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 2.2.031Mar30272625242322212019181312111096543228Feb2726252423212019181716141312111076543131Jan30292827242322212017161514109873[StreamingFC] simplify weight strm FIFO interface[StreamingDWC] Add dummy npysim path with output = input[Test] Add test for streaming dwc[StreamingDWC] Add execute_node() function for dwc[StreamingFC] manually add Verilog FIFO to streaming weights[StreamingFC] "fix" weight FIFO depth pragma, but it won't work[Test] bring back random input to ip stitch test[Registry] add data width converter to registryFixed images settings and typo[Test] debug changes to ip stitch test[StreamingFC] check current mem depth for decoupled[HLSCustomOp] add a first draft of StreamingDataWidthConverter[Test] switch to 2-FC stitching testcase[Test] fix IP stitching tests w/ ReplaceVerilogRelPaths[StreamingFC] set vlnv differently for decoupled ip gen[Transform] handle more cases in ReplaceVerilogRelPaths[IPPack] support more families for IP packing[Transform] use new attributes in IP stitching[HLSCustomOp] add ip_vlnv attribute[Blog] add QuartzNet blog post[Sphinx Documentation] change text in end2end rst file[Documentation] Change FINN flow diagram and corresponding images[StreamingFC] use ip_path to treat decoupled/const IP prods same[StreamingFC] fix DataType inference (too much copy paste...)[Sphinx-Documentation] Change images for FINN flowMerge branch 'dev' into feature/update_documentation[Util] Change in numpy_to_hls_code data packing function: pad number to multiple of 4[StreamingFC] add a first v. of IP packaging for decoupled mem[Docs] update example networks status[Test] fix for test_batchnorm_to_affine_cnv_w1a1[Transform] call shape&dt inference after HLS conversion[StreamingFC] add shape and type inference to StreamingFC[Test] fix cnv batchnorm2affine testcase[Test] remove test_verify_custom_nodes[Test] correct expected im2col values for inner dim orderingMerge branch 'feature/cnv_w1a1_convert_to_hls_layers' into dev[Test] add final checks to cnv-w1a1 HLS conversion[ModelWrapper] helper fxns to get nodes by type, domain[Test] add InferQuantizedStreamingFCLayer to cnv-w1a1 HLS convMerge branch 'feature/weight_streamers_rtlsim' of https://github.com/Xilinx/finn into feature/cnv_w1a1_convert_to_hls_layers