search

NVIDIA-Genomics-Research / GenomeWorks

SDK for GPU accelerated genome assembly and analysis
https://clara-parabricks.github.io/GenomeWorks/
Apache License 2.0
286 stars 76 forks source link

[cudapoa] reduce register count in cudapoa kernels #547

Closed tijyojwad closed 4 years ago

tijyojwad commented 4 years ago

The recent changes to banded and adaptive banded have increased the register count in cuda kernels and hence limited occupancy of the kernels. Investigate steps to keep the register count in check.