rapidsai / raft

RAFT contains fundamental widely-used algorithms and primitives for machine learning and information retrieval. The algorithms are CUDA-accelerated and form building blocks for more easily writing high performance applications.
https://docs.rapids.ai/api/raft/stable/
Apache License 2.0
746 stars 189 forks source link

Add workaround for syevd in CUDA 12.0 #2332

Closed lowener closed 2 months ago

lowener commented 4 months ago

Bug 4580093 of cusolver is causing an issue with cusolverDnXsyevd. This bug has been seen in https://github.com/rapidsai/cuml/issues/5555 and impact PCA and Linear Regression with CUDA 12.0+. Setting the stream to a different value than cudaStreamPerThread seems to solve it as a workaround.

cjnolet commented 2 months ago

/merge