Skip to content
Snippets Groups Projects

Repository graph

You can move around the graph by using the arrow keys.
Select Git revision
  • 3-error-in-run-the-program
  • containers
  • containers-m10
  • containers-m8
  • enable_svd
  • experiment
  • fix_layered_spheres_bug
  • magma_refinement
  • main
  • master default protected
  • original protected
  • parallel_angles
  • parallel_angles_gmu
  • profile_omp_leonardo
  • release9
  • script_devel
  • shaditest
  • test1
  • test_nvidia_profiler
  • NP_TMcode-M10a.02
  • NP_TMcode-M10a.01
  • NP_TMcode-M10a.00
  • NP_TMcode-M9.01
  • NP_TMcode-M9.00
  • NP_TMcode-M8.03
  • NP_TMcode-M8.02
  • NP_TMcode-M8.01
  • NP_TMcode-M8.00
  • NP_TMcode-M7.00
  • v0.0
30 results
Created with Raphaël 2.2.028May2726242221171615141312111097432130Apr292624231917125428Mar2625232221201918151312118765429Feb282723222120161413129765229Jan262524191817161514121110986542131Dec2928272625242120181615141312111076330Nov292827241310863231Oct29262019171613125429Sep26252422211918765415Febprepare moving to writing virtual files to disk at each MPI iterationFor some reason, I missed some commits you didmove binary file output to virtual file passed via MPI to process 0, thread 0 for actual writing to diskWrite CS_SPHERE, CSM_CLUSTER, CS1 and CS2 data to c_OCLUSet line-wise comparison as default and ignore lines starting with "INSERTION:" tagAssemble ASCII output on MPI proc 0, thread 0 then write only from thereadd some comments to VirtualAsciiFileRedirect output to VirtualAsciiFile objectsIgnore null-termination warning in format stringsImplement VirtualAsciiFile local interfaceDefine VirtualAsciiFile classMerge branch 'fix_io' into 'master'profile_omp_leo…profile_omp_leonardofix remounting files from threads and processes, fix pycompare accordinglyMerge branch 'prepare_magma' into 'master'There was no ifndef CXXFLAGS, thus its value was not respected if set outsideAdd nvidia-cuda-dev to the container of the gitlab runnertest_nvidia_pro…test_nvidia_profilerCorrect USE_NVTX flag logicUse compiler flags to enable NVIDIA profilingPlace NVIDIA markers at the same code block level and add them to the parallel loop functionEnable NVIDIA markersput the preprocessor checks for logger entries of different matrix-inversion options in the correct orderstreamline preprocessor checks for type definitionsfix type definition of argument for magma function callDisable separate CUDA and MAGMA loggingRebase loval prepare_magma on remote branchEnable line-wise pycompare option for big files.correct inconsistent devices between cuda and magma in case of ilp64fix typo in make.incupdate env variable compilation flags to allow for optional ilp64 interfacesEnsure that the devices array exists also when not using MAGMAUse CUDA calls to test for devicesFix inversion error logging and calculation stoppingStop calculation with message if first matrix inversion failsPut all loggers to debug levelAdded test cases with 48 speheres and 10 orders of expansionMerge MPI branch with MAGMA development branchRebase cluster.cpp to MPI versionMerge branch 'mpi_result_packaging' into 'master'Use null character to terminate chunk buffersRewind ASCII files after getting their size and skip EOF character transmission
Loading