* add Dockerfile and SConfigISCE to build cuda-enabled modules * add Dockerfile and SConfigISCE to build cuda-enabled modules * set correct name * update for centos7 and cuda-dev image * restore * disable GPUampcor * update * save * sync up Dockerfile updates * fix base image * change docker image names * create gpu vs. cpu specific tags * update with nodata WBD Stitcher * fix segmentation fault when running sciflo workflows - remove dependencies that downgrade the `geos` conda package * sync fix for segmentation fault to cuda builds * ping ffi to version 1.12.2 Latest version of ffi, 1.13.0, breaks installation of fpm: ``` $ sudo gem install --no-ri --no-rdoc fpm Fetching: cabin-0.9.0.gem (100%) Successfully installed cabin-0.9.0 Fetching: backports-3.17.2.gem (100%) Successfully installed backports-3.17.2 Fetching: arr-pm-0.0.10.gem (100%) Successfully installed arr-pm-0.0.10 Fetching: clamp-1.0.1.gem (100%) Successfully installed clamp-1.0.1 Fetching: ffi-1.13.0.gem (100%) ERROR: Error installing fpm: ffi requires Ruby version >= 2.3. ``` TODO: remove pin when ffi's backwards compatiblity is restored. * comment out unused import * add build circleci job to PR tests * pin ffi in cuda build * revert logging hackery * fix "target_include_directories called with non-compilable target type" errors * Keep source directory for topsStack Co-authored-by: dustinlo <dustin.k.lo@jpl.nasa.gov> Co-authored-by: shitong01 <stchin@ntu.edu.sg> Co-authored-by: Ryan Burns <47790121+rtburns-jpl@users.noreply.github.com> |
||
---|---|---|
.. | ||
cuda.py |