commit	b01a87b27c4c8765488d441e401e82ac23a6baa3	[log] [tgz]
author	Luis Vega <vegaluisjose@users.noreply.github.com>	Sun Jul 07 23:47:48 2019 -0700
committer	Thierry Moreau <moreau@uw.edu>	Sun Jul 07 23:47:48 2019 -0700
tree	1c52f333a8e995a0b86396d25345f2242471cbff
parent	1cad4c6f5470cf11dbcbe5276b73ab17859fb782 [diff]

[VTA] TSIM improvements and fixes (#3505) * add tsim init function * add sim device * test wait and resume * launch simulation thread from DPILoader * add VTASimDPI module to handle all simulation related stuff * test tsim init * move exit to simdpi module * update vta driver * add chisel DPI module * get back simshell * update vta to support dpi sim * update unittests * add tsim to integration-conv2d test * run resnet on tsim * remove max-cycles * match tsim counters with sim counters * use env in simulator to switch between sim and tsim * update unittest * rollback conv2d test * update resnet * add stats to matrix multiply * add stats * print stats after assert * update other tests * add stats to gemm * add return and remove unused libs * add missing arg * return lib * update comments for linter * add more comments to VTASimDPI module * remove trailing spaces * remove trailing spaces

tree: 1c52f333a8e995a0b86396d25345f2242471cbff

README.md

VTA: Open, Modular, Deep Learning Accelerator Stack

VTA (versatile tensor accelerator) is an open-source deep learning accelerator complemented with an end-to-end TVM-based compiler stack.

The key features of VTA include:

Generic, modular, open-source hardware
- Streamlined workflow to deploy to FPGAs.
- Simulator support to prototype compilation passes on regular workstations.
Driver and JIT runtime for both simulator and FPGA hardware back-end.
End-to-end TVM stack integration
- Direct optimization and deployment of models from deep learning frameworks via TVM.
- Customized and extensible TVM compiler back-end.
- Flexible RPC support to ease deployment, and program FPGAs with the convenience of Python.

Learn more about VTA here.