Skip to content
Snippets Groups Projects

Repository graph

You can move around the graph by using the arrow keys.
Select Git revision
  • d2bcb7fa5487c523c42b2e71b4bd7844d9987198
  • master default protected
  • 3-error-in-run-the-program
  • containers
  • containers-m10
  • containers-m8
  • enable_svd
  • experiment
  • magma_refinement
  • main
  • offload_trapping
  • original protected
  • parallel_angles
  • parallel_angles_gmu
  • parallel_trapping
  • profile_omp_leonardo
  • release9
  • script_devel
  • shaditest
  • test1
  • test_nvidia_profiler
  • NP_TMcode-M10a.03
  • 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
33 results
Created with Raphaël 2.2.022Jul211918161411972113Jun12111098654328May27212019141097630Apr16151411987654327Mar2625242320191865425Feb2421191614131110987630Jan2924232221201720Dec191887654229Nov28262522212019181514131187631Oct29282524222118158726Sep242320131211543221Aug842129Jul28252321191716151211109827Jun262524211916141265331May29282726242221171615141312111097432130Apr29Add vkv and vec_vkzm vectors to mappingoffload_trappingoffload_trappingAdded doxygen inline documentation expansionUse separate functions to map data, calculate loop and unmapFix typo in configuration messagesWrap offloadable code in separate functionMerge branch 'master' into script_develscript_develscript_develPrepare data mapping in cfrfme.cppRemove unified shared memory requirement from libraryMerge branch 'master' into offload_trappingMerge branch 'script_devel' into 'master'mastermasterConfiguration logFix configure.log formattingImprove ar test logic and write a configuration log filePrepare nested OpenMP parallelism in TRAPPINGparallel_trappingparallel_trappingAllocate global work-space directly on device, if using offloadAdd target declaration directives to clu_subs.hCreate a global host work-space to allocate thread-private device work-spacesDrop unified shared memory requirement and enable GPU offload in TRAPPINGAdd optimization level message to configure.logWrite a log file of the configuration stepUse generic OFFLOAD compiler flags in place of NVIDIA specific onesImplement ClusterIterationData size estimatorPrepare ParticleDescriptor interfaces to estimate size in memoryClean up outdated commented code linesMerge branch 'master' into parallel_trapping to update to trapping offloadMerge branch 'master' into script_devel to update to offload trappingMerge branch 'master' into offload_trappingMerge branch 'offload_trapping' of git.ia2.inaf.it:giacomo.mulas/np_tmcode into offload_trappingclean up nested omp directivesMerge branch 'offload_trapping' into 'master'Call configuration object by correct name in model_maker.py::write_legacy_gconf()Make undected compiler messages silent and ensure CUBLAS is not invoked, if not foundDefine default refinement and dynamic order runtime behaviour in model makerclean up USE_TARGET_OFFLOAD conditionalsfix pipeline (no more refinement configure option), clean up USE_TARGET_OFFLOAD conditionalsfix configure script to correctly set USE_TARGET_OFFLOAD if offload is enabledfix races in ztmDelete logger at end of MPI process 0 instruction blockEnsure that cuBLAS is not linked, when it is not detectedRe-introduce the USE_TARGET_OFFLOAD compilation flag