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

ggml : add test for SVE and disable when it fails #10906

Merged
merged 1 commit into from
Dec 20, 2024
Merged

Conversation

slaren
Copy link
Collaborator

@slaren slaren commented Dec 19, 2024

I verified that this disables SVE when building on Snapdragon 8 Gen 3, which is otherwise incorrectly enabled with -mcpu=native (clang 19.1.6)

I don't have a machine with SVE to test if it is correctly enabled when supported, any help testing this would be appreciated.

@github-actions github-actions bot added the ggml changes relating to the ggml tensor library for machine learning label Dec 19, 2024
Copy link
Owner

@ggerganov ggerganov left a comment

Choose a reason for hiding this comment

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

Tentatively approving, although I don't have any SVE hardware to test this. If there is some cloud hosting with SVE-enabled machines, I can give this a try.

@angt
Copy link
Contributor

angt commented Dec 20, 2024

SVE works and is detected on graviton4:

-- ARM detected
-- Performing Test GGML_COMPILER_SUPPORTS_FP16_FORMAT_I3E
-- Performing Test GGML_COMPILER_SUPPORTS_FP16_FORMAT_I3E - Failed
-- Performing Test GGML_MACHINE_SUPPORTS_dotprod
-- Performing Test GGML_MACHINE_SUPPORTS_dotprod - Success
-- Performing Test GGML_MACHINE_SUPPORTS_i8mm
-- Performing Test GGML_MACHINE_SUPPORTS_i8mm - Success
-- Performing Test GGML_MACHINE_SUPPORTS_sve
-- Performing Test GGML_MACHINE_SUPPORTS_sve - Success
-- ARM feature DOTPROD enabled
-- ARM feature SVE enabled
-- ARM feature MATMUL_INT8 enabled
-- ARM feature FMA enabled
-- ARM feature FP16_VECTOR_ARITHMETIC enabled
-- Adding CPU backend variant ggml-cpu: -mcpu=neoverse-v2+crc+sve2-aes+sve2-sha3+dotprod+i8mm+sve 

@slaren slaren merged commit 21ae3b9 into master Dec 20, 2024
48 checks passed
@slaren slaren deleted the sl/fix-sve-native branch December 20, 2024 12:31
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
ggml changes relating to the ggml tensor library for machine learning
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants