Skip to content
Snippets Groups Projects
Select Git revision
  • accl default
  • adegendt/accl_clone
  • dev
  • full_accl_support
  • georg/accl-build
  • georg/accl-complete
  • georg/accl-finn
  • georg/end2end
  • main protected
9 results
You can move around the graph by using the arrow keys.
Created with Raphaël 2.2.020Sep19161514987631Aug3029262524221918151211109843129Jul282726252221201918151413121198765430Jun292827242322212017151312109872131May30252423201817161312111098654328Apr2120730Mar2825242322151411842124Feb222019181716151110983131Jan2725211322Dec211716151362130Nov2927262423201615131211108543229Oct2827222120191815[FIFO] instead of fixed-depth large FIFO in sim, use tensor size[FIFO] instead of fixed-depth large FIFO in sim, use tensor size[FIFO] use hw maxcount monitoring in InsertAndSetFIFODepths[FIFO] add hw maxcount tracking to rtl FIFOs with opt attributeMerge branch 'feature/lookup_bounds' into feature/rtlsim-vivado-ip[Deps] update QONNXMerge branch 'dev' into feature/rtlsim-vivado-ipAddress reviewer commentsfix name in fetch repos and capitalize kv260 in templatesupdate fetch-repos.shMerge pull request #656 from Xilinx/deps/update-qonnx-versionChanges to make[Test] batch-4 inputs and result checking for test_build_dataflow[Build] keep different vcd's from batch inputs[Util] set property on SDP nodes to get full context[Build] support batched verification i/o, one at a timeLint fixMove parallel impl. to different branch, cleanup[pre-commit] Run pre-commit on lookup layer fileRebalanced lookup implementation code to go mostly into header file.Match requested II with achievable one.Maintain static OOB count internally requiring explicit acknowledging reset.Initial QONNX ingestion notebookRemove cell executionRename brevitas_network_import notebook and add intro noteInitial VVAU SIMD supportUpdate basic.pyZynqBuild: use AXI port width from part map[FIFO] move characterization into HLSCustomOp member fxns[FIFO] use correct type for empty chrc data[FIFO] adapt FIFO sizing to new attributes[HLSCustomOp] refactor types for FIFO attributes[Deps] update QONNX to get tensor attribute support[Test] simply linear FIFO sizing test[FIFO] derive sizes for multiple consumers, DuplicateStreams bugfix[InsertFIFO] make use of multi FIFO depths attributes[AddStreams] default inputFIFODepths attr[FIFO] use outFIFODepths attr for multi-out[FIFO] characterize Add/DuplicateStreams, optional bypass fix, pad[HLSCustomOp] new attributes for multi-IO FIFO sizes, chrc. padding