Skip to content

Conversation

@yuchaocs
Copy link

Fix the bug that the ptx parser will be blocked when CUDART_VERSION < 6000.

@gangmul12
Copy link
Contributor

big thanks for fixing it

init_directive_state();
init_instruction_state();

#if (CUDART_VERSION >= 6000)
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

What exactly was the error here? The Travis regressions are passing CUDA 4.2.

Copy link
Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

No error message was output, but the simulator will just be stalled without any progress.

Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Sorry I let this die for so long...
I am really wondering what the use-case you observed the hang in is. We regress against CUDA 4.2 (which is obviously < 6) and the code does not hang. It seems very odd to me that this code should be CUDA-version specific.

Copy link
Author

@yuchaocs yuchaocs Oct 18, 2019

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Sorry I let this die for so long...
I am really wondering what the use-case you observed the hang in is. We regress against CUDA 4.2 (which is obviously < 6) and the code does not hang. It seems very odd to me that this code should be CUDA-version specific.

My configuration:
OS: ubuntu 14.04.1
gcc:4.6.4
cuda:4.2
simulator config: SM2_GTX480
use-case: all workloads in ispass2009

nassosliak pushed a commit to nassosliak/gpgpu-sim_distribution that referenced this pull request Oct 1, 2025
* 1. Add a queue to promote fairness CTA scheduling
2. Add a Perfect xbar interconnect option

* remove merge queue

* Should not change this

* rename pending cta to allocated_ctas

* run formatter
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants