NVIDIA-Genomics-Research / GenomeWorks

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

[cudaextender] Calculate memory limits based on datastructures used. #576

Open atadkase opened 3 years ago

atadkase commented 3 years ago

Currently element and memory limits are artifacts of hardcoded global memory limits in SegAlign. To be replaced with actual calculation of memory requirements with sizes of datastructures taken into consideration. Also currently the max limit is based on total global memory, which should be replaced with memory available from the passed in allocator.