer execution failed #35

vdejager opened this issue Oct 17, 2022 · 3 comments
Assignees
Labels
bug Something isn't working

Comments

@vdejager
Copy link

Om MacOS M1 with 16 GB memory I get

dorado basecaller --emit-fastq ~/bin/dorado-0.0.1+4b67720-Darwin/bin/dna_r9.4.1_e8_sup@v3.3 ./fast5 | gzip > run1.fastq.gz

Creating basecall pipeline
Reads basecalled: 200Metal command buffer execution failed: 5, try #0
Reads basecalled: 300Metal command buffer execution failed: 5, try #0
Metal command buffer execution failed: 5, try #1
Metal command buffer execution failed: 5, try #2

etc. etc.
what can I do to solve this?

@vellamike vellamike self-assigned this Oct 18, 2022
@vellamike vellamike added the bug Something isn't working label Oct 18, 2022
@vellamike
Copy link
Collaborator

Hi @vdejager - are basecalls actually produced or is this error preventing that from happening?

@sabercrombie
Copy link

I think this is caused by memory usage exceeding physical ram, leading to in effect swapping, causing GPU command buffer submissions to time out.

We're looking at reducing memory usage, but an interim solution would be to reduce batch size by adding -b 192.

@iiSeymour iiSeymour assigned sabercrombie and unassigned vellamike Oct 19, 2022
@vellamike
Copy link
Collaborator

@vdejager Dorado version 0.0.2 Should fix this problem - can you try it?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
bug Something isn't working
Projects
None yet
Development

No branches or pull requests

4 participants