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

Add fatbin.ld linker script, compile with -fPIC, use -I instead of -isystem #3

Merged
merged 6 commits into from
May 14, 2021

Conversation

trxcllnt
Copy link
Collaborator

No description provided.

)

# Per-thread default stream option see https://docs.nvidia.com/cuda/cuda-runtime-api/stream-sync-behavior.html
# The per-thread default stream does not synchronize with other streams
target_compile_definitions(cugraph PUBLIC CUDA_API_PER_THREAD_DEFAULT_STREAM)

file(WRITE "${CUGRAPH_BINARY_DIR}/fatbin.ld"
Copy link
Owner

Choose a reason for hiding this comment

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

In what situations are you hitting cugraph needing the fatbin trick? Was this the solution to the relocation truncated to fit: R_X86_64_REX_GOTPCRELX error you reported?

Copy link
Collaborator Author

@trxcllnt trxcllnt May 14, 2021

Choose a reason for hiding this comment

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

I'm thinking that either this fixed it, or compiling with -fPIC did. Even if this wasn't the fix, we'll probably need it soon anyway because debug builds are starting to get big:

$ du -sh .cache/build/{Debug,Release}/{cudf,cugraph}-build/lib{cudf,cugraph}.so 2>/dev/null
3.2G	.cache/build/Debug/cudf-build/libcudf.so
2.7G	.cache/build/Debug/cugraph-build/libcugraph.so
142M	.cache/build/Release/cudf-build/libcudf.so
149M	.cache/build/Release/cugraph-build/libcugraph.so

@trxcllnt trxcllnt merged commit 2728d0e into robertmaynard:use_rapids_cmake May 14, 2021
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.

2 participants