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 2.2.08Jul765230Jun29282625242219181715141311109830May27262523211816543230Apr292827262521191613121198765432131Mar3029262524232223222120192019181716151413121312111092127Feb26242322191817161412111098Fixed a problem with quantizationBuild in Release by defaultAdded a patch to remove exception throwing in swMerge branch 'hpvm-release-epochs0' of https://gitlab.engr.illinois.edu/llvm/hpvm into hpvm-release-epochs0Adding a description of the scheduler backend to top level READMEReplaced source for distillerNo timeout in ssh testsAdding Epochs backend target build to installer scriptMerge branch 'hpvm-release-nvdla' into hpvm-release-epochs0-backendFinalizing minieraRemoving unsupported print debug statementAdded end-to-end test scriptRemoved outputs from NVDLA passAdding missing directory to CMakeLists.txtFixed a few issues with quantizationAdded routine for quantizing miniera model:Gathered all epoch_dnn files to the same locationAdded calibration scales for various quantization strategies using distillerhpvm-clang moves generated buffer to target directoryFixed a few issues in NVDLA passUpdated pytorch frontend and hpvm-clang to handle NVDLA correctlyAdded weights and scripts for miniera dnnUpdated hpvm_installer for a few things:commiting small bug fixesMerging all remainging files (headers, BuildDFG), added no-OpenCL hpvm-rt, removed unneeded patches, and added EPOCHS backend passMerging GenHPVM, DFG2LLVM_CPU, DFG2LLVM.h from hpvm-epochs0-backendMerging llvm patches from hpvm-epochs0-backendRemoving identical (and misleading) weightsMergiongAdding MIO AlexNet CNN weights (NVDLA testing)Update README.mdUpdate README.mdUpdate README.mdupdating instructionsAdding instructions for compiling mini-era benchmark for NVDLAAdding script to invoke hpvm-clang with mini-era compilationUpdating LeNet source to be NVDLA consistent (reads fp16 weights)testing images for MNISTAdding working FP16 quantization and Tranpose Dense weights scripts (tested on simulator)Adding weight manipulation scripts (FP16 + Transpose)