Skip to content
Snippets Groups Projects

Repository graph

You can move around the graph by using the arrow keys.
Select Git revision
  • hpvm-release-epochs
  • hpvm-release-epochs0
  • main default
  • v2.0
  • v2.0rc
  • v1.0
  • v0.5
7 results
Created with Raphaël 2.2.024Feb232019181716151413121110742131Jan30292827252423222120191817161514131098743231Dec3029272618765228Nov2625212019201918171817161716Adding utils support for dumping class confidences and predicted labelsAdding time profiling for DevTunerAdding code to dump references files + dumping all configs for comparison with ParetoAdding script to generate pareto curve plots for visualizationgenerate onnx model from kerasChange README.md and onnx_environment.ymlSpecified targets in ReadMEAdding devtime knobs for remaining benchsFixing Pareto Runtime file construction - using FP32 in Devtime modemergingAdding dev-time knobs with no-FP16Specify supported targets in README.mdSpecified targets in README.mdSpecify targets in ReadMESpecify targets in ReadMESpecified supported targetsparsing onnx model with building hape and cfg, not finishedAdded workflow documentationAdded workflow documentationRemove unnecessary functions related to attributesAdding fixits for pareto file constructionsemi-faulty pareto dump-construction completed for devtunerAdding utilities script for pareto constructionAdding automatic baseline extraction - not relying on static valuesAdd more fixes for API differencesFixing utils bug in directory creationfixing bug in devtuner - using accuracy not min_accuracyMergingCleaning up devtuner workflow - separating common utilitiesFixed compilation error in NVPTX HPVM backendUsing Unique IDs across multiple devtuner invocationsRenaming ClangsFlagTuner appropriately to DevTunerFixing old tuner_results paths to move to ./autotuner/dataMoving benchmark data files to ./autotuner/data/Moving to /home/hsharif3/Gitlab/hpvm/llvm/ relative paths + moving tuner output directoryfixing file extensionAdding global path to hpvmtensor-rtAdding bechmarks backupFixing tensor_runtime_online rule to useFixed merge error