ML SW toolchain based on IREE

Clone this repo:

Branches

  1. d80ac5f Update params for iree_hal_module creation by Alex Van Damme · 6 days ago master
  2. 96b39cd sw/vec_iree Allow additional warning flags to accommodate IREE upstream change by Lun Dong · 8 days ago
  3. 3e2bc29 Merge "Add missing extensions to Kelvin's march setting" by Alex Van Damme · 3 months ago
  4. 3c4dff4 Add missing extensions to Kelvin's march setting by Alex Van Damme · 3 months ago
  5. d291b78 sw/vec_iree: fix breakage due to IREE device API change by Lun Dong · 3 months ago

Springbok Model Execution Repository

This project contains ML model codegen and execution libraries/examples. The artifacts built from this project is targeted for RISC-V 32-bit baremetal machine (Springbok or Kelvin).

Prerequisite

If you get this project from Project Shodan manifest, you are all set. If not, you need to have following projects as well to build the project successfully.

This project needs to be at <dir>/sw/vec_iree

Code structure

  • audio_prep: Audio preprocessing libarary
  • build_tools: Utility scripts for the project
  • cmake: CMake Macros for the project
  • device: Device HAL driver library
  • model_util: Runtime utility library for model execution
  • native_log: BSP support for the Linux userspace emulation
  • risp4ml: Vision preprocessing library (Reduced ISP for ML)
  • samples: Codegen and execution of ML models based on IREE
    • branch_mul: Branch multiplication example
    • microbenchmarks: Currently only contain a convolution 1x1 example
    • simple_vec_mul: Point-wise vector multiplication examples
  • ssd_postprocess: Vision postprocessing library for Single-Shot Detectors (SSD)
  • ukernel: Custom microkernel library for VMVX and LLVM

Build the project

If you are running from Project Shodan repo, you can build the artifacts with m iree. If you download this project alone, you need to download/build IREE's host compiler, then go to the top level directory.

For Springbok

  cmake -B <output dir> -G Ninja \
     -DCMAKE_TOOLCHAIN_FILE="$(realpath sw/vec_iree/cmake/riscv_iree.cmake)" \
     -DCMAKE_BUILD_TYPE=MinSizeRel \
     -DIREE_HOST_BIN_DIR="$(IREE_COMPILER_DIR)/install/bin" \
     -DRISCV_TOOLCHAIN_ROOT=$(TOOLCHAINRV32_PATH) \
     <dir>/sw/vec_iree
  cmake --build <output dir> --target all

For Kelvin

  cmake -B <output dir> -G Ninja \
     -DCMAKE_TOOLCHAIN_FILE="$(realpath sw/vec_iree/cmake/riscv_iree_gcc.cmake)" \
     -DCMAKE_BUILD_TYPE=MinSizeRel \
     -DIREE_HOST_BIN_DIR="$(IREE_COMPILER_DIR)/install/bin" \
     -DRISCV_TOOLCHAIN_ROOT=$(TOOLCHAINRV32_PATH) \
     <dir>/sw/vec_iree
  cmake --build <output dir> --target all

Run the executables

You can run RENODE emulation with the built executables. In Shodan repo, sim_springbok for Renode simulation on Springbok; sim_kelvin for Renode simulation on Kelvin. Out-of-repo emulation is possible but requires more steps.

Test the executables

In Shodan, this project utilizes LLVM lit and Python filecheck to test the ML executable performance. The tests are defined in the *_test.run files under <output dir>. To run the test, at the Shodan top level directory

lit -a <output dir>

Default is renode tests for Springbok. Add-D RUNNER=kelvin to enable renode tests for Kelvin. Add-D RUNNER=kelvin_hw to enable renode tests for Kelvin HW.