adavare opened a new pull request #27: URL: https://github.com/apache/tvm-vta/pull/27
A pipelined implementation of the Chisel "TensorAlu" module as well as more flexible scratchpad read/write interfaces are added. Chisel unit tests are added for the modified ALU. Around ~4x speedup is seen in the cycle count reported by the "ALU Unit test" portion of "tvm/vta/tests/python/integration/test_benchmark_gemm.py", while more modest speedups are seen in all other tests located in the "tvm/vta/tests/python/integration" and "tvm/vta/tests/python/unittest" directories. Code contributions to this PR were made by the following individuals (in alphabetical order): @suvadeep89, @stevenmburns, @pasqoc, @adavare, @sjain12intel, @aasorokiin, and @zhenkuny. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: [email protected]
